byre/docs/operations.md

# Operations

## Layout

- `cmd/byre`: `byre serve` runs the server; `byre run` drives one Claude session in the current directory from the terminal.
- `api/openapi.yaml` is the API source of truth. `go generate ./internal/api` regenerates `internal/api/api.gen.go`, whose types are also the store's model types.
- `internal/store`: SQLite (WAL). Every mutation and its event commit in one transaction; events are published to SSE subscribers in `seq` order.
- `internal/server`: HTTP handlers, identity, SSE, the worktree file browser (see "Files"), terminals (see "Terminals").
- `internal/git`: worktrees, the task changes view (see "Changes"), snapshots (see "Snapshots"), unmerged-change summaries, squash merges and pushes.
- `internal/agents`: the agent session manager. It owns the running agent processes, task agents, lead agents (see "Lead agent") and reviewers (see "Reviews") alike, and records their activity as events.
- `internal/claude`: the Claude Code stream-json client (see `docs/claude-protocol.md`).
- `internal/codex`: the `codex app-server` JSON-RPC client, with types generated from the CLI's schema by `go generate ./internal/codex` (see `docs/codex-protocol.md`).
- `internal/push`: web push notifications for new inbox items (see "Notifications").
- `internal/tailscale`: `tailscale serve` for task previews (see "Previews").
- `web/`: the SPA, frameworkless TypeScript compiled file-by-file to ES modules (no bundler). `web/src/*.ts` is the source; `web/src/api.gen.ts` holds types generated from `api/openapi.yaml`, and `web/src/api.ts` is the typed client over them. `go generate ./web` runs `npm ci`, regenerates the types and compiles `web/dist/`, which is committed so `go install` needs no Node. The binary embeds `index.html`, `style.css`, `dist/`, `src/` (for source maps), `fonts/` and `vendor/` (Mermaid, see "Inbox"; xterm.js, see "Terminals"). `byre serve --dev` serves `./web` from disk instead (run from the repo root); pair it with `npm --prefix web exec tsc -- --watch`.

## Data

State lives in the directory given by `byre serve --data`, by default the `byre` directory under Go's `os.UserConfigDir()` (on macOS, `~/Library/Application Support/byre`): `byre.db`, `worktrees/<project-id>/<task-id>`, `leads/<login>` (each lead agent's working directory, the login path-escaped), and `blobs/<blob-id>` (uploaded images; the `blobs` table maps each id to its content type and its path relative to this directory). Task branches are `byre/<task-id>` in the project's repo.

Schema changes are the `migrations` slice in `internal/store/store.go`: named entries, each with a short kebab-case name saying what it does. On open, byre applies, in slice order, every entry whose name isn't in the `migrations` table, each in its own transaction that also records the name. Each runs with foreign keys off, so a migration can rebuild a table other tables reference, and `PRAGMA foreign_key_check` must come back empty before it commits. byre is deployed from task branches that each append their own migrations, so after a merge a migration can land before others the database has already applied, and it still runs. Give a new migration a name no other branch will use, and make any data migration safe to run twice. `sqlite3 byre.db 'SELECT * FROM migrations'` lists what has been applied. A database from before the table existed is moved over on open: the first `PRAGMA user_version` entries are recorded as applied, and `user_version` is no longer read or written.

## Worktree setup and ports

Every task worktree is made by `createTask` (`internal/agents/tasks.go`): new tasks, `create_task`, `start_todo` and forks alike.

- **Ports.** Each active task holds a block of `store.PortBlock` ports starting at `tasks.port_base` (`port_base` on the Task). `Store.CreateTask` gives a new task the lowest block from `byre serve --ports` (default `store.DefaultPortFirst`) up that no active task holds, so a merged or discarded task's block is reused. The agent's `claude` process gets `PORT` (the first port, which most dev servers read on their own), and the session guidance names the range, says to run dev servers on it listening on `127.0.0.1`, and points at `expose_port` (see "Previews"). `sqlite3 byre.db "SELECT id, port_base FROM tasks WHERE status = 'active'"` lists the blocks in use.
- **Setup.** byre runs nothing in a new worktree. The session guidance says the worktree starts with only what git tracks and tells the agent to do any setup the project's AGENTS.md describes before other work, so installing dependencies or copying untracked files such as `.env` is the project's own instruction, carried out by the agent with its own tools. A project's checkout is the parent of `git rev-parse --path-format=absolute --git-common-dir` in the worktree.

## Closing a task

A task ends `merged` or `discarded`; either way its sessions are stopped, its snapshot refs, worktree and branch are removed, its `open` inbox items become `dismissed` (resolved by whoever closed it), and its record and events remain. `GET /api/tasks/{id}/unmerged` reports what would be lost or merged: commits on the branch that aren't on the default branch, and files, lines and uncommitted paths that differ from the merge base. The UI's Merge and Discard buttons each ask a one-line confirmation, opened just below the button like the task picker's switcher (centred when ⌘S opens Merge's from a tab without the button), and are disabled while the task's session is `running`. Merge is also disabled until `unmerged` reports a commit or a changed file; the transcript fetches it when the task is opened and again shortly after each tool result or turn end.

`POST /api/tasks/{id}/merge-in` (the transcript's **Sync from main** button, labelled with the default branch) brings the default branch into the task branch through the agent: it sends `mergeInPrompt` (`internal/agents/mergein.go`) as a `byre` message to the task's session, or starts a session with it when the task has none. The prompt has the agent run `git merge --no-ff --no-commit`, resolve conflicts, regenerate generated files rather than hand-merging them, check the build and tests, and leave the merge uncommitted; byre's end-of-turn commit concludes it as a merge commit. The prompt ends by showing the task's current merge title and asking the agent to set a better one with `set_merge_title` if it no longer describes all the work on the branch. It is refused (409) while a session is `running`.

A task's `merge_title` is the title of the squash commit Merge makes. It is the task title until the agent calls the `set_merge_title` MCP tool (`internal/agents/mergein.go`), which it may do at any point: one line of at most 72 characters (`maxMergeTitle`), stored in `tasks.merge_title` (empty there means "use the title"), recorded as a `task.merge_title` event that the transcript shows as a note. Malformed titles are rejected with a corrective message, and so is a call once the task is closed. The Merge confirm dialog quotes the title the commit will get and lists its co-authors.

A task's participants are the users who put a message bubble with their name in its transcript, derived from its events (`Store.Participants`): the actors of its `user.message` events, joined to `users` so `byre` and `agent` drop out. That covers messages sent to the agent and inbox answers, whose delivery message carries the name of the first responder in it (`Deliver` in `internal/agents/inbox.go`); dismissing an item puts nothing in the transcript and doesn't count. They are ordered by their first such message. `GET /api/tasks/{id}/co-authors` returns the participants other than the caller, with their git name and email from `PUT /api/me` (empty for a user who hasn't set one). The Merge confirm fetches it and lists `Name <email>` for each co-author, and separately those with no git identity, who get no trailer.

`POST /api/tasks/{id}/merge` starts the same turn and records in `tasks.merging_by` that the task is to be merged by the requesting user, who must have a git identity (400 otherwise). Every turn end of the task's session reads and clears it. It survives a byre restart during the turn: startup resumes the session with the restart notice, and the merge happens when that resumed turn ends. When that turn ends normally (not interrupted, not an error), byre squashes the worktree, now containing the default branch, onto it with `git merge-tree --merge-base`, makes one commit titled with the task's `merge_title` with `git commit-tree`, authored and committed by the merging user with no agent attribution, its body one `Co-authored-by: Name <email>` trailer per co-author with a git identity (`squashMessage` in `internal/agents/mergein.go`; the co-authors are computed when the squash runs, relative to the user who clicked Merge), and pushes that commit to the default branch on the `origin` remote of the project's checkout (`git push --porcelain origin <commit>:refs/heads/<default branch>`, run in the checkout). Only once the push is accepted does it run `git merge --ff-only` in the project's checkout (which must have the default branch checked out) and close the task; the `task.merged` event carries the commit and `pushed` (`origin/<default branch>`), and the transcript shows both. When the merge changes nothing, no commit is made and nothing is pushed.

