From 33e682a9d50d5b5ac21c72ab070777cbf428e91d Mon Sep 17 00:00:00 2001 From: Ian Gulliver Date: Wed, 14 Oct 2026 22:28:25 -0700 Subject: [PATCH] SSE reconnect, task switcher state/inbox/new task, stream throttle --- docs/operations.md | 4 +- internal/agents/manager.go | 7 ++ internal/claude/session.go | 4 +- .../TestCommitIdentityHooksAndMCP.jsonl | 74 +++++++------- .../testdata/transcripts/TestImageInput.jsonl | 14 +-- .../testdata/transcripts/TestInterrupt.jsonl | 35 ++++--- .../transcripts/TestResume-first.jsonl | 14 +-- .../transcripts/TestResume-resumed.jsonl | 16 +-- .../transcripts/TestStopHookBlocks.jsonl | 30 +++--- .../testdata/transcripts/TestTextDeltas.jsonl | 14 +-- internal/server/sse.go | 4 +- web/dist/api.js | 54 +++++++++- web/dist/api.js.map | 2 +- web/dist/navbar.js | 84 +++++++++++----- web/dist/navbar.js.map | 2 +- web/dist/panes.js | 11 +++ web/dist/panes.js.map | 2 +- web/dist/task.js | 12 +-- web/dist/task.js.map | 2 +- web/dist/tasks.js | 3 +- web/dist/tasks.js.map | 2 +- web/src/api.ts | 60 +++++++++-- web/src/navbar.ts | 99 +++++++++++++------ web/src/panes.ts | 14 +++ web/src/task.ts | 14 +-- web/src/tasks.ts | 3 +- web/style.css | 20 ++++ 27 files changed, 418 insertions(+), 182 deletions(-) diff --git a/docs/operations.md b/docs/operations.md index a6766e9..6382c2e 100644 --- a/docs/operations.md +++ b/docs/operations.md @@ -89,6 +89,8 @@ Agent activity becomes events with `agent_session_id` set: `user.message`, `agen Messages byre itself sends an agent (actor `byre`, such as the restart notice) show as a muted note, not a user bubble. The transcript view has an accent border while the session is `running`, and a braille spinner on its last line. The spinner is pure CSS: six dots laid out as a braille cell, each switched on and off by its own `step-end` keyframes (`braille-1` to `braille-6` in `web/style.css`) so together they cycle ⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏ every 0.8s. Browsers that freeze animated GIFs (Orion) still run it. Consecutive tool calls (with any thinking between them) collapse into one group whose summary counts calls per tool and file, and file paths show relative to the worktree. A turn's final message that is at least half visible in the transcript while the page is visible dismisses its `report` inbox item, as the viewing user. In the composer, Enter sends and Shift-Enter adds a newline; unsent text is kept per task in memory, so it survives switching tabs or tasks but not a page reload. +The task switcher (⌘K, or the navbar crumb) lists active tasks with their session state and open inbox item count, live while it is open. Tasks with inbox items come first; otherwise the order is the server's (projects by name, tasks newest first). Typing filters them and adds a last row that creates a task with the typed text as its title, in the current task's project (the first project when no task is selected); Enter picks the highlighted row. Picking a task here or in the Tasks view selects it and, if neither pane shows the Transcript tab, switches a pane that isn't showing Tasks to it. + ## Inbox Agents ask questions with the `ask_human` MCP tool. Each question carries a `context` with the background the human needs to answer without reading the transcript; the UI renders it, the question, and the options as Markdown. A malformed call (no `context` or `why_blocked`, fewer than two options, a recommendation that isn't one of the options, an unknown attachment kind, a foreign `thread_id`) is rejected with a message saying what to fix, and nothing is filed. Each turn's final message (as a `report`) and each agent error (a turn that ends in error without a human interrupt, a process that dies mid-turn) also files an item. @@ -128,4 +130,4 @@ The Changes view lists the files with their counts, opens a file's diff on click ## Events -`GET /api/events` is server-sent events: `id` is the event's `seq`, `data` the Event JSON. Reconnecting with `Last-Event-ID` (EventSource does this itself) or `?after=` replays everything after that seq before going live. Unstored events (`seq` 0, currently only `agent.delta`) go out live only, without an `id` line, so they don't move `Last-Event-ID`. A client that falls further behind than its subscriber buffer (`subscribe` in `internal/server/hub.go`) is disconnected and catches up by reconnecting. +`GET /api/events` is server-sent events: `id` is the event's `seq`, `data` the Event JSON. Reconnecting with `Last-Event-ID` (EventSource does this itself) or `?after=` replays everything after that seq before going live. Unstored events (`seq` 0, currently only `agent.delta`) go out live only, without an `id` line, so they don't move `Last-Event-ID`. A client that falls further behind than its subscriber buffer (`subscribe` in `internal/server/hub.go`) is disconnected and catches up by reconnecting. Every 15s the server sends an `event: ping` so clients can tell a live stream from a dead one. The web UI (`subscribe` in `web/src/api.ts`) tracks the last seq it saw and opens a new stream from it when nothing (event or ping) has arrived for 40s, 2s after the browser gives up on one (as it does when `tailscale serve` answers 502 while byre restarts), when the browser comes back online, and on becoming visible if the stream is stale. While disconnected the navbar shows a red dot and "reconnecting…"; partial output (`agent.delta`) sent while disconnected is lost, and the finished `agent.message` replaces it. diff --git a/internal/agents/manager.go b/internal/agents/manager.go index 3b24970..e98eaa8 100644 --- a/internal/agents/manager.go +++ b/internal/agents/manager.go @@ -587,10 +587,17 @@ func (m *Manager) pump(l *live) { ctx := context.Background() for ev := range l.sess.Events() { + start := time.Now() + if wait := start.Sub(ev.Read); wait > 200*time.Millisecond { + slog.Info("agent event waited", "session", l.id, "type", ev.Type, "wait", wait) + } err := m.handle(ctx, l, ev) if err != nil { slog.Error("record agent event", "session", l.id, "type", ev.Type, "err", err) } + if took := time.Since(start); took > 200*time.Millisecond { + slog.Info("agent event slow", "session", l.id, "type", ev.Type, "took", took) + } } m.mu.Lock() diff --git a/internal/claude/session.go b/internal/claude/session.go index 59a7f8c..00a1a73 100644 --- a/internal/claude/session.go +++ b/internal/claude/session.go @@ -45,6 +45,7 @@ type Event struct { Type string Subtype string Raw json.RawMessage + Read time.Time } type Block struct { @@ -505,6 +506,7 @@ func (s *Session) readLoop(stdout io.Reader) { } func (s *Session) handleLine(line []byte) { + read := time.Now() env := envelope{} err := json.Unmarshal(line, &env) if err != nil { @@ -540,7 +542,7 @@ func (s *Session) handleLine(line []byte) { s.idMu.Unlock() } - s.events <- Event{Type: env.Type, Subtype: env.Subtype, Raw: append(json.RawMessage{}, line...)} + s.events <- Event{Type: env.Type, Subtype: env.Subtype, Raw: append(json.RawMessage{}, line...), Read: read} } func (s *Session) learnScrub(raw json.RawMessage) { diff --git a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl index cad6304..deba79b 100644 --- a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl +++ b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl @@ -1,36 +1,40 @@ -{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_02e702779a0886a7","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"f9e50f30-3886-4042-891e-d0e7fc997c7d","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"claude-code","title":"Claude Code","description":"Anthropic's agentic coding tool","websiteUrl":"https://claude.com/claude-code","version":"2.1.296"}},"jsonrpc":"2.0","id":0}}}} -{"dir":"send","msg":{"response":{"request_id":"f9e50f30-3886-4042-891e-d0e7fc997c7d","response":{"mcp_response":{"jsonrpc":"2.0","id":0,"result":{"capabilities":{"tools":{}},"protocolVersion":"2025-06-18","serverInfo":{"name":"byre","version":"0.0.0"}}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_02e702779a0886a7","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":12874,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_d4b9302d601710f6","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"3af614c5-3d2a-484b-a61f-73b62d09d69c","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"claude-code","title":"Claude Code","description":"Anthropic's agentic coding tool","websiteUrl":"https://claude.com/claude-code","version":"2.1.296"}},"jsonrpc":"2.0","id":0}}}} +{"dir":"send","msg":{"response":{"request_id":"3af614c5-3d2a-484b-a61f-73b62d09d69c","response":{"mcp_response":{"jsonrpc":"2.0","id":0,"result":{"capabilities":{"tools":{}},"protocolVersion":"2025-06-18","serverInfo":{"name":"byre","version":"0.0.0"}}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_d4b9302d601710f6","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":30381,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Create a file hello.txt containing exactly the word hi, then git add and git commit it with the message \"add hello\", then call the finish tool.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"fe70e70e-c384-4ba3-a142-b5519fb3b714","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} -{"dir":"send","msg":{"response":{"request_id":"fe70e70e-c384-4ba3-a142-b5519fb3b714","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"9406138a-1548-4ec7-90b0-30ff9289d78c","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} -{"dir":"send","msg":{"response":{"request_id":"9406138a-1548-4ec7-90b0-30ff9289d78c","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"finish","description":"Call this once the task is complete.","inputSchema":{"type":"object","properties":{}}}]}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__byre__finish"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"},{"name":"byre","status":"connected","source":"sdk"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"58be0129-7321-4c9d-b90b-ef2cddf36c1a","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182/scratchpad","messaging_socket_path":"/tmp/cc-socks/12874.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"4a7911fd-1dfd-44b0-b420-d18cc50711fe"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"ae2038e3-df04-434c-94c2-acd4e606f045","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PDvPxfw4EzujGvabdR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ArWWWwNpcpjQTh5hjiev2x","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001/hello.txt","content":"hi"},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15289,"cache_read_input_tokens":22425,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15289},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"271e9c8a-a00a-44f4-94d9-4a3443268bbd","timestamp":"2026-10-15T04:22:31.577Z","request_id":"req_011Cg3PDv9L4dudR2uNbkED1","wire_tool_inputs":{"toolu_01ArWWWwNpcpjQTh5hjiev2x":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001/hello.txt","content":"hi"}}}} -{"dir":"recv","msg":{"type":"control_request","request_id":"911219aa-bc01-47e5-8f05-ea508410a440","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182/scratchpad","prompt_id":"7a66b2ff-760c-4c7e-b50e-1d01cad63707","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_01ArWWWwNpcpjQTh5hjiev2x","duration_ms":11},"tool_use_id":"toolu_01ArWWWwNpcpjQTh5hjiev2x"}}} -{"dir":"send","msg":{"response":{"request_id":"911219aa-bc01-47e5-8f05-ea508410a440","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ArWWWwNpcpjQTh5hjiev2x","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"1144a475-e7a3-4940-b382-74954cf5bf22","timestamp":"2026-10-15T04:22:31.617Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_01ArWWWwNpcpjQTh5hjiev2x","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"90c43601-5404-4f3a-a96c-0eeb3af07dc1"}} -{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"6a08ae39-381a-468d-8053-5f835134ee0f"}} -{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":202,"estimated_tokens_delta":152,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"1b86207d-0bc3-4ad0-b917-fefaa24bbd12"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PE5HjnnEb29jZ6QzoL","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSnwYKEAgSGAI4AUIIdGhpbmtpbmcSDKBOxIDfrWJ4BiW6uhoMk9D4mCMCDsPRTrUJIjDws7EQalDgBVlT5r8ZYivOQdhTOHZT/xaKHp6cLi4xOvhFG0ZRvJgFESDlyOcBlNgqvAXLwExODTijbZy6Fo1Zo4yIOvkY1pb53bcHR4F0foGJ7OFM3rBWzQv2Lumtc2EoMBtv2qY/HG7M22SsSW1KauTqFXRaSQySlX0m8MExTSbk5dgvnjso+VTImH384fwTpr/8WRAwGaSJaoGPyQxRqtTs6TXEyn6EZOpPrtY0/NyQLPIS94NU42W+EQ+UBc/6/Yo/cLw+yP82/7/Z8pfzn/adWuMXnMgogGD2ESoiecEoDqskzo4GKegdOj0lm5uWerc5ab26vTW+bN9KOgiY8Og8UDuzNmrQ8tk/XXJU7BxZuiCSHkvoeoZk0VgL57LLAkjco29LnzAr5VDv/7Tl8xOeHaKXbDvfij1/dUVI7dnAknkRHyJ+FsK2rwGl/aNOppK/LO5NeC6bhKN17XApLR2UOwtLc4ATM9/ANvgyggrdtAsqoBPQCYtasotxbqV2GxAoyMg4PL7cnNBMHShG9UhIQOHwZ4eR/kX5RlHUVwrPs7rH3Cza+jJ/FN9Gaq8DTzprddEfk6YYDVqppWBX2UXdAMFrRXwfTQBfkgW/gz/A3MmrNrI69waRpG5CIjSIi3WTc9Deny9/4OREHsBPFXC/wAKYbWwNAw3EPVVoYEVRfggtribQoL1do7kzJsGG5FxSN2+tyJKWCGf++qNe+bPHBU3t0P6iLmwn+NBLJ/XhFduAhElLwaa7BxPERDIGk6NPFMdxlx1/qhkej0OBZjAE6RleuO2euqRdG+OGO6qdpHV794E+rONn9CUHSni3AUgubNxBikrQG5IE6Sy6dp226yNUMxg/H20PXU/te27eAm6gIleWezGH8c2I02LoOV8szr8KNNzai1aWuqMhjGv/TagQ4yb88PO8YZVGtJXSk4nSwW9joSf1ZHdA+Zu9ARg9xJbrTD9npBInoQDOAROi0y7rptCs1JYYgMDNGAE="}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4712,"cache_read_input_tokens":37714,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4712},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"419e9b53-d82c-4e2c-b922-4f475e0d5a74","timestamp":"2026-10-15T04:22:33.729Z","request_id":"req_011Cg3PE52NKoNFaWerTqx95","thinking_duration_ms":1178,"thinking_display":"updates"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PE5HjnnEb29jZ6QzoL","type":"message","role":"assistant","content":[{"type":"text","text":"Authorization for the commit, quoted from this turn: \"then git add and git commit it with the message \"add hello\"\"."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4712,"cache_read_input_tokens":37714,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4712},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"7d57f0ef-5bd0-414f-b4bb-1b192e727a39","timestamp":"2026-10-15T04:22:33.730Z","request_id":"req_011Cg3PE52NKoNFaWerTqx95"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PE5HjnnEb29jZ6QzoL","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WP5nDgtoyGTdxNMU9w39Ly","name":"Bash","input":{"command":"timeout 20 git add hello.txt \u0026\u0026 timeout 20 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Stage and commit hello.txt","timeout":60000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4712,"cache_read_input_tokens":37714,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4712},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"d6a10bfa-fbf8-41ef-9f26-65861b4b7682","timestamp":"2026-10-15T04:22:34.470Z","request_id":"req_011Cg3PE52NKoNFaWerTqx95","wire_tool_inputs":{"toolu_01WP5nDgtoyGTdxNMU9w39Ly":{"command":"timeout 20 git add hello.txt \u0026\u0026 timeout 20 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Stage and commit hello.txt","timeout":60000}}}} -{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001","uuid":"5e02a1fa-6fa3-43d7-9f69-7b2d864cf6d0","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"9ff81925-0c3d-4a9c-af2c-bbd77bb0d149","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182/scratchpad","prompt_id":"7a66b2ff-760c-4c7e-b50e-1d01cad63707","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"timeout 20 git add hello.txt \u0026\u0026 timeout 20 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":60000,"description":"Stage and commit hello.txt"},"tool_response":{"stdout":"[main 35e23e1] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"35e23e1","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_01WP5nDgtoyGTdxNMU9w39Ly","duration_ms":102},"tool_use_id":"toolu_01WP5nDgtoyGTdxNMU9w39Ly"}}} -{"dir":"send","msg":{"response":{"request_id":"9ff81925-0c3d-4a9c-af2c-bbd77bb0d149","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WP5nDgtoyGTdxNMU9w39Ly","type":"tool_result","content":"[main 35e23e1] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"c8c92cb3-320a-4593-bbbc-0e210afb1de3","timestamp":"2026-10-15T04:22:34.596Z","tool_use_result":{"stdout":"[main 35e23e1] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"35e23e1","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_01WP5nDgtoyGTdxNMU9w39Ly","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"529409a4-9b19-4a2e-bc46-f96468e819f5"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PEJ4TBHgaMd9g7keMD","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019UGBnUqxgCSZcXCuXa1cUS","name":"mcp__byre__finish","input":{},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":379,"cache_read_input_tokens":42426,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":379},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"5e623e53-f122-49c3-be8b-2be1ded4f8e9","timestamp":"2026-10-15T04:22:35.420Z","request_id":"req_011Cg3PEHirntAt2JQYuBvZn","wire_tool_inputs":{"toolu_019UGBnUqxgCSZcXCuXa1cUS":{}},"tool_use_meta":[{"id":"toolu_019UGBnUqxgCSZcXCuXa1cUS","display_name":"Finish","server_display_name":"byre"}]}} -{"dir":"recv","msg":{"type":"control_request","request_id":"5384267d-1c19-418a-9182-34dc0b685691","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"finish","arguments":{},"_meta":{"claudecode/toolUseId":"toolu_019UGBnUqxgCSZcXCuXa1cUS","progressToken":2}},"jsonrpc":"2.0","id":2}}}} -{"dir":"send","msg":{"response":{"request_id":"5384267d-1c19-418a-9182-34dc0b685691","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"noted"}]}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"5dd32843-a432-4c6a-8037-ae59116a31b4","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP671040166/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP671040166-001/5e94ceb3-1c19-4499-b690-3c2bb2e15182/scratchpad","prompt_id":"7a66b2ff-760c-4c7e-b50e-1d01cad63707","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__finish","tool_input":{},"tool_response":[{"type":"text","text":"noted"}],"tool_use_id":"toolu_019UGBnUqxgCSZcXCuXa1cUS","duration_ms":2,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_019UGBnUqxgCSZcXCuXa1cUS"}}} -{"dir":"send","msg":{"response":{"request_id":"5dd32843-a432-4c6a-8037-ae59116a31b4","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019UGBnUqxgCSZcXCuXa1cUS","type":"tool_result","content":[{"type":"text","text":"noted"}]}]},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"d1b8ae5e-a68a-4399-9682-46b9e607728d","timestamp":"2026-10-15T04:22:35.425Z","tool_use_result":[{"type":"text","text":"noted"}],"tool_result_meta":[{"id":"toolu_019UGBnUqxgCSZcXCuXa1cUS","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"ce88dbd1-a902-4a96-a8a0-1f12dcd56ace"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PEMcmFy4nt4Wg2wsw9","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi`, staged it, and committed it to `main` with the message \"add hello\" (commit `35e23e1`). I then called the finish tool."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":63,"cache_read_input_tokens":42805,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"output_tokens":58,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","uuid":"8e0deeec-10cf-4e6e-9733-8a325035b00f","timestamp":"2026-10-15T04:22:36.736Z","request_id":"req_011Cg3PEMKAEBYYDJzjQP2V7"}} -{"dir":"recv","msg":{"duration_api_ms":7738,"stop_reason":"end_turn","session_id":"5e94ceb3-1c19-4499-b690-3c2bb2e15182","total_cost_usd":0.10176469999999999,"usage":{"input_tokens":8,"cache_creation_input_tokens":20443,"cache_read_input_tokens":145370,"output_tokens":531,"output_tokens_details":{"thinking_tokens":82},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":20443,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":58,"cache_read_input_tokens":42805,"cache_creation_input_tokens":63,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1207,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001297,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":8,"outputTokens":531,"cacheReadInputTokens":145370,"cacheCreationInputTokens":20443,"webSearchRequests":0,"costUSD":0.101635,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":82,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":4,"subtype":"success","api_error_status":null,"result":"I created `hello.txt` containing `hi`, staged it, and committed it to `main` with the message \"add hello\" (commit `35e23e1`). I then called the finish tool.","ttft_ms":2151,"type":"result","duration_ms":7339,"uuid":"4dbef309-2dec-4e81-a45f-9b0a8e3d1889","ttft_stream_ms":1186,"time_to_request_ms":23,"first_content_frame_ms":1186,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"control_request","request_id":"6af9d0e4-2648-415e-b2ae-b70807b1e769","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} +{"dir":"send","msg":{"response":{"request_id":"6af9d0e4-2648-415e-b2ae-b70807b1e769","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"c83452cc-aefd-4ee3-8ee4-ca28dcd008b5","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} +{"dir":"send","msg":{"response":{"request_id":"c83452cc-aefd-4ee3-8ee4-ca28dcd008b5","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"finish","description":"Call this once the task is complete.","inputSchema":{"type":"object","properties":{}}}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001","session_id":"d455130d-ed8f-4795-8019-74267417650e","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__byre__finish"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"},{"name":"byre","status":"connected","source":"sdk"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"671ffd3d-e9b4-4692-9ca3-203cd33246b1","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e/scratchpad","messaging_socket_path":"/tmp/cc-socks/30381.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"0dab62cc-47c7-4aee-9a0e-723f18a34a4d"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"113d145b-2731-496c-8feb-832471d84917","session_id":"d455130d-ed8f-4795-8019-74267417650e"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCtA4qTpBfPijBvBra","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WHqqzpSjf3GGA1m7yrnm9A","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001/hello.txt","content":"hi"},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15285,"cache_read_input_tokens":22425,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15285},"output_tokens":17,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"ed4344b4-bbab-4aa4-8741-df2da8c543e4","timestamp":"2026-10-15T05:27:51.858Z","request_id":"req_011Cg3UCsvgP9SnFfTxfg3mU","wire_tool_inputs":{"toolu_01WHqqzpSjf3GGA1m7yrnm9A":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001/hello.txt","content":"hi"}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"d59697cd-073a-4b2e-99fd-210cc2bb628e","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d455130d-ed8f-4795-8019-74267417650e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e/scratchpad","prompt_id":"1cb746df-6ced-45f6-8211-83b73ed4ae75","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_01WHqqzpSjf3GGA1m7yrnm9A","duration_ms":2},"tool_use_id":"toolu_01WHqqzpSjf3GGA1m7yrnm9A"}}} +{"dir":"send","msg":{"response":{"request_id":"d59697cd-073a-4b2e-99fd-210cc2bb628e","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WHqqzpSjf3GGA1m7yrnm9A","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"b635ec4e-048a-4eac-bc8e-44127a2b5b10","timestamp":"2026-10-15T05:27:51.869Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_01WHqqzpSjf3GGA1m7yrnm9A","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"ef495695-42f0-4706-9374-dfb74ef56c32"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"0f41f575-5399-4703-89f4-8d1446178147"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":264,"estimated_tokens_delta":214,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"e64367dc-971e-4300-904c-86d73a576841"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UD45831z8s1vkz3Vkb","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37710,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"1ca3ac43-98dc-4cbf-82f6-3870612a11fe","timestamp":"2026-10-15T05:27:54.763Z","request_id":"req_011Cg3UD3n2Cf8pbTd7GtGLA","thinking_duration_ms":1809,"thinking_display":"updates"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UD45831z8s1vkz3Vkb","type":"message","role":"assistant","content":[{"type":"text","text":"Authorizing words from the current turn: \"git add and git commit it with the message \"add hello\"\"."