diff --git a/api/oapi-codegen.yaml b/api/oapi-codegen.yaml new file mode 100644 index 0000000..ca04060 --- /dev/null +++ b/api/oapi-codegen.yaml @@ -0,0 +1,8 @@ +package: api +output: api.gen.go +generate: + std-http-server: true + models: true + embedded-spec: true +output-options: + skip-prune: true diff --git a/api/openapi.yaml b/api/openapi.yaml new file mode 100644 index 0000000..5526c89 --- /dev/null +++ b/api/openapi.yaml @@ -0,0 +1,246 @@ +openapi: 3.0.3 +info: + title: byre + version: 0.0.0 +paths: + /api/me: + get: + operationId: getMe + responses: + "200": + description: The calling user. + content: + application/json: + schema: { $ref: "#/components/schemas/User" } + put: + operationId: updateMe + requestBody: + required: true + content: + application/json: + schema: { $ref: "#/components/schemas/UserUpdate" } + responses: + "200": + description: The updated user. + content: + application/json: + schema: { $ref: "#/components/schemas/User" } + "400": { $ref: "#/components/responses/Error" } + + /api/projects: + get: + operationId: listProjects + responses: + "200": + description: All projects. + content: + application/json: + schema: + type: array + items: { $ref: "#/components/schemas/Project" } + post: + operationId: createProject + requestBody: + required: true + content: + application/json: + schema: { $ref: "#/components/schemas/ProjectCreate" } + responses: + "201": + description: The new project. + content: + application/json: + schema: { $ref: "#/components/schemas/Project" } + "400": { $ref: "#/components/responses/Error" } + + /api/projects/{projectId}: + parameters: + - { name: projectId, in: path, required: true, schema: { type: string } } + get: + operationId: getProject + responses: + "200": + description: The project. + content: + application/json: + schema: { $ref: "#/components/schemas/Project" } + "404": { $ref: "#/components/responses/Error" } + + /api/projects/{projectId}/tasks: + parameters: + - { name: projectId, in: path, required: true, schema: { type: string } } + get: + operationId: listTasks + responses: + "200": + description: The project's tasks, newest first. + content: + application/json: + schema: + type: array + items: { $ref: "#/components/schemas/Task" } + "404": { $ref: "#/components/responses/Error" } + post: + operationId: createTask + description: Creates the task's branch and worktree from the project's default branch. + requestBody: + required: true + content: + application/json: + schema: { $ref: "#/components/schemas/TaskCreate" } + responses: + "201": + description: The new task. + content: + application/json: + schema: { $ref: "#/components/schemas/Task" } + "400": { $ref: "#/components/responses/Error" } + "404": { $ref: "#/components/responses/Error" } + + /api/tasks/{taskId}: + parameters: + - { name: taskId, in: path, required: true, schema: { type: string } } + get: + operationId: getTask + responses: + "200": + description: The task. + content: + application/json: + schema: { $ref: "#/components/schemas/Task" } + "404": { $ref: "#/components/responses/Error" } + + /api/tasks/{taskId}/complete: + parameters: + - { name: taskId, in: path, required: true, schema: { type: string } } + post: + operationId: completeTask + description: Removes the task's worktree and branch. The task's record and events remain. + responses: + "200": + description: The completed task. + content: + application/json: + schema: { $ref: "#/components/schemas/Task" } + "404": { $ref: "#/components/responses/Error" } + "409": { $ref: "#/components/responses/Error" } + + /api/events: + get: + operationId: streamEvents + description: > + Server-sent events. Each event's id is its seq; data is the Event as JSON. + Events after Last-Event-ID (or the after query parameter) are replayed before live events. + parameters: + - { name: Last-Event-ID, in: header, required: false, schema: { type: integer, format: int64 } } + - { name: after, in: query, required: false, schema: { type: integer, format: int64 } } + responses: + "200": + description: Event stream. + content: + text/event-stream: + schema: { type: string } + + /api/admin/status: + get: + operationId: getStatus + responses: + "200": + description: Server health and usage. + content: + application/json: + schema: { $ref: "#/components/schemas/Status" } + +components: + responses: + Error: + description: Error. + content: + application/json: + schema: { $ref: "#/components/schemas/Error" } + + schemas: + Error: + type: object + required: [message] + properties: + message: { type: string } + + User: + type: object + required: [login, display_name, git_name, git_email] + properties: + login: { type: string } + display_name: { type: string } + git_name: { type: string } + git_email: { type: string } + + UserUpdate: + type: object + required: [git_name, git_email] + properties: + git_name: { type: string } + git_email: { type: string } + + Project: + type: object + required: [id, name, repo_path, default_branch, remote, created_by, created_at] + properties: + id: { type: string } + name: { type: string } + repo_path: { type: string } + default_branch: { type: string } + remote: { type: string } + created_by: { type: string } + created_at: { type: string, format: date-time } + + ProjectCreate: + type: object + required: [name, repo_path] + properties: + name: { type: string } + repo_path: { type: string } + + Task: + type: object + required: [id, project_id, title, branch, worktree_path, base_ref, status, created_by, created_at] + properties: + id: { type: string } + project_id: { type: string } + title: { type: string } + branch: { type: string } + worktree_path: { type: string } + base_ref: { type: string } + status: { type: string, enum: [active, completed] } + created_by: { type: string } + created_at: { type: string, format: date-time } + completed_at: { type: string, format: date-time } + + TaskCreate: + type: object + required: [title] + properties: + title: { type: string } + + Event: + type: object + required: [seq, kind, actor, payload, created_at] + properties: + seq: { type: integer, format: int64 } + kind: { type: string } + project_id: { type: string } + task_id: { type: string } + actor: { type: string } + payload: { type: object } + created_at: { type: string, format: date-time } + + Status: + type: object + required: [started_at, db_bytes, last_event_seq, projects, active_tasks, sse_clients] + properties: + started_at: { type: string, format: date-time } + db_bytes: { type: integer, format: int64 } + last_event_seq: { type: integer, format: int64 } + projects: { type: integer } + active_tasks: { type: integer } + sse_clients: { type: integer } diff --git a/cmd/byre/main.go b/cmd/byre/main.go index 51618d7..3fc399e 100644 --- a/cmd/byre/main.go +++ b/cmd/byre/main.go @@ -1,206 +1,29 @@ package main import ( - "bufio" - "context" - "encoding/json" - "flag" "fmt" "log/slog" "os" - "os/exec" - "os/signal" - "strings" - - "g.fc.run/misc/byre/internal/claude" - "g.fc.run/misc/byre/internal/mcp" - "g.fc.run/misc/byre/internal/report" ) func main() { - resume := flag.String("resume", "", "claude session id to resume") - flag.Parse() - - dir, err := os.Getwd() - if err != nil { - fatal("getwd", "err", err) + if len(os.Args) < 2 { + usage() } - gate := &report.Gate{OnReport: printReport} - - ctx := context.Background() - s, err := claude.Start(ctx, claude.Options{ - Cwd: dir, - Resume: *resume, - GitName: gitConfig(dir, "user.name"), - GitEmail: gitConfig(dir, "user.email"), - MCPServers: []*mcp.Server{{Name: "byre", Version: "0.0.0", Tools: []mcp.Tool{gate.Tool()}}}, - Hooks: map[string][]claude.HookMatcher{ - "Stop": {{Func: gate.StopHook}}, - }, - }) - if err != nil { - fatal("start claude", "err", err) - } - - sigs := make(chan os.Signal, 1) - signal.Notify(sigs, os.Interrupt) - - lines := make(chan string) - go readLines(lines) - - for { - fmt.Print("> ") - - select { - case line, ok := <-lines: - if !ok { - shutdown(s) - return - } - if strings.TrimSpace(line) == "" { - continue - } - gate.Reset() - err := s.Send(line) - if err != nil { - fatal("send", "err", err) - } - runTurn(ctx, s, sigs) - - case <-sigs: - fmt.Println() - shutdown(s) - return - } + switch os.Args[1] { + case "serve": + serveCmd(os.Args[2:]) + case "run": + runCmd(os.Args[2:]) + default: + usage() } } -func runTurn(ctx context.Context, s *claude.Session, sigs <-chan os.Signal) { - for { - select { - case ev, ok := <-s.Events(): - if !ok { - fatal("claude exited") - } - if printEvent(ev) { - return - } - - case <-sigs: - fmt.Println("\n[interrupting]") - err := s.Interrupt(ctx) - if err != nil { - slog.Error("interrupt", "err", err) - } - } - } -} - -func printEvent(ev claude.Event) bool { - switch { - case ev.Type == "system" && ev.Subtype == "init": - info := struct { - SessionID string `json:"session_id"` - Model string `json:"model"` - }{} - err := json.Unmarshal(ev.Raw, &info) - if err != nil { - fatal("parse init", "err", err) - } - fmt.Printf("[session %s, %s]\n", info.SessionID, info.Model) - - case ev.Type == "assistant": - blocks, err := ev.Blocks() - if err != nil { - fatal("parse assistant", "err", err) - } - for _, b := range blocks { - switch b.Type { - case "text": - fmt.Println(b.Text) - case "tool_use": - fmt.Printf("→ %s %s\n", b.Name, oneLine(string(b.Input), 160)) - } - } - - case ev.Type == "user": - blocks, err := ev.Blocks() - if err != nil { - fatal("parse user", "err", err) - } - for _, b := range blocks { - if b.Type == "tool_result" && b.IsError { - fmt.Printf("← error %s\n", oneLine(string(b.Content), 160)) - } - } - - case ev.Type == "result": - res, err := ev.Result() - if err != nil { - fatal("parse result", "err", err) - } - fmt.Printf("[%s, %d turns, %.1fs, $%.4f]\n", res.Subtype, res.NumTurns, float64(res.DurationMS)/1000, res.TotalCostUSD) - return true - } - - return false -} - -func printReport(r report.Report) { - fmt.Println("── report") - sections := []struct { - name string - items []string - }{ - {"done", r.Done}, - {"open questions", r.OpenQuestions}, - {"next steps", r.NextSteps}, - {"risks", r.Risks}, - {"deviations", r.Deviations}, - } - for _, sec := range sections { - if len(sec.items) == 0 { - continue - } - fmt.Printf(" %s:\n", sec.name) - for _, item := range sec.items { - fmt.Printf(" • %s\n", item) - } - } -} - -func readLines(out chan<- string) { - defer close(out) - sc := bufio.NewScanner(os.Stdin) - for sc.Scan() { - out <- sc.Text() - } -} - -func shutdown(s *claude.Session) { - err := s.Close() - if err != nil { - slog.Warn("claude exit", "err", err) - } -} - -func gitConfig(dir, key string) string { - cmd := exec.Command("git", "config", key) - cmd.Dir = dir - out, err := cmd.Output() - if err != nil { - fatal("git config", "key", key, "err", err) - } - return strings.TrimSpace(string(out)) -} - -func oneLine(s string, max int) string { - s = strings.Join(strings.Fields(s), " ") - if len(s) > max { - return s[:max] + "…" - } - return s +func usage() { + fmt.Fprintln(os.Stderr, "usage: byre serve [--dev] | byre run [--resume ID]") + os.Exit(2) } func fatal(msg string, args ...any) { diff --git a/cmd/byre/run.go b/cmd/byre/run.go new file mode 100644 index 0000000..03e926e --- /dev/null +++ b/cmd/byre/run.go @@ -0,0 +1,205 @@ +package main + +import ( + "bufio" + "context" + "encoding/json" + "flag" + "fmt" + "log/slog" + "os" + "os/exec" + "os/signal" + "strings" + + "g.fc.run/misc/byre/internal/claude" + "g.fc.run/misc/byre/internal/mcp" + "g.fc.run/misc/byre/internal/report" +) + +func runCmd(args []string) { + fs := flag.NewFlagSet("run", flag.ExitOnError) + resume := fs.String("resume", "", "claude session id to resume") + fs.Parse(args) + + dir, err := os.Getwd() + if err != nil { + fatal("getwd", "err", err) + } + + gate := &report.Gate{OnReport: printReport} + + ctx := context.Background() + s, err := claude.Start(ctx, claude.Options{ + Cwd: dir, + Resume: *resume, + GitName: gitConfig(dir, "user.name"), + GitEmail: gitConfig(dir, "user.email"), + MCPServers: []*mcp.Server{{Name: "byre", Version: "0.0.0", Tools: []mcp.Tool{gate.Tool()}}}, + Hooks: map[string][]claude.HookMatcher{ + "Stop": {{Func: gate.StopHook}}, + }, + }) + if err != nil { + fatal("start claude", "err", err) + } + + sigs := make(chan os.Signal, 1) + signal.Notify(sigs, os.Interrupt) + + lines := make(chan string) + go readLines(lines) + + for { + fmt.Print("> ") + + select { + case line, ok := <-lines: + if !ok { + shutdown(s) + return + } + if strings.TrimSpace(line) == "" { + continue + } + gate.Reset() + err := s.Send(line) + if err != nil { + fatal("send", "err", err) + } + runTurn(ctx, s, sigs) + + case <-sigs: + fmt.Println() + shutdown(s) + return + } + } +} + +func runTurn(ctx context.Context, s *claude.Session, sigs <-chan os.Signal) { + for { + select { + case ev, ok := <-s.Events(): + if !ok { + fatal("claude exited") + } + if printEvent(ev) { + return + } + + case <-sigs: + fmt.Println("\n[interrupting]") + err := s.Interrupt(ctx) + if err != nil { + slog.Error("interrupt", "err", err) + } + } + } +} + +func printEvent(ev claude.Event) bool { + switch { + case ev.Type == "system" && ev.Subtype == "init": + info := struct { + SessionID string `json:"session_id"` + Model string `json:"model"` + }{} + err := json.Unmarshal(ev.Raw, &info) + if err != nil { + fatal("parse init", "err", err) + } + fmt.Printf("[session %s, %s]\n", info.SessionID, info.Model) + + case ev.Type == "assistant": + blocks, err := ev.Blocks() + if err != nil { + fatal("parse assistant", "err", err) + } + for _, b := range blocks { + switch b.Type { + case "text": + fmt.Println(b.Text) + case "tool_use": + fmt.Printf("→ %s %s\n", b.Name, oneLine(string(b.Input), 160)) + } + } + + case ev.Type == "user": + blocks, err := ev.Blocks() + if err != nil { + fatal("parse user", "err", err) + } + for _, b := range blocks { + if b.Type == "tool_result" && b.IsError { + fmt.Printf("← error %s\n", oneLine(string(b.Content), 160)) + } + } + + case ev.Type == "result": + res, err := ev.Result() + if err != nil { + fatal("parse result", "err", err) + } + fmt.Printf("[%s, %d turns, %.1fs, $%.4f]\n", res.Subtype, res.NumTurns, float64(res.DurationMS)/1000, res.TotalCostUSD) + return true + } + + return false +} + +func printReport(r report.Report) { + fmt.Println("── report") + sections := []struct { + name string + items []string + }{ + {"done", r.Done}, + {"open questions", r.OpenQuestions}, + {"next steps", r.NextSteps}, + {"risks", r.Risks}, + {"deviations", r.Deviations}, + } + for _, sec := range sections { + if len(sec.items) == 0 { + continue + } + fmt.Printf(" %s:\n", sec.name) + for _, item := range sec.items { + fmt.Printf(" • %s\n", item) + } + } +} + +func readLines(out chan<- string) { + defer close(out) + sc := bufio.NewScanner(os.Stdin) + for sc.Scan() { + out <- sc.Text() + } +} + +func shutdown(s *claude.Session) { + err := s.Close() + if err != nil { + slog.Warn("claude exit", "err", err) + } +} + +func gitConfig(dir, key string) string { + cmd := exec.Command("git", "config", key) + cmd.Dir = dir + out, err := cmd.Output() + if err != nil { + fatal("git config", "key", key, "err", err) + } + return strings.TrimSpace(string(out)) +} + +func oneLine(s string, max int) string { + s = strings.Join(strings.Fields(s), " ") + if len(s) > max { + return s[:max] + "…" + } + return s +} diff --git a/cmd/byre/serve.go b/cmd/byre/serve.go new file mode 100644 index 0000000..ff89be6 --- /dev/null +++ b/cmd/byre/serve.go @@ -0,0 +1,65 @@ +package main + +import ( + "context" + "errors" + "flag" + "io/fs" + "log/slog" + "net" + "net/http" + "os" + "os/signal" + "path/filepath" + "syscall" + "time" + + "g.fc.run/misc/byre/internal/server" + "g.fc.run/misc/byre/web" +) + +const listenAddr = "127.0.0.1:8270" + +func serveCmd(args []string) { + flags := flag.NewFlagSet("serve", flag.ExitOnError) + dev := flags.Bool("dev", false, "serve the SPA from ./web on disk instead of the embedded copy") + flags.Parse(args) + + configDir, err := os.UserConfigDir() + if err != nil { + fatal("user config dir", "err", err) + } + + spa := fs.FS(web.FS) + if *dev { + spa = os.DirFS("web") + } + + srv, err := server.New(filepath.Join(configDir, "byre"), spa) + if err != nil { + fatal("start server", "err", err) + } + defer srv.Close() + + ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM) + defer stop() + + hs := &http.Server{ + Addr: listenAddr, + Handler: srv.Handler(), + BaseContext: func(net.Listener) context.Context { return ctx }, + } + + go func() { + <-ctx.Done() + shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second) + defer cancel() + hs.Shutdown(shutdownCtx) + }() + + slog.Info("listening", "addr", listenAddr, "dev", *dev) + err = hs.ListenAndServe() + if !errors.Is(err, http.ErrServerClosed) { + fatal("serve", "err", err) + } +} diff --git a/deploy/run.fc.byre.plist b/deploy/run.fc.byre.plist new file mode 100644 index 0000000..173cf8b --- /dev/null +++ b/deploy/run.fc.byre.plist @@ -0,0 +1,26 @@ + + + + + Label + run.fc.byre + ProgramArguments + + /Users/flamingcow/bin/byre + serve + + EnvironmentVariables + + PATH + /Users/flamingcow/bin:/Users/flamingcow/.local/bin:/opt/homebrew/bin:/usr/bin:/bin:/usr/sbin:/sbin + + RunAtLoad + + KeepAlive + + StandardOutPath + /Users/flamingcow/Library/Logs/byre.log + StandardErrorPath + /Users/flamingcow/Library/Logs/byre.log + + diff --git a/docs/claude-protocol.md b/docs/claude-protocol.md index cbeca8e..34e84f9 100644 --- a/docs/claude-protocol.md +++ b/docs/claude-protocol.md @@ -2,6 +2,8 @@ How `internal/claude` drives the `claude` CLI. Worked out from the Agent SDKs (`@anthropic-ai/claude-agent-sdk` on npm, `claude-agent-sdk` on PyPI); the Python SDK's `_internal/query.py` and `_internal/transport/subprocess_cli.py` are the most readable references. The CLI version the tests last passed against is in the `system`/`init` event of any transcript under `internal/claude/testdata/transcripts/` (`claude_code_version`). +Transcripts (`Options.Transcript`) record every line in both directions as `{"dir":"send"|"recv","msg":...}`. The account email from the `initialize` response is replaced with `[redacted]` everywhere it appears. + ## Launch ``` diff --git a/docs/operations.md b/docs/operations.md new file mode 100644 index 0000000..123e53d --- /dev/null +++ b/docs/operations.md @@ -0,0 +1,45 @@ +# 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. +- `internal/git`: worktree create and remove. +- `web/`: the SPA, embedded into the binary. `byre serve --dev` serves `./web` from disk instead (run from the repo root). + +## Data + +State lives in the `byre` directory under Go's `os.UserConfigDir()` (on macOS, `~/Library/Application Support/byre`): `byre.db` and `worktrees//`. Task branches are `byre/` in the project's repo. + +## Running as a service + +The listen address is `listenAddr` in `cmd/byre/serve.go`; it binds loopback only. + +``` +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= http:// +``` + +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. + +## 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:///api/me +``` + +## 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. A client that falls further behind than its subscriber buffer (`subscribe` in `internal/server/hub.go`) is disconnected and catches up by reconnecting. diff --git a/go.mod b/go.mod index 0532932..259b40d 100644 --- a/go.mod +++ b/go.mod @@ -1,3 +1,37 @@ module g.fc.run/misc/byre -go 1.26 +go 1.26.0 + +require ( + github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect + github.com/dprotaso/go-yit v0.0.0-20220510233725-9ba8df137936 // indirect + github.com/dustin/go-humanize v1.0.1 // indirect + github.com/getkin/kin-openapi v0.142.0 // indirect + github.com/go-openapi/jsonpointer v0.23.1 // indirect + github.com/go-openapi/swag/jsonname v0.26.0 // indirect + github.com/google/uuid v1.6.0 // indirect + github.com/mattn/go-isatty v0.0.24 // indirect + github.com/ncruces/go-strftime v1.0.0 // indirect + github.com/oapi-codegen/oapi-codegen/v2 v2.8.0 // indirect + github.com/oapi-codegen/runtime v1.7.0 // indirect + github.com/oasdiff/yaml v0.1.1 // indirect + github.com/oasdiff/yaml3 v0.0.14 // indirect + github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect + github.com/santhosh-tekuri/jsonschema/v6 v6.0.2 // indirect + github.com/speakeasy-api/jsonpath v0.6.3 // indirect + github.com/speakeasy-api/openapi v1.24.0 // indirect + github.com/vmware-labs/yaml-jsonpath v0.3.2 // indirect + go.yaml.in/yaml/v3 v3.0.4 // indirect + golang.org/x/mod v0.41.0 // indirect + golang.org/x/sync v0.23.0 // indirect + golang.org/x/sys v0.48.0 // indirect + golang.org/x/text v0.40.0 // indirect + golang.org/x/tools v0.50.0 // indirect + gopkg.in/yaml.v3 v3.0.1 // indirect + modernc.org/libc v1.77.1 // indirect + modernc.org/mathutil v1.7.1 // indirect + modernc.org/memory v1.12.1 // indirect + modernc.org/sqlite v1.60.1 // indirect +) + +tool github.com/oapi-codegen/oapi-codegen/v2/cmd/oapi-codegen diff --git a/go.sum b/go.sum new file mode 100644 index 0000000..0cc5f0f --- /dev/null +++ b/go.sum @@ -0,0 +1,169 @@ +github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk= +github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ= +github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk= +github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w= +github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI= +github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI= +github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/dprotaso/go-yit v0.0.0-20191028211022-135eb7262960/go.mod h1:9HQzr9D/0PGwMEbC3d5AB7oi67+h4TsQqItC1GVYG58= +github.com/dprotaso/go-yit v0.0.0-20220510233725-9ba8df137936 h1:PRxIJD8XjimM5aTknUK9w6DHLDox2r2M3DI4i2pnd3w= +github.com/dprotaso/go-yit v0.0.0-20220510233725-9ba8df137936/go.mod h1:ttYvX5qlB+mlV1okblJqcSMtR4c52UKxDiX9GRBS8+Q= +github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY= +github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto= +github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo= +github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ= +github.com/getkin/kin-openapi v0.142.0 h1:izj0vBdFprMhitfzaX8sTqztsEQyvwhssBoB6n8NO7w= +github.com/getkin/kin-openapi v0.142.0/go.mod h1:3BH9M9XDe/y9M5DSvEocVYAYq1w0qrhJHjC/vZi0AaY= +github.com/go-openapi/jsonpointer v0.23.1 h1:1HBACs7XIwR2RcmItfdSFlALhGbe6S92p0ry4d1GWg4= +github.com/go-openapi/jsonpointer v0.23.1/go.mod h1:iWRmZTrGn7XwYhtPt/fvdSFj1OfNBngqRT2UG3BxSqY= +github.com/go-openapi/swag/jsonname v0.26.0 h1:gV1NFX9M8avo0YSpmWogqfQISigCmpaiNci8cGECU5w= +github.com/go-openapi/swag/jsonname v0.26.0/go.mod h1:urBBR8bZNoDYGr653ynhIx+gTeIz0ARZxHkAPktJK2M= +github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE= +github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= +github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8= +github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA= +github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs= +github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w= +github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0= +github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI= +github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk= +github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY= +github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= +github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU= +github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= +github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE= +github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= +github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= +github.com/hpcloud/tail