Before starting the turn, Merge runs `git fetch origin <default branch>` and `git merge --ff-only origin/<default branch>` in the checkout, so the agent merges in what the remote has; the request waits for the fetch, and a failure (network, or a checkout with commits the remote lacks) is returned as the request's error. If the push is still refused, for example because someone pushed during the turn, or fails for any other reason, byre files the error in the inbox and the task stays active; clicking Merge again fetches and goes round once more. A refused push leaves the checkout's default branch where it was, since the squash commit was never moved onto it. If the squash fails, for example because the default branch moved again during the turn, byre also files an error and the task stays active. An interrupted or failed turn, an agent process that exits mid-turn, or a session that can't be resumed after a restart clears `merging_by` and leaves the task active without squashing. `POST /api/tasks/{id}/discard` removes everything without merging.

One merge runs per project at a time. The Manager keeps the task holding each project's merge in memory (`mergeHolders` in `internal/agents/manager.go`), from just before the fetch until the merge closes the task, fails, or is abandoned as above, or the task is discarded; on startup it is rebuilt from the active tasks with `merging_by` set. Merge on another task of that project while one is held doesn't fetch or start a turn: it records the request in `tasks.merge_queued_by` and `merge_queued_at` (`merge_queued_at` on the Task), emits `task.merge_queued` (a transcript note), and returns the task with 202. A second Merge on a held or merging task is a 409. Whenever a project's merge is released, any task turn in it ends, and on startup, byre starts the oldest held merge in the project whose task session is not `running`: it clears the request (emitting `task.merge_unqueued`, not drawn) and goes through the same fetch and turn as a direct Merge by the user who asked, so it merges in what the earlier merge pushed. If that start fails (the fetch, or the user has no git identity), byre files the error in the task's inbox and tries the next held merge. The Merge button reads **Merge held**, disabled, while the task has `merge_queued_at`; discarding the task drops the request. `sqlite3 byre.db "SELECT id, merge_queued_by, merge_queued_at FROM tasks WHERE merge_queued_by != ''"` lists held merges.

## Running as a service

The listen address is `byre serve --listen`, whose default is in `cmd/byre/serve.go` (`go run ./cmd/byre serve --help` prints it); keep it on loopback, since identity relies on requests arriving from `tailscale serve`.

```
go install ./cmd/byre
cp deploy/run.fc.byre.plist ~/Library/LaunchAgents/
launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/run.fc.byre.plist
tailscale serve --bg --https=<listen port> http://<listen address>
```

byre gets its own HTTPS port on the machine's `ts.net` name rather than a path under another service: the SPA and API use absolute paths, which break under a path prefix. `tailscale serve status` shows the URL and what else the machine serves.

After rebuilding: `go install ./cmd/byre && launchctl kickstart -k gui/$(id -u)/run.fc.byre`. Logs go to `~/Library/Logs/byre.log`.

Clients reach `tailscale serve` over HTTP/2; it proxies to byre over HTTP/1.1 and passes SSE through unbuffered.

## Previews

An agent shows the human a server it runs with the `expose_port` MCP tool (`internal/agents/preview.go`): `name` labels it, `port` is where it listens. The agent starts the server itself, usually as a background command; byre doesn't supervise it, so it dies with the agent's `claude` process (a byre restart, compaction, the task closing) and the agent starts it again when asked. The call is refused when `port` is outside the task's block or nothing accepts a connection on `127.0.0.1:<port>`. Otherwise byre runs `tailscale serve --bg --https=<port> http://127.0.0.1:<port>` (`internal/tailscale`, which runs the macOS CLI at `/Applications/Tailscale.app/Contents/MacOS/Tailscale`, since byre's environment has no `tailscale` on its `PATH`), so the server is at `https://<byre's ts.net name>:<port>/` with Tailscale's identity headers, and records a row in the `previews` table (task, name, port, time) with a `preview.exposed` event, which the transcript shows as a note linking the URL. Each port gets its own HTTPS port rather than a path under byre's, since path-prefix proxying breaks apps that use absolute paths. Exposing a name or port the task already has replaces that row, and a port it no longer uses is turned off with `tailscale serve --https=<port> off`. A server must listen on `127.0.0.1`: while `tailscale serve` holds a port, binding `0.0.0.0` on it fails with "address already in use". When the task is merged or discarded, byre turns off each of its ports (`Manager.Unexpose`); the rows stay. `GET /api/tasks/{taskId}/previews` lists a task's rows by name, and `tailscale serve status` shows what is served.

The **Preview** tab (`web/src/preview.ts`) lists the task's previews by name and port, shows the selected one (the first by default; the choice is kept per task in memory) in an iframe, and links it in a new tab. It fetches the list when it opens, when the selected task changes, and on each `preview.exposed` in the task's stream, which also reloads the iframe.

## Previewing byre

A task's build of byre runs alongside the service with its own empty state, from the worktree root, on the task's port, and the agent exposes it with `expose_port`:

```
go run ./cmd/byre serve --dev --data "$PWD/.preview" --listen 127.0.0.1:$PORT --ports 51000
```

It must never share the service's data directory: nothing locks the database, and startup resumes every session marked `running` in its recorded worktree. `--ports` puts the preview's own tasks' port blocks in a range the service's tasks don't use; each instance only knows its own tasks, so with the default both would hand out blocks from the same first port, starting with the one the preview listens on. `.preview/` is gitignored, so the end-of-turn commit leaves it out. The preview starts with no users, projects or sessions; set a git identity with `PUT /api/me` and add a project to try things. A project's Merge pushes to its checkout's `origin`, so a preview project should be a clone whose `origin` is a local bare repository (`git clone --bare <checkout> .preview/origin.git`, then clone that), never the real checkout.

## Identity

`tailscale serve` adds `Tailscale-User-Login` and `Tailscale-User-Name` to proxied requests. The server accepts API requests only from loopback and only with both headers; anything else gets 401 or 403. The SPA's static files need no identity. Users are created on first request; each sets their commit identity with `PUT /api/me`.

To call the API locally without Tailscale, send the headers yourself:

```
curl -H 'Tailscale-User-Login: you@example.com' -H 'Tailscale-User-Name: You' http://<listen address>/api/me
```

## Agent sessions

`POST /api/tasks/{id}/sessions` starts a Claude session in the task's worktree and sends the prompt as its first turn; `POST /api/sessions/{id}/messages` starts later turns and `POST /api/sessions/{id}/interrupt` ends the current one. A task has at most one session that isn't `completed`. A message may carry `model`; when it differs from the session's, byre writes it to `agent_sessions.model`, records a `session.model` event (shown as a note), and sends the live CLI a `set_model` control request before the message, so the switch applies from that turn and survives a resume (`--model`) or compaction. The composer's model menu sends `model` only when the choice differs from the session's model, or from the `session.context` model when the session has none. The session's commits use the git identity of the user who created it, so that user must have set one with `PUT /api/me`.

Images: `POST /api/blobs` takes a raw image body (type sniffed from the bytes, PNG, JPEG, GIF or WebP only, at most 5 MiB, `maxBlobBytes` in `internal/server/blobs.go`) and returns its id; `GET /api/blobs/{id}` serves it. A message or session prompt may carry `images`, a list of blob ids (unknown ids are a 400); a message may then have empty text. byre reads each blob when the turn is sent and passes it before the text: to Claude as a base64 `image` content block (`claude.Session.Send`), to Codex as an `image` input with a `data:` URL (`codex.Session.Send`). The `user.message` event records the ids as `images`. In the composer, pasting or dropping an image adds a thumbnail with a × to remove it; images upload when the message is sent, and the transcript shows them on the user's message, each linking to the full image.

Compaction is vendor-agnostic: `POST /api/sessions/{id}/compact` (the transcript's **Compact** button, always shown and enabled only while the task has an idle session) sends the agent `handoffPrompt` (`internal/agents/compact.go`) as a `byre` message, asking for a handoff covering the goal, decisions and why, current state, dead ends, open questions and files. That turn files no inbox summary and isn't bounced for questions. When it ends normally, its `turn.ended` carries `handoff: true`, the session is completed, and a new session on the same task and model starts with `handoffPreamble` plus the handoff as its first message (actor `byre`; its `user.message` carries `continuation: true`). The context meter tracks the new session. The request's `user.message` carries `handoff: true`, and from it the transcript puts the request and everything the agent does in that turn into one collapsed note reading "writing a handoff…", without streaming the agent's text; when the turn ends its summary becomes the `turn.ended` note, or "handoff not written" if the turn ended without one. The transcript never draws the new session's first message (`continuation: true`), so that note, which holds the handoff, is the only marker of the switch. If byre restarts during the handoff turn, the continuation is lost and the old session simply goes idle.