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37710,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"d7f1fbd5-fc5f-422f-9ec7-84bef75a2de0","timestamp":"2026-10-15T05:27:54.765Z","request_id":"req_011Cg3UD3n2Cf8pbTd7GtGLA"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UD45831z8s1vkz3Vkb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GbDATdsCdhKk4Txxrc7QWM","name":"Bash","input":{"command":"git add hello.txt","description":"Stage hello.txt","timeout":15000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37710,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"c22db4e2-2e43-46cf-af37-7b0a2f0b88e9","timestamp":"2026-10-15T05:27:55.267Z","request_id":"req_011Cg3UD3n2Cf8pbTd7GtGLA","wire_tool_inputs":{"toolu_01GbDATdsCdhKk4Txxrc7QWM":{"command":"git add hello.txt","timeout":15000,"description":"Stage hello.txt"}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"1b2e959c-fa5b-43d6-bf30-342733bbee7a","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d455130d-ed8f-4795-8019-74267417650e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e/scratchpad","prompt_id":"1cb746df-6ced-45f6-8211-83b73ed4ae75","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git add hello.txt","timeout":15000,"description":"Stage hello.txt"},"tool_response":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_use_id":"toolu_01GbDATdsCdhKk4Txxrc7QWM","duration_ms":75},"tool_use_id":"toolu_01GbDATdsCdhKk4Txxrc7QWM"}}} +{"dir":"send","msg":{"response":{"request_id":"1b2e959c-fa5b-43d6-bf30-342733bbee7a","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GbDATdsCdhKk4Txxrc7QWM","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"f1815878-99aa-45ba-b7ea-06916a6539e3","timestamp":"2026-10-15T05:27:55.382Z","tool_use_result":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_result_meta":[{"id":"toolu_01GbDATdsCdhKk4Txxrc7QWM","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UD45831z8s1vkz3Vkb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016rzr9duVb1VawpLCncjKq5","name":"Bash","input":{"command":"git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Commit hello.txt","timeout":15000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37710,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":3,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"8e7d0175-51b9-4906-aaf3-4decc5d7ff84","timestamp":"2026-10-15T05:27:55.892Z","request_id":"req_011Cg3UD3n2Cf8pbTd7GtGLA","wire_tool_inputs":{"toolu_016rzr9duVb1VawpLCncjKq5":{"command":"git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":15000,"description":"Commit hello.txt"}}}} +{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001","uuid":"721d4d48-ccdd-4512-a641-02a97862fb00","session_id":"d455130d-ed8f-4795-8019-74267417650e"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"767f2c67-ce83-4a72-bbb4-83852785ac2b","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d455130d-ed8f-4795-8019-74267417650e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e/scratchpad","prompt_id":"1cb746df-6ced-45f6-8211-83b73ed4ae75","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":15000,"description":"Commit hello.txt"},"tool_response":{"stdout":"[main fd018d8] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"fd018d8","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_016rzr9duVb1VawpLCncjKq5","duration_ms":30},"tool_use_id":"toolu_016rzr9duVb1VawpLCncjKq5"}}} +{"dir":"send","msg":{"response":{"request_id":"767f2c67-ce83-4a72-bbb4-83852785ac2b","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016rzr9duVb1VawpLCncjKq5","type":"tool_result","content":"[main fd018d8] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"9e487755-738f-4317-b65d-860d10199536","timestamp":"2026-10-15T05:27:55.942Z","tool_use_result":{"stdout":"[main fd018d8] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"fd018d8","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_016rzr9duVb1VawpLCncjKq5","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"d262d02c-3b1c-412f-b436-569ff20b2dbf"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UDMPuvmBmEudQjKwxQ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TrfERWR6u9B8vTXmaaQ82Q","name":"mcp__byre__finish","input":{},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":603,"cache_read_input_tokens":42424,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":603},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"cb452658-51e5-4689-a7fd-c35d91b141ff","timestamp":"2026-10-15T05:27:56.872Z","request_id":"req_011Cg3UDM7oGQZuH857QyUJa","wire_tool_inputs":{"toolu_01TrfERWR6u9B8vTXmaaQ82Q":{}},"tool_use_meta":[{"id":"toolu_01TrfERWR6u9B8vTXmaaQ82Q","display_name":"Finish","server_display_name":"byre"}]}} +{"dir":"recv","msg":{"type":"control_request","request_id":"37151517-cd6c-4b3d-bc1b-03f12d77e7ba","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"finish","arguments":{},"_meta":{"claudecode/toolUseId":"toolu_01TrfERWR6u9B8vTXmaaQ82Q","progressToken":2}},"jsonrpc":"2.0","id":2}}}} +{"dir":"send","msg":{"response":{"request_id":"37151517-cd6c-4b3d-bc1b-03f12d77e7ba","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"noted"}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"7abcb77f-6b04-4bce-a68e-af1b01bed944","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d455130d-ed8f-4795-8019-74267417650e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1031187475/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1031187475-001/d455130d-ed8f-4795-8019-74267417650e/scratchpad","prompt_id":"1cb746df-6ced-45f6-8211-83b73ed4ae75","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__finish","tool_input":{},"tool_response":[{"type":"text","text":"noted"}],"tool_use_id":"toolu_01TrfERWR6u9B8vTXmaaQ82Q","duration_ms":3,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_01TrfERWR6u9B8vTXmaaQ82Q"}}} +{"dir":"send","msg":{"response":{"request_id":"7abcb77f-6b04-4bce-a68e-af1b01bed944","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TrfERWR6u9B8vTXmaaQ82Q","type":"tool_result","content":[{"type":"text","text":"noted"}]}]},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"ca941c93-0eec-4ba4-9dca-d6ab090d6d69","timestamp":"2026-10-15T05:27:56.880Z","tool_use_result":[{"type":"text","text":"noted"}],"tool_result_meta":[{"id":"toolu_01TrfERWR6u9B8vTXmaaQ82Q","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"a1837cd3-4562-4cbe-a949-94aff15b476e"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UDRYhqD2A8tZpgusXD","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi`, staged it, and committed it as `fd018d8` with the message \"add hello\". I then called the finish tool."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":63,"cache_read_input_tokens":43027,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"output_tokens":51,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d455130d-ed8f-4795-8019-74267417650e","uuid":"80e203f5-d9c3-4f20-b65c-c7d7432ee95b","timestamp":"2026-10-15T05:27:57.961Z","request_id":"req_011Cg3UDRB8kHyv2E6cnMtnA"}} +{"dir":"recv","msg":{"duration_api_ms":9057,"stop_reason":"end_turn","session_id":"d455130d-ed8f-4795-8019-74267417650e","total_cost_usd":0.1042533,"usage":{"input_tokens":8,"cache_creation_input_tokens":20665,"cache_read_input_tokens":145586,"output_tokens":689,"output_tokens_details":{"thinking_tokens":173},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":20665,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":51,"cache_read_input_tokens":43027,"cache_creation_input_tokens":63,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1207,"outputTokens":16,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001287,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":8,"outputTokens":689,"cacheReadInputTokens":145586,"cacheCreationInputTokens":20665,"webSearchRequests":0,"costUSD":0.1041246,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":173,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":5,"subtype":"success","api_error_status":null,"result":"I created `hello.txt` containing `hi`, staged it, and committed it as `fd018d8` with the message \"add hello\". I then called the finish tool.","ttft_ms":2348,"type":"result","duration_ms":8463,"uuid":"a9770b5b-6908-4d37-b00d-4f82e8cc72ab","ttft_stream_ms":1458,"time_to_request_ms":29,"first_content_frame_ms":1458,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestImageInput.jsonl b/internal/claude/testdata/transcripts/TestImageInput.jsonl index 9514182..099e1eb 100644 --- a/internal/claude/testdata/transcripts/TestImageInput.jsonl +++ b/internal/claude/testdata/transcripts/TestImageInput.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_e74b68ba2d384e2e","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_e74b68ba2d384e2e","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":12876,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_ca2491a1b24fb314","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_ca2491a1b24fb314","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":30380,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":[{"source":{"data":"iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAAZElEQVR4nOzPUQkAIBTAQBH7V9YQfhwPdgm2c9dsWwf8akBrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0B7AQAA///jRQGCmaQfxwAAAABJRU5ErkJggg==","media_type":"image/png","type":"base64"},"type":"image"},{"text":"Without using any tools, what single colour fills the attached image? Reply with just the colour name.","type":"text"}],"role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestImageInput4181536126/001","session_id":"7102bb3c-8ea7-4adc-8362-46c79b0065fc","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"4d344ba6-b300-4829-a854-6ae7617e6e5f","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput4181536126-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput4181536126-001/7102bb3c-8ea7-4adc-8362-46c79b0065fc/scratchpad","messaging_socket_path":"/tmp/cc-socks/12876.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"7102bb3c-8ea7-4adc-8362-46c79b0065fc","uuid":"c3206c81-4906-499b-afe4-373b66e33581"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"798b01da-9d83-4e00-8c24-b36db9386c10","session_id":"7102bb3c-8ea7-4adc-8362-46c79b0065fc"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PDvXeNQVcusvprc2kz","type":"message","role":"assistant","content":[{"type":"text","text":"Red"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15359,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15359},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"7102bb3c-8ea7-4adc-8362-46c79b0065fc","uuid":"5423f570-2b32-4f0a-8ced-30ffee20e5e6","timestamp":"2026-10-15T04:22:32.694Z","request_id":"req_011Cg3PDvGXAHzfFELiuAv8d"}} -{"dir":"recv","msg":{"duration_api_ms":3919,"stop_reason":"end_turn","session_id":"7102bb3c-8ea7-4adc-8362-46c79b0065fc","total_cost_usd":0.0638439,"usage":{"input_tokens":2,"cache_creation_input_tokens":15359,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15359,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15359,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15359},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1192,"outputTokens":16,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001272,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15359,"webSearchRequests":0,"costUSD":0.0637167,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"Red","ttft_ms":3245,"type":"result","duration_ms":3260,"uuid":"c01ab479-b3fa-4de5-a10a-e8af3a07e484","ttft_stream_ms":3240,"time_to_request_ms":37,"first_content_frame_ms":3241,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestImageInput3134564439/001","session_id":"4ccc7d57-8965-4a64-b10b-e4b1bf11306e","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"6384dbcb-7700-4832-8147-bd10b2519b40","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput3134564439-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput3134564439-001/4ccc7d57-8965-4a64-b10b-e4b1bf11306e/scratchpad","messaging_socket_path":"/tmp/cc-socks/30380.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"4ccc7d57-8965-4a64-b10b-e4b1bf11306e","uuid":"bd1923fa-96c6-45a7-8425-998c5e01330d"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"056f1fdf-f00e-4577-93b4-158741e5096a","session_id":"4ccc7d57-8965-4a64-b10b-e4b1bf11306e"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCt3P4Ng6U942JotN9","type":"message","role":"assistant","content":[{"type":"text","text":"Red"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15360,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15360},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"4ccc7d57-8965-4a64-b10b-e4b1bf11306e","uuid":"35b42b69-becb-4d65-a9f3-e30c1ac2e6a5","timestamp":"2026-10-15T05:27:51.466Z","request_id":"req_011Cg3UCspjhmMkJkeffyp2i"}} +{"dir":"recv","msg":{"duration_api_ms":2703,"stop_reason":"end_turn","session_id":"4ccc7d57-8965-4a64-b10b-e4b1bf11306e","total_cost_usd":0.0638479,"usage":{"input_tokens":2,"cache_creation_input_tokens":15360,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15360,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15360,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15360},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1192,"outputTokens":16,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001272,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15360,"webSearchRequests":0,"costUSD":0.0637207,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"Red","ttft_ms":1995,"type":"result","duration_ms":2018,"uuid":"cd3a4baf-5ebc-4a34-b369-c0ed3328cda6","ttft_stream_ms":1989,"time_to_request_ms":42,"first_content_frame_ms":1990,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestInterrupt.jsonl b/internal/claude/testdata/transcripts/TestInterrupt.jsonl index aee9d46..4d309b7 100644 --- a/internal/claude/testdata/transcripts/TestInterrupt.jsonl +++ b/internal/claude/testdata/transcripts/TestInterrupt.jsonl @@ -1,17 +1,20 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_e75c82e9a93fa7cd","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_e75c82e9a93fa7cd","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":12877,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_efcc7ae4ea6b1eb4","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_efcc7ae4ea6b1eb4","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":30376,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Run the bash command `ping -c 120 127.0.0.1` in the foreground (not in the background) and wait for it to finish, then say done.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt2595525365/001","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"3a4ef9ec-9973-4841-a4a4-bf6933b76507","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt2595525365-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt2595525365-001/05c42b7f-81dd-4f05-915b-691a2ca162cf/scratchpad","messaging_socket_path":"/tmp/cc-socks/12877.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","uuid":"bf809592-346f-4465-ae84-2e901ea6cc6d"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"877741a1-8211-4d53-a0fa-21c356ef3a45","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PDvTgDyhPaaFGncnoo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Dj9sr4ktjLvZ4TNVcjY4Bh","name":"Bash","input":{"command":"ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":180000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15264,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15264},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","uuid":"49877ade-a426-4c75-aa49-ef33dfcac85e","timestamp":"2026-10-15T04:22:31.777Z","request_id":"req_011Cg3PDvCo8ytQ5pbs9nbEX","wire_tool_inputs":{"toolu_01Dj9sr4ktjLvZ4TNVcjY4Bh":{"command":"ping -c 120 127.0.0.1","timeout":180000,"description":"Ping localhost 120 times"}}}} -{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_1b4908ef48c6f074","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_1b4908ef48c6f074","response":{"still_queued":[]}}}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"The user doesn't want to proceed with this tool use. The tool use was rejected (eg. if it was a file edit, the new_string was NOT written to the file). STOP what you are doing and wait for the user to tell you how to proceed.\n\nNote: The user's next message may contain a correction or preference. Pay close attention — if they explain what went wrong or how they'd prefer you to work, consider saving that to memory for future sessions.","is_error":true,"tool_use_id":"toolu_01Dj9sr4ktjLvZ4TNVcjY4Bh"}]},"parent_tool_use_id":null,"session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","uuid":"aa616233-4898-4ae8-8ded-8c7234a88f32","timestamp":"2026-10-15T04:22:33.787Z","tool_use_result":"User rejected tool use","tool_result_meta":[{"id":"toolu_01Dj9sr4ktjLvZ4TNVcjY4Bh","non_execution_kind":"user-rejected"}]}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user for tool use]"}]},"parent_tool_use_id":null,"session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","uuid":"efcb1433-8b53-4630-92ed-df69a77677a0","timestamp":"2026-10-15T04:22:33.788Z"}} -{"dir":"recv","msg":{"duration_api_ms":2934,"stop_reason":"tool_use","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","total_cost_usd":0.0645672,"usage":{"input_tokens":2,"cache_creation_input_tokens":15264,"cache_read_input_tokens":22367,"output_tokens":114,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15264,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":114,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15264,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15264},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":114,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15264,"webSearchRequests":0,"costUSD":0.0644367,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"aborted_tools","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":true,"num_turns":3,"subtype":"error_during_execution","errors":["[ede_diagnostic] result_type=user last_content_type=n/a stop_reason=tool_use"],"type":"result","duration_ms":4365,"uuid":"6582f3dc-6843-4228-a1d4-030676209dd9","queued_turn_count":0,"result_index":0}} -{"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt2595525365/001","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","ListMcpResourcesTool","LSP","Monitor","NotebookEdit","PushNotification","Read","ReadMcpResourceDirTool","ReadMcpResourceTool","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__claude_ai_Claude_Docs__batch","mcp__claude_ai_Claude_Docs__create","mcp__claude_ai_Claude_Docs__delete","mcp__claude_ai_Claude_Docs__export","mcp__claude_ai_Claude_Docs__guide","mcp__claude_ai_Claude_Docs__query","mcp__claude_ai_Claude_Docs__read","mcp__claude_ai_Claude_Docs__update","mcp__claude_ai_Fastmail__list_calendars","mcp__claude_ai_Fastmail__list_identities","mcp__claude_ai_Fastmail__list_labels","mcp__claude_ai_Fastmail__read_attachment","mcp__claude_ai_Fastmail__read_email","mcp__claude_ai_Fastmail__read_note","mcp__claude_ai_Fastmail__read_thread","mcp__claude_ai_Fastmail__search_contacts","mcp__claude_ai_Fastmail__search_email","mcp__claude_ai_Fastmail__search_events","mcp__claude_ai_Fastmail__search_notes","mcp__claude_ai_Fastmail__search_org_contacts","mcp__claude_ai_Heliosian__helios_activities","mcp__claude_ai_Heliosian__helios_classroom","mcp__claude_ai_Heliosian__helios_days","mcp__claude_ai_Heliosian__helios_describe_schema","mcp__claude_ai_Heliosian__helios_describe_table","mcp__claude_ai_Heliosian__helios_events","mcp__claude_ai_Heliosian__helios_find_people","mcp__claude_ai_Heliosian__helios_get","mcp__claude_ai_Heliosian__helios_group","mcp__claude_ai_Heliosian__helios_links","mcp__claude_ai_Heliosian__helios_lists","mcp__claude_ai_Heliosian__helios_nearby_families","mcp__claude_ai_Heliosian__helios_parties","mcp__claude_ai_Heliosian__helios_policies","mcp__claude_ai_Heliosian__helios_query","mcp__claude_ai_Heliosian__helios_query_json","mcp__claude_ai_Heliosian__helios_read_document","mcp__claude_ai_Heliosian__helios_search","mcp__claude_ai_Heliosian__helios_similar","mcp__claude_ai_Heliosian__helios_whoami"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"connected","source":"claudeai"},{"name":"claude.ai Heliosian","status":"connected","source":"claudeai"},{"name":"claude.ai Fastmail","status":"connected","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"1a1ff232-7502-4358-bfe2-9249be1af336","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt2595525365-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt2595525365-001/05c42b7f-81dd-4f05-915b-691a2ca162cf/scratchpad","messaging_socket_path":"/tmp/cc-socks/12877.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","uuid":"7248679d-9ecb-4abc-860a-3fe1c44a6dce"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PEEY7UPDDkjzdczvDX","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37631,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","uuid":"2534aeda-e7b8-4e59-869e-be999b03c4c8","timestamp":"2026-10-15T04:22:34.785Z","request_id":"req_011Cg3PEEGFNZbUTLeP7RgQD"}} -{"dir":"recv","msg":{"duration_api_ms":3936,"stop_reason":"end_turn","session_id":"05c42b7f-81dd-4f05-915b-691a2ca162cf","total_cost_usd":0.0874623,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37631,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":4772,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37631,"cache_creation_input_tokens":4772,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":118,"cacheReadInputTokens":59998,"cacheCreationInputTokens":20036,"webSearchRequests":0,"costUSD":0.0873318,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":994,"type":"result","duration_ms":1012,"uuid":"09385359-ee8f-480c-ba5a-a1d7e87d4aeb","ttft_stream_ms":993,"time_to_request_ms":8,"first_content_frame_ms":993,"queued_turn_count":0,"result_index":1}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt3697698025/001","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"08bf3d7f-2945-4866-882f-3d7e0c023e2e","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3697698025-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3697698025-001/73371b04-bd33-470f-acf0-e14b5d8bf691/scratchpad","messaging_socket_path":"/tmp/cc-socks/30376.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"c89a954e-d155-4474-8651-7d83117287d2"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"e6153c33-eaab-4202-aaa2-b5ea87592369","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"380740e5-4d8c-4f2a-83a3-bfe0c5a5a32b"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":198,"estimated_tokens_delta":148,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"ee491c98-c5cc-4d77-8235-2cc8f823863d"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCtB4ygxypUb41qFsX","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15262,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15262},"output_tokens":10,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"1b2eaffc-bba4-42bd-984b-9d85fbbf3605","timestamp":"2026-10-15T05:27:52.093Z","request_id":"req_011Cg3UCsuSEyDwnSS8nVdYz","thinking_duration_ms":752,"thinking_display":"updates"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCtB4ygxypUb41qFsX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015rzTRLEXa4cuBixDUMEL49","name":"Bash","input":{"command":"timeout 150 ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":160000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15262,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15262},"output_tokens":10,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"eba1b1b0-818e-4c2a-bbbf-c6c1d1d1c395","timestamp":"2026-10-15T05:27:52.604Z","request_id":"req_011Cg3UCsuSEyDwnSS8nVdYz","wire_tool_inputs":{"toolu_015rzTRLEXa4cuBixDUMEL49":{"command":"timeout 150 ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":160000}}}} +{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_3eccbced6631a539","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_3eccbced6631a539","response":{"still_queued":[]}}}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"The user doesn't want to proceed with this tool use. The tool use was rejected (eg. if it was a file edit, the new_string was NOT written to the file). STOP what you are doing and wait for the user to tell you how to proceed.\n\nNote: The user's next message may contain a correction or preference. Pay close attention — if they explain what went wrong or how they'd prefer you to work, consider saving that to memory for future sessions.","is_error":true,"tool_use_id":"toolu_015rzTRLEXa4cuBixDUMEL49"}]},"parent_tool_use_id":null,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"d6c7c1bb-8643-4620-9e8b-d88b8e7cbeeb","timestamp":"2026-10-15T05:27:54.613Z","tool_use_result":"User rejected tool use","tool_result_meta":[{"id":"toolu_015rzTRLEXa4cuBixDUMEL49","non_execution_kind":"user-rejected"}]}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user for tool use]"}]},"parent_tool_use_id":null,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"9c8a0a43-81ad-4404-b449-ea672d6fd1bc","timestamp":"2026-10-15T05:27:54.614Z"}} +{"dir":"recv","msg":{"duration_api_ms":3830,"stop_reason":"tool_use","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","total_cost_usd":0.06549920000000001,"usage":{"input_tokens":2,"cache_creation_input_tokens":15262,"cache_read_input_tokens":22367,"output_tokens":208,"output_tokens_details":{"thinking_tokens":87},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15262,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":208,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15262,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15262},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":208,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15262,"webSearchRequests":0,"costUSD":0.0653687,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":87,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"aborted_tools","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":true,"num_turns":3,"subtype":"error_during_execution","errors":["[ede_diagnostic] result_type=user last_content_type=n/a stop_reason=tool_use"],"type":"result","duration_ms":5121,"uuid":"1a026f7a-6cc7-4798-9d85-8e614ff9981b","queued_turn_count":0,"result_index":0}} +{"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt3697698025/001","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","ListMcpResourcesTool","LSP","Monitor","NotebookEdit","PushNotification","Read","ReadMcpResourceDirTool","ReadMcpResourceTool","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__claude_ai_Claude_Docs__batch","mcp__claude_ai_Claude_Docs__create","mcp__claude_ai_Claude_Docs__delete","mcp__claude_ai_Claude_Docs__export","mcp__claude_ai_Claude_Docs__guide","mcp__claude_ai_Claude_Docs__query","mcp__claude_ai_Claude_Docs__read","mcp__claude_ai_Claude_Docs__update","mcp__claude_ai_Fastmail__list_calendars","mcp__claude_ai_Fastmail__list_identities","mcp__claude_ai_Fastmail__list_labels","mcp__claude_ai_Fastmail__read_attachment","mcp__claude_ai_Fastmail__read_email","mcp__claude_ai_Fastmail__read_note","mcp__claude_ai_Fastmail__read_thread","mcp__claude_ai_Fastmail__search_contacts","mcp__claude_ai_Fastmail__search_email","mcp__claude_ai_Fastmail__search_events","mcp__claude_ai_Fastmail__search_notes","mcp__claude_ai_Fastmail__search_org_contacts","mcp__claude_ai_Heliosian__helios_activities","mcp__claude_ai_Heliosian__helios_classroom","mcp__claude_ai_Heliosian__helios_days","mcp__claude_ai_Heliosian__helios_describe_schema","mcp__claude_ai_Heliosian__helios_describe_table","mcp__claude_ai_Heliosian__helios_events","mcp__claude_ai_Heliosian__helios_find_people","mcp__claude_ai_Heliosian__helios_get","mcp__claude_ai_Heliosian__helios_group","mcp__claude_ai_Heliosian__helios_links","mcp__claude_ai_Heliosian__helios_lists","mcp__claude_ai_Heliosian__helios_nearby_families","mcp__claude_ai_Heliosian__helios_parties","mcp__claude_ai_Heliosian__helios_policies","mcp__claude_ai_Heliosian__helios_query","mcp__claude_ai_Heliosian__helios_query_json","mcp__claude_ai_Heliosian__helios_read_document","mcp__claude_ai_Heliosian__helios_search","mcp__claude_ai_Heliosian__helios_similar","mcp__claude_ai_Heliosian__helios_whoami"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"connected","source":"claudeai"},{"name":"claude.ai Heliosian","status":"connected","source":"claudeai"},{"name":"claude.ai Fastmail","status":"connected","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"83202ae1-5a4b-488f-b90f-eedafbd2b1f0","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3697698025-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3697698025-001/73371b04-bd33-470f-acf0-e14b5d8bf691/scratchpad","messaging_socket_path":"/tmp/cc-socks/30376.