v1.0.0/go.mod h1:ab1qPbhIpdTxEkNHXyeSf5vhxWSCs/tWer42PpOxQnU= +github.com/ianlancetaylor/demangle v0.0.0-20200824232613-28f6c0f3b639/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc= +github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE= +github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= +github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= +github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= +github.com/mattn/go-isatty v0.0.24 h1:tGZZoVgT/KiqK1c8ocVLeDS8BSWMRd47J3Lbz7vsReI= +github.com/mattn/go-isatty v0.0.24/go.mod h1:nMCL3Zebbrt45jsMDgnfIwz6ydEQApk5oEI3HqDio6A= +github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w= +github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls= +github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A= +github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU= +github.com/oapi-codegen/oapi-codegen/v2 v2.8.0 h1:s4hxMxuqtR8jPzXkBTtFwY/SBuj3gEAYikmbBSdtLMM= +github.com/oapi-codegen/oapi-codegen/v2 v2.8.0/go.mod h1:yae2TI9IYB5vxQ35gFrpXh9L5H1eJv4MAUK1jumGMTo= +github.com/oapi-codegen/runtime v1.7.0 h1:t7358VYPvNbWJ9gdAkIK/smVeHpBf6yp8VTsaZsb/7k= +github.com/oapi-codegen/runtime v1.7.0/go.mod h1:GwV7hC2hviaMzj+ITfHVRESK5J2W/GefVwIND/bMGvU= +github.com/oasdiff/yaml v0.1.1 h1:6nHx+pn9gBRM6YpBlFZFQGCCd1nuvqOBtTD3KKTgGxY= +github.com/oasdiff/yaml v0.1.1/go.mod h1:EYJNoyktvWMJ0Hmhx+6qTaqMOsalUaRGT8Sj1hNcegU= +github.com/oasdiff/yaml3 v0.0.14 h1:aLJee3hxBK2H5wdXd9iPcIXb93Nty1Ge0pT171eHtkw= +github.com/oasdiff/yaml3 v0.0.14/go.mod h1:csto2xfDjYccdUn/yw/bPjj/cYTdp6HtFA0J4TWG+gg= +github.com/onsi/ginkgo v1.6.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE= +github.com/onsi/ginkgo v1.10.2/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE= +github.com/onsi/ginkgo v1.12.1/go.mod h1:zj2OWP4+oCPe1qIXoGWkgMRwljMUYCdkwsT2108oapk= +github.com/onsi/ginkgo v1.16.4/go.mod h1:dX+/inL/fNMqNlz0e9LfyB9TswhZpCVdJM/Z6Vvnwo0= +github.com/onsi/ginkgo/v2 v2.1.3/go.mod h1:vw5CSIxN1JObi/U8gcbwft7ZxR2dgaR70JSE3/PpL4c= +github.com/onsi/gomega v1.7.0/go.mod h1:ex+gbHU/CVuBBDIJjb2X0qEXbFg53c61hWP/1CpauHY= +github.com/onsi/gomega v1.7.1/go.mod h1:XdKZgCCFLUoM/7CFJVPcG8C1xQ1AJ0vpAezJrB7JYyY= +github.com/onsi/gomega v1.10.1/go.mod h1:iN09h71vgCQne3DLsj+A5owkum+a2tYe+TOCB1ybHNo= +github.com/onsi/gomega v1.17.0/go.mod h1:HnhC7FXeEQY45zxNK3PPoIUhzk/80Xly9PcubAlGdZY= +github.com/onsi/gomega v1.19.0/go.mod h1:LY+I3pBVzYsTBU1AnDwOSxaYi9WoWiqgwooUqq9yPro= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE= +github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo= +github.com/santhosh-tekuri/jsonschema/v6 v6.0.2 h1:KRzFb2m7YtdldCEkzs6KqmJw4nqEVZGK7IN2kJkjTuQ= +github.com/santhosh-tekuri/jsonschema/v6 v6.0.2/go.mod h1:JXeL+ps8p7/KNMjDQk3TCwPpBy0wYklyWTfbkIzdIFU= +github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM= +github.com/speakeasy-api/jsonpath v0.6.3 h1:c+QPwzAOdrWvzycuc9HFsIZcxKIaWcNpC+xhOW9rJxU= +github.com/speakeasy-api/jsonpath v0.6.3/go.mod h1:2cXloNuQ+RSXi5HTRaeBh7JEmjRXTiaKpFTdZiL7URI= +github.com/speakeasy-api/openapi v1.24.0 h1:opoD27rupX7zBVPq1HkIGLeMOzNNA7JalhYP8q34i04= +github.com/speakeasy-api/openapi v1.24.0/go.mod h1:g3+dIMe0AYgbbGvnlQZqesmjAVWSm9BmsjLevnefQrg= +github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= +github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= +github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA= +github.com/vmware-labs/yaml-jsonpath v0.3.2 h1:/5QKeCBGdsInyDCyVNLbXyilb61MXGi9NP674f9Hobk= +github.com/vmware-labs/yaml-jsonpath v0.3.2/go.mod h1:U6whw1z03QyqgWdgXxvVnQ90zN1BWz5V+51Ewf8k+rQ= +github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74= +go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc= +go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI= +golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= +golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA= +golang.org/x/mod v0.41.0 h1:qJmnOUb4YB+FsEuM3HcWucdZASCPGhsX6uljO6pog0c= +golang.org/x/mod v0.41.0/go.mod h1:Ek9pY8RKWXwsWvd3rQiHYtMqkjSUV+s1Rj7j4H5Ur6o= +golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= +golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= +golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20200520004742-59133d7f0dd7/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A= +golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU= +golang.org/x/net v0.0.0-20210428140749-89ef3d95e781/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk= +golang.org/x/net v0.0.0-20220225172249-27dd8689420f/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk= +golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.23.0 h1:KameEIfc1IkluZyXWLn39Wd4tURc6GbCiISGiZm2bQk= +golang.org/x/sync v0.23.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0= +golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20190904154756-749cb33beabd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20191005200804-aed5e4c7ecf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20191120155948-bd437916bb0e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210112080510-489259a85091/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20211216021012-1d35b9e2eb4e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo= +golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs= +golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= +golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA= +golang.org/x/tools v0.50.0 h1:c2ifzfcuY7L90lZ2aKd8S4K2NpASF08SZx9ZuJkHmSU= +golang.org/x/tools v0.50.0/go.mod h1:7ulVMw3831Mwi5EZD6RomGyffr4VFjuNYXf2BbCEAV0= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8= +google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0= +google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM= +google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE= +google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo= +google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU= +google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw= +google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/fsnotify.v1 v1.4.7/go.mod h1:Tz8NjZHkW78fSQdbUxIjBTcgA1z1m8ZHf0WmKUhAMys= +gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw= +gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= +gopkg.in/yaml.v3 v3.0.0-20191026110619-0b21df46bc1d/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= +gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +modernc.org/libc v1.77.1 h1:Ct8j47QtiZ1Enj2DtFXQtUqrPCAjdCmPjtCuvrYQ0Hs= +modernc.org/libc v1.77.1/go.mod h1:87/pZ4L6nD1zqW4nItuS12YO7hN1igAah34xjnQo/W0= +modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU= +modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg= +modernc.org/memory v1.12.1 h1:nFMiWrpStgZczNl6XI9GnIk/rWhYIyHGUaR04pGbp9g= +modernc.org/memory v1.12.1/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw= +modernc.org/sqlite v1.60.1 h1:/blz53O951KWFOso4QQvEs/Fq6cDBKLtMVrYNSeJVKw= +modernc.org/sqlite v1.60.1/go.mod h1:1dIoEagfDE72QytD5scH1lxARtaUgKgHC/NuApA27r0= diff --git a/internal/api/api.gen.go b/internal/api/api.gen.go new file mode 100644 index 0000000..e4dc84d --- /dev/null +++ b/internal/api/api.gen.go @@ -0,0 +1,688 @@ +//go:build go1.22 + +// Package api provides primitives to interact with the openapi HTTP API. +// +// Code generated by github.com/oapi-codegen/oapi-codegen/v2 version v2.8.0 DO NOT EDIT. +package api + +import ( + "bytes" + "compress/flate" + "encoding/base64" + "errors" + "fmt" + "net/http" + "net/url" + "path" + "strings" + "time" + + "github.com/getkin/kin-openapi/openapi3" + "github.com/oapi-codegen/runtime" +) + +// Defines values for TaskStatus. +const ( + Active TaskStatus = "active" + Completed TaskStatus = "completed" +) + +// Valid indicates whether the value is a known member of the TaskStatus enum. +func (e TaskStatus) Valid() bool { + switch e { + case Active: + return true + case Completed: + return true + default: + return false + } +} + +// Error defines model for Error. +type Error struct { + Message string `json:"message"` +} + +// Event defines model for Event. +type Event struct { + Actor string `json:"actor"` + CreatedAt time.Time `json:"created_at"` + Kind string `json:"kind"` + Payload map[string]interface{} `json:"payload"` + ProjectId *string `json:"project_id,omitempty"` + Seq int64 `json:"seq"` + TaskId *string `json:"task_id,omitempty"` +} + +// Project defines model for Project. +type Project struct { + CreatedAt time.Time `json:"created_at"` + CreatedBy string `json:"created_by"` + DefaultBranch string `json:"default_branch"` + Id string `json:"id"` + Name string `json:"name"` + Remote string `json:"remote"` + RepoPath string `json:"repo_path"` +} + +// ProjectCreate defines model for ProjectCreate. +type ProjectCreate struct { + Name string `json:"name"` + RepoPath string `json:"repo_path"` +} + +// Status defines model for Status. +type Status struct { + ActiveTasks int `json:"active_tasks"` + DbBytes int64 `json:"db_bytes"` + LastEventSeq int64 `json:"last_event_seq"` + Projects int `json:"projects"` + SseClients int `json:"sse_clients"` + StartedAt time.Time `json:"started_at"` +} + +// Task defines model for Task. +type Task struct { + BaseRef string `json:"base_ref"` + Branch string `json:"branch"` + CompletedAt *time.Time `json:"completed_at,omitempty"` + CreatedAt time.Time `json:"created_at"` + CreatedBy string `json:"created_by"` + Id string `json:"id"` + ProjectId string `json:"project_id"` + Status TaskStatus `json:"status"` + Title string `json:"title"` + WorktreePath string `json:"worktree_path"` +} + +// TaskStatus defines model for Task.Status. +type TaskStatus string + +// TaskCreate defines model for TaskCreate. +type TaskCreate struct { + Title string `json:"title"` +} + +// User defines model for User. +type User struct { + DisplayName string `json:"display_name"` + GitEmail string `json:"git_email"` + GitName string `json:"git_name"` + Login string `json:"login"` +} + +// UserUpdate defines model for UserUpdate. +type UserUpdate struct { + GitEmail string `json:"git_email"` + GitName string `json:"git_name"` +} + +// StreamEventsParams defines parameters for StreamEvents. +type StreamEventsParams struct { + After *int64 `form:"after,omitempty" json:"after,omitempty"` + LastEventID *int64 `json:"Last-Event-ID,omitempty"` +} + +// UpdateMeJSONRequestBody defines body for UpdateMe for application/json ContentType. +type UpdateMeJSONRequestBody = UserUpdate + +// CreateProjectJSONRequestBody defines body for CreateProject for application/json ContentType. +type CreateProjectJSONRequestBody = ProjectCreate + +// CreateTaskJSONRequestBody defines body for CreateTask for application/json ContentType. +type CreateTaskJSONRequestBody = TaskCreate + +// ServerInterface represents all server handlers. +type ServerInterface interface { + + // (GET /api/admin/status) + GetStatus(w http.ResponseWriter, r *http.Request) + + // (GET /api/events) + StreamEvents(w http.ResponseWriter, r *http.Request, params StreamEventsParams) + + // (GET /api/me) + GetMe(w http.ResponseWriter, r *http.Request) + + // (PUT /api/me) + UpdateMe(w http.ResponseWriter, r *http.Request) + + // (GET /api/projects) + ListProjects(w http.ResponseWriter, r *http.Request) + + // (POST /api/projects) + CreateProject(w http.ResponseWriter, r *http.Request) + + // (GET /api/projects/{projectId}) + GetProject(w http.ResponseWriter, r *http.Request, projectId string) + + // (GET /api/projects/{projectId}/tasks) + ListTasks(w http.ResponseWriter, r *http.Request, projectId string) + + // (POST /api/projects/{projectId}/tasks) + CreateTask(w http.ResponseWriter, r *http.Request, projectId string) + + // (GET /api/tasks/{taskId}) + GetTask(w http.ResponseWriter, r *http.Request, taskId string) + + // (POST /api/tasks/{taskId}/complete) + CompleteTask(w http.ResponseWriter, r *http.Request, taskId string) +} + +// ServerInterfaceWrapper converts contexts to parameters. +type ServerInterfaceWrapper struct { + Handler ServerInterface + HandlerMiddlewares []MiddlewareFunc + ErrorHandlerFunc func(w http.ResponseWriter, r *http.Request, err error) +} + +type MiddlewareFunc func(http.Handler) http.Handler + +// GetStatus operation middleware +func (siw *ServerInterfaceWrapper) GetStatus(w http.ResponseWriter, r *http.Request) { + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.GetStatus(w, r) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// StreamEvents operation middleware +func (siw *ServerInterfaceWrapper) StreamEvents(w http.ResponseWriter, r *http.Request) { + + var err error + _ = err + + // Parameter object where we will unmarshal all parameters from the context + var params StreamEventsParams + + // ------------- Optional query parameter "after" ------------- + + err = runtime.BindQueryParameterWithOptions("form", true, false, "after", r.URL.Query(), ¶ms.After, runtime.BindQueryParameterOptions{Type: "integer", Format: "int64"}) + if err != nil { + var requiredError *runtime.RequiredParameterError + if errors.As(err, &requiredError) { + siw.ErrorHandlerFunc(w, r, &RequiredParamError{ParamName: "after"}) + } else { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "after", Err: err}) + } + return + } + + headers := r.Header + + // ------------- Optional header parameter "Last-Event-ID" ------------- + if valueList, found := headers[http.CanonicalHeaderKey("Last-Event-ID")]; found { + var LastEventID int64 + n := len(valueList) + if n != 1 { + siw.ErrorHandlerFunc(w, r, &TooManyValuesForParamError{ParamName: "Last-Event-ID", Count: n}) + return + } + + err = runtime.BindStyledParameterWithOptions("simple", "Last-Event-ID", valueList[0], &LastEventID, runtime.BindStyledParameterOptions{ParamLocation: runtime.ParamLocationHeader, Explode: false, Required: false, Type: "integer", Format: "int64"}) + if err != nil { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "Last-Event-ID", Err: err}) + return + } + + params.LastEventID = &LastEventID + + } + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.StreamEvents(w, r, params) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// GetMe operation middleware +func (siw *ServerInterfaceWrapper) GetMe(w http.ResponseWriter, r *http.Request) { + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.GetMe(w, r) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// UpdateMe operation middleware +func (siw *ServerInterfaceWrapper) UpdateMe(w http.ResponseWriter, r *http.Request) { + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.UpdateMe(w, r) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// ListProjects operation middleware +func (siw *ServerInterfaceWrapper) ListProjects(w http.ResponseWriter, r *http.Request) { + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.ListProjects(w, r) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// CreateProject operation middleware +func (siw *ServerInterfaceWrapper) CreateProject(w http.ResponseWriter, r *http.Request) { + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.CreateProject(w, r) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// GetProject operation middleware +func (siw *ServerInterfaceWrapper) GetProject(w http.ResponseWriter, r *http.Request) { + + var err error + _ = err + + // ------------- Path parameter "projectId" ------------- + var projectId string + + err = runtime.BindStyledParameterWithOptions("simple", "projectId", r.PathValue("projectId"), &projectId, runtime.BindStyledParameterOptions{ParamLocation: runtime.ParamLocationPath, Explode: false, Required: true, Type: "string", Format: "", ValueIsUnescaped: true}) + if err != nil { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "projectId", Err: err}) + return + } + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.GetProject(w, r, projectId) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// ListTasks operation middleware +func (siw *ServerInterfaceWrapper) ListTasks(w http.ResponseWriter, r *http.Request) { + + var err error + _ = err + + // ------------- Path parameter "projectId" ------------- + var projectId string + + err = runtime.BindStyledParameterWithOptions("simple", "projectId", r.PathValue("projectId"), &projectId, runtime.BindStyledParameterOptions{ParamLocation: runtime.ParamLocationPath, Explode: false, Required: true, Type: "string", Format: "", ValueIsUnescaped: true}) + if err != nil { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "projectId", Err: err}) + return + } + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.ListTasks(w, r, projectId) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// CreateTask operation middleware +func (siw *ServerInterfaceWrapper) CreateTask(w http.ResponseWriter, r *http.Request) { + + var err error + _ = err + + // ------------- Path parameter "projectId" ------------- + var projectId string + + err = runtime.BindStyledParameterWithOptions("simple", "projectId", r.PathValue("projectId"), &projectId, runtime.BindStyledParameterOptions{ParamLocation: runtime.ParamLocationPath, Explode: false, Required: true, Type: "string", Format: "", ValueIsUnescaped: true}) + if err != nil { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "projectId", Err: err}) + return + } + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.CreateTask(w, r, projectId) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// GetTask operation middleware +func (siw *ServerInterfaceWrapper) GetTask(w http.ResponseWriter, r *http.Request) { + + var err error + _ = err + + // ------------- Path parameter "taskId" ------------- + var taskId string + + err = runtime.BindStyledParameterWithOptions("simple", "taskId", r.PathValue("taskId"), &taskId, runtime.BindStyledParameterOptions{ParamLocation: runtime.ParamLocationPath, Explode: false, Required: true, Type: "string", Format: "", ValueIsUnescaped: true}) + if err != nil { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "taskId", Err: err}) + return + } + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.GetTask(w, r, taskId) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +// CompleteTask operation middleware +func (siw *ServerInterfaceWrapper) CompleteTask(w http.ResponseWriter, r *http.Request) { + + var err error + _ = err + + // ------------- Path parameter "taskId" ------------- + var taskId string + + err = runtime.BindStyledParameterWithOptions("simple", "taskId", r.PathValue("taskId"), &taskId, runtime.BindStyledParameterOptions{ParamLocation: runtime.ParamLocationPath, Explode: false, Required: true, Type: "string", Format: "", ValueIsUnescaped: true}) + if err != nil { + siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "taskId", Err: err}) + return + } + + handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + siw.Handler.CompleteTask(w, r, taskId) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + +type UnescapedCookieParamError struct { + ParamName string + Err error +} + +func (e *UnescapedCookieParamError) Error() string { + return fmt.Sprintf("error unescaping cookie parameter '%s'", e.ParamName) +} + +func (e *UnescapedCookieParamError) Unwrap() error { + return e.Err +} + +type UnmarshalingParamError struct { + ParamName string + Err error +} + +func (e *UnmarshalingParamError) Error() string { + return fmt.Sprintf("Error unmarshaling parameter %s as JSON: %s", e.ParamName, e.Err.Error()) +} + +func (e *UnmarshalingParamError) Unwrap() error { + return e.Err +} + +type RequiredParamError struct { + ParamName string +} + +func (e *RequiredParamError) Error() string { + return fmt.Sprintf("Query argument %s is required, but not found", e.ParamName) +} + +type RequiredHeaderError struct { + ParamName string + Err error +} + +func (e *RequiredHeaderError) Error() string { + return fmt.Sprintf("Header parameter %s is required, but not found", e.ParamName) +} + +func (e *RequiredHeaderError) Unwrap() error { + return e.Err +} + +type InvalidParamFormatError struct { + ParamName string + Err error +} + +func (e *InvalidParamFormatError) Error() string { + return fmt.Sprintf("Invalid format for parameter %s: %s", e.ParamName, e.Err.Error()) +} + +func (e *InvalidParamFormatError) Unwrap() error { + return e.Err +} + +type TooManyValuesForParamError struct { + ParamName string + Count int +} + +func (e *TooManyValuesForParamError) Error() string { + return fmt.Sprintf("Expected one value for %s, got %d", e.ParamName, e.Count) +} + +// Handler creates http.Handler with routing matching OpenAPI spec. +func Handler(si ServerInterface) http.Handler { + return HandlerWithOptions(si, StdHTTPServerOptions{}) +} + +// ServeMux is an abstraction of [http.ServeMux]. +type ServeMux interface { + HandleFunc(pattern string, handler func(http.ResponseWriter, *http.Request)) + http.Handler +} + +type StdHTTPServerOptions struct { + BaseURL string + BaseRouter ServeMux + Middlewares []MiddlewareFunc + ErrorHandlerFunc func(w http.ResponseWriter, r *http.Request, err error) +} + +// HandlerFromMux creates http.Handler with routing matching OpenAPI spec based on the provided mux. +func HandlerFromMux(si ServerInterface, m ServeMux) http.Handler { + return HandlerWithOptions(si, StdHTTPServerOptions{ + BaseRouter: m, + }) +} + +func HandlerFromMuxWithBaseURL(si ServerInterface, m ServeMux, baseURL string) http.Handler { + return HandlerWithOptions(si, StdHTTPServerOptions{ + BaseURL: baseURL, + BaseRouter: m, + }) +} + +// HandlerWithOptions creates http.Handler with additional options +func HandlerWithOptions(si ServerInterface, options StdHTTPServerOptions) http.Handler { + m := options.BaseRouter + + if m == nil { + m = http.NewServeMux() + } + if options.ErrorHandlerFunc == nil { + options.ErrorHandlerFunc = func(w http.ResponseWriter, r *http.Request, err error) { + http.Error(w, err.Error(), http.StatusBadRequest) + } + } + + wrapper := ServerInterfaceWrapper{ + Handler: si, + HandlerMiddlewares: options.Middlewares, + ErrorHandlerFunc: options.ErrorHandlerFunc, + } + + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/me", wrapper.GetMe) + m.HandleFunc(http.MethodPut+" "+options.BaseURL+"/api/me", wrapper.UpdateMe) + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/projects", wrapper.ListProjects) + m.HandleFunc(http.MethodPost+" "+options.BaseURL+"/api/projects", wrapper.CreateProject) + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/projects/{projectId}", wrapper.GetProject) + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/projects/{projectId}/tasks", wrapper.ListTasks) + m.HandleFunc(http.MethodPost+" "+options.BaseURL+"/api/projects/{projectId}/tasks", wrapper.CreateTask) + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/tasks/{taskId}", wrapper.GetTask) + m.HandleFunc(http.MethodPost+" "+options.BaseURL+"/api/tasks/{taskId}/complete", wrapper.CompleteTask) + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/events", wrapper.StreamEvents) + m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/admin/status", wrapper.GetStatus) + + return m +} + +// Base64 encoded, compressed with