Agents spawn parallel work with the `create_task` MCP tool (`internal/agents/tasks.go`): `title`, `prompt`, `base` and optional `model` (default: the caller's session model). It creates a task in the caller's project exactly as `POST /api/projects/{id}/tasks` does, and starts a session there with `prompt` as the first message (actor `agent`), created by the caller's session creator so commits use that user's git identity. `base` is the agent's choice: `default_branch` starts from the project's default branch, `this_task` from the caller's worktree `HEAD`, which leaves out uncommitted edits from the current turn. The tool returns the new task's id at once; the new session is independent of the caller.

Agents don't commit; byre does. Each `user.message` event that starts a turn records `head`, the worktree's `HEAD` when the turn started. When a turn ends, byre runs `git add --all` and commits if anything changed (`git.CommitAll`), as the session's creator, with the first sentence of the turn's final message as the message (`commitMessage` in `internal/agents/manager.go`); `turn.ended` then carries the new sha as `commit`. A failed commit is logged and the turn still ends.

A session runs on one of two vendors, picked by the model it is created with (`vendorOf` in `internal/agents/process.go`): `gpt-*` models run on Codex (`codex app-server`), every other model on Claude Code. The UI's model list is `models` in `web/src/task.ts`; a live session's picker offers only its own vendor's models, and the API refuses (400) a switch to the other vendor's model. Both vendors sit behind `agentProcess` (`internal/agents/process.go`), and both end a turn through the same `turnEnded`, so commits, reports, snapshots, handoffs, merges and deliveries don't depend on the vendor.

For Claude, byre chooses the session ID (`vendor_session_id`) up front. Codex picks its own thread id: a Codex session is created with an empty `vendor_session_id`, and byre stores the thread id when its first process starts (`startCodex`); a session with an id resumes it with `thread/resume`. Processes start on demand: the first message after a restart resumes the session (`--resume` for Claude). Sessions are `running` from the moment a turn is sent until it ends (Claude's `result`, Codex's `turn/completed`); on startup, every session still marked `running` was cut off mid-turn, and byre resumes it and sends a message telling the agent to re-check the working tree. Stopping the server kills all agent processes. Merging or discarding a task kills its sessions and marks them `completed`.

Every session gets byre's guidance (`guidance` in `internal/agents/guidance.go`): ask questions with `ask_human`, end each turn with a final message that summarizes it (including every departure from the plan), put everything the human needs in a blocking question's context since that turn files no report, don't commit (byre commits each turn), and don't push, touch other branches or run git maintenance. A task agent's guidance also names its port range and tells it to do the setup AGENTS.md describes in a new worktree (see "Worktree setup and ports"). A task started from a `TODO.md` item gets one more line naming the item and telling the agent to remove it from `TODO.md` in its worktree when the work is done (`taskGuidance`; see "TODO"). For Claude it is passed as `--append-system-prompt`, which Claude Code records on a session's first request and reuses on resume, so a running session keeps the text it started with; a `UserPromptSubmit` hook also attaches it as `additionalContext` to every user turn, which reaches existing sessions too. For Codex it is the thread's `developerInstructions`, and every `turn/start` also carries it as `additionalContext` under the key `byre`. The guidance names byre's tools vendor-neutrally ("byre's ask_human tool"): Claude sees them as `mcp__byre__<name>`, Codex as `<name>` in the namespace `byre` (Codex reserves the `mcp__` prefix).

A turn whose final message asks the human something in prose is bounced once (`takeBounce` in `internal/agents/guidance.go`): if `ask_human` wasn't called during the turn and the final message has a sentence ending in `?` outside code spans, code blocks, quotes and blockquotes, the agent is told to ask through `ask_human` and carries on. For Claude this is a Stop hook (`bounceProseQuestion`) that blocks the stop; Claude Code reports the block as a "Stop hook error" notification, which is expected. For Codex, byre doesn't end its turn on `turn/completed`: it records the nudge as a `byre` `user.message` with `mid_turn: true` and starts another Codex turn with it, and only that turn's end ends byre's turn. The per-turn flags reset when the next user message is sent. An agent told explicitly to ask in plain text will refuse the bounce.

A turn's final message is its summary. When a turn ends normally (not an error, not interrupted) with non-empty `result` text, byre files that text as a `report` inbox item, unless the turn called `ask_human` with `blocking` true. The final message comes after the question, so a report would land in the inbox after the question it explains; such a turn's final message stays in the transcript only, and the guidance tells agents to put everything the human needs in the question's context. There is no report tool: models write a closing recap whatever they are told, so byre uses it rather than asking for a second one.

Every turn starts as soon as it is sent; byre doesn't cap how many run at once. Whether a turn resumes the Claude conversation is decided by whether the session has ever sent one.

When Claude Code reports a rate-limit status of `rejected` and the turn then fails, or a Codex turn fails with `codexErrorInfo` `usageLimitExceeded` or `rateLimitExceeded`, the inbox gets a `rate_limited` item carrying the vendor's status instead of a generic error.

Codex runs with its own home, `codex` under the data directory (`CODEX_HOME`, set by `startCodex`), so the human's `~/.codex/config.toml` (its `notify` program, MCP servers and plugins) doesn't apply and byre's threads stay out of the ChatGPT app's history. That home needs its own login, once: `CODEX_HOME="$HOME/Library/Application Support/byre/codex" codex login`. Until then a Codex turn fails with `401 Unauthorized`, filed as a session error. The `codex` binary comes from `PATH`; see `docs/codex-protocol.md`.

## Status

`GET /api/admin/status` reports `running_turns` (task sessions now `running`, as session, task and vendor; lead turns aren't listed); `rate_limits`, the latest status each vendor sent since byre started (Claude's `rate_limit_info` unchanged; Codex's `account/rateLimits/updated` reshaped by `codexRateLimit` in `internal/agents/codex.go` into the same `status`, `rateLimitType` and `unifiedWindows` fields); `agent_processes`, `zombies`, `stuck_after_seconds` and `protocol_errors` (below); and server counts (start time, agent processes, projects, active tasks, SSE clients, database size including WAL, last event seq).

Agent health is `internal/agents/health.go`:

- **Processes.** `agent_processes` lists every process byre is tracking (idle sessions keep theirs), with session, task, vendor, pid, the session's state, `last_event_at` (when the process last wrote any line to stdout, or when it started; `claude.Session.LastLine`) and `health`. `health` is `exited` when the stream has closed or `kill(pid, 0)` says the pid is gone, `stuck` when the session is `running` and nothing has arrived for `StuckAfter`, otherwise `ok`. The stream does mark long tool calls: while a tool runs, Claude Code sends a `tool_progress` line with `"heartbeat": true` every 30 seconds, so a long `go test` keeps `last_event_at` fresh and a silent stream means nothing is happening.
- **Zombies.** `running_without_process`: a session marked `running` whose process byre isn't tracking or has `exited`. `process_without_session`: a `claude` child of the byre process (from `ps -A -o pid=,ppid=,comm=`) whose pid belongs to no tracked process, or a tracked process still alive for a `completed` session. A live process for an `idle` session is normal and not a zombie.
- **Watching.** `Manager.Watch` recomputes health every `healthInterval`. When the set of problems (non-`ok` processes and zombies) changes, it logs each new one as `agent health problem` and broadcasts an unstored `admin.health` event (`seq` 0). Nothing is killed or repaired automatically.
- **Protocol errors.** `internal/claude` reports a stdout line that isn't a JSON object, doesn't parse, or has a `type` outside `knownTypes` (the line is still passed on), and the manager adds lines whose content it fails to decode. `protocol_errors.counts` counts them per vendor since byre started; `recent` holds the last `keptBadLines`, newest first, each with session, time, reason, the raw line cut to `badLineBytes` and its full `size`. They live in memory only, and each one also broadcasts `admin.health`.