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"592f605b-8dad-416b-926e-a6747f6d03b3"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UDFkLs4HGSejfx1uJP","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4866,"cache_read_input_tokens":37629,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4866},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","uuid":"ecf0e625-1ee6-4faa-a8b9-8d7f47a907dd","timestamp":"2026-10-15T05:27:55.806Z","request_id":"req_011Cg3UDFVUFMP1QsLfPoGiT"}} +{"dir":"recv","msg":{"duration_api_ms":5022,"stop_reason":"end_turn","session_id":"73371b04-bd33-470f-acf0-e14b5d8bf691","total_cost_usd":0.0887701,"usage":{"input_tokens":2,"cache_creation_input_tokens":4866,"cache_read_input_tokens":37629,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":4866,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37629,"cache_creation_input_tokens":4866,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4866},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":212,"cacheReadInputTokens":59996,"cacheCreationInputTokens":20128,"webSearchRequests":0,"costUSD":0.0886396,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":87,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1188,"type":"result","duration_ms":1208,"uuid":"920474bd-58c0-4020-82f6-5ff6789f4e96","ttft_stream_ms":1186,"time_to_request_ms":10,"first_content_frame_ms":1187,"queued_turn_count":0,"result_index":1}} diff --git a/internal/claude/testdata/transcripts/TestResume-first.jsonl b/internal/claude/testdata/transcripts/TestResume-first.jsonl index 61a5401..a82aec4 100644 --- a/internal/claude/testdata/transcripts/TestResume-first.jsonl +++ b/internal/claude/testdata/transcripts/TestResume-first.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_fada41897fe2b498","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_fada41897fe2b498","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":12879,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_ffcd92379bd727fe","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_ffcd92379bd727fe","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":30378,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Remember the codeword AZURE-17. Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume631419293/001","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"5739f16c-908a-40ef-af37-10f3be4d3810","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume631419293-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume631419293-001/3c0da634-cb14-4a4d-ba11-57538393d6a9/scratchpad","messaging_socket_path":"/tmp/cc-socks/12879.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","uuid":"a1b217b3-43ec-4714-8bcf-e38e50be014d"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"de9a2406-1b88-438e-8fbb-ecd0f3ec86fa","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PDvg4zP1dgZKTDrhJU","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15230,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15230},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","uuid":"c2bef50f-60e7-490d-bb34-4a271ba81819","timestamp":"2026-10-15T04:22:30.962Z","request_id":"req_011Cg3PDvGGWqFA6UU9GhoTm"}} -{"dir":"recv","msg":{"duration_api_ms":2150,"stop_reason":"end_turn","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","total_cost_usd":0.06333,"usage":{"input_tokens":2,"cache_creation_input_tokens":15230,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15230,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15230,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15230},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15230,"webSearchRequests":0,"costUSD":0.0632007,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1530,"type":"result","duration_ms":1546,"uuid":"ef0e8d5b-6ab8-4040-a7ca-68f02c3808c4","ttft_stream_ms":1526,"time_to_request_ms":30,"first_content_frame_ms":1526,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume2170932437/001","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"3ff06749-d2d1-44d0-8b7c-f93c58888e6a","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2170932437-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2170932437-001/37a9f822-ad8c-4288-b81e-2b34213cef6a/scratchpad","messaging_socket_path":"/tmp/cc-socks/30378.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","uuid":"0e42b7c9-c2b7-42b6-9a46-fa3699ca750f"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"111b1acf-fa82-4b31-b9ec-0b7dcd97ce15","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCtQi6VChmZJwDGyAx","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15232,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15232},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","uuid":"5186e4c1-8d08-4f51-9e43-816d602dafa1","timestamp":"2026-10-15T05:27:51.464Z","request_id":"req_011Cg3UCt8Lg6BHCjEvzfFqZ"}} +{"dir":"recv","msg":{"duration_api_ms":2573,"stop_reason":"end_turn","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","total_cost_usd":0.063338,"usage":{"input_tokens":2,"cache_creation_input_tokens":15232,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15232,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15232,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15232},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15232,"webSearchRequests":0,"costUSD":0.0632087,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1923,"type":"result","duration_ms":1945,"uuid":"3ee116ad-5426-4279-b7bd-0a9cc5ab0acb","ttft_stream_ms":1922,"time_to_request_ms":35,"first_content_frame_ms":1922,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl index 586e0e7..ecb3751 100644 --- a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl +++ b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_a7865d9ba62d762f","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_a7865d9ba62d762f","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":13530,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} -{"dir":"send","msg":{"message":{"content":"What was the codeword? Reply with just the codeword.","role":"user"},"parent_tool_use_id":null,"session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume631419293/001","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"3a7452ac-e549-4dd5-8274-6c8323153064","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume631419293-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume631419293-001/3c0da634-cb14-4a4d-ba11-57538393d6a9/scratchpad","messaging_socket_path":"/tmp/cc-socks/13530.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","uuid":"3dc8ac03-4815-4ef1-a5e6-3b267380ea68"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PEA2zvjrsK2T5DxhLe","type":"message","role":"assistant","content":[{"type":"text","text":"AZURE-17"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7015,"cache_read_input_tokens":30629,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7015},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13150}},"context_management":null},"parent_tool_use_id":null,"session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","uuid":"7b33026d-3085-4b3e-8cbd-dbd8d9375238","timestamp":"2026-10-15T04:22:34.045Z","request_id":"req_011Cg3PE9egUrHLLoWpynRjA"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"ad9c616f-fc04-46c8-b8bc-040446d0668f","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9"}} -{"dir":"recv","msg":{"duration_api_ms":3519,"stop_reason":"end_turn","session_id":"3c0da634-cb14-4a4d-ba11-57538393d6a9","total_cost_usd":0.09453690000000001,"usage":{"input_tokens":2,"cache_creation_input_tokens":7015,"cache_read_input_tokens":30629,"output_tokens":8,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":7015,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":8,"cache_read_input_tokens":30629,"cache_creation_input_tokens":7015,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7015},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"thinkingTokens":0,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":12,"thinkingTokens":0,"cacheReadInputTokens":52996,"cacheCreationInputTokens":22245,"webSearchRequests":0,"costUSD":0.09440760000000001,"contextWindow":1000000,"maxOutputTokens":128000,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"AZURE-17","ttft_ms":1385,"type":"result","duration_ms":1406,"uuid":"26501256-8cad-4fea-a06a-740ba3bc4625","ttft_stream_ms":1379,"time_to_request_ms":34,"first_content_frame_ms":1380,"queued_turn_count":0,"result_index":0}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_6bd626b80499b9d3","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_6bd626b80499b9d3","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":31135,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"message":{"content":"What was the codeword? Reply with just the codeword.","role":"user"},"parent_tool_use_id":null,"session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume2170932437/001","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"4cfb62f1-7c08-48cc-86af-dc3c1df35810","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2170932437-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2170932437-001/37a9f822-ad8c-4288-b81e-2b34213cef6a/scratchpad","messaging_socket_path":"/tmp/cc-socks/31135.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","uuid":"3d882533-58bb-4b71-9557-5deac76bd8a4"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UD9NchLTMj1ZirY6Gd","type":"message","role":"assistant","content":[{"type":"text","text":"AZURE-17"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7017,"cache_read_input_tokens":30629,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7017},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13150}},"context_management":null},"parent_tool_use_id":null,"session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","uuid":"b92fb3a2-e5d5-4db4-b08e-8312bf967ebf","timestamp":"2026-10-15T05:27:54.425Z","request_id":"req_011Cg3UD98VAYyxGpAthLNqU"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"d950e71a-8eed-4c7f-9b7b-31e6e14080d8","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a"}} +{"dir":"recv","msg":{"duration_api_ms":3896,"stop_reason":"end_turn","session_id":"37a9f822-ad8c-4288-b81e-2b34213cef6a","total_cost_usd":0.09455290000000001,"usage":{"input_tokens":2,"cache_creation_input_tokens":7017,"cache_read_input_tokens":30629,"output_tokens":8,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":7017,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":8,"cache_read_input_tokens":30629,"cache_creation_input_tokens":7017,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7017},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"thinkingTokens":0,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":12,"thinkingTokens":0,"cacheReadInputTokens":52996,"cacheCreationInputTokens":22249,"webSearchRequests":0,"costUSD":0.09442360000000001,"contextWindow":1000000,"maxOutputTokens":128000,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"AZURE-17","ttft_ms":1341,"type":"result","duration_ms":1356,"uuid":"64fd8499-ddb7-434e-80d4-fcdd2d43cd2b","ttft_stream_ms":1335,"time_to_request_ms":32,"first_content_frame_ms":1335,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl index f14dbe7..3300d15 100644 --- a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl +++ b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl @@ -1,16 +1,16 @@ -{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_445b13d62e755c5b","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_445b13d62e755c5b","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":12878,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_2e88ce8fe4a3993c","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_2e88ce8fe4a3993c","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":30379,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks786577145/001","session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"43655c3f-4e0f-475e-8598-921ee59cc1db","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks786577145-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks786577145-001/24045dcf-e93b-468d-98a6-41cad91ae43f/scratchpad","messaging_socket_path":"/tmp/cc-socks/12878.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","uuid":"6b637fb7-9886-4e26-8e8b-a579c7864943"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"b7239b4c-abef-46ac-bdb4-143238bc8166","session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PDvTvaWXPfS6wgUTp2","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15233,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15233},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","uuid":"9ee099d9-82e7-449b-a837-589b5b22b4d0","timestamp":"2026-10-15T04:22:31.081Z","request_id":"req_011Cg3PDvEHVxtHNnekGmy4r"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"a2586822-4fe3-49fa-8e63-2b82facaf176","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks786577145-001/24045dcf-e93b-468d-98a6-41cad91ae43f.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks786577145/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks786577145-001/24045dcf-e93b-468d-98a6-41cad91ae43f/scratchpad","prompt_id":"24769c4c-fae5-4371-b334-6c97516120b2","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":false,"last_assistant_message":"ok","background_tasks":[],"session_crons":[]},"tool_use_id":"a2fdc947-4e6a-4e01-8a68-4ad2be62770c"}}} -{"dir":"send","msg":{"response":{"request_id":"a2586822-4fe3-49fa-8e63-2b82facaf176","response":{"decision":"block","reason":"Before stopping, reply with the single word PINEAPPLE."},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"Stop hook feedback:\nBefore stopping, reply with the single word PINEAPPLE."}]},"parent_tool_use_id":null,"session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","uuid":"a9cd980f-bab2-4a93-a54f-4c53bcffc0e8","timestamp":"2026-10-15T04:22:31.101Z","isSynthetic":true}} -{"dir":"recv","msg":{"type":"system","subtype":"notification","key":"stop-hook-error","text":"Stop hook error occurred · ctrl+o to see","priority":"immediate","session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","uuid":"6daf56aa-13b9-4200-a607-106b4ee42730"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","uuid":"9b67aae1-d116-46b4-a782-25230eca0c7d"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PE33ZAJ3VeD9gFMPdk","type":"message","role":"assistant","content":[{"type":"text","text":"PINEAPPLE"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7059,"cache_read_input_tokens":30621,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7059},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13144}},"context_management":null},"parent_tool_use_id":null,"session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","uuid":"b707bcad-8665-4403-808f-2f4cff676583","timestamp":"2026-10-15T04:22:32.484Z","request_id":"req_011Cg3PE2nRsvAMNWdtauk61"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"3629dfe5-eece-49db-9b8f-a5b43b6d8eb1","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks786577145-001/24045dcf-e93b-468d-98a6-41cad91ae43f.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks786577145/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks786577145-001/24045dcf-e93b-468d-98a6-41cad91ae43f/scratchpad","prompt_id":"24769c4c-fae5-4371-b334-6c97516120b2","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":true,"last_assistant_message":"PINEAPPLE","background_tasks":[],"session_crons":[]},"tool_use_id":"9f8dd092-434c-4874-833a-ab960c0df51f"}}} -{"dir":"send","msg":{"response":{"request_id":"3629dfe5-eece-49db-9b8f-a5b43b6d8eb1","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"duration_api_ms":3617,"stop_reason":"end_turn","session_id":"24045dcf-e93b-468d-98a6-41cad91ae43f","total_cost_usd":0.0947392,"usage":{"input_tokens":4,"cache_creation_input_tokens":22292,"cache_read_input_tokens":52988,"output_tokens":14,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":22292,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30621,"cache_creation_input_tokens":7059,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7059},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1174,"outputTokens":14,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001244,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":14,"cacheReadInputTokens":52988,"cacheCreationInputTokens":22292,"webSearchRequests":0,"costUSD":0.0946148,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":2,"subtype":"success","api_error_status":null,"result":"PINEAPPLE","ttft_ms":1660,"type":"result","duration_ms":3079,"uuid":"0318ac1e-f705-433d-a8a9-d71fd8964e2b","ttft_stream_ms":1653,"time_to_request_ms":27,"first_content_frame_ms":1654,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks825336021/001","session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"3ab0e9b2-3625-4e92-a801-e2b317f0e79f","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks825336021-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks825336021-001/89c67d6d-1eea-4608-88b1-6988074e7bc2/scratchpad","messaging_socket_path":"/tmp/cc-socks/30379.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","uuid":"351bb26c-d1a1-4720-b7d3-c73b5aec4792"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"fde75e63-14c0-40c5-aa07-bc6fb1fcf649","session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCtE3FBz1kxt6Xk2mX","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15233,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15233},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","uuid":"b4c5f9cc-4487-481d-9c95-29a9c0aa0332","timestamp":"2026-10-15T05:27:50.965Z","request_id":"req_011Cg3UCszPukjZFfYGUt1xs"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"87e11c4f-e5c0-4d62-b6fc-33239a5b1f0d","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks825336021-001/89c67d6d-1eea-4608-88b1-6988074e7bc2.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks825336021/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks825336021-001/89c67d6d-1eea-4608-88b1-6988074e7bc2/scratchpad","prompt_id":"f730fd42-3ccd-46f6-bc5f-92f482e4cc86","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":false,"last_assistant_message":"ok","background_tasks":[],"session_crons":[]},"tool_use_id":"b27042cd-029a-49d0-91b0-9768e406fe5b"}}} +{"dir":"send","msg":{"response":{"request_id":"87e11c4f-e5c0-4d62-b6fc-33239a5b1f0d","response":{"decision":"block","reason":"Before stopping, reply with the single word PINEAPPLE."},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"Stop hook feedback:\nBefore stopping, reply with the single word PINEAPPLE."}]},"parent_tool_use_id":null,"session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","uuid":"cc2da827-0b6a-4731-bf7c-31e409615019","timestamp":"2026-10-15T05:27:50.991Z","isSynthetic":true}} +{"dir":"recv","msg":{"type":"system","subtype":"notification","key":"stop-hook-error","text":"Stop hook error occurred · ctrl+o to see","priority":"immediate","session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","uuid":"189bac7d-8eb1-429c-a085-8b26f62c6d21"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","uuid":"f6dd8a81-bd4d-4b60-84df-419f3a2345ad"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCzFCBfREHqNU9G6QL","type":"message","role":"assistant","content":[{"type":"text","text":"PINEAPPLE"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7060,"cache_read_input_tokens":30620,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13144}},"context_management":null},"parent_tool_use_id":null,"session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","uuid":"5d00dbcd-7685-484c-aa83-62f20cac8e29","timestamp":"2026-10-15T05:27:52.324Z","request_id":"req_011Cg3UCyzYyK8xApE7brBTX"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"bc92ff48-d8ea-46c7-b8ec-96c442d9fb1b","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks825336021-001/89c67d6d-1eea-4608-88b1-6988074e7bc2.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks825336021/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks825336021-001/89c67d6d-1eea-4608-88b1-6988074e7bc2/scratchpad","prompt_id":"f730fd42-3ccd-46f6-bc5f-92f482e4cc86","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":true,"last_assistant_message":"PINEAPPLE","background_tasks":[],"session_crons":[]},"tool_use_id":"3d1b32cf-2fdf-4bf5-b288-ce9d57736e3b"}}} +{"dir":"send","msg":{"response":{"request_id":"bc92ff48-d8ea-46c7-b8ec-96c442d9fb1b","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"duration_api_ms":3949,"stop_reason":"end_turn","session_id":"89c67d6d-1eea-4608-88b1-6988074e7bc2","total_cost_usd":0.0947431,"usage":{"input_tokens":4,"cache_creation_input_tokens":22293,"cache_read_input_tokens":52987,"output_tokens":14,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":22293,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30620,"cache_creation_input_tokens":7060,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1174,"outputTokens":14,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001244,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":14,"cacheReadInputTokens":52987,"cacheCreationInputTokens":22293,"webSearchRequests":0,"costUSD":0.0946187,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":2,"subtype":"success","api_error_status":null,"result":"PINEAPPLE","ttft_ms":1444,"type":"result","duration_ms":2827,"uuid":"e20e2fa7-5821-4d45-8d9b-0c65db7c4447","ttft_stream_ms":1442,"time_to_request_ms":31,"first_content_frame_ms":1442,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestTextDeltas.jsonl b/internal/claude/testdata/transcripts/TestTextDeltas.jsonl index 37e3b2d..33219e6 100644 --- a/internal/claude/testdata/transcripts/TestTextDeltas.jsonl +++ b/internal/claude/testdata/transcripts/TestTextDeltas.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_4ac0ce21d6dc8fd7","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_4ac0ce21d6dc8fd7","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":12875,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_5db6e21d23577dbb","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_5db6e21d23577dbb","response":{"commands":[{"name":"deep-research","description":"Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. (dynamic workflow)","argumentHint":"","builtin":true},{"name":"design","description":"Make a new Design artifact from a brief","argumentHint":"[what to design]","builtin":true},{"name":"slides","description":"Make a new Slides deck artifact from a brief","argumentHint":"[what the deck is about]","builtin":true},{"name":"design-sync","description":"Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says \"sync my design system to Claude Design\".","argumentHint":"[\u003cproject hint, e.g. \"Acme DS\"\u003e]","builtin":true},{"name":"dataviz","description":"Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact, inline SVG, plotting code in any library (matplotlib, plotly, d3, Recharts, …), an image/PNG you will render and upload, or a chart shared into Slack. Read it BEFORE writing the first line of chart code, choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. When the destination is a first-party document connector (host-designated, never self-described) that renders live charts, hand it the rows (inline, or as an uploaded data file the chart cites) rather than a rendered PNG/SVG — a picture of a chart loses hover, data inspection and per-value comments. Produces visualizations that read as one system — elegant, accessible, consistent in light and dark — using a brand-neutral placeholder palette you swap for your own. Teaches a design-system-agnostic method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"visualization\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential / diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","argumentHint":"","builtin":true},{"name":"artifact-diagramming","description":"Diagramming know-how for Artifacts - when a picture earns its place, how to draw one that shows the real mechanism, and the inline-SVG mechanics that keep it legible in both themes.","argumentHint":"","builtin":true},{"name":"artifact-capabilities","description":"Runtime capabilities a published Artifact page can be granted — behavior static HTML cannot provide on its own, such as the page reading live or connected data, remembering what people do on it (a poll, a sign-up sheet, a checklist, a document edited in place — it saves new versions of itself), keeping state shared across viewers, knowing who is viewing, asking Claude a question of its own, storing files people add, handing the viewer a file to save, or using the viewer's camera, microphone, location, screen or device motion. Serves this user's live capability roster and the typed call definitions. Load it whenever any such runtime behavior would make an artifact more useful, before writing the page.","argumentHint":"","builtin":true},{"name":"update-config","description":"Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.","argumentHint":"","builtin":true},{"name":"verify","description":"Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.","argumentHint":"","builtin":true},{"name":"debug","description":"Enable debug logging for this session and help diagnose issues","argumentHint":"[issue description]","builtin":true},{"name":"code-review","description":"Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep multi-agent review in the cloud); with no level given, it reuses the level you typed last. Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review. Pass --max-findings \u003cn\u003e to report up to n findings, or --max-findings all for every finding. The choice stays until you pass --max-findings default. For ultra on a GitHub.com PR target, --post asks to post the finished review’s findings to the PR as a single comment from the user’s GitHub account (not a review; the launch dialog still confirms in interactive sessions, while non-interactive mode posts on the flag alone) and --no-post hides that option.","argumentHint":"[low|medium|high|xhigh|max|ultra] [--fix] [--comment] [\u003cpr#\u003e|\u003cbranch\u003e|\u003cpath\u003e] [--max-findings \u003cn\u003e|all]","aliases":["review"],"builtin":true},{"name":"simplify","description":"Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.","argumentHint":"[\u003ctarget\u003e]","builtin":true},{"name":"batch","description":"Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.","argumentHint":"\u003cinstruction\u003e","builtin":true},{"name":"fewer-permission-prompts","description":"Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.","argumentHint":"","builtin":true},{"name":"doctor","description":"Health-check the user's Claude Code setup and fix issues: diagnose installation health — what the `claude doctor` terminal diagnostics cover — from local data (duplicate or leftover installs, PATH, unparseable settings files, broken or colliding agent definitions, skills whose frontmatter fails to parse); find unused skills, MCP servers, and plugins versus their context cost and disable dead weight; deduplicate local CLAUDE.md files against checked-in ones; trim checked-in CLAUDE.md files by cutting content a session could derive from the codebase (directory layouts, tech-stack lists, architecture overviews) while keeping gotchas, rationale, and non-standard conventions; migrate always-loaded CLAUDE.md guidance into lazy skills and nested CLAUDE.md files; flag slow hooks and context-heavy extensions; check the installed version is current; make auto mode the default permission mode; and pre-approve frequently denied read-only commands. Use when the user asks for a doctor run, checkup, audit, tune-up, or cleanup of their Claude Code setup or configuration.","argumentHint":"[prompt-audit [\u003cpath\u003e]]","aliases":["checkup"],"builtin":true},{"name":"loop","description":"Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace.","argumentHint":"[interval] [prompt]","aliases":["proactive"],"builtin":true},{"name":"schedule","description":"Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule.","argumentHint":"","aliases":["routines"],"builtin":true},{"name":"claude-api","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","argumentHint":"","builtin":true},{"name":"workflow-authoring","description":"Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.","argumentHint":"","builtin":true},{"name":"run","description":"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","argumentHint":"","builtin":true},{"name":"run-skill-generator","description":"Author or improve the run-\u003cunit\u003e skill - a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.","argumentHint":"","builtin":true},{"name":"plugin-authoring","description":"Make a mod: a change to Claude's own interface or behaviour, such as a live pane or panel, a band above the prompt, a status line, a toast, a slash command, or a hook on tool calls or prompts. Use to make, change or debug a mod or its hooks module.","argumentHint":"","builtin":true},{"name":"advisor","description":"Let Claude consult a stronger model at key moments","argumentHint":"[fable|opus|sonnet|off]","builtin":true},{"name":"agents","description":"(removed) Ask Claude to create/manage subagents, or edit .claude/agents/","argumentHint":"","builtin":true},{"name":"auto-mode-setup","description":"Teach auto mode about your environment, plus optional rule tweaks","argumentHint":"[--request-id \u003cuuid\u003e] (--wizard posture=… scope=… depth=… --propose | --expect-sha256 \u003c64-hex\u003e --apply-file \u003cpath\u003e)","builtin":true},{"name":"autocompact","description":"Configure the auto-compact window size","argumentHint":"[auto|\u003ctokens\u003e]","builtin":true},{"name":"clear","description":"Start a new session with empty context; previous session stays on disk (resumable with /resume)","argumentHint":"[name]","aliases":["reset","new"],"builtin":true},{"name":"color","description":"Set the prompt bar color for this session","argumentHint":"[red|blue|green|yellow|purple|orange|pink|cyan|default]","builtin":true},{"name":"compact","description":"Free up context by summarizing the conversation so far","argumentHint":"\u003coptional custom summarization instructions\u003e","builtin":true},{"name":"config","description":"Set a setting by key","argumentHint":"key=value","aliases":["settings"],"builtin":true},{"name":"output-style","description":"List output styles or switch to one","argumentHint":"[style]","builtin":true},{"name":"context","description":"Show current context usage","argumentHint":"","builtin":true},{"name":"effort","description":"Set effort level for model usage","argumentHint":"\u003clow|medium|high|xhigh|max|auto|ultracode [on|off]\u003e","builtin":true},{"name":"fast","description":"Toggle fast mode (Opus 5.5)","argumentHint":"[on|off]","builtin":true},{"name":"focus","description":"Toggle focus view: just your prompt, summary, and response","argumentHint":"[on|off]","builtin":true},{"name":"heapdump","description":"Dump the JS heap to the Desktop; on Linux with no Desktop folder, the home directory","argumentHint":"","builtin":true},{"name":"init","description":"Initialize a new CLAUDE.md file with codebase documentation","argumentHint":"","builtin":true},{"name":"mcp","description":"Manage MCP servers","argumentHint":"[reconnect|enable|disable [\u003cserver\u003e|all]]","builtin":true},{"name":"import","description":"Import config from another AI coding agent","argumentHint":"","builtin":true},{"name":"model","description":"Set the AI model for Claude Code","argumentHint":"\u003cmodel\u003e","builtin":true},{"name":"__remote-workflow","description":"Run the workflow script delivered in this session environment (server-launched sessions only)","argumentHint":"","builtin":true},{"name":"workflow-launch-exec","description":"Execute a server-launched workflow handoff (workflow_launch event sessions only)","argumentHint":"","builtin":true},{"name":"reload-plugins","description":"Activate pending plugin changes in the current session","argumentHint":"[--force]","builtin":true},{"name":"reload-skills","description":"Pick up skills added or changed on disk during this session","argumentHint":"","builtin":true},{"name":"rename","description":"Rename the current conversation","argumentHint":"[name]","aliases":["name"],"builtin":true},{"name":"ultrareview","description":"Start a cloud agent that finds and verifies bugs in your branch (~15-25 min, $5-$25 USD) · Runs in a cloud session. See https://code.claude.com/docs/en/claude-code-on-the-web","argumentHint":"","builtin":true},{"name":"security-review","description":"Complete a security review of the pending changes on the current branch","argumentHint":"","builtin":true},{"name":"usage-credits","description":"Configure usage credits or request them from your admin when you hit a limit","argumentHint":"","builtin":true},{"name":"extra-usage","description":"Renamed to /usage-credits","argumentHint":"","builtin":true},{"name":"usage","description":"Show session cost, plan usage, and what's contributing to your limits","argumentHint":"","aliases":["cost","stats"],"builtin":true},{"name":"insights","description":"Generate a report analyzing your Claude Code sessions","argumentHint":"","builtin":true},{"name":"recap","description":"Generate a one-line session recap now","argumentHint":"","builtin":true},{"name":"skill-doctor","description":"Show which loaded skills are unused and costing context","argumentHint":"","builtin":true},{"name":"goal","description":"Set a goal — keep working until the condition is met","argumentHint":"","builtin":true},{"name":"design-consent","description":"Grant Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"design-revoke","description":"Revoke Claude agent access to your Design projects","argumentHint":"","builtin":true},{"name":"list-agents","description":"List subagents, teammates, and other Claude sessions you can message","argumentHint":"","aliases":["peers"],"builtin":true},{"name":"team-onboarding","description":"Help teammates ramp on Claude Code with a guide from your usage","argumentHint":"","builtin":true},{"name":"docs","description":"docs (editable docs people share and comment on; the default for any document, named as a doc or not: a document, report, proposal, resume, cover letter, letter, contract, policy, form, template, worksheet, essay, handbook, guide, how-to, cheat sheet, SOP or other writing to keep, share, collaborate on, send, submit, print or sign; a doc exports to Word, PDF, Markdown or Google Docs, so needing a file to send, attach, upload, submit or print is no reason to pick Word, and a file nobody asked for is a doc, not Word; a plan, comparison, summary or notes asked in chat stays in chat; a pasted claude.ai artifact link may be a doc: check with docs tools first; Word or another file format named, tracked changes wanted, or a .docx to change or use as a template → that format's skill): making one → if no docs-connector instructions are in context, call its `guide` (topic.instructions) first; then create the doc (headings only, no body) before any search, file read or plan, even with files attached. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docs"]},{"name":"docx","description":"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of Microsoft Word Documents, such as 'Word doc', 'word document', '.docx', '.dotx', 'microsoft doc'. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers Claude's own dedicated document or page skill or connector, use that instead, even if they will email or print it. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:docx"]},{"name":"google-workspace","description":"Read this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs, Sheets, Slides or Drive and asks to make, edit, format, copy or rename a file; a docs.google.com link with a request to change that file, even a one-line fix or suggested edits; and any follow-up change to a Google file from earlier in the chat, even \"change it\" or \"add a tab\". Includes helper scripts for document positions, cell ranges and slide layout. However, if the user asks for a doc, deck or spreadsheet without naming Google, or gives a Google file only as source material for something new, use Claude's own output type instead. Do NOT use for read-only questions about a Google file, or for Word, Excel, PowerPoint or PDF files. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:google-workspace"]},{"name":"import-memory","description":"Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:import-memory"]},{"name":"morning","description":"Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer it directly instead. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:morning"]},{"name":"pdf","description":"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pdf"]},{"name":"pptx","description":"Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email, summary, or creating a different type of slide deck); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user asks for a PowerPoint or .pptx file, or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. However, when the user asks for a deck, slides, a slide deck, or a presentation without naming a file format, default to using a dedicated slide-deck artifact type or a separate slides skill if this session offers one; otherwise, use this skill. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:pptx"]},{"name":"skill-creator","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:skill-creator"]},{"name":"xlsx","description":"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. (claude.ai sync)","argumentHint":"","aliases":["anthropic-skills:xlsx"]}],"agents":[{"name":"claude","description":"Catch-all for any task that doesn't fit a more specific agent. FleetView's default when no agent name is typed."},{"name":"claude-code-guide","description":"Use this agent when the user asks questions (\"Can Claude...\", \"Does Claude...\", \"How do I...\") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - Messages API for directly passing messages to Claude, Tool Runner (`client.beta.messages.tool_runner`) for running an agentic loop over your own tools, manual tool-use loops, Managed Agents for server-hosted agents with a managed sandbox, prompt caching, and general Anthropic SDK usage; (4) Claude Tag (Claude in Slack) - what it is, setting it up for a Slack workspace, `/install-slack-app`; (5) `claude plugin eval` (writing and running plugin eval suites, its JSON/report, sandbox, CI) and the `/skill-doctor` report. **IMPORTANT:** Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can continue via SendMessage.","model":"haiku"},{"name":"Explore","description":"Fast read-only search agent for locating code. Use it to find files by pattern (eg. \"src/components/**/*.tsx\"), grep for symbols or keywords (eg. \"API endpoints\"), or answer \"where is X defined / which files reference Y.\" Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis — it reads excerpts rather than whole files and will miss content past its read window. When calling, specify search breadth: \"quick\" for a single targeted lookup, \"medium\" for moderate exploration, or \"very thorough\" to search across multiple locations and naming conventions.","model":"inherit"},{"name":"general-purpose","description":"General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you."},{"name":"Plan","description":"Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.","model":"inherit"},{"name":"statusline-setup","description":"Use this agent to configure the user's Claude Code status line setting.","model":"sonnet"}],"output_style":"default","available_output_styles":["default","Proactive","Concise","Explanatory","Learning"],"user_output_styles_dir":"/Users/flamingcow/.claude/output-styles","models":[{"value":"default","resolvedModel":"claude-opus-5-5","displayName":"Default (recommended)","description":"Opus 5.5 · Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"opus","resolvedModel":"claude-opus-5-5","displayName":"Opus 5.5","description":"For complex work and everyday tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"fable","resolvedModel":"claude-fable-5-1","displayName":"Fable 5.1","description":"For your toughest challenges","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"sonnet","resolvedModel":"claude-sonnet-5-5","displayName":"Sonnet 5.5","description":"Most efficient for simpler tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"haiku","resolvedModel":"claude-haiku-5-5","displayName":"Haiku 5.5","description":"Fastest for quick answers","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-haiku-4-5-20251001","resolvedModel":"claude-haiku-4-5-20251001","displayName":"Haiku 4.5","description":"Fastest for quick answers"},{"value":"claude-sonnet-5","resolvedModel":"claude-sonnet-5","displayName":"Sonnet 5","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-5","resolvedModel":"claude-opus-5","displayName":"Opus 5","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-fable-5","resolvedModel":"claude-fable-5","displayName":"Fable 5","description":"Most capable for your hardest and longest-running tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-8","resolvedModel":"claude-opus-4-8","displayName":"Opus 4.8","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsFastMode":true,"supportsAutoMode":true},{"value":"claude-opus-4-7","resolvedModel":"claude-opus-4-7","displayName":"Opus 4.7","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","xhigh","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-opus-4-6","resolvedModel":"claude-opus-4-6","displayName":"Opus 4.6","description":"Best for everyday, complex tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true},{"value":"claude-sonnet-4-6","resolvedModel":"claude-sonnet-4-6","displayName":"Sonnet 4.6","description":"Efficient for routine tasks","supportsEffort":true,"supportedEffortLevels":["low","medium","high","max"],"supportsAdaptiveThinking":true,"supportsAutoMode":true}],"account":{"email":"[redacted]","organization":"[redacted]'s Organization","subscriptionType":"Claude Max","apiProvider":"firstParty"},"pid":30377,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Without using any tools, count from one to twenty in words, separated by spaces.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestTextDeltas101965551/001","session_id":"01471592-8eb7-4530-89ec-c22ff173d226","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"fd5c32ae-61b7-4925-87ca-921e15bedb6c","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas101965551-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas101965551-001/01471592-8eb7-4530-89ec-c22ff173d226/scratchpad","messaging_socket_path":"/tmp/cc-socks/12875.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"01471592-8eb7-4530-89ec-c22ff173d226","uuid":"e1694db2-de78-4135-be64-8efc4f6ba962"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.05,"resetsAt":1792054200},"seven_day":{"utilization":0.35,"resetsAt":1792270800}}},"uuid":"8284de47-e2fa-4a89-a68a-d8384c9e9888","session_id":"01471592-8eb7-4530-89ec-c22ff173d226"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3PDv5McKBQ7hB9ob9U5","type":"message","role":"assistant","content":[{"type":"text","text":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15239,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15239},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"01471592-8eb7-4530-89ec-c22ff173d226","uuid":"0d32072f-9496-4f0c-bd38-19d4cd3e1c99","timestamp":"2026-10-15T04:22:31.259Z","request_id":"req_011Cg3PDuojoogPsnD1EehDH"}} -{"dir":"recv","msg":{"duration_api_ms":2475,"stop_reason":"end_turn","session_id":"01471592-8eb7-4530-89ec-c22ff173d226","total_cost_usd":0.0638545,"usage":{"input_tokens":2,"cache_creation_input_tokens":15239,"cache_read_input_tokens":22367,"output_tokens":53,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15239,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":53,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15239,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15239},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012780000000000002,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":53,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15239,"webSearchRequests":0,"costUSD":0.0637267,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty","ttft_ms":1881,"type":"result","duration_ms":1913,"uuid":"b3ccd378-3156-4c84-a20b-5db0545a2f7a","ttft_stream_ms":1289,"time_to_request_ms":23,"first_content_frame_ms":1289,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestTextDeltas3930789421/001","session_id":"397c02eb-2bf7-462d-9daa-1859b156e6eb","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"56c9b22e-84d7-40cc-a9cb-a11aff984123","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas3930789421-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas3930789421-001/397c02eb-2bf7-462d-9daa-1859b156e6eb/scratchpad","messaging_socket_path":"/tmp/cc-socks/30377.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"397c02eb-2bf7-462d-9daa-1859b156e6eb","uuid":"309c434e-b753-4c87-bac5-2dc37c6ce61e"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.09,"resetsAt":1792054200},"seven_day":{"utilization":0.36,"resetsAt":1792270800}}},"uuid":"4c27482e-062a-427e-9aa5-2f285e68cb95","session_id":"397c02eb-2bf7-462d-9daa-1859b156e6eb"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3UCtC3ohND1K7Z2oEuu","type":"message","role":"assistant","content":[{"type":"text","text":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15244,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15244},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"397c02eb-2bf7-462d-9daa-1859b156e6eb","uuid":"19674b20-1a45-4e63-8d94-79c3ad7169ec","timestamp":"2026-10-15T05:27:51.372Z","request_id":"req_011Cg3UCswvh85v35WkWTgSM"}} +{"dir":"recv","msg":{"duration_api_ms":2541,"stop_reason":"end_turn","session_id":"397c02eb-2bf7-462d-9daa-1859b156e6eb","total_cost_usd":0.063875,"usage":{"input_tokens":2,"cache_creation_input_tokens":15244,"cache_read_input_tokens":22367,"output_tokens":53,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15244,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":53,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15244,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15244},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012830000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":53,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15244,"webSearchRequests":0,"costUSD":0.0637467,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty","ttft_ms":1870,"type":"result","duration_ms":1894,"uuid":"ecd3f14c-7287-45e8-840c-aaefe665afd0","ttft_stream_ms":1287,"time_to_request_ms":38,"first_content_frame_ms":1288,"queued_turn_count":0,"result_index":0}} diff --git a/internal/server/sse.go b/internal/server/sse.go index bfd6eda..5a1bb22 100644 --- a/internal/server/sse.go +++ b/internal/server/sse.go @@ -48,7 +48,7 @@ func (s *Server) StreamEvents(w http.ResponseWriter, r *http.Request, params api return } - ping := time.NewTicker(30 * time.Second) + ping := time.NewTicker(15 * time.Second) defer ping.Stop() for { @@ -68,7 +68,7 @@ func (s *Server) StreamEvents(w http.ResponseWriter, r *http.Request, params api } case <-ping.C: - _, err := fmt.Fprint(w, ": ping\n\n") + _, err := fmt.Fprint(w, "event: ping\ndata: ping\n\n") if err != nil { return } diff --git a/web/dist/api.js b/web/dist/api.js index 26abfdb..8369040 100644 --- a/web/dist/api.js +++ b/web/dist/api.js @@ -46,11 +46,55 @@ export const get = (path, opts) => request("get", path, opts); export const post = (path, opts) => request("post", path, opts); export const put = (path, opts) => request("put", path, opts); export const del = (path, opts) => request("delete", path, opts); +const staleAfterMs = 40_000; +const retryAfterMs = 2_000; export function subscribe(after, onEvent, onState) { - const source = new EventSource(`/api/events?after=${after}`); - source.onopen = () => onState(true); - source.onerror = () => onState(false); - source.onmessage = (msg) => onEvent(JSON.parse(msg.data)); - return source; + let last = after; + let heard = Date.now(); + let source; + let retry = 0; + const connect = () => { + clearTimeout(retry); + source?.close(); + heard = Date.now(); + const s = new EventSource(`/api/events?after=${last}`); + source = s; + s.onopen = () => { + heard = Date.now(); + onState(true); + }; + s.onerror = () => { + onState(false); + if (s.readyState === EventSource.CLOSED) { + retry = setTimeout(connect, retryAfterMs); + } + }; + s.addEventListener("ping", () => { + heard = Date.now(); + }); + s.onmessage = (msg) => { + heard = Date.now(); + const ev = JSON.parse(msg.data); + if (ev.seq > last) { + last = ev.seq; + } + onEvent(ev); + }; + }; + const check = () => { + if (Date.now() - heard < staleAfterMs) { + return; + } + onState(false); + connect(); + }; + setInterval(check, 5_000); + addEventListener("online", connect); + document.addEventListener("visibilitychange", () => { + if (document.visibilityState === "visible") { + check(); + } + }); + connect(); } //# sourceMappingURL=api.js.map \ No newline at end of file diff --git a/web/dist/api.js.map b/web/dist/api.js.map index 385373a..144941a 100644 --- a/web/dist/api.js.map +++ b/web/dist/api.js.map @@ -1 +1 @@ -{"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAyCA,MAAM,OAAO,QAAS,SAAQ,KAAK;IACZ;IAArB,YAAqB,MAAc,EAAE,OAAe;QAClD,KAAK,CAAC,OAAO,CAAC,CAAC;QADI,WAAM,GAAN,MAAM,CAAQ;IAEnC,CAAC;CACF;AAED,MAAM,CAAC,KAAK,UAAU,OAAO,CAC3B,MAAS,EACT,IAAO,EACP,OAA0B,EAAE;IAE5B,MAAM,UAAU,GAAG,CAAC,IAAI,CAAC,IAAI,IAAI,EAAE,CAA4B,CAAC;IAChE,IAAI,GAAG,GAAW,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC,CAAC,EAAE,GAAW,EAAE,EAAE;QAC9D,MAAM,KAAK,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CAAC,0BAA0B,GAAG,QAAQ,IAAI,EAAE,CAAC,CAAC;QAC/D,CAAC;QACD,OAAO,kBAAkB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;IAC3C,CAAC,CAAC,CAAC;IAEH,MAAM,KAAK,GAAG,IAAI,eAAe,EAAE,CAAC;IACpC,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAA4B,CAAC,EAAE,CAAC;QACzF,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;QAChC,CAAC;IACH,CAAC;IACD,IAAI,KAAK,CAAC,IAAI,GAAG,CAAC,EAAE,CAAC;QACnB,GAAG,IAAI,IAAI,KAAK,EAAE,CAAC;IACrB,CAAC;IAED,MAAM,IAAI,GAAgB,EAAE,MAAM,EAAE,MAAM,CAAC,WAAW,EAAE,EAAE,CAAC;IAC3D,IAAI,IAAI,CAAC,IAAI,YAAY,IAAI,EAAE,CAAC;QAC9B,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,IAAI,CAAC,IAAI,CAAC,IAAI,IAAI,0BAA0B,EAAE,CAAC;QAChF,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC;IACxB,CAAC;SAAM,IAAI,IAAI,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;QACnC,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,kBAAkB,EAAE,CAAC;QACtD,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACxC,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IACnC,IAAI,GAAG,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;QACvB,OAAO,SAA6B,CAAC;IACvC,CAAC;IACD,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC;IAC9B,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC;QACZ,MAAM,IAAI,QAAQ,CAAC,GAAG,CAAC,MAAM,EAAG,IAAyB,CAAC,OAAO,CAAC,CAAC;IACrE,CAAC;IACD,OAAO,IAAwB,CAAC;AAClC,CAAC;AAED,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACrH,MAAM,CAAC,MAAM,IAAI,GAAG,CAA8B,IAAO,EAAE,IAA6B,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACzH,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACrH,MAAM,CAAC,MAAM,GAAG,GAAG,CAAgC,IAAO,EAAE,IAA+B,EAAE,EAAE,CAAC,OAAO,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AAE9H,MAAM,UAAU,SAAS,CAAC,KAAa,EAAE,OAAgC,EAAE,OAAqC;IAC9G,MAAM,MAAM,GAAG,IAAI,WAAW,CAAC,qBAAqB,KAAK,EAAE,CAAC,CAAC;IAC7D,MAAM,CAAC,MAAM,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACpC,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;IACtC,MAAM,CAAC,SAAS,GAAG,CAAC,GAAyB,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAc,CAAC,CAAC;IAC7F,OAAO,MAAM,CAAC;AAChB,CAAC"} \ No newline at end of file +{"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAyCA,MAAM,OAAO,QAAS,SAAQ,KAAK;IACZ;IAArB,YAAqB,MAAc,EAAE,OAAe;QAClD,KAAK,CAAC,OAAO,CAAC,CAAC;QADI,WAAM,GAAN,MAAM,CAAQ;IAEnC,CAAC;CACF;AAED,MAAM,CAAC,KAAK,UAAU,OAAO,CAC3B,MAAS,EACT,IAAO,EACP,OAA0B,EAAE;IAE5B,MAAM,UAAU,GAAG,CAAC,IAAI,CAAC,IAAI,IAAI,EAAE,CAA4B,CAAC;IAChE,IAAI,GAAG,GAAW,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC,CAAC,EAAE,GAAW,EAAE,EAAE;QAC9D,MAAM,KAAK,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CAAC,0BAA0B,GAAG,QAAQ,IAAI,EAAE,CAAC,CAAC;QAC/D,CAAC;QACD,OAAO,kBAAkB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;IAC3C,CAAC,CAAC,CAAC;IAEH,MAAM,KAAK,GAAG,IAAI,eAAe,EAAE,CAAC;IACpC,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAA4B,CAAC,EAAE,CAAC;QACzF,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;QAChC,CAAC;IACH,CAAC;IACD,IAAI,KAAK,CAAC,IAAI,GAAG,CAAC,EAAE,CAAC;QACnB,GAAG,IAAI,IAAI,KAAK,EAAE,CAAC;IACrB,CAAC;IAED,MAAM,IAAI,GAAgB,EAAE,MAAM,EAAE,MAAM,CAAC,WAAW,EAAE,EAAE,CAAC;IAC3D,IAAI,IAAI,CAAC,IAAI,YAAY,IAAI,EAAE,CAAC;QAC9B,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,IAAI,CAAC,IAAI,CAAC,IAAI,IAAI,0BAA0B,EAAE,CAAC;QAChF,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC;IACxB,CAAC;SAAM,IAAI,IAAI,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;QACnC,IAAI,CAAC,OAAO,GAAG,EAAE,cAAc,EAAE,kBAAkB,EAAE,CAAC;QACtD,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACxC,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IACnC,IAAI,GAAG,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;QACvB,OAAO,SAA6B,CAAC;IACvC,CAAC;IACD,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC;IAC9B,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC;QACZ,MAAM,IAAI,QAAQ,CAAC,GAAG,CAAC,MAAM,EAAG,IAAyB,CAAC,OAAO,CAAC,CAAC;IACrE,CAAC;IACD,OAAO,IAAwB,CAAC;AAClC,CAAC;AAED,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACrH,MAAM,CAAC,MAAM,IAAI,GAAG,CAA8B,IAAO,EAAE,IAA6B,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACzH,MAAM,CAAC,MAAM,GAAG,GAAG,CAA6B,IAAO,EAAE,IAA4B,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AACrH,MAAM,CAAC,MAAM,GAAG,GAAG,CAAgC,IAAO,EAAE,IAA+B,EAAE,EAAE,CAAC,OAAO,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;AAE9H,MAAM,YAAY,GAAG,MAAM,CAAC;AAC5B,MAAM,YAAY,GAAG,KAAK,CAAC;AAE3B,MAAM,UAAU,SAAS,CAAC,KAAa,EAAE,OAAgC,EAAE,OAAqC;IAC9G,IAAI,IAAI,GAAG,KAAK,CAAC;IACjB,IAAI,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;IACvB,IAAI,MAA+B,CAAC;IACpC,IAAI,KAAK,GAAG,CAAC,CAAC;IAEd,MAAM,OAAO,GAAG,GAAG,EAAE;QACnB,YAAY,CAAC,KAAK,CAAC,CAAC;QACpB,MAAM,EAAE,KAAK,EAAE,CAAC;QAChB,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QACnB,MAAM,CAAC,GAAG,IAAI,WAAW,CAAC,qBAAqB,IAAI,EAAE,CAAC,CAAC;QACvD,MAAM,GAAG,CAAC,CAAC;QACX,CAAC,CAAC,MAAM,GAAG,GAAG,EAAE;YACd,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;YACnB,OAAO,CAAC,IAAI,CAAC,CAAC;QAChB,CAAC,CAAC;QACF,CAAC,CAAC,OAAO,GAAG,GAAG,EAAE;YACf,OAAO,CAAC,KAAK,CAAC,CAAC;YACf,IAAI,CAAC,CAAC,UAAU,KAAK,WAAW,CAAC,MAAM,EAAE,CAAC;gBACxC,KAAK,GAAG,UAAU,CAAC,OAAO,EAAE,YAAY,CAAC,CAAC;YAC5C,CAAC;QACH,CAAC,CAAC;QACF,CAAC,CAAC,gBAAgB,CAAC,MAAM,EAAE,GAAG,EAAE;YAC9B,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QACrB,CAAC,CAAC,CAAC;QACH,CAAC,CAAC,SAAS,GAAG,CAAC,GAAyB,EAAE,EAAE;YAC1C,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;YACnB,MAAM,EAAE,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAc,CAAC;YAC7C,IAAI,EAAE,CAAC,GAAG,GAAG,IAAI,EAAE,CAAC;gBAClB,IAAI,GAAG,EAAE,CAAC,GAAG,CAAC;YAChB,CAAC;YACD,OAAO,CAAC,EAAE,CAAC,CAAC;QACd,CAAC,CAAC;IACJ,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,GAAG,EAAE;QACjB,IAAI,IAAI,CAAC,GAAG,EAAE,GAAG,KAAK,GAAG,YAAY,EAAE,CAAC;YACtC,OAAO;QACT,CAAC;QACD,OAAO,CAAC,KAAK,CAAC,CAAC;QACf,OAAO,EAAE,CAAC;IACZ,CAAC,CAAC;IAEF,WAAW,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;IAC1B,gBAAgB,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;IACpC,QAAQ,CAAC,gBAAgB,CAAC,kBAAkB,EAAE,GAAG,EAAE;QACjD,IAAI,QAAQ,CAAC,eAAe,KAAK,SAAS,EAAE,CAAC;YAC3C,KAAK,EAAE,CAAC;QACV,CAAC;IACH,CAAC,CAAC,CAAC;IACH,OAAO,EAAE,CAAC;AACZ,CAAC"} \ No newline at end of file diff --git a/web/dist/navbar.js b/web/dist/navbar.js index a53c584..c018e18 100644 --- a/web/dist/navbar.js +++ b/web/dist/navbar.js @@ -1,5 +1,7 @@ -import { h, replace } from "./dom.js"; -import { activeTasks, findTask, onEach, state } from "./state.js"; +import { post } from "./api.js"; +import { errorText, h, replace } from "./dom.js"; +import { openTranscript } from "./panes.js"; +import { activeTasks, currentSession, findTask, onEach, state } from "./state.js"; export function mountNavbar(root, show) { const crumb = h("button", { class: "crumb", title: "Switch task (⌘K)" }); crumb.onclick = openSwitcher; @@ -8,6 +10,7 @@ export function mountNavbar(root, show) { const admin = h("button", { class: "nav-link" }, "Admin"); admin.onclick = () => show("admin"); const conn = h("span", { class: "connection down", title: "connecting" }); + const connLabel = h("span", { class: "connection-label" }, "reconnecting…"); const me = h("span", { class: "me" }); const render = () => { const task = state.selectedTaskId ? findTask(state.selectedTaskId) : undefined; @@ -18,10 +21,11 @@ export function mountNavbar(root, show) { replace(inbox, `Inbox ${state.inbox.length}`, blocked > 0 && h("span", { class: "blocked-count" }, ` · ${blocked} blocked`)); conn.className = state.connected ? "connection up" : "connection down"; conn.title = state.connected ? "live" : "reconnecting"; + connLabel.hidden = state.connected; replace(me, state.me?.display_name ?? ""); }; onEach(["me", "projects", "tasks", "inbox", "selection", "connection"], render); - replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, admin, conn, me); + replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, admin, connLabel, conn, me); render(); addEventListener("keydown", (e) => { if (e.key === "k" && (e.metaKey || e.ctrlKey)) { @@ -34,44 +38,80 @@ function openSwitcher() { if (document.querySelector(".switcher")) { return; } - const input = h("input", { placeholder: "Go to task…", autocomplete: "off" }); + const input = h("input", { placeholder: "Go to a task, or type a title to create one…", autocomplete: "off" }); const list = h("ul", { class: "switcher-list" }); const backdrop = h("div", { class: "switcher-backdrop" }); const box = h("div", { class: "switcher" }, input, list); let selected = 0; - let matches = []; + let rows = []; + const offs = onEach(["projects", "tasks", "sessions", "inbox"], () => render()); + const onEscape = (e) => { + if (e.key !== "Escape") { + return; + } + e.preventDefault(); + e.stopPropagation(); + close(); + }; + addEventListener("keydown", onEscape, { capture: true }); const close = () => { + offs(); + removeEventListener("keydown", onEscape, { capture: true }); backdrop.remove(); box.remove(); }; const go = (taskId) => { close(); location.hash = `#/task/${taskId}`; + openTranscript(); + }; + const create = async (projectId, title) => { + close(); + try { + const task = await post("/api/projects/{projectId}/tasks", { path: { projectId }, body: { title } }); + go(task.id); + } + catch (err) { + alert(errorText(err)); + } }; const render = () => { - const q = input.value.trim().toLowerCase(); - matches = activeTasks().filter(({ project, task }) => `${project.name} ${task.title}`.toLowerCase().includes(q)); - selected = Math.min(selected, Math.max(matches.length - 1, 0)); - replace(list, ...matches.map(({ project, task }, i) => { - const li = h("li", { class: i === selected ? "selected" : "" }, h("span", { class: "project-name" }, project.name), " ", task.title); - li.onmousedown = (e) => { + const title = input.value.trim(); + const q = title.toLowerCase(); + const inbox = (taskId) => state.inbox.filter((item) => item.task_id === taskId).length; + const matches = activeTasks() + .filter(({ project, task }) => `${project.name} ${task.title}`.toLowerCase().includes(q)) + .map((m) => ({ ...m, count: inbox(m.task.id) })) + .sort((a, b) => Number(b.count > 0) - Number(a.count > 0)); + rows = matches.map(({ project, task, count }) => { + const sess = currentSession(task.id); + const el = h("li", {}, h("span", { class: `dot ${sess?.state ?? "none"}`, title: sess?.state ?? "no session" }), h("span", { class: "task-title" }, h("span", { class: "project-name" }, project.name), " ", task.title), count > 0 && h("span", { class: "badge", title: "inbox items" }, count), h("span", { class: "task-state" }, sess?.state ?? "no agent")); + return { el, pick: () => go(task.id) }; + }); + const current = state.selectedTaskId ? findTask(state.selectedTaskId) : undefined; + const project = state.projects.find((p) => p.id === current?.project_id) ?? state.projects[0]; + if (title && project) { + const el = h("li", { class: "new-task" }, h("span", { class: "task-title" }, "New task in ", h("span", { class: "project-name" }, project.name), ": ", title)); + rows.push({ el, pick: () => void create(project.id, title) }); + } + selected = Math.min(selected, Math.max(rows.length - 1, 0)); + rows.forEach((row, i) => { + row.el.classList.toggle("selected", i === selected); + row.el.onmousedown = (e) => { e.preventDefault(); - go(task.id); + row.pick(); }; - return li; - }), matches.length === 0 && h("li", { class: "empty-row" }, "No matching tasks.")); + }); + replace(list, ...rows.map((r) => r.el), rows.length === 0 && h("li", { class: "empty-row" }, "No active tasks. Type a title to create one.")); }; input.oninput = () => { selected = 0; render(); }; input.onkeydown = (e) => { - if (e.key === "Escape") { - close(); - } - else if (e.key === "ArrowDown") { + if (e.key === "ArrowDown") { e.preventDefault(); - selected = Math.min(selected + 1, matches.length - 1); + selected = Math.min(selected + 1, rows.length - 1); render(); } else if (e.key === "ArrowUp") { @@ -80,10 +120,8 @@ function openSwitcher() { render(); } else if (e.key === "Enter") { - const match = matches[selected]; - if (match) { - go(match.task.id); - } + e.preventDefault(); + rows[selected]?.pick(); } }; backdrop.onclick = close; diff --git a/web/dist/navbar.js.map b/web/dist/navbar.js.map index f0a15ca..f468990 100644 --- a/web/dist/navbar.js.map +++ b/web/dist/navbar.js.map @@ -1 +1 @@ -{"version":3,"file":"navbar.js","sourceRoot":"","sources":["../src/navbar.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AAEtC,OAAO,EAAE,WAAW,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAElE,MAAM,UAAU,WAAW,CAAC,IAAiB,EAAE,IAA0B;IACvE,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,kBAAkB,EAAE,CAAC,CAAC;IACzE,KAAK,CAAC,OAAO,GAAG,YAAY,CAAC;IAE7B,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACpD,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpC,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,OAAO,CAAC,CAAC;IAC1D,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpC,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IAC1E,MAAM,EAAE,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC;IAEtC,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,MAAM,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QACxF,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,GAAG,OAAO,EAAE,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;QAElF,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,MAAM,CAAC;QAC3E,KAAK,CAAC,SAAS,GAAG,OAAO,GAAG,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,aAAa,CAAC;QACrE,OAAO,CAAC,KAAK,EAAE,SAAS,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,OAAO,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,EAAE,MAAM,OAAO,UAAU,CAAC,CAAC,CAAC;QAE7H,IAAI,CAAC,SAAS,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,iBAAiB,CAAC;QACvE,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,cAAc,CAAC;QACvD,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,EAAE,YAAY,IAAI,EAAE,CAAC,CAAC;IAC5C,CAAC,CAAC;IAEF,MAAM,CAAC,CAAC,IAAI,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,YAAY,CAAC,EAAE,MAAM,CAAC,CAAC;IAChF,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,CAAC;IAC7H,MAAM,EAAE,CAAC;IAET,gBAAgB,CAAC,SAAS,EAAE,CAAC,CAAC,EAAE,EAAE;QAChC,IAAI,CAAC,CAAC,GAAG,KAAK,GAAG,IAAI,CAAC,CAAC,CAAC,OAAO,IAAI,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;YAC9C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,YAAY,EAAE,CAAC;QACjB,CAAC;IACH,CAAC,CAAC,CAAC;AACL,CAAC;AAED,SAAS,YAAY;IACnB,IAAI,QAAQ,CAAC,aAAa,CAAC,WAAW,CAAC,EAAE,CAAC;QACxC,OAAO;IACT,CAAC;IAED,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,aAAa,EAAE,YAAY,EAAE,KAAK,EAAE,CAAC,CAAC;IAC9E,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,CAAC,CAAC;IACjD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,mBAAmB,EAAE,CAAC,CAAC;IAC1D,MAAM,GAAG,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC;IACzD,IAAI,QAAQ,GAAG,CAAC,CAAC;IACjB,IAAI,OAAO,GAAmC,EAAE,CAAC;IAEjD,MAAM,KAAK,GAAG,GAAG,EAAE;QACjB,QAAQ,CAAC,MAAM,EAAE,CAAC;QAClB,GAAG,CAAC,MAAM,EAAE,CAAC;IACf,CAAC,CAAC;IAEF,MAAM,EAAE,GAAG,CAAC,MAAc,EAAE,EAAE;QAC5B,KAAK,EAAE,CAAC;QACR,QAAQ,CAAC,IAAI,GAAG,UAAU,MAAM,EAAE,CAAC;IACrC,CAAC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,CAAC,GAAG,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;QAC3C,OAAO,GAAG,WAAW,EAAE,CAAC,MAAM,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,GAAG,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC;QACjH,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;QAC/D,OAAO,CACL,IAAI,EACJ,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE;YACtC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,OAAO,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;YACrI,EAAE,CAAC,WAAW,GAAG,CAAC,CAAC,EAAE,EAAE;gBACrB,CAAC,CAAC,cAAc,EAAE,CAAC;gBACnB,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACd,CAAC,CAAC;YACF,OAAO,EAAE,CAAC;QACZ,CAAC,CAAC,EACF,OAAO,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,oBAAoB,CAAC,CAC9E,CAAC;IACJ,CAAC,CAAC;IAEF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE;QACnB,QAAQ,GAAG,CAAC,CAAC;QACb,MAAM,EAAE,CAAC;IACX,CAAC,CAAC;IACF,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,QAAQ,EAAE,CAAC;YACvB,KAAK,EAAE,CAAC;QACV,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,WAAW,EAAE,CAAC;YACjC,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACtD,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,SAAS,EAAE,CAAC;YAC/B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC;YACrC,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,EAAE,CAAC;YAC7B,MAAM,KAAK,GAAG,OAAO,CAAC,QAAQ,CAAC,CAAC;YAChC,IAAI,KAAK,EAAE,CAAC;gBACV,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACpB,CAAC;QACH,CAAC;IACH,CAAC,CAAC;IACF,QAAQ,CAAC,OAAO,GAAG,KAAK,CAAC;IAEzB,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACpC,MAAM,EAAE,CAAC;IACT,KAAK,CAAC,KAAK,EAAE,CAAC;AAChB,CAAC"} \ No newline at end of file +{"version":3,"file":"navbar.js","sourceRoot":"","sources":["../src/navbar.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAE,MAAM,UAAU,CAAC;AAChC,OAAO,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACjD,OAAO,EAAE,cAAc,EAAa,MAAM,YAAY,CAAC;AACvD,OAAO,EAAE,WAAW,EAAE,cAAc,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAElF,MAAM,UAAU,WAAW,CAAC,IAAiB,EAAE,IAA0B;IACvE,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,kBAAkB,EAAE,CAAC,CAAC;IACzE,KAAK,CAAC,OAAO,GAAG,YAAY,CAAC;IAE7B,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACpD,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpC,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,OAAO,CAAC,CAAC;IAC1D,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpC,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IAC1E,MAAM,SAAS,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,kBAAkB,EAAE,EAAE,eAAe,CAAC,CAAC;IAC5E,MAAM,EAAE,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC;IAEtC,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,MAAM,OAAO,GAAG,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QACxF,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,GAAG,OAAO,EAAE,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;QAElF,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,MAAM,CAAC;QAC3E,KAAK,CAAC,SAAS,GAAG,OAAO,GAAG,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,aAAa,CAAC;QACrE,OAAO,CAAC,KAAK,EAAE,SAAS,KAAK,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,OAAO,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,EAAE,MAAM,OAAO,UAAU,CAAC,CAAC,CAAC;QAE7H,IAAI,CAAC,SAAS,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,iBAAiB,CAAC;QACvE,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,cAAc,CAAC;QACvD,SAAS,CAAC,MAAM,GAAG,KAAK,CAAC,SAAS,CAAC;QACnC,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,EAAE,YAAY,IAAI,EAAE,CAAC,CAAC;IAC5C,CAAC,CAAC;IAEF,MAAM,CAAC,CAAC,IAAI,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,YAAY,CAAC,EAAE,MAAM,CAAC,CAAC;IAChF,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,SAAS,EAAE,IAAI,EAAE,EAAE,CAAC,CAAC;IACxI,MAAM,EAAE,CAAC;IAET,gBAAgB,CAAC,SAAS,EAAE,CAAC,CAAC,EAAE,EAAE;QAChC,IAAI,CAAC,CAAC,GAAG,KAAK,GAAG,IAAI,CAAC,CAAC,CAAC,OAAO,IAAI,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;YAC9C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,YAAY,EAAE,CAAC;QACjB,CAAC;IACH,CAAC,CAAC,CAAC;AACL,CAAC;AAED,SAAS,YAAY;IACnB,IAAI,QAAQ,CAAC,aAAa,CAAC,WAAW,CAAC,EAAE,CAAC;QACxC,OAAO;IACT,CAAC;IAED,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,8CAA8C,EAAE,YAAY,EAAE,KAAK,EAAE,CAAC,CAAC;IAC/G,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,eAAe,EAAE,CAAC,CAAC;IACjD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,mBAAmB,EAAE,CAAC,CAAC;IAC1D,MAAM,GAAG,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC;IACzD,IAAI,QAAQ,GAAG,CAAC,CAAC;IACjB,IAAI,IAAI,GAA4C,EAAE,CAAC;IAEvD,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,UAAU,EAAE,OAAO,EAAE,UAAU,EAAE,OAAO,CAAC,EAAE,GAAG,EAAE,CAAC,MAAM,EAAE,CAAC,CAAC;IAChF,MAAM,QAAQ,GAAG,CAAC,CAAgB,EAAE,EAAE;QACpC,IAAI,CAAC,CAAC,GAAG,KAAK,QAAQ,EAAE,CAAC;YACvB,OAAO;QACT,CAAC;QACD,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,CAAC,CAAC,eAAe,EAAE,CAAC;QACpB,KAAK,EAAE,CAAC;IACV,CAAC,CAAC;IACF,gBAAgB,CAAC,SAAS,EAAE,QAAQ,EAAE,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC;IACzD,MAAM,KAAK,GAAG,GAAG,EAAE;QACjB,IAAI,EAAE,CAAC;QACP,mBAAmB,CAAC,SAAS,EAAE,QAAQ,EAAE,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC;QAC5D,QAAQ,CAAC,MAAM,EAAE,CAAC;QAClB,GAAG,CAAC,MAAM,EAAE,CAAC;IACf,CAAC,CAAC;IAEF,MAAM,EAAE,GAAG,CAAC,MAAc,EAAE,EAAE;QAC5B,KAAK,EAAE,CAAC;QACR,QAAQ,CAAC,IAAI,GAAG,UAAU,MAAM,EAAE,CAAC;QACnC,cAAc,EAAE,CAAC;IACnB,CAAC,CAAC;IAEF,MAAM,MAAM,GAAG,KAAK,EAAE,SAAiB,EAAE,KAAa,EAAE,EAAE;QACxD,KAAK,EAAE,CAAC;QACR,IAAI,CAAC;YACH,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,iCAAiC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;YACrG,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACd,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;QACjC,MAAM,CAAC,GAAG,KAAK,CAAC,WAAW,EAAE,CAAC;QAC9B,MAAM,KAAK,GAAG,CAAC,MAAc,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,KAAK,MAAM,CAAC,CAAC,MAAM,CAAC;QAC/F,MAAM,OAAO,GAAG,WAAW,EAAE;aAC1B,MAAM,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,GAAG,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;aACxF,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,KAAK,EAAE,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC;aAC/C,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,MAAM,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC;QAC7D,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,EAAE,EAAE;YAC9C,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;YACrC,MAAM,EAAE,GAAG,CAAC,CACV,IAAI,EACJ,EAAE,EACF,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,OAAO,IAAI,EAAE,KAAK,IAAI,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,IAAI,YAAY,EAAE,CAAC,EACxF,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,OAAO,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,KAAK,CAAC,EACvG,KAAK,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,aAAa,EAAE,EAAE,KAAK,CAAC,EACvE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,EAAE,KAAK,IAAI,UAAU,CAAC,CAC9D,CAAC;YACF,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,CAAC;QACzC,CAAC,CAAC,CAAC;QACH,MAAM,OAAO,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAClF,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,OAAO,EAAE,UAAU,CAAC,IAAI,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;QAC9F,IAAI,KAAK,IAAI,OAAO,EAAE,CAAC;YACrB,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,cAAc,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,OAAO,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC;YAC/J,IAAI,CAAC,IAAI,CAAC,EAAE,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,KAAK,MAAM,CAAC,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC;QAChE,CAAC;QACD,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,EAAE,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;QAC5D,IAAI,CAAC,OAAO,CAAC,CAAC,GAAG,EAAE,CAAC,EAAE,EAAE;YACtB,GAAG,CAAC,EAAE,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,EAAE,CAAC,KAAK,QAAQ,CAAC,CAAC;YACpD,GAAG,CAAC,EAAE,CAAC,WAAW,GAAG,CAAC,CAAC,EAAE,EAAE;gBACzB,CAAC,CAAC,cAAc,EAAE,CAAC;gBACnB,GAAG,CAAC,IAAI,EAAE,CAAC;YACb,CAAC,CAAC;QACJ,CAAC,CAAC,CAAC;QACH,OAAO,CAAC,IAAI,EAAE,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,IAAI,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,8CAA8C,CAAC,CAAC,CAAC;IAChJ,CAAC,CAAC;IAEF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE;QACnB,QAAQ,GAAG,CAAC,CAAC;QACb,MAAM,EAAE,CAAC;IACX,CAAC,CAAC;IACF,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,WAAW,EAAE,CAAC;YAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;YACnD,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,SAAS,EAAE,CAAC;YAC/B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC;YACrC,MAAM,EAAE,CAAC;QACX,CAAC;aAAM,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,EAAE,CAAC;YAC7B,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,QAAQ,CAAC,EAAE,IAAI,EAAE,CAAC;QACzB,CAAC;IACH,CAAC,CAAC;IACF,QAAQ,CAAC,OAAO,GAAG,KAAK,CAAC;IAEzB,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACpC,MAAM,EAAE,CAAC;IACT,KAAK,CAAC,KAAK,EAAE,CAAC;AAChB,CAAC"} \ No newline at end of file diff --git a/web/dist/panes.js b/web/dist/panes.js index 71bd544..8a0263b 100644 --- a/web/dist/panes.js +++ b/web/dist/panes.js @@ -14,6 +14,13 @@ const views = { settings: { label: "Settings", mount: mountSettings }, }; const order = ["transcript", "changes", "tasks", "inbox", "admin", "settings"]; +const panes = []; +export function openTranscript() { + if (panes.some((p) => p.current() === "transcript")) { + return; + } + (panes.find((p) => p.current() !== "tasks") ?? panes[0])?.show("transcript"); +} export class Pane { key; el; @@ -29,6 +36,10 @@ export class Pane { const saved = localStorage.getItem(this.storageKey()); this.view = saved && saved in views ? saved : fallback; this.show(this.view); + panes.push(this); + } + current() { + return this.view; } show(view) { this.dispose(); diff --git a/web/dist/panes.js.map b/web/dist/panes.js.map index d95aa3d..e74feeb 100644 --- a/web/dist/panes.js.map +++ b/web/dist/panes.js.map @@ -1 +1 @@ -{"version":3,"file":"panes.js","sourceRoot":"","sources":["../src/panes.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,eAAe,EAAE,MAAM,WAAW,CAAC;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAIxC,MAAM,KAAK,GAA8E;IACvF,UAAU,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,eAAe,EAAE;IAC3D,OAAO,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,EAAE;IAClE,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,QAAQ,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,aAAa,EAAE;CACtD,CAAC;AAEF,MAAM,KAAK,GAAW,CAAC,YAAY,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,UAAU,CAAC,CAAC;AAEvF,MAAM,OAAO,IAAI;IAOc;IANpB,EAAE,CAAc;IACR,IAAI,CAAc;IAClB,IAAI,CAAc;IAC3B,IAAI,CAAO;IACX,OAAO,GAAe,GAAG,EAAE,GAAE,CAAC,CAAC;IAEvC,YAA6B,GAAW,EAAE,QAAc;QAA3B,QAAG,GAAH,GAAG,CAAQ;QACtC,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,EAAE,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAEhE,MAAM,KAAK,GAAG,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,CAAgB,CAAC;QACrE,IAAI,CAAC,IAAI,GAAG,KAAK,IAAI,KAAK,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC;QACvD,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACvB,CAAC;IAED,IAAI,CAAC,IAAU;QACb,IAAI,CAAC,OAAO,EAAE,CAAC;QACf,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC;QACjB,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,EAAE,IAAI,CAAC,CAAC;QAE9C,OAAO,CACL,IAAI,CAAC,IAAI,EACT,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE;YACjB,MAAM,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YAC7E,CAAC,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YAC/B,OAAO,CAAC,CAAC;QACX,CAAC,CAAC,CACH,CAAC;QAEF,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,IAAI,EAAE,EAAE,CAAC,CAAC;QACtD,OAAO,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QACzB,IAAI,CAAC,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACzC,CAAC;IAEO,UAAU;QAChB,OAAO,aAAa,IAAI,CAAC,GAAG,EAAE,CAAC;IACjC,CAAC;CACF"} \ No newline at end of file +{"version":3,"file":"panes.js","sourceRoot":"","sources":["../src/panes.