deflate, json marshaled OpenAPI spec. +// Stored as a slice of fixed-width chunks rather than one concatenated +// const string: with thousands of chunks the chained `+` fold is several +// times slower for the Go compiler than parsing a slice literal. +var swaggerSpec = []string{ + "zFhbb+M2E/0rBL8PSAsottsNCtR96iUoUmzbRZN92gYCLY1tbiRSGY69NQL994KkrjblS2p3+xRZJIdn", + "Ds8ZDfPCE50XWoEiw6cvHMEUWhlwP24RNdqHRCsCRfZRFEUmE0FSq/FHo5V9Z5Il5MI+/R9hzqf8f+M2", + "6tiPmrGPVpZlxFMwCcrCBuFTv82I24Fqbm/zAnUBSNJjysEYsQD7SJsC+JQbQqkWbjnC80oipHz6oZn4", + "GNUT9ewjJMTLiN+uq2z6sUVCfsutyBFPEARBGgu3aq4xt088FQTXJHPg0e6aJ6nSYLBCbDItumMtsgK1", + "fYxleKmB5x4Aqeibm3ZzqQgWgHYmCfMUjrLFkw1ZgY0qBlqIvcxDTL7zeHe5fA1j9ZrZJph8CnOxyiie", + "oVDJMjhlgDYlcggOIOSahoYKHReClocplJYot0d32Q7gZrtepsdS/KObtUv0ntyOTmAHewjHPQlamaBr", + "5BpiKzjT2aqjxXQWzzbkZx8h3UwYisFaND5e75VxBhAYA3GSybrKBSaQwNPkum2jNkAn4Z1kOkCjPnN9", + "kKEDeBDmaZf+mTAQu7Ib0MAeq9gKncFrLXpGWw949lAlbNQIapXbE/Bs8k5mHRbbhSQpCxvmk8YnQoBT", + "XN9BWYduWN+OGLVn1eA/rRRYBQzVgaG8tlD7aaHg7w0EvrepNEUmNvFgmVlIiiEXMhscHVya6YVUhyH7", + "aVEfSid0F8NQYu+LNMjaq9FvYTwSjF0m1Vx3DozPNmiXrQGN74cmo8loYrfXBShRSD7lb0aT0Rv3Xaal", + "wz0WhRyLNJdq3DphAc6VNj/XoN2lfMp/Brqvtdbr7r6eTM7W21U7BJq7e8A1IFuCyGjJhErZyrZltt2z", + "k10erjx2MwiFuDagiPmpI3YrkqX/cWWYTJk0TJJhBp6/Y6kgYV/QEpjr9Jgw7Jf7338b+Z+GiTkBsrfC", + "0LV7c333E/tCo1vhx55XgBtWCBQ5EOCXTCAwBKs/SNkM5hqBZXINNaI/rUL7zN8Tgsj9lu7sqmCGTz+8", + "cKt8vgSRAtbdw5T3IPGow/7BT2AZVTEd9Daky+fEUI8HpULwF/lzuzYuzb5Wts2y2/O7c/FLe1rwZhtS", + "8q9wSRW7ChgA+7AElogsk2rBVgbcXcV+oVYBkL7QVDifV2DoB51uzgqxqmVlvwYRrqD8TOSsHKK0Jifi", + "N37jULwGYHshrM++28MFFfBWGnrX9k//KFdJkJtDSdfXm7IxiUAUmxAP32cZqxOoBaJNIAn/Aa8jX0Ym", + "/TvDUUr56tybD4lFwaeaqDNoZfxSPd2l5b7K0eX7Qg45kHc/55sTcg5/O6qesirzDQt8+6ijPXX5cR+d", + "4+ZKN2jGh+rqcnknusvPETbsMH1lmMsgspIDQ2wu0fzH+G+LRD8N71zfw9gkrgzztwrXQtX3CjZHnbs5", + "bcrVPx2q6aOdrsRHdnRepvZ0Lin/cuHxGhmuOpbIk0vOqWKpHeWkN36xfw6UpuYsLlSX9tHSoeTcjvCZ", + "v64c9ckb1zd6d3+7yMZDPvwDcr3u+7Axn3Vi5TL20I4jJBpTN+rvBgztdVAFrFil9TkF0Pyz5HVSsLO/", + "PcUdZfl3AAAA//8=", +} + +// decodeSpec returns the embedded OpenAPI spec as raw JSON bytes, +// after base64-decoding and flate-decompressing the embedded blob. +func decodeSpec() ([]byte, error) { + encoded := strings.Join(swaggerSpec, "") + compressed, err := base64.StdEncoding.DecodeString(encoded) + if err != nil { + return nil, fmt.Errorf("error base64 decoding spec: %w", err) + } + zr := flate.NewReader(bytes.NewReader(compressed)) + var buf bytes.Buffer + if _, err := buf.ReadFrom(zr); err != nil { + return nil, fmt.Errorf("read flate: %w", err) + } + if err := zr.Close(); err != nil { + return nil, fmt.Errorf("close flate reader: %w", err) + } + + return buf.Bytes(), nil +} + +var rawSpec = decodeSpecCached() + +// a naive cache of the decoded OpenAPI spec +func decodeSpecCached() func() ([]byte, error) { + data, err := decodeSpec() + return func() ([]byte, error) { + return data, err + } +} + +// Constructs a synthetic filesystem for resolving external references when loading openapi specifications. +func PathToRawSpec(pathToFile string) map[string]func() ([]byte, error) { + res := make(map[string]func() ([]byte, error)) + if len(pathToFile) > 0 { + res[pathToFile] = rawSpec + } + + return res +} + +// GetSpec returns the OpenAPI specification corresponding to the generated +// code in this file. External references in the spec are resolved through +// PathToRawSpec; externally-referenced files must be embedded in their +// corresponding Go packages (via the import-mapping feature). URL-based +// external refs are not supported. +func GetSpec() (swagger *openapi3.T, err error) { + resolvePath := PathToRawSpec("") + + loader := openapi3.NewLoader() + loader.IsExternalRefsAllowed = true + loader.ReadFromURIFunc = func(loader *openapi3.Loader, url *url.URL) ([]byte, error) { + pathToFile := url.String() + pathToFile = path.Clean(pathToFile) + getSpec, ok := resolvePath[pathToFile] + if !ok { + err1 := fmt.Errorf("path not found: %s", pathToFile) + return nil, err1 + } + return getSpec() + } + var specData []byte + specData, err = rawSpec() + if err != nil { + return + } + swagger, err = loader.LoadFromData(specData) + if err != nil { + return + } + return +} + +// GetSpecJSON returns the raw JSON bytes of the embedded OpenAPI +// specification: decompressed but not unmarshaled. External references +// are not resolved here; the bytes are the spec exactly as embedded by +// codegen. The result is cached at package init time, so repeated calls +// are cheap. +func GetSpecJSON() ([]byte, error) { + return rawSpec() +} + +// GetSwagger returns the OpenAPI specification corresponding to the +// generated code in this file. +// +// Deprecated: GetSwagger predates kin-openapi renaming openapi3.Swagger +// to openapi3.T. Use [GetSpec] instead. This wrapper is retained for +// backwards compatibility. +func GetSwagger() (*openapi3.T, error) { + return GetSpec() +} diff --git a/internal/api/generate.go b/internal/api/generate.go new file mode 100644 index 0000000..6d0ef9b --- /dev/null +++ b/internal/api/generate.go @@ -0,0 +1,3 @@ +package api + +//go:generate go tool oapi-codegen -config ../../api/oapi-codegen.yaml ../../api/openapi.yaml diff --git a/internal/claude/session.go b/internal/claude/session.go index e041974..8959aaa 100644 --- a/internal/claude/session.go +++ b/internal/claude/session.go @@ -2,6 +2,7 @@ package claude import ( "bufio" + "bytes" "context" "crypto/rand" "encoding/hex" @@ -103,6 +104,7 @@ type Session struct { writeMu sync.Mutex transcript io.Writer + scrub []byte pendingMu sync.Mutex pending map[string]chan controlResult @@ -360,6 +362,10 @@ func (s *Session) record(dir string, line []byte) { return } + if len(s.scrub) > 0 { + line = bytes.ReplaceAll(line, s.scrub, []byte("[redacted]")) + } + b, err := json.Marshal(map[string]any{"dir": dir, "msg": json.RawMessage(line)}) if err != nil { slog.Error("record transcript", "err", err) @@ -389,10 +395,6 @@ func (s *Session) readLoop(stdout io.Reader) { } func (s *Session) handleLine(line []byte) { - s.writeMu.Lock() - s.record("recv", line) - s.writeMu.Unlock() - env := envelope{} err := json.Unmarshal(line, &env) if err != nil { @@ -400,6 +402,13 @@ func (s *Session) handleLine(line []byte) { return } + s.writeMu.Lock() + if env.Type == "control_response" { + s.learnScrub(env.Response) + } + s.record("recv", line) + s.writeMu.Unlock() + switch env.Type { case "control_response": s.handleControlResponse(env.Response) @@ -422,6 +431,21 @@ func (s *Session) handleLine(line []byte) { s.events <- Event{Type: env.Type, Subtype: env.Subtype, Raw: append(json.RawMessage{}, line...)} } +func (s *Session) learnScrub(raw json.RawMessage) { + resp := struct { + Response struct { + Account struct { + Email string `json:"email"` + } `json:"account"` + } `json:"response"` + }{} + err := json.Unmarshal(raw, &resp) + if err != nil || resp.Response.Account.Email == "" { + return + } + s.scrub = []byte(resp.Response.Account.Email) +} + func (s *Session) handleControlResponse(raw json.RawMessage) { resp := struct { Subtype string `json:"subtype"` diff --git a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndReport.jsonl b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndReport.jsonl new file mode 100644 index 0000000..7dfb94f --- /dev/null +++ b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndReport.jsonl @@ -0,0 +1,50 @@ +{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_1"],"matcher":""}],"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_98b8a2871e398e28","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"ae025cfd-8d44-4af4-adf4-bf1ed76b90e5","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":"ae025cfd-8d44-4af4-adf4-bf1ed76b90e5","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_98b8a2871e398e28","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":20702,"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\".","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"9ba7332c-67f4-422a-9ee0-54b2824fec6f","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} +{"dir":"send","msg":{"response":{"request_id":"9ba7332c-67f4-422a-9ee0-54b2824fec6f","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"running","uuid":"a9b7cb42-d498-44ff-80b1-4904fc37fdf5","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"5537ba33-c058-402e-980c-46c3bb41508c","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} +{"dir":"send","msg":{"response":{"request_id":"5537ba33-c058-402e-980c-46c3bb41508c","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"report","description":"Report what you did this turn. You must call this before ending every turn. List every departure from the plan in deviations.","inputSchema":{"type":"object","properties":{"done":{"type":"array","items":{"type":"string"}},"open_questions":{"type":"array","items":{"type":"string"}},"next_steps":{"type":"array","items":{"type":"string"}},"risks":{"type":"array","items":{"type":"string"}},"deviations":{"type":"array","items":{"type":"string"}}},"required":["done"]}}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","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__report"],"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":"9973a0da-fb3a-4ff5-8d25-25d8935e291f","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","messaging_socket_path":"/tmp/cc-socks/20702.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":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1791972000,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.02,"resetsAt":1791972000},"seven_day":{"utilization":0.25,"resetsAt":1792270800}}},"uuid":"777429c5-271c-4729-8cfa-ab5ae6ac3f45","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxZaJdzCZgPmrrWZHm","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RofYKskEDoXCqQj5ZvM2EE","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001/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":15276,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15276},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"4c6ddc60-f6c9-4992-a316-cf51e476b988","timestamp":"2026-10-14T05:09:00.545Z","request_id":"req_011Cg1YxZLvA3vqGZEPqAHo9","wire_tool_inputs":{"toolu_01RofYKskEDoXCqQj5ZvM2EE":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001/hello.txt","content":"hi"}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"13ddb9a2-0189-4a8e-923a-ed67d91d5b78","request":{"subtype":"hook_callback","callback_id":"hook_1","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_01RofYKskEDoXCqQj5ZvM2EE","duration_ms":3},"tool_use_id":"toolu_01RofYKskEDoXCqQj5ZvM2EE"}}} +{"dir":"send","msg":{"response":{"request_id":"13ddb9a2-0189-4a8e-923a-ed67d91d5b78","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01RofYKskEDoXCqQj5ZvM2EE","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"b041d068-de54-4b93-b68c-30667f00cf92","timestamp":"2026-10-14T05:09:00.556Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_01RofYKskEDoXCqQj5ZvM2EE","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"95eb7c9d-72d4-4d83-a876-51715d076ce5"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":263,"estimated_tokens_delta":213,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"776b124f-0132-452c-81b4-49728596effb"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1Yxk8K7Z9zR5fGmrrCM","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":4710,"cache_read_input_tokens":37643,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4710},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"3c170738-3e73-4e8f-8c48-17cd709453f3","timestamp":"2026-10-14T05:09:03.541Z","request_id":"req_011Cg1YxjrwZj4W8VLE3TFSM","thinking_duration_ms":1750,"thinking_display":"updates"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1Yxk8K7Z9zR5fGmrrCM","type":"message","role":"assistant","content":[{"type":"text","text":"Authorizing