The Status modal (the navbar's **Status** button; Esc, ×, a click outside it or following a task link closes it) shows, from the top: a Problems section only when there are zombies or protocol errors (one line per zombie, and per vendor the error count with the latest line folded under it); each running turn, linking to its task, with the time since its process's last event and `stuck` or `exited` when it is; each vendor's rate-limit status with its reset time and per-window utilization, and the server counts. It refetches the status when a `session.created`, `session.state`, `task.*`, `project.created` or `admin.health` event arrives, when an `agent.vendor` event carries a `rate_limit_event`, and when the SSE stream reconnects. Other events advance the last-event seq it shows, and any event carrying a process's `agent_session_id` (stored or not, such as `agent.delta`) moves that process's last-event time forward, re-rendering at most once a second per process. A re-render keeps the scroll position and which folded lines are open. There is no timer, so "time since last event" and the "in 2h 10m" beside a reset time are as of the last render; a process going quiet long enough to be stuck shows up when the next health check broadcasts `admin.health`.

Agent activity becomes events with `agent_session_id` set: `user.message`, `agent.message`, `agent.thinking`, `agent.tool_call`, `agent.tool_result`, `turn.ended`, `session.state`, `session.model`, and `session.context`. Anything else Claude Code emits (rate-limit status, task progress, state changes) is recorded unchanged as `agent.vendor`. Codex items map onto the same kinds (`handleCodex` in `internal/agents/codex.go`): an `agentMessage` becomes `agent.message`, a `reasoning` item's summary `agent.thinking`, and `commandExecution` (as `Bash`), `fileChange` (as `apply_patch`), `dynamicToolCall`, `mcpToolCall` and `webSearch` items an `agent.tool_call` when they start and an `agent.tool_result` when they complete. Other completed items and the `error` and `warning` notifications are recorded as `agent.vendor`; the remaining notifications (thread status, MCP startup and the like) aren't recorded. `item/agentMessage/delta` becomes `agent.delta`, and `thread/tokenUsage/updated` `session.context`. The one exception is partial output: each top-level `text_delta` is broadcast to SSE clients as an `agent.delta` event (`payload.text`, `seq` 0) that is never stored, and the transcript grows a live message from them until the finished `agent.message` replaces it. A `turn.ended` event carries `inbox_item_id` when its final message was filed as a `report` item. Activity inside a subagent (`agent.message`, `agent.thinking`, `agent.tool_call`, `agent.tool_result`) carries `payload.parent_tool_use_id`, the ID of the tool call that started the subagent, and never updates `session.context`. `session.context` records the context size whenever it changes: `used` is the last assistant message's input, cache-read, cache-creation and output tokens, and `window` is the model's context window from the turn's `result` (`modelUsage[model].contextWindow`), so it is 0 until the session's first turn after a server start ends. The task header's **Compact** button shows the latest one as a background fill across the button, proportional to the window, tinted amber from 70% and red from 90%; the exact count is in its tooltip.

Messages byre itself sends an agent (actor `byre`: the restart notice, Sync and Merge prompts, Compact's handoff request) show collapsed like a tool call, labelled `byre` with the first line as the brief; expanding it shows the full text. The transcript view has a border in the task's colour (see "Task colours"; the accent in the lead pane) while the session is `running`, and a braille spinner on its last line in the same colour, cycling ⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏ every 0.8s. It is one element with one CSS animation: the ten frames are drawn side by side in an inline SVG used as the `.spinner` mask over a coloured background, and the `braille` keyframes in `web/style.css` step the mask position through them. Orion freezes animated GIFs and per-dot `step-end` opacity animations partway through a turn, so it stays a single element with a single animation. 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 Claude Code subagent call (the `Agent` or `Task` tool) stands on its own, collapsed, labelled with its `subagent_type` and `description`; expanding it shows the prompt and the call's result. Its summary carries a status from the `agent.vendor` `system` events whose `tool_use_id` names it (`task_started`: running, or running in the background; `task_progress`: its `description`; `task_notification`: its `status`, red unless `completed`). The subagent's own messages, thinking and tool calls (events whose `parent_tool_use_id` names the call) stream inline with the main agent's, in arrival order, each marked `↳ <subagent_type>` with the description as its tooltip; its messages also get an accent rule down their left edge. A run of tool calls groups only calls from the same agent, so a call from another agent starts a new group. A subagent's messages never end the main agent's live message, count as a turn's final message or hide a quiet turn. Claude Code streams a background subagent's activity, but for a foreground one only its prompt, so a foreground subagent shows only as its call, its status and its result. 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. Selecting a task that has never had a session focuses the composer. 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 composer has no `@`-file mentions or path picker: text reaches the agent exactly as typed (stream-json doesn't expand `@path` the way the interactive CLI does), and the agent reads any file the message names with its own tools. The composer is the same whether or not the task has a live session: Send posts to the session's messages, or starts a session with the text when there is none or the last one completed. A sent message shows at once as a "sending…" bubble, replaced by the server's `user.message` event with the same text when it arrives, and removed (text and images back in the composer) if the request fails.

The task switcher (⌘K, or the project ▸ task picker at the right end of the right pane's tab strip) lists active tasks with their session state and open inbox item count, and **merge held** on a task with `merge_queued_at`, live while it is open. Tasks with inbox items come first; within each group, the task least recently visited in this browser comes first (never-visited tasks before all others, ties in the server's order: projects by name, tasks newest first). Visit times are kept in the browser's localStorage under `byre.visits`, stamped when a task is selected and again when it is left. After the tasks come the projects, one row each; picking one points the right pane at the project with no task, on the Project tab. Typing filters both and adds a last row that creates a task with the typed text as its title, in the right pane's project (the first project when there is none); Enter picks the highlighted row. Picking a task points the right pane at it on the Transcript tab (see "Lead agent").

**Task colours.** Each task has a colour, `tasks.color` (`color` in the API), an index into the palette of `--task-0` … `--task-N` custom properties at the top of `web/style.css`, one set for light and one for dark, all at least 4.5:1 against the backgrounds so they work as text. `CreateTask` assigns it in the same transaction as the task's row: of the `store.TaskColors` colours, one no active task holds, and among those the one given out longest ago (the lowest `max(rowid)` of tasks with that colour, never-used first), so a new task doesn't take the colour of one just closed. Active tasks have distinct colours until more than `TaskColors` are active at once. `TaskColors` must match the number of palette entries. An element styled with `taskStyle(id)` (`web/src/taskcolor.ts`) sets `--task` for itself and its children from the task's `color`; `--task` defaults to the accent, which is also what a task the page doesn't know gets. The right pane sets it for the selected task, which tints its tab strip, colours the task picker's text, the selected tab's underline, the composer's border and the running border and spinner. Everywhere a task is named it shows in its colour: task titles in the switcher, the Project tab and the Status modal (`.task-name`), and task links (`a.task-link`), including any Markdown link to `#/task/<id>`. The lead's guidance tells it to link every task it names that way, and clicking one points the right pane at the task.

## Lead agent

Each user has one long-running lead agent, shown in the left pane. It is not tied to a project: it watches every task, tells the human what needs them, points the right pane at it, and acts on the other agents. Its code is `internal/agents/lead.go` (sessions, held input, signals) and `internal/agents/leadtools.go` (its MCP tools).