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtC,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,eAAe,EAAE,MAAM,WAAW,CAAC;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAIxC,MAAM,KAAK,GAA8E;IACvF,UAAU,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,eAAe,EAAE;IAC3D,OAAO,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,EAAE;IAClE,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE;IAC5C,QAAQ,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,aAAa,EAAE;CACtD,CAAC;AAEF,MAAM,KAAK,GAAW,CAAC,YAAY,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,UAAU,CAAC,CAAC;AAEvF,MAAM,KAAK,GAAW,EAAE,CAAC;AAEzB,MAAM,UAAU,cAAc;IAC5B,IAAI,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,OAAO,EAAE,KAAK,YAAY,CAAC,EAAE,CAAC;QACpD,OAAO;IACT,CAAC;IACD,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,OAAO,EAAE,KAAK,OAAO,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,YAAY,CAAC,CAAC;AAC/E,CAAC;AAED,MAAM,OAAO,IAAI;IAOc;IANpB,EAAE,CAAc;IACR,IAAI,CAAc;IAClB,IAAI,CAAc;IAC3B,IAAI,CAAO;IACX,OAAO,GAAe,GAAG,EAAE,GAAE,CAAC,CAAC;IAEvC,YAA6B,GAAW,EAAE,QAAc;QAA3B,QAAG,GAAH,GAAG,CAAQ;QACtC,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,CAAC;QAC7C,IAAI,CAAC,EAAE,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAEhE,MAAM,KAAK,GAAG,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,CAAgB,CAAC;QACrE,IAAI,CAAC,IAAI,GAAG,KAAK,IAAI,KAAK,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC;QACvD,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACrB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACnB,CAAC;IAED,OAAO;QACL,OAAO,IAAI,CAAC,IAAI,CAAC;IACnB,CAAC;IAED,IAAI,CAAC,IAAU;QACb,IAAI,CAAC,OAAO,EAAE,CAAC;QACf,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC;QACjB,YAAY,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,EAAE,EAAE,IAAI,CAAC,CAAC;QAE9C,OAAO,CACL,IAAI,CAAC,IAAI,EACT,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE;YACjB,MAAM,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YAC7E,CAAC,CAAC,OAAO,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YAC/B,OAAO,CAAC,CAAC;QACX,CAAC,CAAC,CACH,CAAC;QAEF,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,IAAI,EAAE,EAAE,CAAC,CAAC;QACtD,OAAO,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QACzB,IAAI,CAAC,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACzC,CAAC;IAEO,UAAU;QAChB,OAAO,aAAa,IAAI,CAAC,GAAG,EAAE,CAAC;IACjC,CAAC;CACF"} \ No newline at end of file diff --git a/web/dist/task.js b/web/dist/task.js index c29ea9b..656cb8f 100644 --- a/web/dist/task.js +++ b/web/dist/task.js @@ -155,31 +155,31 @@ export function mountTranscript(root) { if (!stream) { return; } - cancelAnimationFrame(stream.frame); + clearTimeout(stream.timer); stream.el.remove(); stream = undefined; }; const appendDelta = (ev) => { if (!stream) { - stream = { el: h("div", { class: "msg agent" }), text: "", frame: 0 }; + stream = { el: h("div", { class: "msg agent" }), text: "", timer: 0 }; ctx.run = undefined; put(stream.el); } stream.text += String(ev.payload["text"] ?? ""); - if (stream.frame) { + if (stream.timer) { return; } - stream.frame = requestAnimationFrame(() => { + stream.timer = setTimeout(() => { if (!stream) { return; } - stream.frame = 0; + stream.timer = 0; const pinned = transcript.scrollHeight - transcript.scrollTop - transcript.clientHeight < 80; replace(stream.el, markdown(stream.text, "text md")); if (pinned) { transcript.scrollTop = transcript.scrollHeight; } - }); + }, 100); }; const foldTurn = (start, end) => { const summary = h("summary"); diff --git a/web/dist/task.js.map b/web/dist/task.js.map index 342dfcd..00aadd7 100644 --- a/web/dist/task.js.map +++ b/web/dist/task.js.map @@ -1 +1 @@ -{"version":3,"file":"task.js","sourceRoot":"","sources":["../src/task.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAE,IAAI,EAA4C,MAAM,UAAU,CAAC;AAC/E,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,MAAM,eAAe,CAAC;AACzC,OAAO,EAAE,cAAc,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAErE,MAAM,MAAM,GAAG,CAAC,iBAAiB,EAAE,mBAAmB,EAAE,kBAAkB,EAAE,kBAAkB,CAAC,CAAC;AAmBhG,MAAM,UAAU,eAAe,CAAC,IAAiB;IAC/C,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACnD,MAAM,UAAU,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IACrD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,CAAC,CAAC;IAEjD,MAAM,cAAc,GAAG,IAAI,GAAG,EAAmB,CAAC;IAClD,MAAM,KAAK,GAAG,IAAI,GAAG,EAAU,CAAC;IAChC,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,QAAQ,CAAC,eAAe,KAAK,SAAS,EAAE,CAAC;YAC3C,OAAO;QACT,CAAC;QACD,MAAM,GAAG,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,cAAc,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;QACzH,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACrB,OAAO;QACT,CAAC;QACD,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;YACrB,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QAChB,CAAC;QACD,IAAI,CAAC,sBAAsB,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,SAAkB,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,EAAE,EAAE;YAChI,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;gBACrB,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;YACnB,CAAC;YACD,OAAO,CAAC,KAAK,CAAC,qBAAqB,EAAE,GAAG,CAAC,CAAC;QAC5C,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IACF,MAAM,QAAQ,GAAG,IAAI,oBAAoB,CACvC,CAAC,OAAO,EAAE,EAAE;QACV,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACxB,MAAM,EAAE,GAAI,CAAC,CAAC,MAAsB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAC1D,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,cAAc,EAAE,CAAC;gBACrB,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;YACnC,CAAC;iBAAM,CAAC;gBACN,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YAClC,CAAC;QACH,CAAC;QACD,UAAU,EAAE,CAAC;IACf,CAAC,EACD,EAAE,IAAI,EAAE,UAAU,EAAE,SAAS,EAAE,GAAG,EAAE,CACrC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAQ,EAAE;QACvB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,OAAO;YACL,KAAK,EAAE,IAAI,GAAG,EAAE;YAChB,GAAG,EAAE,SAAS;YACd,WAAW,EAAE,SAAS;YACtB,SAAS,EAAE,SAAS;YACpB,IAAI,EAAE,IAAI,EAAE,aAAa,IAAI,EAAE;YAC/B,WAAW,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,EAAE;gBAC1B,EAAE,CAAC,OAAO,CAAC,WAAW,CAAC,GAAG,MAAM,CAAC;gBACjC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;YACvB,CAAC;SACF,CAAC;IACJ,CAAC,CAAC;IACF,IAAI,GAAG,GAAG,MAAM,EAAE,CAAC;IACnB,IAAI,OAAO,GAAG,IAAI,GAAG,EAA2D,CAAC;IAEjF,MAAM,OAAO,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;IAChI,MAAM,UAAU,GAAG,CAAC,OAAgB,EAAE,EAAE;QACtC,UAAU,CAAC,SAAS,CAAC,MAAM,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QAChD,IAAI,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;YAChC,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,OAAO,CAAC,MAAM,GAAG,CAAC,OAAO,CAAC;QAC1B,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,EAAe,EAAE,EAAE;QAC9B,IAAI,OAAO,CAAC,UAAU,KAAK,UAAU,EAAE,CAAC;YACtC,UAAU,CAAC,YAAY,CAAC,EAAE,EAAE,OAAO,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,UAAU,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,UAAU,CAAC,IAAI,KAAK,SAAS,IAAI,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,KAAK,SAAS,CAAC,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,IAAI,CAAC,CAAC;YACd,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,IAAI,CAAC,MAAM,KAAK,QAAQ,EAAE,CAAC;YAC7B,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;YAChE,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,EAAE,cAAc,IAAI,oBAAoB,CAAC;QAC5G,MAAM,IAAI,GAAG,IAAI,EAAE,KAAK,KAAK,SAAS,IAAI,IAAI,EAAE,KAAK,KAAK,QAAQ,CAAC;QACnE,MAAM,KAAK,GAAG,CAAC,CACb,QAAQ,EACR,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,oBAAoB,MAAM,8CAA8C,MAAM,qBAAqB,EAAE,EAC9H,OAAO,CACR,CAAC;QACF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CACnB,cAAc,CACZ,IAAI,EACJ,CAAC,CAAC,EAAE,EAAE,CACJ,UAAU,IAAI,CAAC,KAAK,UAAU,MAAM,4BAA4B,MAAM,wDAAwD,WAAW,CAAC,CAAC,CAAC,yBAAyB,MAAM,YAAY,IAAI,CAAC,WAAW,4CAA4C,EACrP,KAAK,IAAI,EAAE;YACT,MAAM,IAAI,CAAC,2BAA2B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACzE,CAAC,CACF,CAAC;QACJ,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,0BAA0B,MAAM,6CAA6C,EAAE,EAAE,SAAS,MAAM,KAAK,CAAC,CAAC;QAC5J,OAAO,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;YAC3B,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC;YACxB,IAAI,CAAC;gBACH,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;YAC5E,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;gBACtB,OAAO,CAAC,QAAQ,GAAG,KAAK,CAAC;YAC3B,CAAC;QACH,CAAC,CAAC;QACF,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,gDAAgD,EAAE,EAAE,SAAS,CAAC,CAAC;QACrI,OAAO,CAAC,OAAO,GAAG,GAAG,EAAE,CACrB,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,YAAY,IAAI,CAAC,KAAK,MAAM,WAAW,CAAC,CAAC,CAAC,mBAAmB,MAAM,yCAAyC,EAAE,KAAK,IAAI,EAAE;YACnJ,MAAM,IAAI,CAAC,6BAA6B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;YACzE,QAAQ,CAAC,IAAI,GAAG,IAAI,CAAC;QACvB,CAAC,CAAC,CAAC;QACL,OAAO,CACL,IAAI,EACJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,8BAA8B,EAAE,EAAE,IAAI,IAAI,YAAY,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,IAAI,IAAI,aAAa,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAAE,OAAO,CAAC,EACpJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,KAAK,EAAE,OAAO,CAAC,CACpD,CAAC;IACJ,CAAC,CAAC;IAEF,IAAI,aAAa,GAAG,EAAE,CAAC;IACvB,MAAM,cAAc,GAAG,GAAG,EAAE;QAC1B,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,QAAQ,CAAC,CAAC;YAClB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,KAAK,WAAW,EAAE,CAAC;YACxC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;YACtC,OAAO;QACT,CAAC;QACD,aAAa,GAAG,IAAI,CAAC,KAAK,IAAI,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC;QAChE,OAAO,CAAC,QAAQ,EAAE,WAAW,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,EAAE,aAAa,CAAC,CAAC,CAAC;IAC9E,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,EAAe,EAAE,IAAsB,EAAE,EAAE;QAC3D,MAAM,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC;QACpB,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,GAAG,CAAC,GAAG,GAAG,EAAE,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;YACrE,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,OAAO;QACT,CAAC;QACD,IAAI,IAAI,EAAE,CAAC;YACT,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACvB,CAAC;QACD,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC;YACf,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;YAC7B,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,CAAC,CAAC;YACpD,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC;YACnE,GAAG,CAAC,KAAK,CAAC,WAAW,CAAC,KAAK,CAAC,CAAC;YAC7B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACvB,GAAG,CAAC,KAAK,GAAG,EAAE,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC;QAC3C,CAAC;QACD,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QAC1B,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;IACpD,CAAC,CAAC;IAEF,IAAI,MAAoE,CAAC;IACzE,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,OAAO;QACT,CAAC;QACD,oBAAoB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACnC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC;QACnB,MAAM,GAAG,SAAS,CAAC;IACrB,CAAC,CAAC;IACF,MAAM,WAAW,GAAG,CAAC,EAAa,EAAE,EAAE;QACpC,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,MAAM,GAAG,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;YACtE,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;QACD,MAAM,CAAC,IAAI,IAAI,MAAM,CAAC,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;QAChD,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;YACjB,OAAO;QACT,CAAC;QACD,MAAM,CAAC,KAAK,GAAG,qBAAqB,CAAC,GAAG,EAAE;YACxC,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO;YACT,CAAC;YACD,MAAM,CAAC,KAAK,GAAG,CAAC,CAAC;YACjB,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;YAC7F,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC,CAAC;YACrD,IAAI,MAAM,EAAE,CAAC;gBACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;YACjD,CAAC;QACH,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,KAAkB,EAAE,GAAgB,EAAE,EAAE;QACxD,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;QAC7B,OAAO,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;QAChD,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC,CAAC;QAC7D,IAAI,IAAI,GAAqB,KAAK,CAAC;QACnC,OAAO,IAAI,IAAI,IAAI,KAAK,OAAO,EAAE,CAAC;YAChC,MAAM,IAAI,GAAqB,IAAI,CAAC,WAAW,CAAC;YAChD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;YAClB,IAAI,GAAG,IAAI,CAAC;QACd,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,YAAY,GAAG,CAAC,MAAmB,EAAE,EAAE;QAC3C,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,IAAI,cAAc,GAAG,KAAK,CAAC;QAC3B,KAAK,MAAM,EAAE,IAAI,MAAM,EAAE,CAAC;YACxB,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;YAChD,IAAI,EAAE,CAAC,IAAI,KAAK,eAAe,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC1F,UAAU,EAAE,CAAC;YACf,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,IAAI,EAAE,CAAC,gBAAgB,EAAE,CAAC;gBACzD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,CAAC,CAAC;gBAC9C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,CAAC;gBACxD,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC;gBACvG,cAAc,GAAG,IAAI,CAAC;gBACtB,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,EAAE,CAAC;gBAClC,QAAQ,CAAC,cAAc,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBACxG,SAAS;YACX,CAAC;YACD,MAAM,EAAE,GAAG,WAAW,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC;YAChC,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,gBAAgB,EAAE,CAAC;gBACjC,QAAQ,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;gBACxB,SAAS;YACX,CAAC;YACD,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,IAAI,GAAG,CAAC,SAAS,EAAE,UAAU,KAAK,UAAU,EAAE,CAAC;gBAClG,QAAQ,CAAC,GAAG,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;gBAC5B,GAAG,CAAC,SAAS,GAAG,SAAS,CAAC;gBAC1B,SAAS;YACX,CAAC;YACD,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC/B,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC;YACrB,CAAC;QACH,CAAC;QACD,IAAI,cAAc,EAAE,CAAC;YACnB,UAAU,EAAE,CAAC;YACb,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,cAAc,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;YACrF,IAAI,IAAI,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC,KAAK,aAAa,EAAE,CAAC;gBACjF,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC;QACD,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,SAAS,GAAG,GAAG,EAAE;QACrB,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,cAAc,CAAC,KAAK,EAAE,CAAC;QACvB,UAAU,EAAE,CAAC;QACb,GAAG,GAAG,MAAM,EAAE,CAAC;QACf,OAAO,GAAG,IAAI,GAAG,EAAE,CAAC;QACpB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC,KAAK,CAAC,cAAc,EAAE,CAAC;YAC1B,cAAc,EAAE,CAAC;YACjB,OAAO,CAAC,UAAU,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,2DAA2D,CAAC,CAAC,CAAC;YAC/G,OAAO;QACT,CAAC;QACD,OAAO,CAAC,UAAU,EAAE,OAAO,CAAC,CAAC;QAC7B,YAAY,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;QAC/B,cAAc,EAAE,CAAC;IACnB,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG;QACX,MAAM,CAAC,CAAC,WAAW,CAAC,EAAE,SAAS,CAAC;QAChC,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,EAAE;YACrB,UAAU,EAAE,CAAC;YACb,cAAc,EAAE,CAAC;QACnB,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE;YAC9B,IAAI,MAAM,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;gBACpC,UAAU,EAAE,CAAC;gBACb,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,YAAY,CAAC,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAoB,CAAC,CAAC;QACrE,MAAM,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,EAAE,EAAE,EAAE,CAAC,WAAW,CAAC,EAAe,CAAC,CAAC;QACxD,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,UAAU,CAAC;KAC9B,CAAC;IACF,QAAQ,CAAC,gBAAgB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;IAE1D,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC,CAAC;IAClF,SAAS,EAAE,CAAC;IACZ,OAAO,GAAG,EAAE;QACV,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;QACD,QAAQ,CAAC,mBAAmB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;QAC7D,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,UAAU,EAAE,CAAC;IACf,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,cAAc,GAAG,IAAI,GAAG,EAAkB,CAAC;AAEjD,SAAS,SAAS,CAAC,KAA0B,EAAE,GAAW;IACxD,KAAK,CAAC,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;IAC5C,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,GAAG,EAAE;QACnC,IAAI,KAAK,CAAC,KAAK,EAAE,CAAC;YAChB,cAAc,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QAC7B,CAAC;IACH,CAAC,CAAC,CAAC;IACH,OAAO,GAAG,EAAE,CAAC,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;AAC1C,CAAC;AAID,MAAM,WAAW,GAAG,IAAI,GAAG,EAA0B,CAAC;AAEtD,MAAM,UAAU,GAAG,CAAC,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,YAAY,CAAC,CAAC;AAC1E,MAAM,aAAa,GAAG,CAAC,IAAI,EAAE,CAAC;AAE9B,SAAS,SAAS,CAAC,IAAqB,EAAE,KAA0B,EAAE,GAAW;IAC/E,MAAM,EAAE,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,gBAAgB,EAAE,CAAC,CAAC;IACjD,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;QACxC,EAAE,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,KAAK,CAAC,CAAC;QAC9B,OAAO,CACL,EAAE,EACF,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YAClB,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,GAAG,CAAC,CAAC;YAC5F,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE;gBACpB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;gBAC7B,MAAM,IAAI,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC;gBACnE,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;gBAC7B,CAAC;qBAAM,CAAC;oBACN,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;gBAC1B,CAAC;gBACD,MAAM,EAAE,CAAC;YACX,CAAC,CAAC;YACF,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC;QACjG,CAAC,CAAC,CACH,CAAC;IACJ,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,KAAqB,EAAE,EAAE;QACpC,MAAM,KAAK,GAAmB,EAAE,CAAC;QACjC,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;YACtB,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC;gBACjC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,WAAW,wCAAwC,CAAC,CAAC;gBACxE,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,IAAI,GAAG,aAAa,EAAE,CAAC;gBAC3B,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,YAAY,YAAY,aAAa,IAAI,EAAE,OAAO,CAAC,CAAC;gBACvE,SAAS;YACX,CAAC;YACD,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,GAAG,EAAE,GAAG,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QACvD,CAAC;QACD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,KAAK,CAAC;QACf,CAAC;QACD,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,EAAE,GAAG,KAAK,CAAC,CAAC,CAAC;QAClE,MAAM,EAAE,CAAC;QACT,OAAO,IAAI,CAAC;IACd,CAAC,CAAC;IAEF,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,CAAC,CAAC,EAAE,EAAE;QACpC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC;QAC7F,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,UAAU,EAAE,CAAC,CAAC,EAAE,EAAE;QACtC,IAAI,CAAC,CAAC,YAAY,EAAE,KAAK,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;YAC5C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;QACjC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,EAAE;QACvC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,aAA4B,CAAC,EAAE,CAAC;YACnD,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QACpC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,MAAM,EAAE,CAAC,CAAC,EAAE,EAAE;QAClC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,YAAY,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,MAAM,EAAE,CAAC;IACT,OAAO;QACL,EAAE;QACF,IAAI,EAAE,GAAG,EAAE;YACT,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;YACxC,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;YACxB,MAAM,EAAE,CAAC;YACT,OAAO,IAAI,CAAC;QACd,CAAC;QACD,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE;YAChB,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,IAAI,EAAE,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YACnE,CAAC;YACD,MAAM,EAAE,CAAC;QACX,CAAC;KACF,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,YAAY,CAAC,IAAoB;IAC9C,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,YAAY,EAAE,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC;QAC1D,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACpB,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,aAAa,CAAC,IAAoB;IACzC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED,SAAS,SAAS,CAAC,MAAc;IAC/B,MAAM,MAAM,GAAG,CAAC,CAAC,UAAU,EAAE,EAAE,WAAW,EAAE,gEAAgE,EAAE,IAAI,EAAE,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACzI,MAAM,UAAU,GAAG,SAAS,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,KAAK,GAAG,WAAW,CAAC,SAAS,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IACzD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,aAAa,CAAC,CAAC,CAAC,CAAC;IAC5H,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC;QAC3B,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,MAAM,CAAC,KAAK,GAAG,EAAE,CAAC;QAClB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC;YACtH,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,SAAS,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC7C,MAAM,CAAC,KAAK,GAAG,KAAK,CAAC;YACrB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;IAC5B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,MAAM,YAAY,GAAG,IAAI,GAAG,EAAkB,CAAC;AAE/C,SAAS,WAAW,CAAC,GAAW,EAAE,OAAe;IAC/C,MAAM,OAAO,GAAG,OAAO,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;IACrF,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,yBAAyB,EAAE,EAAE,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IACtH,MAAM,CAAC,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,IAAI,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IAChE,MAAM,CAAC,QAAQ,GAAG,GAAG,EAAE;QACrB,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC;IACtC,CAAC,CAAC;IACF,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,WAAW,CAAC,MAAc,EAAE,SAAiB,EAAE,YAAoB,EAAE,YAAoB;IAChG,MAAM,IAAI,GAAG,CAAC,CAAC,UAAU,EAAE;QACzB,WAAW,EAAE,YAAY,KAAK,MAAM,CAAC,CAAC,CAAC,yDAAyD,CAAC,CAAC,CAAC,2CAA2C;QAC9I,IAAI,EAAE,CAAC;KACR,CAAC,CAAC;IACH,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC;IACxF,MAAM,SAAS,GAAG,CAAC,CACjB,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,SAAS,IAAI,YAAY,KAAK,QAAQ,EAAE,EACtG,YAAY,KAAK,QAAQ,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,WAAW,CAC/D,CAAC;IACF,SAAS,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QAC7B,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,qCAAqC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC7E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,WAAW,CAAC,WAAW,SAAS,EAAE,EAAE,YAAY,CAAC,CAAC;IAChE,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,IAAI,CAAC,CAAC,CAAC;IAC3F,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC;QACzB,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,CAAC,EAAE,CAAC;YAC3D,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,IAAI,CAAC,KAAK,GAAG,EAAE,CAAC;QAChB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,oCAAoC,EAAE;gBAC/C,IAAI,EAAE,EAAE,SAAS,EAAE;gBACnB,IAAI,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,KAAK,YAAY,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,EAAE;aAC7F,CAAC,CAAC;YACH,YAAY,CAAC,MAAM,CAAC,WAAW,SAAS,EAAE,CAAC,CAAC;YAC5C,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC/C,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;YACnB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IAC1B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,KAA0B,EAAE,IAAqB;IACtE,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC;YACvD,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,aAAa,EAAE,CAAC;QACvB,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,SAAS,aAAa,CAAC,SAAiB,EAAE,YAAoB;IAC5D,MAAM,CAAC,GAAG,CAAC,CACT,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,KAAK,EAAE,kFAAkF,EAAE,EAChJ,SAAS,CACV,CAAC;IACF,CAAC,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QACrB,CAAC,CAAC,QAAQ,GAAG,IAAI,CAAC;QAClB,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,mCAAmC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC3E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;YACtB,CAAC,CAAC,QAAQ,GAAG,KAAK,CAAC;QACrB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,CAAC,CAAC;AACX,CAAC;AAED,SAAS,YAAY,CAAC,CAA8D;IAClF,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QACxB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC;IACrD,MAAM,KAAK,GAAG,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC;IAC/D,MAAM,KAAK,GAAG,YAAY,CAAC,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC,MAAM,CAAC,cAAc,EAAE,UAAU,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;IAC5H,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,KAAK,EAAE,EAAE,KAAK,EAAE,EAAE,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;AACtF,CAAC;AAED,SAAS,cAAc,CAAC,CAA0B,EAAE,GAAQ;IAC1D,MAAM,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,qBAAqB,EAAE,EAAE,UAAU,CAAC,CAAC;IACtE,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;IACvC,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,MAAM,EAAE,EACjB,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAChJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EACtE,MAAM,CACP,CAAC;AACJ,CAAC;AAED,SAAS,UAAU,CAAC,KAAa;IAC/B,MAAM,MAAM,GAAG,IAAI,GAAG,EAAqC,CAAC;IAC5D,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,MAAM,GAAG,GAAG,GAAG,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,MAAM,EAAE,CAAC;QACrC,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,EAAE,CAAC;YACV,KAAK,CAAC,CAAC,EAAE,CAAC;QACZ,CAAC;aAAM,CAAC;YACN,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,UAAU,CAAC,CAAC;IACxD,CAAC;IACD,MAAM,KAAK,GAA6B,EAAE,CAAC;IAC3C,KAAK,MAAM,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,MAAM,CAAC,MAAM,EAAE,EAAE,CAAC;QAC1C,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACnB,CAAC;QACD,KAAK,CAAC,IAAI,CACR,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CACpM,CAAC;IACJ,CAAC;IACD,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,GAAG,KAAK,CAAC,CAAC;AACjC,CAAC;AAED,SAAS,WAAW,CAAC,EAAa,EAAE,GAAQ;IAC1C,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;IAChD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,QAAQ,EAAE,EAAE,CAAC,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC,UAAU,EAAE,EAAE,GAAG,CAAC,EAAE,CAAC,UAAU,CAAC,CAAC,CAAC;IAE9F,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;QAChB,KAAK,cAAc;YACjB,GAAG,CAAC,WAAW,GAAG,SAAS,CAAC;YAC5B,IAAI,EAAE,CAAC,KAAK,KAAK,MAAM,EAAE,CAAC;gBACxB,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC;gBAC/B,MAAM,CAAC,KAAK,EAAE,GAAG,IAAI,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;gBAC1C,IAAI,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;oBAChC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;gBACtD,CAAC;gBACD,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAAE,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YACnH,CAAC;YACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,UAAU,EAAE,EACrB,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAC/C,aAAa,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAC1B,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,IAAI,CAC/E,CAAC;QAEJ,KAAK,eAAe;YAClB,GAAG,CAAC,WAAW,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YAC3F,OAAO,GAAG,CAAC,WAAW,CAAC;QAEzB,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;QAEnH,KAAK,mBAAmB,CAAC,CAAC,CAAC;YACzB,MAAM,MAAM,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;YACvD,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,EAAE,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;YACpD,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,oBAAoB,EAAE,EAAE,IAAI,CAAC,CAAC;YACzD,CAAC;YACD,MAAM,CAAC,SAAS,GAAG,aAAa,CAAC;YACjC,OAAO,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YACtB,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,YAAY;YACf,IAAI,OAAO,CAAC,CAAC,eAAe,CAAC,KAAK,QAAQ,IAAI,CAAC,CAAC,eAAe,CAAC,IAAI,GAAG,CAAC,WAAW,EAAE,CAAC;gBACpF,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC;YACvD,CAAC;YACD,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,EAAE,CAAC;gBAC1B,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,oEAAoE,EAAE,IAAI,CAAC,CAAC;YACjH,CAAC;YACD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,eAAe,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAE1J,KAAK,iBAAiB;YACpB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,cAAc,CAAC,CAAC,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEtI,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,0BAA0B,CAAC,CAAC,OAAO,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;QAE/F,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,WAAW,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAEvG,KAAK,eAAe,CAAC,CAAC,CAAC;YACrB,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC;YACvB,IAAI,IAAI,KAAK,UAAU,EAAE,CAAC;gBACxB,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,QAAQ,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAChH,CAAC;YACD,IAAI,IAAI,KAAK,eAAe,IAAI,IAAI,KAAK,cAAc,EAAE,CAAC;gBACxD,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC/D,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,kBAAkB;YACrB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,mCAAmC,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAEvH,KAAK,aAAa;YAChB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,mBAAmB,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,OAAO,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEzI,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,sBAAsB,EAAE,IAAI,CAAC,CAAC;IAChF,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,GAAY;IACjC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC5C,OAAO,IAAI,CAAC;IACd,CAAC;IACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,YAAY,EAAE,EACvB,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QAChB,MAAM,GAAG,GAAG,cAAc,kBAAkB,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;QAC3D,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC;IAC7H,CAAC,CAAC,CACH,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,IAAU,EAAE,MAA+B,EAAE,GAAwB;IACjG,IAAI,CAAC;QACH,MAAM,CAAC,GAAG,MAAM,GAAG,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACnF,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,OAAO;QACT,CAAC;QACD,MAAM,GAAG,EAAE,CAAC;IACd,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;IACxB,CAAC;AACH,CAAC;AAED,SAAS,WAAW,CAAC,CAAW;IAC9B,MAAM,MAAM,GAAG,CAAC,CAAS,EAAE,IAAY,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC;IAChF,MAAM,WAAW,GAAG,CAAC,CAAC,WAAW,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,WAAW,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC;IAC9E,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,MAAM,CAAC,CAAC,CAAC,KAAK,EAAE,cAAc,CAAC,MAAM,CAAC,CAAC,UAAU,KAAK,CAAC,CAAC,SAAS,GAAG,WAAW,GAAG,CAAC;AAClI,CAAC;AAED,SAAS,SAAS,CAAC,KAAc,EAAE,IAAY;IAC7C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,CAAC,GAAG,KAAgC,CAAC;IAC3C,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,aAAa,CAAC,IAAI,EAAE,CAAC;IACpH,MAAM,IAAI,GAAG,QAAQ,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,IAAI,CAAC,CAAC;IAC3C,OAAO,IAAI,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC;AAC7D,CAAC;AAED,SAAS,UAAU,CAAC,KAAc,EAAE,IAAY;IAC9C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,IAAI,GAAI,KAAiC,CAAC,WAAW,CAAC,CAAC;IAC7D,OAAO,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AAC9D,CAAC;AAED,SAAS,QAAQ,CAAC,IAAY,EAAE,IAAY;IAC1C,OAAO,IAAI,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;AAClF,CAAC;AAED,SAAS,UAAU,CAAC,OAAgB;IAClC,IAAI,OAAO,OAAO,KAAK,QAAQ,EAAE,CAAC;QAChC,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,IAAI,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;QAC3B,OAAO,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,QAAQ,IAAI,CAAC,KAAK,IAAI,IAAI,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAClI,CAAC;IACD,OAAO,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;AAC1C,CAAC"} \ No newline at end of file +{"version":3,"file":"task.js","sourceRoot":"","sources":["../src/task.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAE,IAAI,EAA4C,MAAM,UAAU,CAAC;AAC/E,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,MAAM,eAAe,CAAC;AACzC,OAAO,EAAE,cAAc,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAErE,MAAM,MAAM,GAAG,CAAC,iBAAiB,EAAE,mBAAmB,EAAE,kBAAkB,EAAE,kBAAkB,CAAC,CAAC;AAmBhG,MAAM,UAAU,eAAe,CAAC,IAAiB;IAC/C,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACnD,MAAM,UAAU,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IACrD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,CAAC,CAAC;IAEjD,MAAM,cAAc,GAAG,IAAI,GAAG,EAAmB,CAAC;IAClD,MAAM,KAAK,GAAG,IAAI,GAAG,EAAU,CAAC;IAChC,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,QAAQ,CAAC,eAAe,KAAK,SAAS,EAAE,CAAC;YAC3C,OAAO;QACT,CAAC;QACD,MAAM,GAAG,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,cAAc,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;QACzH,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACrB,OAAO;QACT,CAAC;QACD,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;YACrB,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QAChB,CAAC;QACD,IAAI,CAAC,sBAAsB,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,SAAkB,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,EAAE,EAAE;YAChI,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;gBACrB,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;YACnB,CAAC;YACD,OAAO,CAAC,KAAK,CAAC,qBAAqB,EAAE,GAAG,CAAC,CAAC;QAC5C,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IACF,MAAM,QAAQ,GAAG,IAAI,oBAAoB,CACvC,CAAC,OAAO,EAAE,EAAE;QACV,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACxB,MAAM,EAAE,GAAI,CAAC,CAAC,MAAsB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAC1D,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,cAAc,EAAE,CAAC;gBACrB,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;YACnC,CAAC;iBAAM,CAAC;gBACN,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YAClC,CAAC;QACH,CAAC;QACD,UAAU,EAAE,CAAC;IACf,CAAC,EACD,EAAE,IAAI,EAAE,UAAU,EAAE,SAAS,EAAE,GAAG,EAAE,CACrC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAQ,EAAE;QACvB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,OAAO;YACL,KAAK,EAAE,IAAI,GAAG,EAAE;YAChB,GAAG,EAAE,SAAS;YACd,WAAW,EAAE,SAAS;YACtB,SAAS,EAAE,SAAS;YACpB,IAAI,EAAE,IAAI,EAAE,aAAa,IAAI,EAAE;YAC/B,WAAW,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,EAAE;gBAC1B,EAAE,CAAC,OAAO,CAAC,WAAW,CAAC,GAAG,MAAM,CAAC;gBACjC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;YACvB,CAAC;SACF,CAAC;IACJ,CAAC,CAAC;IACF,IAAI,GAAG,GAAG,MAAM,EAAE,CAAC;IACnB,IAAI,OAAO,GAAG,IAAI,GAAG,EAA2D,CAAC;IAEjF,MAAM,OAAO,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;IAChI,MAAM,UAAU,GAAG,CAAC,OAAgB,EAAE,EAAE;QACtC,UAAU,CAAC,SAAS,CAAC,MAAM,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QAChD,IAAI,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;YAChC,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,OAAO,CAAC,MAAM,GAAG,CAAC,OAAO,CAAC;QAC1B,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,EAAe,EAAE,EAAE;QAC9B,IAAI,OAAO,CAAC,UAAU,KAAK,UAAU,EAAE,CAAC;YACtC,UAAU,CAAC,YAAY,CAAC,EAAE,EAAE,OAAO,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,UAAU,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,UAAU,CAAC,IAAI,KAAK,SAAS,IAAI,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,KAAK,SAAS,CAAC,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,IAAI,CAAC,CAAC;YACd,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,IAAI,CAAC,MAAM,KAAK,QAAQ,EAAE,CAAC;YAC7B,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;YAChE,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,EAAE,cAAc,IAAI,oBAAoB,CAAC;QAC5G,MAAM,IAAI,GAAG,IAAI,EAAE,KAAK,KAAK,SAAS,IAAI,IAAI,EAAE,KAAK,KAAK,QAAQ,CAAC;QACnE,MAAM,KAAK,GAAG,CAAC,CACb,QAAQ,EACR,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,oBAAoB,MAAM,8CAA8C,MAAM,qBAAqB,EAAE,EAC9H,OAAO,CACR,CAAC;QACF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CACnB,cAAc,CACZ,IAAI,EACJ,CAAC,CAAC,EAAE,EAAE,CACJ,UAAU,IAAI,CAAC,KAAK,UAAU,MAAM,4BAA4B,MAAM,wDAAwD,WAAW,CAAC,CAAC,CAAC,yBAAyB,MAAM,YAAY,IAAI,CAAC,WAAW,4CAA4C,EACrP,KAAK,IAAI,EAAE;YACT,MAAM,IAAI,CAAC,2BAA2B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACzE,CAAC,CACF,CAAC;QACJ,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,0BAA0B,MAAM,6CAA6C,EAAE,EAAE,SAAS,MAAM,KAAK,CAAC,CAAC;QAC5J,OAAO,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;YAC3B,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC;YACxB,IAAI,CAAC;gBACH,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;YAC5E,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;gBACtB,OAAO,CAAC,QAAQ,GAAG,KAAK,CAAC;YAC3B,CAAC;QACH,CAAC,CAAC;QACF,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,gDAAgD,EAAE,EAAE,SAAS,CAAC,CAAC;QACrI,OAAO,CAAC,OAAO,GAAG,GAAG,EAAE,CACrB,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,YAAY,IAAI,CAAC,KAAK,MAAM,WAAW,CAAC,CAAC,CAAC,mBAAmB,MAAM,yCAAyC,EAAE,KAAK,IAAI,EAAE;YACnJ,MAAM,IAAI,CAAC,6BAA6B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;YACzE,QAAQ,CAAC,IAAI,GAAG,IAAI,CAAC;QACvB,CAAC,CAAC,CAAC;QACL,OAAO,CACL,IAAI,EACJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,8BAA8B,EAAE,EAAE,IAAI,IAAI,YAAY,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,IAAI,IAAI,aAAa,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAAE,OAAO,CAAC,EACpJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,KAAK,EAAE,OAAO,CAAC,CACpD,CAAC;IACJ,CAAC,CAAC;IAEF,IAAI,aAAa,GAAG,EAAE,CAAC;IACvB,MAAM,cAAc,GAAG,GAAG,EAAE;QAC1B,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,QAAQ,CAAC,CAAC;YAClB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,KAAK,WAAW,EAAE,CAAC;YACxC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;YACtC,OAAO;QACT,CAAC;QACD,aAAa,GAAG,IAAI,CAAC,KAAK,IAAI,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC;QAChE,OAAO,CAAC,QAAQ,EAAE,WAAW,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,EAAE,aAAa,CAAC,CAAC,CAAC;IAC9E,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,EAAe,EAAE,IAAsB,EAAE,EAAE;QAC3D,MAAM,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC;QACpB,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,GAAG,CAAC,GAAG,GAAG,EAAE,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;YACrE,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,OAAO;QACT,CAAC;QACD,IAAI,IAAI,EAAE,CAAC;YACT,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACvB,CAAC;QACD,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC;YACf,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;YAC7B,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,CAAC,CAAC;YACpD,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC;YACnE,GAAG,CAAC,KAAK,CAAC,WAAW,CAAC,KAAK,CAAC,CAAC;YAC7B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACvB,GAAG,CAAC,KAAK,GAAG,EAAE,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC;QAC3C,CAAC;QACD,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QAC1B,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;IACpD,CAAC,CAAC;IAEF,IAAI,MAAoE,CAAC;IACzE,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,OAAO;QACT,CAAC;QACD,YAAY,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QAC3B,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC;QACnB,MAAM,GAAG,SAAS,CAAC;IACrB,CAAC,CAAC;IACF,MAAM,WAAW,GAAG,CAAC,EAAa,EAAE,EAAE;QACpC,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,MAAM,GAAG,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;YACtE,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;QACD,MAAM,CAAC,IAAI,IAAI,MAAM,CAAC,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;QAChD,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;YACjB,OAAO;QACT,CAAC;QACD,MAAM,CAAC,KAAK,GAAG,UAAU,CAAC,GAAG,EAAE;YAC7B,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO;YACT,CAAC;YACD,MAAM,CAAC,KAAK,GAAG,CAAC,CAAC;YACjB,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;YAC7F,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC,CAAC;YACrD,IAAI,MAAM,EAAE,CAAC;gBACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;YACjD,CAAC;QACH,CAAC,EAAE,GAAG,CAAC,CAAC;IACV,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,KAAkB,EAAE,GAAgB,EAAE,EAAE;QACxD,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;QAC7B,OAAO,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;QAChD,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC,CAAC;QAC7D,IAAI,IAAI,GAAqB,KAAK,CAAC;QACnC,OAAO,IAAI,IAAI,IAAI,KAAK,OAAO,EAAE,CAAC;YAChC,MAAM,IAAI,GAAqB,IAAI,CAAC,WAAW,CAAC;YAChD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;YAClB,IAAI,GAAG,IAAI,CAAC;QACd,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,YAAY,GAAG,CAAC,MAAmB,EAAE,EAAE;QAC3C,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,IAAI,cAAc,GAAG,KAAK,CAAC;QAC3B,KAAK,MAAM,EAAE,IAAI,MAAM,EAAE,CAAC;YACxB,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;YAChD,IAAI,EAAE,CAAC,IAAI,KAAK,eAAe,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC1F,UAAU,EAAE,CAAC;YACf,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,IAAI,EAAE,CAAC,gBAAgB,EAAE,CAAC;gBACzD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,CAAC,CAAC;gBAC9C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,CAAC;gBACxD,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC;gBACvG,cAAc,GAAG,IAAI,CAAC;gBACtB,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,EAAE,CAAC;gBAClC,QAAQ,CAAC,cAAc,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBACxG,SAAS;YACX,CAAC;YACD,MAAM,EAAE,GAAG,WAAW,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC;YAChC,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,gBAAgB,EAAE,CAAC;gBACjC,QAAQ,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;gBACxB,SAAS;YACX,CAAC;YACD,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,IAAI,GAAG,CAAC,SAAS,EAAE,UAAU,KAAK,UAAU,EAAE,CAAC;gBAClG,QAAQ,CAAC,GAAG,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;gBAC5B,GAAG,CAAC,SAAS,GAAG,SAAS,CAAC;gBAC1B,SAAS;YACX,CAAC;YACD,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC/B,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC;YACrB,CAAC;QACH,CAAC;QACD,IAAI,cAAc,EAAE,CAAC;YACnB,UAAU,EAAE,CAAC;YACb,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,cAAc,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;YACrF,IAAI,IAAI,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC,KAAK,aAAa,EAAE,CAAC;gBACjF,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC;QACD,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,SAAS,GAAG,GAAG,EAAE;QACrB,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,cAAc,CAAC,KAAK,EAAE,CAAC;QACvB,UAAU,EAAE,CAAC;QACb,GAAG,GAAG,MAAM,EAAE,CAAC;QACf,OAAO,GAAG,IAAI,GAAG,EAAE,CAAC;QACpB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC,KAAK,CAAC,cAAc,EAAE,CAAC;YAC1B,cAAc,EAAE,CAAC;YACjB,OAAO,CAAC,UAAU,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,2DAA2D,CAAC,CAAC,CAAC;YAC/G,OAAO;QACT,CAAC;QACD,OAAO,CAAC,UAAU,EAAE,OAAO,CAAC,CAAC;QAC7B,YAAY,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;QAC/B,cAAc,EAAE,CAAC;IACnB,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG;QACX,MAAM,CAAC,CAAC,WAAW,CAAC,EAAE,SAAS,CAAC;QAChC,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,EAAE;YACrB,UAAU,EAAE,CAAC;YACb,cAAc,EAAE,CAAC;QACnB,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE;YAC9B,IAAI,MAAM,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;gBACpC,UAAU,EAAE,CAAC;gBACb,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,YAAY,CAAC,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAoB,CAAC,CAAC;QACrE,MAAM,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,EAAE,EAAE,EAAE,CAAC,WAAW,CAAC,EAAe,CAAC,CAAC;QACxD,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,UAAU,CAAC;KAC9B,CAAC;IACF,QAAQ,CAAC,gBAAgB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;IAE1D,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC,CAAC;IAClF,SAAS,EAAE,CAAC;IACZ,OAAO,GAAG,EAAE;QACV,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;QACD,QAAQ,CAAC,mBAAmB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;QAC7D,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,UAAU,EAAE,CAAC;IACf,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,cAAc,GAAG,IAAI,GAAG,EAAkB,CAAC;AAEjD,SAAS,SAAS,CAAC,KAA0B,EAAE,GAAW;IACxD,KAAK,CAAC,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;IAC5C,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,GAAG,EAAE;QACnC,IAAI,KAAK,CAAC,KAAK,EAAE,CAAC;YAChB,cAAc,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QAC7B,CAAC;IACH,CAAC,CAAC,CAAC;IACH,OAAO,GAAG,EAAE,CAAC,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;AAC1C,CAAC;AAID,MAAM,WAAW,GAAG,IAAI,GAAG,EAA0B,CAAC;AAEtD,MAAM,UAAU,GAAG,CAAC,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,YAAY,CAAC,CAAC;AAC1E,MAAM,aAAa,GAAG,CAAC,IAAI,EAAE,CAAC;AAE9B,SAAS,SAAS,CAAC,IAAqB,EAAE,KAA0B,EAAE,GAAW;IAC/E,MAAM,EAAE,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,gBAAgB,EAAE,CAAC,CAAC;IACjD,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;QACxC,EAAE,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,KAAK,CAAC,CAAC;QAC9B,OAAO,CACL,EAAE,EACF,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YAClB,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,GAAG,CAAC,CAAC;YAC5F,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE;gBACpB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;gBAC7B,MAAM,IAAI,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC;gBACnE,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;gBAC7B,CAAC;qBAAM,CAAC;oBACN,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;gBAC1B,CAAC;gBACD,MAAM,EAAE,CAAC;YACX,CAAC,CAAC;YACF,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC;QACjG,CAAC,CAAC,CACH,CAAC;IACJ,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,KAAqB,EAAE,EAAE;QACpC,MAAM,KAAK,GAAmB,EAAE,CAAC;QACjC,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;YACtB,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC;gBACjC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,WAAW,wCAAwC,CAAC,CAAC;gBACxE,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,IAAI,GAAG,aAAa,EAAE,CAAC;gBAC3B,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,YAAY,YAAY,aAAa,IAAI,EAAE,OAAO,CAAC,CAAC;gBACvE,SAAS;YACX,CAAC;YACD,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,GAAG,EAAE,GAAG,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QACvD,CAAC;QACD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,KAAK,CAAC;QACf,CAAC;QACD,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,EAAE,GAAG,KAAK,CAAC,CAAC,CAAC;QAClE,MAAM,EAAE,CAAC;QACT,OAAO,IAAI,CAAC;IACd,CAAC,CAAC;IAEF,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,CAAC,CAAC,EAAE,EAAE;QACpC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC;QAC7F,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,UAAU,EAAE,CAAC,CAAC,EAAE,EAAE;QACtC,IAAI,CAAC,CAAC,YAAY,EAAE,KAAK,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;YAC5C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;QACjC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,EAAE;QACvC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,aAA4B,CAAC,EAAE,CAAC;YACnD,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QACpC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,MAAM,EAAE,CAAC,CAAC,EAAE,EAAE;QAClC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,YAAY,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,MAAM,EAAE,CAAC;IACT,OAAO;QACL,EAAE;QACF,IAAI,EAAE,GAAG,EAAE;YACT,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;YACxC,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;YACxB,MAAM,EAAE,CAAC;YACT,OAAO,IAAI,CAAC;QACd,CAAC;QACD,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE;YAChB,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,IAAI,EAAE,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YACnE,CAAC;YACD,MAAM,EAAE,CAAC;QACX,CAAC;KACF,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,YAAY,CAAC,IAAoB;IAC9C,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,YAAY,EAAE,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC;QAC1D,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACpB,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,aAAa,CAAC,IAAoB;IACzC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED,SAAS,SAAS,CAAC,MAAc;IAC/B,MAAM,MAAM,GAAG,CAAC,CAAC,UAAU,EAAE,EAAE,WAAW,EAAE,gEAAgE,EAAE,IAAI,EAAE,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACzI,MAAM,UAAU,GAAG,SAAS,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,KAAK,GAAG,WAAW,CAAC,SAAS,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IACzD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,aAAa,CAAC,CAAC,CAAC,CAAC;IAC5H,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC;QAC3B,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,MAAM,CAAC,KAAK,GAAG,EAAE,CAAC;QAClB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC;YACtH,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,SAAS,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC7C,MAAM,CAAC,KAAK,GAAG,KAAK,CAAC;YACrB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;IAC5B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,MAAM,YAAY,GAAG,IAAI,GAAG,EAAkB,CAAC;AAE/C,SAAS,WAAW,CAAC,GAAW,EAAE,OAAe;IAC/C,MAAM,OAAO,GAAG,OAAO,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;IACrF,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,yBAAyB,EAAE,EAAE,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IACtH,MAAM,CAAC,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,IAAI,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IAChE,MAAM,CAAC,QAAQ,GAAG,GAAG,EAAE;QACrB,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC;IACtC,CAAC,CAAC;IACF,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,WAAW,CAAC,MAAc,EAAE,SAAiB,EAAE,YAAoB,EAAE,YAAoB;IAChG,MAAM,IAAI,GAAG,CAAC,CAAC,UAAU,EAAE;QACzB,WAAW,EAAE,YAAY,KAAK,MAAM,CAAC,CAAC,CAAC,yDAAyD,CAAC,CAAC,CAAC,2CAA2C;QAC9I,IAAI,EAAE,CAAC;KACR,CAAC,CAAC;IACH,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC;IACxF,MAAM,SAAS,GAAG,CAAC,CACjB,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,SAAS,IAAI,YAAY,KAAK,QAAQ,EAAE,EACtG,YAAY,KAAK,QAAQ,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,WAAW,CAC/D,CAAC;IACF,SAAS,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QAC7B,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,qCAAqC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC7E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,WAAW,CAAC,WAAW,SAAS,EAAE,EAAE,YAAY,CAAC,CAAC;IAChE,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,IAAI,CAAC,CAAC,CAAC;IAC3F,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC;QACzB,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,CAAC,EAAE,CAAC;YAC3D,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,IAAI,CAAC,KAAK,GAAG,EAAE,CAAC;QAChB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,oCAAoC,EAAE;gBAC/C,IAAI,EAAE,EAAE,SAAS,EAAE;gBACnB,IAAI,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,KAAK,YAAY,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,EAAE;aAC7F,CAAC,CAAC;YACH,YAAY,CAAC,MAAM,CAAC,WAAW,SAAS,EAAE,CAAC,CAAC;YAC5C,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC/C,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;YACnB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IAC1B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,KAA0B,EAAE,IAAqB;IACtE,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC;YACvD,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,aAAa,EAAE,CAAC;QACvB,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,SAAS,aAAa,CAAC,SAAiB,EAAE,YAAoB;IAC5D,MAAM,CAAC,GAAG,CAAC,CACT,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,KAAK,EAAE,kFAAkF,EAAE,EAChJ,SAAS,CACV,CAAC;IACF,CAAC,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QACrB,CAAC,CAAC,QAAQ,GAAG,IAAI,CAAC;QAClB,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,mCAAmC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC3E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;YACtB,CAAC,CAAC,QAAQ,GAAG,KAAK,CAAC;QACrB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,CAAC,CAAC;AACX,CAAC;AAED,SAAS,YAAY,CAAC,CAA8D;IAClF,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QACxB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC;IACrD,MAAM,KAAK,GAAG,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC;IAC/D,MAAM,KAAK,GAAG,YAAY,CAAC,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC,MAAM,CAAC,cAAc,EAAE,UAAU,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;IAC5H,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,KAAK,EAAE,EAAE,KAAK,EAAE,EAAE,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;AACtF,CAAC;AAED,SAAS,cAAc,CAAC,CAA0B,EAAE,GAAQ;IAC1D,MAAM,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,qBAAqB,EAAE,EAAE,UAAU,CAAC,CAAC;IACtE,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;IACvC,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,MAAM,EAAE,EACjB,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAChJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EACtE,MAAM,CACP,CAAC;AACJ,CAAC;AAED,SAAS,UAAU,CAAC,KAAa;IAC/B,MAAM,MAAM,GAAG,IAAI,GAAG,EAAqC,CAAC;IAC5D,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,MAAM,GAAG,GAAG,GAAG,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,MAAM,EAAE,CAAC;QACrC,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,EAAE,CAAC;YACV,KAAK,CAAC,CAAC,EAAE,CAAC;QACZ,CAAC;aAAM,CAAC;YACN,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,UAAU,CAAC,CAAC;IACxD,CAAC;IACD,MAAM,KAAK,GAA6B,EAAE,CAAC;IAC3C,KAAK,MAAM,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,MAAM,CAAC,MAAM,EAAE,EAAE,CAAC;QAC1C,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACnB,CAAC;QACD,KAAK,CAAC,IAAI,CACR,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