words from the current 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":4710,"cache_read_input_tokens":37643,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4710},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"0f16d28e-8a84-444a-a65f-c30f14371ac7","timestamp":"2026-10-14T05:09:03.542Z","request_id":"req_011Cg1YxjrwZj4W8VLE3TFSM"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1Yxk8K7Z9zR5fGmrrCM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UETh9zymM3Z25G2gtpZ8eY","name":"Bash","input":{"command":"timeout 20 git add hello.txt","description":"Stage hello.txt","timeout":30000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4710,"cache_read_input_tokens":37643,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4710},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"91c3746d-c464-46b1-8269-17c710cd4734","timestamp":"2026-10-14T05:09:04.109Z","request_id":"req_011Cg1YxjrwZj4W8VLE3TFSM","wire_tool_inputs":{"toolu_01UETh9zymM3Z25G2gtpZ8eY":{"command":"timeout 20 git add hello.txt","description":"Stage hello.txt","timeout":30000}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"5b47aa5d-6e45-4a0e-9103-0a648841d3e9","request":{"subtype":"hook_callback","callback_id":"hook_1","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"timeout 20 git add hello.txt","timeout":30000,"description":"Stage hello.txt"},"tool_response":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_use_id":"toolu_01UETh9zymM3Z25G2gtpZ8eY","duration_ms":69},"tool_use_id":"toolu_01UETh9zymM3Z25G2gtpZ8eY"}}} +{"dir":"send","msg":{"response":{"request_id":"5b47aa5d-6e45-4a0e-9103-0a648841d3e9","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UETh9zymM3Z25G2gtpZ8eY","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"f53ac79f-d89e-41c1-b20d-3b08aee24bc0","timestamp":"2026-10-14T05:09:04.195Z","tool_use_result":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_result_meta":[{"id":"toolu_01UETh9zymM3Z25G2gtpZ8eY","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1Yxk8K7Z9zR5fGmrrCM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01S4TC58gdpgUUWGJSbfvyJX","name":"Bash","input":{"command":"timeout 20 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Commit hello.txt","timeout":30000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4710,"cache_read_input_tokens":37643,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4710},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"f78b1fc4-5d89-4483-a354-5029c98d2422","timestamp":"2026-10-14T05:09:04.764Z","request_id":"req_011Cg1YxjrwZj4W8VLE3TFSM","wire_tool_inputs":{"toolu_01S4TC58gdpgUUWGJSbfvyJX":{"command":"timeout 20 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Commit hello.txt","timeout":30000}}}} +{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","uuid":"074457da-3cd5-43b1-b0ca-61ad315271b4","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"cd980cc0-e6bc-488a-989e-60b3dd09972d","request":{"subtype":"hook_callback","callback_id":"hook_1","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"timeout 20 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":30000,"description":"Commit hello.txt"},"tool_response":{"stdout":"[main 96f2c03] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"96f2c03","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_01S4TC58gdpgUUWGJSbfvyJX","duration_ms":29},"tool_use_id":"toolu_01S4TC58gdpgUUWGJSbfvyJX"}}} +{"dir":"send","msg":{"response":{"request_id":"cd980cc0-e6bc-488a-989e-60b3dd09972d","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01S4TC58gdpgUUWGJSbfvyJX","type":"tool_result","content":"[main 96f2c03] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"a5afa14f-8acc-4429-9dfe-b5d332d1c671","timestamp":"2026-10-14T05:09:04.814Z","tool_use_result":{"stdout":"[main 96f2c03] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"96f2c03","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_01S4TC58gdpgUUWGJSbfvyJX","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1Yy4GiPG51kjiRqZstL","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi`, staged it with `git add`, and committed it on `main` as `96f2c03` with the message \"add hello\". I didn't push."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":612,"cache_read_input_tokens":42353,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":612},"output_tokens":57,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"3244bf8a-e0a2-4a35-baac-065aaa81e3bd","timestamp":"2026-10-14T05:09:06.214Z","request_id":"req_011Cg1Yy3y7YgPm8CoG57wjF"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"9d079fde-b5e7-40aa-9695-f65dc53e06bd","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":false,"last_assistant_message":"I created `hello.txt` containing `hi`, staged it with `git add`, and committed it on `main` as `96f2c03` with the message \"add hello\". I didn't push.","background_tasks":[],"session_crons":[]},"tool_use_id":"673307c6-9f95-4e6e-8543-8551490e5e04"}}} +{"dir":"send","msg":{"response":{"request_id":"9d079fde-b5e7-40aa-9695-f65dc53e06bd","response":{"decision":"block","reason":"You must call the report tool (mcp__byre__report) before ending your turn."},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"Stop hook feedback:\nYou must call the report tool (mcp__byre__report) before ending your turn."}]},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"937d0f48-8dd3-415a-9de2-a41ec485a47b","timestamp":"2026-10-14T05:09:06.243Z","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":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"453132b0-32b7-4bd9-a055-e0caee9bd2e3"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YyAP4tnrZQu5AnZxmb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01L1SvMbkZAEzE3ikXJU3ZGn","name":"ToolSearch","input":{"query":"select:mcp__byre__report","max_results":1},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":140,"cache_read_input_tokens":42965,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":140},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"6121ac97-b2fa-41cf-8c11-756eb8a30c96","timestamp":"2026-10-14T05:09:07.833Z","request_id":"req_011Cg1YyA9SRtxrSGnEM53NJ","wire_tool_inputs":{"toolu_01L1SvMbkZAEzE3ikXJU3ZGn":{"query":"select:mcp__byre__report","max_results":1}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"aa7df2fd-a23a-464a-8b62-67fa4abbf034","request":{"subtype":"hook_callback","callback_id":"hook_1","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"ToolSearch","tool_input":{"query":"select:mcp__byre__report","max_results":1},"tool_response":{"matches":["mcp__byre__report"],"query":"select:mcp__byre__report","total_deferred_tools":61},"tool_use_id":"toolu_01L1SvMbkZAEzE3ikXJU3ZGn","duration_ms":0},"tool_use_id":"toolu_01L1SvMbkZAEzE3ikXJU3ZGn"}}} +{"dir":"send","msg":{"response":{"request_id":"aa7df2fd-a23a-464a-8b62-67fa4abbf034","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","tool_use_id":"toolu_01L1SvMbkZAEzE3ikXJU3ZGn","content":[{"type":"tool_reference","tool_name":"mcp__byre__report"}]}]},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"2944c6c6-888d-489a-9022-e7569153a99d","timestamp":"2026-10-14T05:09:07.837Z","tool_use_result":{"matches":["mcp__byre__report"],"query":"select:mcp__byre__report","total_deferred_tools":61},"tool_result_meta":[{"id":"toolu_01L1SvMbkZAEzE3ikXJU3ZGn","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YyHEpsHmsVbcMbgcNj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BX9qUssty5pPBqLyzxqqkH","name":"mcp__byre__report","input":{"done":["Created hello.txt containing exactly 'hi' (no trailing newline)","Ran git add hello.txt","Committed with message 'add hello' as 96f2c03 on main, quoting the user's authorization beforehand"],"deviations":[],"next_steps":[],"open_questions":[],"risks":[]},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":348,"cache_read_input_tokens":43105,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":348},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"882dd6ba-e9b2-4d7e-be56-33aa2f5d2d89","timestamp":"2026-10-14T05:09:10.128Z","request_id":"req_011Cg1YyGywqBe3UiTQY4rSs","wire_tool_inputs":{"toolu_01BX9qUssty5pPBqLyzxqqkH":{"done":["Created hello.txt containing exactly 'hi' (no trailing newline)","Ran git add hello.txt","Committed with message 'add hello' as 96f2c03 on main, quoting the user's authorization beforehand"],"deviations":[],"next_steps":[],"open_questions":[],"risks":[]}},"tool_use_meta":[{"id":"toolu_01BX9qUssty5pPBqLyzxqqkH","display_name":"Report","server_display_name":"byre"}]}} +{"dir":"recv","msg":{"type":"control_request","request_id":"e1ac98ad-64cf-47ee-a833-43d9919840cc","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"report","arguments":{"done":["Created hello.txt containing exactly 'hi' (no trailing newline)","Ran git add hello.txt","Committed with message 'add hello' as 96f2c03 on main, quoting the user's authorization beforehand"],"deviations":[],"next_steps":[],"open_questions":[],"risks":[]},"_meta":{"claudecode/toolUseId":"toolu_01BX9qUssty5pPBqLyzxqqkH","progressToken":2}},"jsonrpc":"2.0","id":2}}}} +{"dir":"send","msg":{"response":{"request_id":"e1ac98ad-64cf-47ee-a833-43d9919840cc","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"report filed"}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"37cd4c12-25eb-4a07-9017-369409a56e27","request":{"subtype":"hook_callback","callback_id":"hook_1","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__report","tool_input":{"done":["Created hello.txt containing exactly 'hi' (no trailing newline)","Ran git add hello.txt","Committed with message 'add hello' as 96f2c03 on main, quoting the user's authorization beforehand"],"deviations":[],"next_steps":[],"open_questions":[],"risks":[]},"tool_response":[{"type":"text","text":"report filed"}],"tool_use_id":"toolu_01BX9qUssty5pPBqLyzxqqkH","duration_ms":7,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_01BX9qUssty5pPBqLyzxqqkH"}}} +{"dir":"send","msg":{"response":{"request_id":"37cd4c12-25eb-4a07-9017-369409a56e27","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BX9qUssty5pPBqLyzxqqkH","type":"tool_result","content":[{"type":"text","text":"report filed"}]}]},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"bd20a8cc-b1a7-4427-93fa-020cad4c0af3","timestamp":"2026-10-14T05:09:10.139Z","tool_use_result":[{"type":"text","text":"report filed"}],"tool_result_meta":[{"id":"toolu_01BX9qUssty5pPBqLyzxqqkH","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YyT3vMysCWRnMNS3wy","type":"message","role":"assistant","content":[{"type":"text","text":"I've filed the report. `hello.txt` (containing `hi`) is committed on `main` as `96f2c03` with the message \"add hello\". I didn't push it."