- **Sessions.** A lead session is an `agent_sessions` row with `owner` set to the user's login, `role` `lead` and no `task_id`. Its events carry `owner` and no project or task. It runs in `leads/<login>` with `leadGuidance` (passed and re-attached the same way as a task agent's guidance) and the lead tools instead of the task tools. It has no Stop-hook bounce, no snapshots, no end-of-turn commit and no inbox report; a turn that ends in error records the error on its `session.state` event, which the pane shows as a note.
- **Messages.** `POST /api/me/lead/messages` sends the caller's message to their lead, starting a lead session when there is none. While the lead is mid-turn the message is held in `lead_inputs` and becomes its next turn; the composer stays enabled. `GET /api/me/lead/sessions` lists the caller's lead sessions; interrupt and compact use the usual session endpoints.
- **Signals.** Every published event goes through `Manager.Observe`. These become signals in `lead_inputs` for every user who has a lead session: `inbox.created` (a question with its choices and recommendation, a report's text cut to 1500 characters, an error or rate limit), `inbox.updated` when a human answered a question or error, `task.created` (naming the TODO item it was started from, if any), `task.merged` and `task.discarded`. The human switching the right pane is not a signal. A signal caused by the lead itself (actor `<login> (lead)`) is skipped, as is the update from an answer it gave. A task's `task.created` event carries the actor that created it, separately from its `created_by` login: tasks the lead creates with `create_task` or `start_todo` keep the human's login as `created_by` but have actor `<login> (lead)`. Whenever the lead is idle, byre sends the oldest held message from the human as its own turn, or else every held signal as one `byre` message headed "Signals since your last turn (n)". Its guidance tells it not to respond to the human's own actions, and to make its final message exactly `NO_REPLY` when a batch needs nothing from it. A transcript (`quietReply` in `web/src/task.ts`) never draws an `agent.message` whose last line is `NO_REPLY` (the model sometimes writes a sentence before it), and hides the live partial message while its text is still a prefix of it. A lead turn that byre starts without a handoff (a signal batch or a handoff continuation) is held (`ctx.held`): its `byre` message isn't drawn, the spinner stays off and its partial message stays hidden, until the lead draws something else, such as a tool call, thinking or a real message, which draws the `byre` message ahead of it. A `NO_REPLY` turn that drew nothing else ends without anything of it ever drawn; one that did keeps all of it, without the `NO_REPLY`.
- **Tools.** `list_tasks`, `read_transcript` (a task's events in brief, the last `limit` or those after `after_seq`), `read_inbox`, `answer_question` (an `option`, `other` or `dismiss` response recorded as the user, through the same checks as `POST /api/inbox/responses`), `send_message` (starts the task's agent if it has none; refused while it is mid-turn), `create_task`, `start_todo`, `interrupt`, `compact_task`, `merge_task`, `discard_task`, `show` and `compact_self`. The lead also has Claude Code's own tools and reads worktrees by path. Messages it sends task agents have actor `<login> (lead)`, so they don't make the user a participant; tasks, merges, discards and answers are done as the user. Its guidance says to answer a question only when the answer is clear or the human gave it, and to merge or discard only when the human asks.
- **Focus.** `users.focus` holds what the user's right pane shows: `project_id`, `task_id`, `tabs` (the tabs put first, in order) and `tab` (the selected one). With a `task_id`, `project_id` is always that task's project, filled in by the server; with only a `project_id`, the pane shows that project with no task, which only the Project tab has anything for. `GET /api/me/focus` reads it; `PUT /api/me/focus` and the lead's `show` set it, refusing an unknown tab, a task that isn't active or an unknown project, and record a `focus.updated` event owned by the user. The page applies the focus on load and on every `focus.updated` it didn't cause itself; the human's own changes (⌘K, the right pane's task picker, clicking a tab, a task link, a notification) are sent with `PUT /api/me/focus`. The URL follows the focus: `#/task/<id>`, `#/project/<id>`, or `#/` for neither.
- **Pane lock.** A `show` of what the pane already shows (the same task, or the same project with no task, on the same selected tab; `sameView`) tells the lead so and applies only its `tabs` order, whether or not the human is in the pane, so the human's selected tab stays selected. Otherwise, while the human is working in the right pane, the lead's `show` is refused with an error telling it to say in chat what it would have shown, unless its selected tab is `project` (the fallback the lead shows when nothing needs the human, so the human being there doesn't hold it) or the pane is finished (`Manager.paneFinished`): its task is merged or discarded, or its selected tab is `inbox` and the task has no open items. When an `inbox.updated`, `task.merged` or `task.discarded` event leaves a user's focused task finished that way, that user's signal for it gets a line "Your right pane is free: <task> has nothing left in its inbox." (or "is merged."/"is discarded."), even when the event itself makes no signal, such as a dismissed report; `inbox.updated` on a task that is no longer active adds none. The lead's guidance tells it to show the next thing that needs the human on that line, or the project's Project tab with `NO_REPLY` when nothing does. The page sends `PUT /api/me/pane-focus` with `focused` whenever that changes: true while the browser window has focus and the focused element is inside the right pane. The pane itself is focusable (`tabIndex` -1), so a click anywhere in it counts, not only on inputs and buttons; a re-render that removes the focused element hands focus back to the pane rather than counting as leaving. The page sends false on `pagehide` (with `keepalive`) and resends true when its event stream reconnects. byre keeps the flag in memory per user (`Manager.paneFocused`), so it starts false after a restart until the page resends it.
- **Compaction.** The pane's **Compact** button asks the lead for a handoff (`leadHandoffPrompt`). The lead can also call `compact_self` at a logical point; when that turn ends normally, byre sends the same request. The handoff turn ends the session, and a new lead session starts from `leadHandoffPreamble` plus the handoff; held input follows once that turn ends.
- **Restarts.** On shutdown, byre marks each running lead session idle with "byre stopped mid-turn" and holds a restart notice for it, so a lead is never left `running` for a build without lead support to find. After a crash, startup resumes a running lead like a task session. Startup then delivers any held input.

The UI is two panes: the left is the lead's transcript and composer (the same view as a task transcript, with only the Compact button in its header), the right shows the focused task, or project with no task, with the Transcript, Changes, Files, Terminal, Preview, Inbox, Reviews and Project tabs, the lead's `tabs` first. ⌘P (Ctrl+P elsewhere) selects the Project tab, keeping the right pane's task, and replaces the browser's print shortcut. ⌘S (Ctrl+S elsewhere) opens the right pane's task's Merge confirmation, from any tab, when the Merge button would be enabled, and replaces the browser's save shortcut.

## TODO

A project's `TODO.md` is read from the root of its default branch in the project's checkout (`git cat-file blob <default branch>:TODO.md`), so it shows what has been merged, not uncommitted edits in the checkout. `GET /api/projects/{id}/todo` returns `exists` and the parsed `items` (`internal/todo`): every top-level list item (`-`, `*`, `+`, `1.` or `1)` at the start of a line) is an item. Its first line, with any `[ ]` checkbox removed, is its `title`; the lines indented under it (and lines continuing it without a blank line between) are its `body`, with the common indentation removed; `section` is the nearest heading above it. Checked items (`[x]`) are skipped, list markers inside fenced code don't count, and paragraphs between items are ignored.

The title is the item's identity. `POST /api/projects/{id}/todo/tasks` with a `title` re-reads `TODO.md`, refuses an unknown title (404) or one an active task already has (409), creates a task from the default branch with that title and `todo_item` (the `tasks.todo_item` column, empty for other tasks), and starts its session as the requesting user with `todoPrompt` (`internal/agents/tasks.go`): the item as written, and an instruction to remove it from `TODO.md` in the worktree when the work is done. The agent's guidance names the item too (`taskGuidance`, see "Agent sessions"), so the instruction survives compaction and resumes. The agent removes the item on its own branch, so the removal lands on the default branch in the same squash commit as the work.

The **Project** tab is the dashboard of the right pane's project (the focused task's, or the project focused with no task). Under **Tasks** it lists the project's active tasks in the server's order (newest first), each with its session state, open inbox item count and **merge held** when it has `merge_queued_at`, as links that point the right pane at the task's transcript; the focused task is highlighted. Under **TODO** it lists the `TODO.md` items, grouped by section, with each body rendered as Markdown. An item with an active task whose `todo_item` equals its title shows that task's session state as a link to the task instead of a **Start** button. **Start** posts the item with the composer's default model and points the right pane at the new task's transcript. The task list follows byre's live state; the tab fetches the project's `TODO.md` when it opens, when the right pane moves to another project, when the project list changes, when the SSE stream reconnects, and on `task.merged`; a change pushed to the default branch outside byre shows the next time one of those happens.