CACpM,CAAC;IACJ,CAAC;IACD,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,GAAG,KAAK,CAAC,CAAC;AACjC,CAAC;AAED,SAAS,WAAW,CAAC,EAAa,EAAE,GAAQ;IAC1C,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;IAChD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,QAAQ,EAAE,EAAE,CAAC,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC,UAAU,EAAE,EAAE,GAAG,CAAC,EAAE,CAAC,UAAU,CAAC,CAAC,CAAC;IAE9F,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;QAChB,KAAK,cAAc;YACjB,GAAG,CAAC,WAAW,GAAG,SAAS,CAAC;YAC5B,IAAI,EAAE,CAAC,KAAK,KAAK,MAAM,EAAE,CAAC;gBACxB,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC;gBAC/B,MAAM,CAAC,KAAK,EAAE,GAAG,IAAI,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;gBAC1C,IAAI,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;oBAChC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;gBACtD,CAAC;gBACD,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAAE,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YACnH,CAAC;YACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,UAAU,EAAE,EACrB,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAC/C,aAAa,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAC1B,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,IAAI,CAC/E,CAAC;QAEJ,KAAK,eAAe;YAClB,GAAG,CAAC,WAAW,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YAC3F,OAAO,GAAG,CAAC,WAAW,CAAC;QAEzB,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;QAEnH,KAAK,mBAAmB,CAAC,CAAC,CAAC;YACzB,MAAM,MAAM,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;YACvD,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,EAAE,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;YACpD,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,oBAAoB,EAAE,EAAE,IAAI,CAAC,CAAC;YACzD,CAAC;YACD,MAAM,CAAC,SAAS,GAAG,aAAa,CAAC;YACjC,OAAO,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YACtB,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,YAAY;YACf,IAAI,OAAO,CAAC,CAAC,eAAe,CAAC,KAAK,QAAQ,IAAI,CAAC,CAAC,eAAe,CAAC,IAAI,GAAG,CAAC,WAAW,EAAE,CAAC;gBACpF,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC;YACvD,CAAC;YACD,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,EAAE,CAAC;gBAC1B,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,oEAAoE,EAAE,IAAI,CAAC,CAAC;YACjH,CAAC;YACD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,eAAe,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAE1J,KAAK,iBAAiB;YACpB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,cAAc,CAAC,CAAC,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEtI,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,0BAA0B,CAAC,CAAC,OAAO,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;QAE/F,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,WAAW,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAEvG,KAAK,eAAe,CAAC,CAAC,CAAC;YACrB,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC;YACvB,IAAI,IAAI,KAAK,UAAU,EAAE,CAAC;gBACxB,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,QAAQ,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAChH,CAAC;YACD,IAAI,IAAI,KAAK,eAAe,IAAI,IAAI,KAAK,cAAc,EAAE,CAAC;gBACxD,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC/D,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,kBAAkB;YACrB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,mCAAmC,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAEvH,KAAK,aAAa;YAChB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,mBAAmB,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,OAAO,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEzI,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,sBAAsB,EAAE,IAAI,CAAC,CAAC;IAChF,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,GAAY;IACjC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC5C,OAAO,IAAI,CAAC;IACd,CAAC;IACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,YAAY,EAAE,EACvB,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QAChB,MAAM,GAAG,GAAG,cAAc,kBAAkB,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;QAC3D,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC;IAC7H,CAAC,CAAC,CACH,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,IAAU,EAAE,MAA+B,EAAE,GAAwB;IACjG,IAAI,CAAC;QACH,MAAM,CAAC,GAAG,MAAM,GAAG,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACnF,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,OAAO;QACT,CAAC;QACD,MAAM,GAAG,EAAE,CAAC;IACd,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;IACxB,CAAC;AACH,CAAC;AAED,SAAS,WAAW,CAAC,CAAW;IAC9B,MAAM,MAAM,GAAG,CAAC,CAAS,EAAE,IAAY,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC;IAChF,MAAM,WAAW,GAAG,CAAC,CAAC,WAAW,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,WAAW,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC;IAC9E,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,MAAM,CAAC,CAAC,CAAC,KAAK,EAAE,cAAc,CAAC,MAAM,CAAC,CAAC,UAAU,KAAK,CAAC,CAAC,SAAS,GAAG,WAAW,GAAG,CAAC;AAClI,CAAC;AAED,SAAS,SAAS,CAAC,KAAc,EAAE,IAAY;IAC7C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,CAAC,GAAG,KAAgC,CAAC;IAC3C,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,aAAa,CAAC,IAAI,EAAE,CAAC;IACpH,MAAM,IAAI,GAAG,QAAQ,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,IAAI,CAAC,CAAC;IAC3C,OAAO,IAAI,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC;AAC7D,CAAC;AAED,SAAS,UAAU,CAAC,KAAc,EAAE,IAAY;IAC9C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,IAAI,GAAI,KAAiC,CAAC,WAAW,CAAC,CAAC;IAC7D,OAAO,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AAC9D,CAAC;AAED,SAAS,QAAQ,CAAC,IAAY,EAAE,IAAY;IAC1C,OAAO,IAAI,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;AAClF,CAAC;AAED,SAAS,UAAU,CAAC,OAAgB;IAClC,IAAI,OAAO,OAAO,KAAK,QAAQ,EAAE,CAAC;QAChC,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,IAAI,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;QAC3B,OAAO,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,QAAQ,IAAI,CAAC,KAAK,IAAI,IAAI,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAClI,CAAC;IACD,OAAO,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;AAC1C,CAAC"} \ No newline at end of file diff --git a/web/dist/tasks.js b/web/dist/tasks.js index bafd9d9..06fdd66 100644 --- a/web/dist/tasks.js +++ b/web/dist/tasks.js @@ -1,5 +1,6 @@ import { post } from "./api.js"; import { errorText, h, replace } from "./dom.js"; +import { openTranscript } from "./panes.js"; import { currentSession, onEach, state } from "./state.js"; export function mountTasks(root) { const render = () => replace(root, h("div", { class: "tasks-view" }, ...state.projects.map(projectBlock), newProjectForm())); @@ -12,7 +13,7 @@ function projectBlock(project) { return h("section", { class: "project" }, h("h2", {}, project.name, " ", h("span", { class: "repo" }, project.repo_path)), h("ul", { class: "task-list" }, ...tasks.map((task) => { const sess = currentSession(task.id); const count = state.inbox.filter((item) => item.task_id === task.id).length; - return h("li", { class: task.id === state.selectedTaskId ? "selected" : "" }, h("a", { href: `#/task/${task.id}` }, h("span", { class: `dot ${sess?.state ?? "none"}`, title: sess?.state ?? "no session" }), h("span", { class: "task-title" }, task.title), h("span", { class: "task-state" }, sess?.state ?? "no agent"), count > 0 && h("span", { class: "badge" }, count))); + return h("li", { class: task.id === state.selectedTaskId ? "selected" : "" }, h("a", { href: `#/task/${task.id}`, onclick: openTranscript }, h("span", { class: `dot ${sess?.state ?? "none"}`, title: sess?.state ?? "no session" }), h("span", { class: "task-title" }, task.title), h("span", { class: "task-state" }, sess?.state ?? "no agent"), count > 0 && h("span", { class: "badge" }, count))); }), tasks.length === 0 && h("li", { class: "empty-row" }, "No active tasks.")), newTaskForm(project.id)); } function newTaskForm(projectId) { diff --git a/web/dist/tasks.js.map b/web/dist/tasks.js.map index 4e1e88a..f9d7ce1 100644 --- a/web/dist/tasks.js.map +++ b/web/dist/tasks.js.map @@ -1 +1 @@ -{"version":3,"file":"tasks.js","sourceRoot":"","sources":["../src/tasks.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAgB,MAAM,UAAU,CAAC;AAC9C,OAAO,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACjD,OAAO,EAAE,cAAc,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAE3D,MAAM,UAAU,UAAU,CAAC,IAAiB;IAC1C,MAAM,MAAM,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,GAAG,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,YAAY,CAAC,EAAE,cAAc,EAAE,CAAC,CAAC,CAAC;IAC7H,MAAM,GAAG,GAAG,MAAM,CAAC,CAAC,UAAU,EAAE,OAAO,EAAE,UAAU,EAAE,OAAO,EAAE,WAAW,CAAC,EAAE,MAAM,CAAC,CAAC;IACpF,MAAM,EAAE,CAAC;IACT,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,YAAY,CAAC,OAAgB;IACpC,MAAM,KAAK,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC;IAEvF,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,SAAS,EAAE,EACpB,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,OAAO,CAAC,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,OAAO,CAAC,SAAS,CAAC,CAAC,EAC/E,CAAC,CACC,IAAI,EACJ,EAAE,KAAK,EAAE,WAAW,EAAE,EACtB,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE;QACpB,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,KAAK,IAAI,CAAC,EAAE,CAAC,CAAC,MAAM,CAAC;QAC5E,OAAO,CAAC,CACN,IAAI,EACJ,EAAE,KAAK,EAAE,IAAI,CAAC,EAAE,KAAK,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,EAAE,EAC7D,CAAC,CACC,GAAG,EACH,EAAE,IAAI,EAAE,UAAU,IAAI,CAAC,EAAE,EAAE,EAAE,EAC7B,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,OAAO,IAAI,EAAE,KAAK,IAAI,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,IAAI,YAAY,EAAE,CAAC,EACxF,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAC9C,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,EAAE,KAAK,IAAI,UAAU,CAAC,EAC7D,KAAK,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,KAAK,CAAC,CAClD,CACF,CAAC;IACJ,CAAC,CAAC,EACF,KAAK,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,kBAAkB,CAAC,CAC1E,EACD,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,CACxB,CAAC;AACJ,CAAC;AAED,SAAS,WAAW,CAAC,SAAiB;IACpC,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,gBAAgB,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IAC5E,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,QAAQ,CAAC,CAAC,CAAC;IACnG,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,IAAI,CAAC;YACH,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,iCAAiC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YAClH,QAAQ,CAAC,IAAI,GAAG,UAAU,IAAI,CAAC,EAAE,EAAE,CAAC;QACtC,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,cAAc;IACrB,MAAM,IAAI,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACjE,MAAM,IAAI,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,yBAAyB,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACpF,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,aAAa,CAAC,CAAC,CAAC;IAC5G,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,eAAe,EAAE,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,EAAE,SAAS,EAAE,IAAI,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YACnF,IAAI,CAAC,KAAK,EAAE,CAAC;QACf,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,IAAI,EAAE,KAAK,CAAC,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,aAAa,CAAC,EAAE,IAAI,CAAC,CAAC;AAC1H,CAAC"} \ No newline at end of file +{"version":3,"file":"tasks.js","sourceRoot":"","sources":["../src/tasks.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAgB,MAAM,UAAU,CAAC;AAC9C,OAAO,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACjD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAC;AAC5C,OAAO,EAAE,cAAc,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAE3D,MAAM,UAAU,UAAU,CAAC,IAAiB;IAC1C,MAAM,MAAM,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,GAAG,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,YAAY,CAAC,EAAE,cAAc,EAAE,CAAC,CAAC,CAAC;IAC7H,MAAM,GAAG,GAAG,MAAM,CAAC,CAAC,UAAU,EAAE,OAAO,EAAE,UAAU,EAAE,OAAO,EAAE,WAAW,CAAC,EAAE,MAAM,CAAC,CAAC;IACpF,MAAM,EAAE,CAAC;IACT,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,YAAY,CAAC,OAAgB;IACpC,MAAM,KAAK,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC;IAEvF,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,SAAS,EAAE,EACpB,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,OAAO,CAAC,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,OAAO,CAAC,SAAS,CAAC,CAAC,EAC/E,CAAC,CACC,IAAI,EACJ,EAAE,KAAK,EAAE,WAAW,EAAE,EACtB,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE;QACpB,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,KAAK,IAAI,CAAC,EAAE,CAAC,CAAC,MAAM,CAAC;QAC5E,OAAO,CAAC,CACN,IAAI,EACJ,EAAE,KAAK,EAAE,IAAI,CAAC,EAAE,KAAK,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,EAAE,EAC7D,CAAC,CACC,GAAG,EACH,EAAE,IAAI,EAAE,UAAU,IAAI,CAAC,EAAE,EAAE,EAAE,OAAO,EAAE,cAAc,EAAE,EACtD,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,OAAO,IAAI,EAAE,KAAK,IAAI,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,IAAI,YAAY,EAAE,CAAC,EACxF,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAC9C,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,EAAE,KAAK,IAAI,UAAU,CAAC,EAC7D,KAAK,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,KAAK,CAAC,CAClD,CACF,CAAC;IACJ,CAAC,CAAC,EACF,KAAK,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,kBAAkB,CAAC,CAC1E,EACD,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,CACxB,CAAC;AACJ,CAAC;AAED,SAAS,WAAW,CAAC,SAAiB;IACpC,MAAM,KAAK,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,gBAAgB,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IAC5E,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,QAAQ,CAAC,CAAC,CAAC;IACnG,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,IAAI,CAAC;YACH,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,iCAAiC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,IAAI,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YAClH,QAAQ,CAAC,IAAI,GAAG,UAAU,IAAI,CAAC,EAAE,EAAE,CAAC;QACtC,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,cAAc;IACrB,MAAM,IAAI,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACjE,MAAM,IAAI,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,WAAW,EAAE,yBAAyB,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACpF,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,aAAa,CAAC,CAAC,CAAC;IAC5G,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,eAAe,EAAE,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,EAAE,SAAS,EAAE,IAAI,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YACnF,IAAI,CAAC,KAAK,EAAE,CAAC;QACf,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,IAAI,EAAE,KAAK,CAAC,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,aAAa,CAAC,EAAE,IAAI,CAAC,CAAC;AAC1H,CAAC"} \ No newline at end of file diff --git a/web/src/api.ts b/web/src/api.ts index f28c1d2..b4532db 100644 --- a/web/src/api.ts +++ b/web/src/api.ts @@ -94,10 +94,58 @@ export const post =

>(path: P, opts?: Options>(path: P, opts?: Options>) => request("put", path, opts); export const del =

>(path: P, opts?: Options>) => request("delete", path, opts); -export function subscribe(after: number, onEvent: (ev: ByreEvent) => void, onState: (connected: boolean) => void): EventSource { - const source = new EventSource(`/api/events?after=${after}`); - source.onopen = () => onState(true); - source.onerror = () => onState(false); - source.onmessage = (msg: MessageEvent) => onEvent(JSON.parse(msg.data) as ByreEvent); - return source; +const staleAfterMs = 40_000; +const retryAfterMs = 2_000; + +export function subscribe(after: number, onEvent: (ev: ByreEvent) => void, onState: (connected: boolean) => void): void { + let last = after; + let heard = Date.now(); + let source: EventSource | undefined; + let retry = 0; + + const connect = () => { + clearTimeout(retry); + source?.close(); + heard = Date.now(); + const s = new EventSource(`/api/events?after=${last}`); + source = s; + s.onopen = () => { + heard = Date.now(); + onState(true); + }; + s.onerror = () => { + onState(false); + if (s.readyState === EventSource.CLOSED) { + retry = setTimeout(connect, retryAfterMs); + } + }; + s.addEventListener("ping", () => { + heard = Date.now(); + }); + s.onmessage = (msg: MessageEvent) => { + heard = Date.now(); + const ev = JSON.parse(msg.data) as ByreEvent; + if (ev.seq > last) { + last = ev.seq; + } + onEvent(ev); + }; + }; + + const check = () => { + if (Date.now() - heard < staleAfterMs) { + return; + } + onState(false); + connect(); + }; + + setInterval(check, 5_000); + addEventListener("online", connect); + document.addEventListener("visibilitychange", () => { + if (document.visibilityState === "visible") { + check(); + } + }); + connect(); } diff --git a/web/src/navbar.ts b/web/src/navbar.ts index bf43ec3..3e7a6c8 100644 --- a/web/src/navbar.ts +++ b/web/src/navbar.ts @@ -1,6 +1,7 @@ -import { h, replace } from "./dom.js"; -import type { View } from "./panes.js"; -import { activeTasks, findTask, onEach, state } from "./state.js"; +import { post } from "./api.js"; +import { errorText, h, replace } from "./dom.js"; +import { openTranscript, type View } from "./panes.js"; +import { activeTasks, currentSession, findTask, onEach, state } from "./state.js"; export function mountNavbar(root: HTMLElement, show: (view: View) => void): void { const crumb = h("button", { class: "crumb", title: "Switch task (⌘K)" }); @@ -13,6 +14,7 @@ export function mountNavbar(root: HTMLElement, show: (view: View) => void): void admin.onclick = () => show("admin"); const conn = h("span", { class: "connection down", title: "connecting" }); + const connLabel = h("span", { class: "connection-label" }, "reconnecting…"); const me = h("span", { class: "me" }); const render = () => { @@ -26,11 +28,12 @@ export function mountNavbar(root: HTMLElement, show: (view: View) => void): void conn.className = state.connected ? "connection up" : "connection down"; conn.title = state.connected ? "live" : "reconnecting"; + connLabel.hidden = state.connected; replace(me, state.me?.display_name ?? ""); }; onEach(["me", "projects", "tasks", "inbox", "selection", "connection"], render); - replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, admin, conn, me); + replace(root, h("a", { href: "#/", class: "brand" }, "byre"), crumb, h("span", { class: "spacer" }), inbox, admin, connLabel, conn, me); render(); addEventListener("keydown", (e) => { @@ -46,14 +49,26 @@ function openSwitcher(): void { return; } - const input = h("input", { placeholder: "Go to task…", autocomplete: "off" }); + const input = h("input", { placeholder: "Go to a task, or type a title to create one…", autocomplete: "off" }); const list = h("ul", { class: "switcher-list" }); const backdrop = h("div", { class: "switcher-backdrop" }); const box = h("div", { class: "switcher" }, input, list); let selected = 0; - let matches: ReturnType = []; + let rows: { el: HTMLElement; pick: () => void }[] = []; + const offs = onEach(["projects", "tasks", "sessions", "inbox"], () => render()); + const onEscape = (e: KeyboardEvent) => { + if (e.key !== "Escape") { + return; + } + e.preventDefault(); + e.stopPropagation(); + close(); + }; + addEventListener("keydown", onEscape, { capture: true }); const close = () => { + offs(); + removeEventListener("keydown", onEscape, { capture: true }); backdrop.remove(); box.remove(); }; @@ -61,24 +76,54 @@ function openSwitcher(): void { const go = (taskId: string) => { close(); location.hash = `#/task/${taskId}`; + openTranscript(); + }; + + const create = async (projectId: string, title: string) => { + close(); + try { + const task = await post("/api/projects/{projectId}/tasks", { path: { projectId }, body: { title } }); + go(task.id); + } catch (err) { + alert(errorText(err)); + } }; const render = () => { - const q = input.value.trim().toLowerCase(); - matches = activeTasks().filter(({ project, task }) => `${project.name} ${task.title}`.toLowerCase().includes(q)); - selected = Math.min(selected, Math.max(matches.length - 1, 0)); - replace( - list, - ...matches.map(({ project, task }, i) => { - const li = h("li", { class: i === selected ? "selected" : "" }, h("span", { class: "project-name" }, project.name), " ", task.title); - li.onmousedown = (e) => { - e.preventDefault(); - go(task.id); - }; - return li; - }), - matches.length === 0 && h("li", { class: "empty-row" }, "No matching tasks."), - ); + const title = input.value.trim(); + const q = title.toLowerCase(); + const inbox = (taskId: string) => state.inbox.filter((item) => item.task_id === taskId).length; + const matches = activeTasks() + .filter(({ project, task }) => `${project.name} ${task.title}`.toLowerCase().includes(q)) + .map((m) => ({ ...m, count: inbox(m.task.id) })) + .sort((a, b) => Number(b.count > 0) - Number(a.count > 0)); + rows = matches.map(({ project, task, count }) => { + const sess = currentSession(task.id); + const el = h( + "li", + {}, + h("span", { class: `dot ${sess?.state ?? "none"}`, title: sess?.state ?? "no session" }), + h("span", { class: "task-title" }, h("span", { class: "project-name" }, project.name), " ", task.title), + count > 0 && h("span", { class: "badge", title: "inbox items" }, count), + h("span", { class: "task-state" }, sess?.state ?? "no agent"), + ); + return { el, pick: () => go(task.id) }; + }); + const current = state.selectedTaskId ? findTask(state.selectedTaskId) : undefined; + const project = state.projects.find((p) => p.id === current?.project_id) ?? state.projects[0]; + if (title && project) { + const el = h("li", { class: "new-task" }, h("span", { class: "task-title" }, "New task in ", h("span", { class: "project-name" }, project.name), ": ", title)); + rows.push({ el, pick: () => void create(project.id, title) }); + } + selected = Math.min(selected, Math.max(rows.length - 1, 0)); + rows.forEach((row, i) => { + row.el.classList.toggle("selected", i === selected); + row.el.onmousedown = (e) => { + e.preventDefault(); + row.pick(); + }; + }); + replace(list, ...rows.map((r) => r.el), rows.length === 0 && h("li", { class: "empty-row" }, "No active tasks. Type a title to create one.")); }; input.oninput = () => { @@ -86,21 +131,17 @@ function openSwitcher(): void { render(); }; input.onkeydown = (e) => { - if (e.key === "Escape") { - close(); - } else if (e.key === "ArrowDown") { + if (e.key === "ArrowDown") { e.preventDefault(); - selected = Math.min(selected + 1, matches.length - 1); + selected = Math.min(selected + 1, rows.length - 1); render(); } else if (e.key === "ArrowUp") { e.preventDefault(); selected = Math.max(selected - 1, 0); render(); } else if (e.key === "Enter") { - const match = matches[selected]; - if (match) { - go(match.task.id); - } + e.preventDefault(); + rows[selected]?.pick(); } }; backdrop.onclick = close; diff --git a/web/src/panes.ts b/web/src/panes.ts index ffeb04f..474b6b8 100644 --- a/web/src/panes.ts +++ b/web/src/panes.ts @@ -19,6 +19,15 @@ const views: Record () => v const order: View[] = ["transcript", "changes", "tasks", "inbox", "admin", "settings"]; +const panes: Pane[] = []; + +export function openTranscript(): void { + if (panes.some((p) => p.current() === "transcript")) { + return; + } + (panes.find((p) => p.current() !== "tasks") ?? panes[0])?.show("transcript"); +} + export class Pane { readonly el: HTMLElement; private readonly tabs: HTMLElement; @@ -34,6 +43,11 @@ export class Pane { const saved = localStorage.getItem(this.storageKey()) as View | null; this.view = saved && saved in views ? saved : fallback; this.show(this.view); + panes.push(this); + } + + current(): View { + return this.view; } show(view: View): void { diff --git a/web/src/task.ts b/web/src/task.ts index d9b08ce..901f761 100644 --- a/web/src/task.ts +++ b/web/src/task.ts @@ -191,36 +191,36 @@ export function mountTranscript(root: HTMLElement): () => void { replace(run.group.summary, runSummary(run.calls)); }; - let stream: { el: HTMLElement; text: string; frame: number } | undefined; + let stream: { el: HTMLElement; text: string; timer: number } | undefined; const dropStream = () => { if (!stream) { return; } - cancelAnimationFrame(stream.frame); + clearTimeout(stream.timer); stream.el.remove(); stream = undefined; }; const appendDelta = (ev: ByreEvent) => { if (!stream) { - stream = { el: h("div", { class: "msg agent" }), text: "", frame: 0 }; + stream = { el: h("div", { class: "msg agent" }), text: "", timer: 0 }; ctx.run = undefined; put(stream.el); } stream.text += String(ev.payload["text"] ?? ""); - if (stream.frame) { + if (stream.timer) { return; } - stream.frame = requestAnimationFrame(() => { + stream.timer = setTimeout(() => { if (!stream) { return; } - stream.frame = 0; + stream.timer = 0; const pinned = transcript.scrollHeight - transcript.scrollTop - transcript.clientHeight < 80; replace(stream.el, markdown(stream.text, "text md")); if (pinned) { transcript.scrollTop = transcript.scrollHeight; } - }); + }, 100); }; const foldTurn = (start: HTMLElement, end: HTMLElement) => { diff --git a/web/src/tasks.ts b/web/src/tasks.ts index 4ce7805..733c597 100644 --- a/web/src/tasks.ts +++ b/web/src/tasks.ts @@ -1,5 +1,6 @@ import { post, type Project } from "./api.js"; import { errorText, h, replace } from "./dom.js"; +import { openTranscript } from "./panes.js"; import { currentSession, onEach, state } from "./state.js"; export function mountTasks(root: HTMLElement): () => void { @@ -27,7 +28,7 @@ function projectBlock(project: Project): HTMLElement { { class: task.id === state.selectedTaskId ? "selected" : "" }, h( "a", - { href: `#/task/${task.id}` }, + { href: `#/task/${task.id}`, onclick: openTranscript }, h("span", { class: `dot ${sess?.state ?? "none"}`, title: sess?.state ?? "no session" }), h("span", { class: "task-title" }, task.title), h("span", { class: "task-state" }, sess?.state ?? "no agent"), diff --git a/web/style.css b/web/style.css index c22f12d..7d21418 100644 --- a/web/style.css +++ b/web/style.css @@ -233,6 +233,14 @@ textarea { background: var(--danger); } +.connection-label { + color: var(--danger); +} + +.connection-label[hidden] { + display: none; +} + .me { color: var(--muted); } @@ -1218,11 +1226,23 @@ pre.diff .meta { } .switcher-list li { + display: flex; + align-items: center; + gap: 8px; padding: 6px 10px; border-radius: 6px; cursor: pointer; } +.switcher-list .task-title { + flex: 1; + min-width: 0; +} + +.switcher-list li.new-task { + color: var(--accent); +} + .switcher-list li.selected { background: var(--accent-tint); }