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":257,"cache_read_input_tokens":43453,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":257},"output_tokens":54,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","uuid":"87614073-3cd4-446f-8a5b-cb177c9ed0f0","timestamp":"2026-10-14T05:09:11.448Z","request_id":"req_011Cg1YySnJP6hRxhMrP3r9L"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1791972000,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.03,"resetsAt":1791972000},"seven_day":{"utilization":0.25,"resetsAt":1792270800}}},"uuid":"0ecfbb17-7f1a-43c2-baa8-ef26c7d4e7e9","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"e0210769-e59d-4896-81a9-9b995a1a3f8f","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndReport240627930/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndReport240627930-001/8d384fe4-604e-45e3-8831-7d2ba20514a1/scratchpad","prompt_id":"04a3d878-c3d9-4df9-a92b-91cc92789b1e","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"Stop","stop_hook_active":true,"last_assistant_message":"I've filed the report. `hello.txt` (containing `hi`) is committed on `main` as `96f2c03` with the message \"add hello\". I didn't push it.","background_tasks":[],"session_crons":[]},"tool_use_id":"00a2339e-08cc-48f4-a67a-a2be6e9a3fea"}}} +{"dir":"send","msg":{"response":{"request_id":"e0210769-e59d-4896-81a9-9b995a1a3f8f","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"duration_api_ms":13859,"stop_reason":"end_turn","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1","total_cost_usd":0.1189935,"usage":{"input_tokens":12,"cache_creation_input_tokens":21343,"cache_read_input_tokens":231886,"output_tokens":1028,"output_tokens_details":{"thinking_tokens":166},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":21343,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":54,"cache_read_input_tokens":43453,"cache_creation_input_tokens":257,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":257},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1199,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001289,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":12,"outputTokens":1028,"cacheReadInputTokens":231886,"cacheCreationInputTokens":21343,"webSearchRequests":0,"costUSD":0.1188646,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":166,"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":7,"subtype":"success","api_error_status":null,"result":"I've filed the report. `hello.txt` (containing `hi`) is committed on `main` as `96f2c03` with the message \"add hello\". I didn't push it.","ttft_ms":2516,"type":"result","duration_ms":13437,"uuid":"27f7e4f1-a260-49f7-8c4b-78cfebf0bcdf","ttft_stream_ms":1619,"time_to_request_ms":27,"first_content_frame_ms":1619,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"idle","uuid":"f13cf9a0-107f-40f5-88e7-dd810466fbd4","session_id":"8d384fe4-604e-45e3-8831-7d2ba20514a1"}} diff --git a/internal/claude/testdata/transcripts/TestInterrupt.jsonl b/internal/claude/testdata/transcripts/TestInterrupt.jsonl new file mode 100644 index 0000000..0a24142 --- /dev/null +++ b/internal/claude/testdata/transcripts/TestInterrupt.jsonl @@ -0,0 +1,19 @@ +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_3a3fedd6ec4b7c53","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_3a3fedd6ec4b7c53","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":20705,"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 `sleep 120` in the foreground (not in the background), then say done.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"running","uuid":"ed62aa45-e425-4ecc-a33e-6d976ba2c91d","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt369311779/001","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","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":"855c9b3e-9758-4b81-9cca-44598091156f","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt369311779-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt369311779-001/dde05bd5-8604-47f8-9d9f-1fffd09c737f/scratchpad","messaging_socket_path":"/tmp/cc-socks/20705.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":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxZT7fhVTyxyNeMMxF","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016SBTLzZqWFWpq2qftttxUv","name":"Bash","input":{"command":"sleep 120","description":"Sleep for 120 seconds","timeout":130000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15234,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15234},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","uuid":"a1f85258-c708-4a74-bc49-509721f59430","timestamp":"2026-10-14T05:08:59.985Z","request_id":"req_011Cg1YxZDUqCHXdhhqYEvrP","wire_tool_inputs":{"toolu_016SBTLzZqWFWpq2qftttxUv":{"command":"sleep 120","description":"Sleep for 120 seconds","timeout":130000}}}} +{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_c73e86d61faa5d02","type":"control_request"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"\u003ctool_use_error\u003eBlocked: standalone sleep 120. To wait for a condition, use Monitor with an until-loop (e.g. `until \u003ccheck\u003e; do sleep 2; done`). To wait for a command you started, use run_in_background: true. Do not chain shorter sleeps to work around this block.\u003c/tool_use_error\u003e","is_error":true,"tool_use_id":"toolu_016SBTLzZqWFWpq2qftttxUv"}]},"parent_tool_use_id":null,"session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","uuid":"877ca65e-95dd-4200-bcc6-e34759fff696","timestamp":"2026-10-14T05:08:59.994Z","tool_use_result":"Error: Blocked: standalone sleep 120. To wait for a condition, use Monitor with an until-loop (e.g. `until \u003ccheck\u003e; do sleep 2; done`). To wait for a command you started, use run_in_background: true. Do not chain shorter sleeps to work around this block."}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_c73e86d61faa5d02","response":{"still_queued":[]}}}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user]"}]},"parent_tool_use_id":null,"session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","uuid":"333dc5ce-d1e2-42a4-9d58-c710ad00b147","timestamp":"2026-10-14T05:08:59.996Z"}} +{"dir":"recv","msg":{"duration_api_ms":0,"stop_reason":null,"session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","total_cost_usd":0,"usage":{"output_tokens_details":{"thinking_tokens":0},"input_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard","fallback_credit":null},"modelUsage":{},"permission_denials":[],"terminal_reason":"aborted_streaming","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=null"],"type":"result","duration_ms":1988,"uuid":"16a8c882-c6d6-4994-8e08-7c0432c91e66","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":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"idle","uuid":"56688e77-e336-4c52-8a2e-c423f4214ba4","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f"}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"running","uuid":"416d01c3-5792-4d00-b017-d32089ca5db4","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt369311779/001","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","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":"6e80a7cf-70f8-4a7d-88c7-86dd9e8879ab","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt369311779-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt369311779-001/dde05bd5-8604-47f8-9d9f-1fffd09c737f/scratchpad","messaging_socket_path":"/tmp/cc-socks/20705.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":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxhqtrnhvRSmyKpvur","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":4729,"cache_read_input_tokens":37601,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4729},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","uuid":"dc07d315-31e0-4ada-bf16-9d7856fe7a9f","timestamp":"2026-10-14T05:09:01.058Z","request_id":"req_011Cg1YxhcWPFRDhJwKEBbPp"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1791972000,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.02,"resetsAt":1791972000},"seven_day":{"utilization":0.25,"resetsAt":1792270800}}},"uuid":"6848edc6-64bb-45ed-919b-0c1fd9d0ffad","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f"}} +{"dir":"recv","msg":{"duration_api_ms":1073,"stop_reason":"end_turn","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f","total_cost_usd":0.0227201,"usage":{"input_tokens":2,"cache_creation_input_tokens":4729,"cache_read_input_tokens":37601,"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":4729,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37601,"cache_creation_input_tokens":4729,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4729},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":37601,"cacheCreationInputTokens":4729,"webSearchRequests":0,"costUSD":0.0227201,"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":1059,"type":"result","duration_ms":1084,"uuid":"e8386d79-0b5b-40a3-97f0-20abba6f276e","ttft_stream_ms":1058,"time_to_request_ms":9,"first_content_frame_ms":1058,"queued_turn_count":0,"result_index":1}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"idle","uuid":"80c5820a-db09-45d6-90bd-b5cc42334270","session_id":"dde05bd5-8604-47f8-9d9f-1fffd09c737f"}} diff --git a/internal/claude/testdata/transcripts/TestResume-first.jsonl b/internal/claude/testdata/transcripts/TestResume-first.jsonl new file mode 100644 index 0000000..e269694 --- /dev/null +++ b/internal/claude/testdata/transcripts/TestResume-first.jsonl @@ -0,0 +1,9 @@ +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_2e1e7fbfc7b225a0","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_2e1e7fbfc7b225a0","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":20704,"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":"session_state_changed","state":"running","uuid":"49cd1727-99d0-4dda-b7a3-797c6f86b978","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume1396538453/001","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8","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":"c0d396fd-bbe2-468d-94a1-6f8eb0ff86c4","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1396538453-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1396538453-001/d366bb85-9f42-4580-aaef-61fa39016ea8/scratchpad","messaging_socket_path":"/tmp/cc-socks/20704.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":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1791972000,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.02,"resetsAt":1791972000},"seven_day":{"utilization":0.25,"resetsAt":1792270800}}},"uuid":"68b580b7-0908-4fcd-9a9a-4c12b5f0a8b1","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxZZpG1s6QijmxRX2R","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":15222,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15222},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8","uuid":"309da350-4e7a-4f4a-9bb3-d2adcea2c99c","timestamp":"2026-10-14T05:08:59.696Z","request_id":"req_011Cg1YxZHwN15jWpLDDKy88"}} +{"dir":"recv","msg":{"duration_api_ms":2197,"stop_reason":"end_turn","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8","total_cost_usd":0.063298,"usage":{"input_tokens":2,"cache_creation_input_tokens":15222,"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":15222,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15222,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15222},"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":15222,"webSearchRequests":0,"costUSD":0.0631687,"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":1687,"type":"result","duration_ms":1707,"uuid":"729b7a5e-e867-4ff0-b3f7-7e3113d07407","ttft_stream_ms":1684,"time_to_request_ms":34,"first_content_frame_ms":1684,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"idle","uuid":"5216e9ec-29ef-473f-b98c-95cf3fb88021","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8"}} diff --git a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl new file mode 100644 index 0000000..7c1b985 --- /dev/null +++ b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl @@ -0,0 +1,9 @@ +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_63b0c412a1ad1244","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_63b0c412a1ad1244","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":20885,"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":"","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"running","uuid":"c7836f6b-f03c-48d1-920d-81037bf1750b","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume1396538453/001","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8","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":"0937af79-354e-4b91-8ee2-61a22112c14b","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1396538453-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume1396538453-001/d366bb85-9f42-4580-aaef-61fa39016ea8/scratchpad","messaging_socket_path":"/tmp/cc-socks/20885.