## 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, and its choices are written inline in that context as Markdown list items: `- ( ) text` for pick-one choices, with exactly one `- (*) text` marking the recommendation, or `- [ ] text` for pick-any choices, with `- [x] text` marking the recommended ones. There is no separate list of options. byre parses the choices out of `context` (`internal/agents/choices.go`; list items inside code fences and blockquotes don't count) and stores their text in the payload as `options`, with `multiple` (pick-any) and `recommended`. The UI renders the context as Markdown with a radio button or checkbox in place of each choice's marker. A malformed call (no `context` or `why_blocked`, fewer than two choices, pick-one and pick-any choices mixed, a pick-one question without exactly one recommendation, two choices with the same text, an unknown attachment kind, a foreign `thread_id`) is rejected with a message saying what to fix, and nothing is filed. The call returns the item's id as `question_id`. An agent withdraws a question it no longer needs answered (the human answered it in a chat message, say) with the `cancel_question` MCP tool and that id: an `open` question of its own session becomes `dismissed` with no `resolved_by` (its `inbox.updated` event has actor `agent`), which also stops a blocking one from holding back delivery; anything else is rejected with a message saying why. 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.

`GET /api/inbox` is one query over open items, oldest first; `project_id` and `task_id` narrow it to a project or task view, and `state` picks another state. Blocking questions and errors are `blocked`; reports and non-blocking questions are `fyi`. The Inbox tab is task-specific: it shows one of the selected task's open items at a time, the oldest, and the next one once that is answered or dismissed; it shows nothing when no task is selected. While the selected task has open items, the Inbox tab's button is highlighted in the warn colours (`.attention` in `web/style.css`) and carries their count. Answering or dismissing the task's last open item from the Inbox tab switches the pane to the Transcript tab.

`POST /api/inbox/responses` answers any number of items in one submission. Response types and what they do to the item:

| type | allowed on | item becomes |
|---|---|---|
| `option` (the chosen choices' text in `options`: exactly one for pick-one, one or more for pick-any; a pick-any one may also carry `text`, delivered after the checked list) | questions | `answered` |
| `other` (free text in `text`: an answer, a question back, or new instructions) | questions, errors | `answered` |
| `dismiss` | reports, errors | `dismissed` |

Answers reach the agent as one message holding every undelivered `option` and `other` response of the session (`deliveryMessage` in `internal/agents/inbox.go`), never while one of its blocking questions is still open; until then they stay held (`inbox_responses.delivered_at` empty). While a turn is running, the task session's PostToolUse hook (`afterTool` in `internal/agents/snapshots.go`, through `deliverMidTurn`) hands them over after the agent's next tool call as the hook's `additionalContext`, so the agent reads them alongside that tool's result without being interrupted (for Codex, after each completed tool item, `deliverMidTurn` hands them over with `turn/steer` instead); the `user.message` event recording it carries `mid_turn: true` and no `head`, and the transcript doesn't treat it as a turn start. A turn that makes no further tool call leaves them to `Deliver`, which runs after each submission and when a turn ends, and sends them as a new turn once the session is `idle`. The log traces each answer: `inbox response recorded` when it is stored, `deliver held` with the reason, `deliver sent mid-turn`, `deliver sent` with the session's state and whether its agent process had exited or byre was closing, and `undelivered responses` with a reason wherever a session has held answers when its turn ends in a handoff or merge, its agent process ends, startup resumes it, or startup finds it idle. `sqlite3 byre.db "SELECT * FROM inbox_responses WHERE delivered_at IS NULL"` lists the answers held now.

## Notifications

New inbox items are sent as web push notifications to every browser a user has turned them on in. Web push needs a secure origin and a service worker; byre gets the origin from the `tailscale serve` certificate, and serves the worker at `/sw.js` (compiled from `web/src/sw.ts` with its own `web/tsconfig.sw.json`, since it needs the WebWorker library instead of the DOM one) so its scope is the whole SPA.

- **Keys.** byre generates a VAPID key pair on its first start and keeps it in the `vapid_keys` table; `GET /api/push/key` returns the public half, which browsers pass to `PushManager.subscribe`. Replacing the keys invalidates every subscription.
- **Subscriptions.** `POST /api/me/push-subscriptions` stores a browser's endpoint, `p256dh` and `auth` in `push_subscriptions` under the calling user (re-posting an endpoint replaces it), along with `https://` plus the request's `Host`, which becomes the VAPID `sub` claim. `DELETE /api/me/push-subscriptions?endpoint=` removes one. A push service answering 404 or 410 means the subscription expired, and byre deletes it.
- **Preferences.** `users.notification_prefs` holds which item kinds notify the user, returned as `notification_prefs` on `GET /api/me` and set with `PUT /api/me/notifications`: `blocking_questions` (on by default), `questions` (non-blocking), `reports`, `errors` (`session_error`) and `rate_limits`.
- **Sending.** `internal/push` watches the event stream for `inbox.created`. The first item starts a 3-second window (`pushWindow` in `internal/server/server.go`); everything that arrives inside it goes out together, so each subscribed user gets at most one notification per window, built from the items their preferences select. One item reads `byre · <task title>` with the question (or the report's first line, the error, or "Rate limited") as the body; several read `byre · N new inbox items` with one `<task title>: <text>` line each. Encryption and VAPID signing are `github.com/SherClockHolmes/webpush-go`. Notifications carry a 24-hour TTL and `Urgency: high` when any item is blocking. Delivery failures are logged, not retried.
- **Clicking** a notification opens the first item's task (`/#/task/<id>`): the worker focuses an open byre window and tells it to switch task, or opens a new one.

The **Settings** modal (the navbar's **Settings** button) turns notifications on or off for the current browser (asking for permission on the way) and edits the preferences. Opening it re-registers the browser's existing subscription, which restores one byre deleted as expired.

In the UI each card is answered on its own; there is no batch submission. A pick-one question's choices are clickable blocks, and clicking one sends that answer at once. A choice's block (or a pick-any choice's checkbox label) holds the whole list item: its first line, which is the choice's text, and everything under it, such as an example's paragraph or code block. A pick-any question's choices are checkboxes, sent with the Submit button at the bottom of the card. Below the choices, an "Other…" block in the same style opens the only text field. A card has at most one Submit button: on a pick-any question it sends the checked choices with the Other text alongside (one `option` response), or the Other text alone as `other` when nothing is checked. A report has only an OK button, which dismisses it at once; an error has a "Reply…" block (`other`) and a Dismiss button. The Other and Reply text boxes send with the Submit button under them or on Enter (Shift+Enter for a newline), like the message box, and fold back into their block when left empty. The list updates in place: a card stays attached while its item is unchanged, so task and inbox updates from other agents don't pull focus out of a text box being typed in.

There is no snoozing. The `snoozed_until` and `snooze_until` columns are still in the schema, always empty, so builds from older branches keep working against the same database; nothing reads them.

Every Markdown view (inbox items and the transcript) renders a line `<details><summary>Title</summary>` (or `<details>` with the `<summary>` on the next line), Markdown content, and a line `</details>` as a collapsed section (`web/src/markdown.ts`; sections nest) showing only the title; session guidance and the `ask_human` schema tell agents to put long supporting detail in them.

Markdown images (`![alt](src)`, or `![alt](<src>)`; the plain form also accepts spaces, since worktree paths under `Application Support` have one) render inline, linking to the full image. A `src` that is an absolute path, a path relative to the worktree or a `file://` URL is loaded from `GET /api/tasks/{taskId}/image?path=` for the item's or event's task; a `data:image/` URL of PNG, JPEG, GIF or WebP is used as is; any other scheme, `http(s)` included, shows as a link with the alt text and is never fetched. An image that fails to load is replaced by "image not available: <src>". An inbox `image` attachment renders the same way from its `image` (data URL) or `path`.

A code block fenced as `mermaid`, and an inbox `diagram` attachment, render as a Mermaid diagram (`web/src/mermaid.ts`). The library is vendored: `web/package.json` pins `mermaid` as a devDependency, and `go generate ./web` copies `node_modules/mermaid/dist/mermaid.min.js` and its LICENSE into `web/vendor/`, which is committed and embedded. To upgrade, change the pinned version, `npm --prefix web install`, and regenerate. Nothing loads it until the first diagram is drawn; that injects one `<script src="/vendor/mermaid.min.js">` and initializes Mermaid with `securityLevel: "strict"` and the `base` theme, coloured from the custom properties in `web/style.css` as they resolve at that moment (so a light/dark switch applies from the next page load). Each diagram shows its source until its SVG is ready; source Mermaid rejects stays as source with "diagram not rendered: <error>" under it. The endpoint (`internal/server/images.go`) serves PNG, JPEG, GIF, WebP and SVG by extension, resolves symlinks on both the worktree and the file and answers 403 for anything outside the worktree, 404 for a missing file, 400 for another extension or a non-file, and 409 once the task is closed (its worktree is gone). Responses carry `X-Content-Type-Options: nosniff` and a sandboxing `Content-Security-Policy`, so an SVG opened directly runs no script, and `Cache-Control: no-cache` with `Last-Modified`, so a changed file is refetched.

Answers reach the agent as one message, listing each answer under the question or error it responds to, once the session is idle and none of its blocking questions are still waiting for the human. An `other` answer to a question tells the agent that if it asks something back, it should answer with `ask_human` using the item's `thread_id`. Every item change is an `inbox.created` or `inbox.updated` event carrying the whole item, including who resolved it.

## Changes

`GET /api/tasks/{taskId}/changes` snapshots the task's worktree as if everything were staged: it copies the worktree's index to a temporary file, runs `git add --all` against that copy (`GIT_INDEX_FILE`), and `git write-tree`s it, so committed, staged, unstaged and untracked work is included, `.gitignore` is respected, and the worktree's real index is never touched. Starting from the real index rather than `read-tree HEAD` keeps git's stat cache, so unchanged files aren't rehashed. The tree is compared with `git merge-base HEAD <default branch>`, or with `since` when given, using rename detection, giving per-file status and line counts. Work already merged into the default branch therefore drops out. The Changes view toggles between **Since main** and **This turn**, which passes the latest `user.message` event's `head` as `since`; the summary above the inbox always shows since main. `GET /api/tasks/{taskId}/diff` returns one file's patch between a `base` and `tree` from that response. Each request writes the changed blobs and a tree into the repo's object store as loose objects.

The Changes view lists the files with their counts, opens a file's diff on click (open files stay open across refreshes), and refreshes when it opens, when the selected task changes, and 1.5s after the selected task's last tool result or turn end. It can also be pinned to a snapshot (see "Snapshots"). The Inbox view shows just its summary line (file count, +/− totals, base) for the selected task at the top.

## Files

The Files tab browses the selected task's worktree, read-only (`internal/server/files.go`). `GET /api/tasks/{taskId}/dir?path=` lists one directory, directories first and then by name, without entries named `.git`; `GET /api/tasks/{taskId}/file?path=` returns one regular file. Both take a slash-separated path relative to the worktree root and work only while the task is active (409 otherwise). Every path is opened through an `os.Root` on the worktree, so a path that leaves it, through `..`, an absolute path or a symlink at any depth, is a 400; a path with a `.git` component is also refused. A listing reports each entry as `dir`, `file` (with its size) or `other`, following symlinks that stay inside the worktree (`symlink` marks them); a symlink that leaves the worktree or points nowhere is `other` and can't be opened. Gitignored entries are listed with `ignored` set: one `git check-ignore --stdin` per listing (`git.Ignored`) over the entries' paths, taken from the directory's real path so a listing reached through an in-worktree symlink is checked where it really lives; untracked paths under an ignored directory count as ignored, tracked files never do. The view shows them dimmed with `ignored` beside them, and they open like anything else. A listing stops at `maxDirEntries` entries with `truncated` set. A file read sends at most `maxFileBytes`, cut back to a whole UTF-8 character, with `truncated` set when the file is longer; a file with a NUL byte or invalid UTF-8 in that part is `binary` and comes back with no text.

The view shows a breadcrumb from `worktree` down to the current directory or file, the directory's entries (a `../` row to go up), or the file's text with line numbers and a note when only its start is shown. Where you are is kept per task in memory, so switching tasks or tabs returns to it, but a page reload starts at the root. It refetches what it shows 1.5s after the selected task's last tool result or turn end, keeping the scroll position.

## Terminals

Each active task can have one terminal: a login shell (`$SHELL -l`, from byre's environment) on a PTY (`github.com/creack/pty`), started in the task's worktree with byre's environment plus `TERM=xterm-256color`, `COLORTERM=truecolor` and the task's `PORT` (`internal/server/terminal.go`). `GET /api/tasks/{taskId}/terminal?cols=&rows=` is a WebSocket (`github.com/coder/websocket`), the only WebSocket in byre: it attaches to the task's terminal, starting the shell at that size if none is running, and works only while the task is active (409 otherwise). The server first sends the last `terminalBacklog` bytes the terminal printed, then its output as it comes, as binary messages; the client sends keystrokes as binary messages and a `TerminalSize` JSON text message on every resize. Any number of sockets can attach to one terminal: they all get its output and all type into it, and the last resize wins. A socket that falls `terminalClientBuf` reads behind is closed and the page reconnects. When the shell exits, every socket is closed with code 4000 and the exit status (`exit status 0`, `signal: hangup`) as the reason, and the next attach starts a new shell. Merging or discarding the task, and stopping byre, sends the shell's process group SIGHUP and closes the PTY, so terminals don't survive a restart. The WebSocket handshake checks that `Origin` matches `Host`, so another site can't open one through the user's Tailscale identity. The log records `terminal started` and `terminal ended` with the task, pid and exit status.

The **Terminal** tab (`web/src/terminal.ts`) draws it with xterm.js, vendored like Mermaid: `web/package.json` pins `@xterm/xterm` and `@xterm/addon-fit`, and `go generate ./web` copies their ES module builds, `xterm.css` and licenses into `web/vendor/`. Nothing loads them until the tab first opens, which imports the modules, adds the stylesheet and waits for the font. The terminal uses the UI font and is coloured from the custom properties in `web/style.css` (background, text, accent cursor, accent-tint selection); ANSI colours are xterm.js's defaults. It fits the pane and resizes with it. Opening the tab, or selecting another task while it is open, opens one socket for the selected task; switching tab or task closes it, and the shell keeps running, so coming back replays its recent output. A socket that drops for any other reason reconnects after 2s while the task is active; after a byre restart that starts a new shell. When the shell exits the header shows `shell ended: <status>` and a **New shell** button; when it can't be started (the socket closes with 1011, the error in byre's log as `start terminal`), the header says so, with the same button to try again. Ctrl key combinations typed in the terminal go to the shell, not to byre's Ctrl+K, Ctrl+P and Ctrl+S shortcuts; ⌘K, ⌘P and ⌘S still work.

## Snapshots

byre snapshots each task's worktree at the end of every turn (`internal/agents/snapshots.go`, `internal/git/snapshot.go`), so a snapshot always sits on a turn boundary, the only place a Codex conversation can be forked. A snapshot builds the tree the same way as the Changes view (a copy of the real index, `git add --all`, `git write-tree`), commits it with `git commit-tree` whose parent is the worktree's `HEAD`, authored as the session's creator with the message `byre snapshot <n> (<trigger>)`, and points `refs/byre/tasks/<task-id>/snap/<n>` at it (`git update-ref` with an empty old value, so an existing ref is never overwritten). A row in the `snapshots` table records id, task, session, `n` (from 1 per task), commit and tree shas, `event_seq` (the task's latest event when the snapshot started, at or after the turn's `turn.ended`, so the tree holds at least the work up to that event), the trigger and the time, and the same transaction records a `snapshot.created` event carrying the row.

The trigger is `turn_end`: the snapshot starts after byre's end-of-turn commit and the `turn.ended` event. Snapshots taken by earlier builds also carry `message` (mid-turn, when the agent wrote text after tool calls), `tool_call`, `ask_human` and `timer`. A snapshot whose tree equals the task's latest snapshot's tree is skipped, so a turn that changed no files leaves none. Snapshots run one at a time per task: a trigger that arrives while one is running replaces any already waiting one, and the waiting one runs when the current one finishes. Failures are logged and dropped.

Merging or discarding a task stops new snapshots for it, waits for one in progress, and deletes its `refs/byre/tasks/<task-id>/` refs; the rows stay. `GET /api/tasks/{taskId}/snapshots` lists a task's rows, oldest first. `git for-each-ref refs/byre/` in the project's repo lists the live refs.

`GET /api/tasks/{taskId}/changes?snapshot=<n>` reports a snapshot instead of the live worktree: its `tree` is the snapshot's tree, and `base` is the merge-base of the snapshot's commit and the default branch, or with `step=true` the previous snapshot's tree (the snapshot commit's parent for snapshot 1). It reads the stored shas, so it works only while the task is active and its refs keep the objects; `since` with `snapshot` is a 400. `GET /api/tasks/{taskId}/diff` takes that `base` and `tree` as usual.

The transcript is the timeline. The UI learns a task's snapshots from the `snapshot.created` events in its transcript (`snapshots` in `web/src/state.ts`). A snapshot is a point between the agent's events, not part of one, so each gets its own row in the transcript, a divider reading `snapshot #n` (its trigger and time in the tooltip), placed where its `snapshot.created` event falls in the task's event order: just after the turn end it belongs to (after the triggering text for an old `message` snapshot). A snapshot row ends the current group of tool calls, so calls after it start a new group. The row's **changes** button pins the snapshot (`state.pinned`, cleared when the selected task changes) and switches the right pane to the Changes tab; its **fork** button forks it (see "Forking") and points the right pane at the new task. Pinned, the Changes header reads `snapshot <n> · <trigger> · <time>` with ← and → to step to the neighbouring snapshots, and the range buttons are **Since main** and **This step** (`step=true`, the default when pinning) plus **Live**, which unpins. A pinned view doesn't refresh on tool results, since a snapshot never changes.

## Forking

`POST /api/tasks/{taskId}/snapshots/{n}/fork` (the **fork** button on a snapshot's transcript row) starts a new task from a snapshot (`internal/agents/fork.go`). Its branch and worktree start from the snapshot's commit, so the fork's worktree holds exactly the snapshot's tree, uncommitted work of the time included, as the branch's first commit. The task is titled `<title> (fork of #n)`, keeps the source's `merge_title` and `todo_item`, and records `forked_from` (the source task) and `forked_at` (n) in the `tasks` columns of those names. It gets an idle session, created by the requesting user (who needs a git identity), on the snapshot session's model, with `forked_from` set to that session's `vendor_session_id` and `forked_at` to the cut point below. Nothing runs until the first message is sent to it; that turn starts Claude Code with `--resume=<forked_from> --resume-session-at=<forked_at> --fork-session --session-id=<new id>`, or Codex with `thread/fork` (`threadId` `forked_from`, `lastTurnId` `forked_at`) whose new thread id byre then stores, so the new conversation is the source's up to the cut, under its own id, and later starts resume the new id as usual. A forked Codex thread keeps the source's byre tools. Refused (409) while the source task is closed (its snapshot refs are gone) and when there is no cut point; 404 for an unknown snapshot.

The cut point comes from `vendor_uuid`: every top-level `agent.message`, `agent.thinking`, `agent.tool_call` and `agent.tool_result` event (not a subagent's) carries the `uuid` of the Claude Code stream-json line it came from, which is the id of that entry in the CLI's own session transcript. `forkPoint` takes the last such event of the snapshot's session at or before the snapshot's `event_seq`, then extends the cut through the following tool calls and results until every tool call it has kept has its result, so the fork never resumes on an unanswered tool call. For a `turn_end` snapshot the cut is the turn's last message. A Codex session's events carry no `vendor_uuid` except its `turn.ended`, which carries the turn id, so for Codex `forkPoint` picks the last turn that ended at or before the snapshot. Snapshots whose session recorded no `vendor_uuid` by then, such as those from before byre recorded it, can't be forked.

The fork's session guidance gets one more line (`forkGuidance` in `internal/agents/guidance.go`) naming the source task, the snapshot, the fork's branch and worktree and the source's worktree, telling the agent that everything before the fork happened in the other worktree and to work only in its own. Claude Code can reuse the system prompt recorded for the source conversation on a fork, the source's cwd included, so the `UserPromptSubmit` hook's copy is what reliably tells it. The fork's transcript starts with a note from its `task.created` event, "forked this task from <source> at snapshot #n", linking the source while it is active; the lead's signal for it reads "<task> was forked by <user> from <source> at snapshot n", and `list_tasks` notes the source. The fork's transcript shows only its own events, not the source's history.

## Reviews

Every new snapshot of a task gets a review: a separate agent session on the vendor the task's agent doesn't use reads the change and reports on it (`internal/agents/review.go`, `internal/store/review.go`). A turn that changes no files makes no snapshot and so no review. Nothing else starts a review, and nothing waits for one: reviews ride along for the human to look at when they want.

- **Starting.** After `takeSnapshot` creates a snapshot, `afterSnapshot` runs `startReviewer`: it picks the vendor opposite the task's latest implementer session (`reviewVendor`) and that vendor's model in `reviewModels`, checks the snapshot's commit out detached at `worktrees/<project-id>/review-<review-id>`, creates an `agent_sessions` row with `role` `reviewer` on the task (created by the task's creator), a `reviews` row (`running`, one per snapshot), and sends `reviewPrompt` as its first turn (actor `byre`): the change as `git diff` from the previous snapshot (the snapshot commit's parent for the first) with its changed files, the merge-base diff of all the task's work for context, and the task's first message to its agent.
- **Running.** Reviewer sessions get `reviewGuidance` and only the `submit_review` tool, whose arguments (`reviewSchema`: a Markdown `summary` and `findings`, each with `severity`, `category`, `title`, `detail`, `path` and `line`) become the review's `result` and mark it `done`. They run without the Stop-hook bounce, mid-turn delivery, end-of-turn commit, snapshots or reports, and their `user.message` events carry no `head`. When the reviewer's turn ends byre completes its session, kills its process and removes the worktree; a review still `running` then fails with why (no submission, with the final message; an error; an interrupt). A process that exits mid-turn fails the review the same way. Merging or discarding the task fails its running reviews ("the task was closed") and ends their reviewers. On startup, a running reviewer resumes like any session, and a running review whose reviewer isn't `running` fails.
- **Questions.** A question's `reviews` is the review of the first snapshot the task took after the question was filed, the one at the end of the turn that asked it, computed when the item is read; the Inbox tab shows it under the question once it starts.
- **Events.** `review.started` and `review.finished` (state `done` or `failed`) carry the whole review, with the task's ids and no `agent_session_id`. A reviewer's own events carry its session id and the task's ids: the transcript skips every event of a session whose `session.created` has `role` `reviewer`, and draws each `review.finished` as a note with a **reviews** button; the lead's `read_transcript` leaves the reviewer's events out and shows each `review.finished` with its summary and findings (`reviewLine`). `GET /api/tasks/{taskId}/sessions` and everything that looks for the task's agent (`ListSessions`) see only implementer sessions.
- **UI.** The **Reviews** tab (`web/src/reviews.ts`) lists the task's reviews newest first (snapshot, state or severity counts, error, summary and findings). It loads when it opens, when the task changes, and on each `review.*` event in the task's stream. `GET /api/tasks/{taskId}/reviews` lists a task's reviews oldest first. `sqlite3 byre.db "SELECT id, task_id, snapshot_n, vendor, state, error FROM reviews ORDER BY created_at DESC LIMIT 20"` shows recent ones.

## 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. `?task_id=` limits the stream, replay and live, to one task's events (404 for an unknown task); `?lead=true` to the events of the caller's lead agent sessions. An event with an `owner` (a lead agent's events, a user's `focus.updated`) goes only to that user's streams; the others never see it. 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.

The web UI keeps three streams: one for all events from the page's load onward, which drives the task, session, inbox and lead session lists, the right pane's focus and the navbar's connection dot; one per selected task (`selectTask` in `web/src/state.ts`), opened with `?task_id=` and `after=0` so it replays the task's whole history and then stays live; and one for the lead (`startLeadStream`), opened with `?lead=true` and `after=0`. Each transcript is drawn only from its own stream, so a reconnect after a byre restart fills in both the history and anything missed. Selecting another task closes the old task stream. Events arriving together are drawn in one batch.