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":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxoirkEdRJZYVaVZeA","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":7016,"cache_read_input_tokens":30620,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7016},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13140}},"context_management":null},"parent_tool_use_id":null,"session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8","uuid":"83c278b9-64a3-4c79-a00d-6f55afbf5948","timestamp":"2026-10-14T05:09:02.846Z","request_id":"req_011Cg1YxoRWJtNPEaiwRZaQd"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1791972000,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.02,"resetsAt":1791972000},"seven_day":{"utilization":0.25,"resetsAt":1792270800}}},"uuid":"56be0225-dbc9-41a8-ab72-ee0b9b8a2adc","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8"}} +{"dir":"recv","msg":{"duration_api_ms":3655,"stop_reason":"end_turn","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8","total_cost_usd":0.094508,"usage":{"input_tokens":2,"cache_creation_input_tokens":7016,"cache_read_input_tokens":30620,"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":7016,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":8,"cache_read_input_tokens":30620,"cache_creation_input_tokens":7016,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7016},"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":52987,"cacheCreationInputTokens":22238,"webSearchRequests":0,"costUSD":0.0943787,"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":1475,"type":"result","duration_ms":1491,"uuid":"46c4c6a9-e9e3-4232-87b8-254166e1d318","ttft_stream_ms":1471,"time_to_request_ms":33,"first_content_frame_ms":1471,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"idle","uuid":"f92d42d5-e19d-492f-9dbe-61bfd7e09b9e","session_id":"d366bb85-9f42-4580-aaef-61fa39016ea8"}} diff --git a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl new file mode 100644 index 0000000..32537e8 --- /dev/null +++ b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl @@ -0,0 +1,16 @@ +{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_11387a1f77e02328","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_11387a1f77e02328","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":20703,"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":"session_state_changed","state":"running","uuid":"8804286e-2cf5-49c0-a555-11187aa3e087","session_id":"add2442d-452d-492f-b892-1003d0edc8ab"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks1865068212/001","session_id":"add2442d-452d-492f-b892-1003d0edc8ab","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":"f81329d8-81ec-4c21-8d65-7c975fb28bb3","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1865068212-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1865068212-001/add2442d-452d-492f-b892-1003d0edc8ab/scratchpad","messaging_socket_path":"/tmp/cc-socks/20703.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":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1791972000,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.02,"resetsAt":1791972000},"seven_day":{"utilization":0.25,"resetsAt":1792270800}}},"uuid":"40fe3cfb-7751-45bc-ae7f-a3ecacc9c738","session_id":"add2442d-452d-492f-b892-1003d0edc8ab"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxZQe4DB5NwsyxFd32","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":15224,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15224},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"add2442d-452d-492f-b892-1003d0edc8ab","uuid":"d7e13d36-9ff2-4ff8-b8a1-b7c0e3a24026","timestamp":"2026-10-14T05:08:59.760Z","request_id":"req_011Cg1YxZBVJbTwm2HbEqeq2"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"0b06e179-7359-4e77-82fc-205316f90089","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"add2442d-452d-492f-b892-1003d0edc8ab","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1865068212-001/add2442d-452d-492f-b892-1003d0edc8ab.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks1865068212/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1865068212-001/add2442d-452d-492f-b892-1003d0edc8ab/scratchpad","prompt_id":"53b17b13-7ab8-4c20-a62a-191e320ac3c7","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":"21d823c6-f9a1-42fe-8a9c-caa613d6750b"}}} +{"dir":"send","msg":{"response":{"request_id":"0b06e179-7359-4e77-82fc-205316f90089","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":"add2442d-452d-492f-b892-1003d0edc8ab","uuid":"7d7eb014-1d23-4f64-921f-e80874f4a710","timestamp":"2026-10-14T05:08:59.783Z","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":"add2442d-452d-492f-b892-1003d0edc8ab","uuid":"7fbf2031-19f3-48e6-a26c-3d9b39705b39"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg1YxgmeSVB6uMkyNcPje","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":30612,"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":13136}},"context_management":null},"parent_tool_use_id":null,"session_id":"add2442d-452d-492f-b892-1003d0edc8ab","uuid":"aeaef563-3eb1-477c-8e60-3bcda1730e0e","timestamp":"2026-10-14T05:09:01.411Z","request_id":"req_011Cg1YxgVXmvgkDRK2aE2be"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"92af8199-85ca-4616-8fa1-e953b76e5a28","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"add2442d-452d-492f-b892-1003d0edc8ab","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1865068212-001/add2442d-452d-492f-b892-1003d0edc8ab.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks1865068212/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks1865068212-001/add2442d-452d-492f-b892-1003d0edc8ab/scratchpad","prompt_id":"53b17b13-7ab8-4c20-a62a-191e320ac3c7","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":"c9d95b3a-2138-4006-bc10-04870ca8274f"}}} +{"dir":"send","msg":{"response":{"request_id":"92af8199-85ca-4616-8fa1-e953b76e5a28","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"duration_api_ms":3866,"stop_reason":"end_turn","session_id":"add2442d-452d-492f-b892-1003d0edc8ab","total_cost_usd":0.0947023,"usage":{"input_tokens":4,"cache_creation_input_tokens":22283,"cache_read_input_tokens":52979,"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":22283,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30612,"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":52979,"cacheCreationInputTokens":22283,"webSearchRequests":0,"costUSD":0.0945779,"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":1751,"type":"result","duration_ms":3417,"uuid":"2356d15d-514c-4f95-975b-99fd3e557924","ttft_stream_ms":1748,"time_to_request_ms":34,"first_content_frame_ms":1748,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"session_state_changed","state":"idle","uuid":"734cac55-8b2a-4476-9873-a4a95657da4e","session_id":"add2442d-452d-492f-b892-1003d0edc8ab"}} diff --git a/internal/git/git.go b/internal/git/git.go new file mode 100644 index 0000000..61d50df --- /dev/null +++ b/internal/git/git.go @@ -0,0 +1,86 @@ +package git + +import ( + "fmt" + "os/exec" + "path/filepath" + "strings" +) + +type RepoInfo struct { + Root string + DefaultBranch string + Remote string +} + +func Inspect(path string) (RepoInfo, error) { + abs, err := filepath.Abs(path) + if err != nil { + return RepoInfo{}, err + } + + root, err := run(abs, "rev-parse", "--show-toplevel") + if err != nil { + return RepoInfo{}, err + } + + root, err = filepath.EvalSymlinks(root) + if err != nil { + return RepoInfo{}, err + } + + abs, err = filepath.EvalSymlinks(abs) + if err != nil { + return RepoInfo{}, err + } + + if root != abs { + return RepoInfo{}, fmt.Errorf("%s is inside the repo at %s; register the repo root", abs, root) + } + + branch, err := run(root, "symbolic-ref", "--short", "HEAD") + if err != nil { + return RepoInfo{}, err + } + + remote, err := run(root, "remote", "get-url", "origin") + if err != nil { + return RepoInfo{}, err + } + + return RepoInfo{Root: root, DefaultBranch: branch, Remote: remote}, nil +} + +func AddWorktree(repo, path, branch, base string) (string, error) { + sha, err := run(repo, "rev-parse", "--verify", base+"^{commit}") + if err != nil { + return "", err + } + + _, err = run(repo, "worktree", "add", "-b", branch, path, sha) + if err != nil { + return "", err + } + + return sha, nil +} + +func RemoveWorktree(repo, path, branch string) error { + _, err := run(repo, "worktree", "remove", "--force", path) + if err != nil { + return err + } + + _, err = run(repo, "branch", "-D", branch) + return err +} + +func run(dir string, args ...string) (string, error) { + cmd := exec.Command("git", args...) + cmd.Dir = dir + out, err := cmd.CombinedOutput() + if err != nil { + return "", fmt.Errorf("git %s: %w: %s", strings.Join(args, " "), err, strings.TrimSpace(string(out))) + } + return strings.TrimSpace(string(out)), nil +} diff --git a/internal/server/hub.go b/internal/server/hub.go new file mode 100644 index 0000000..3e016e8 --- /dev/null +++ b/internal/server/hub.go @@ -0,0 +1,53 @@ +package server + +import ( + "sync" + + "g.fc.run/misc/byre/internal/api" +) + +type hub struct { + mu sync.Mutex + subs map[chan api.Event]bool +} + +func newHub() *hub { + return &hub{subs: map[chan api.Event]bool{}} +} + +func (h *hub) subscribe() chan api.Event { + h.mu.Lock() + defer h.mu.Unlock() + ch := make(chan api.Event, 256) + h.subs[ch] = true + return ch +} + +func (h *hub) unsubscribe(ch chan api.Event) { + h.mu.Lock() + defer h.mu.Unlock() + if !h.subs[ch] { + return + } + delete(h.subs, ch) + close(ch) +} + +func (h *hub) publish(ev api.Event) { + h.mu.Lock() + defer h.mu.Unlock() + for ch := range h.subs { + select { + case ch <- ev: + default: + delete(h.subs, ch) + close(ch) + } + } +} + +func (h *hub) count() int { + h.mu.Lock() + defer h.mu.Unlock() + return len(h.subs) +} diff --git a/internal/server/server.go b/internal/server/server.go new file mode 100644 index 0000000..3398c7a --- /dev/null +++ b/internal/server/server.go @@ -0,0 +1,360 @@ +package server + +import ( + "context" + "encoding/json" + "errors" + "fmt" + "io/fs" + "log/slog" + "net" + "net/http" + "os" + "path/filepath" + "strings" + "sync" + "time" + + "g.fc.run/misc/byre/internal/api" + "g.fc.run/misc/byre/internal/git" + "g.fc.run/misc/byre/internal/store" +) + +type Server struct { + store *store.Store + hub *hub + worktreeRoot string + startedAt time.Time + spa fs.FS + + usersMu sync.Mutex + users map[string]string +} + +type ctxKey struct{} + +func New(dataDir string, spa fs.FS) (*Server, error) { + err := os.MkdirAll(dataDir, 0o755) + if err != nil { + return nil, err + } + + s := &Server{ + hub: newHub(), + worktreeRoot: filepath.Join(dataDir, "worktrees"), + startedAt: time.Now().UTC(), + spa: spa, + users: map[string]string{}, + } + + s.store, err = store.Open(filepath.Join(dataDir, "byre.db"), s.hub.publish) + if err != nil { + return nil, err + } + + return s, nil +} + +func (s *Server) Close() error { + return s.store.Close() +} + +func (s *Server) Handler() http.Handler { + mux := http.NewServeMux() + api.HandlerWithOptions(s, api.StdHTTPServerOptions{ + BaseRouter: mux, + Middlewares: []api.MiddlewareFunc{s.identify}, + ErrorHandlerFunc: func(w http.ResponseWriter, r *http.Request, err error) { + writeError(w, http.StatusBadRequest, err) + }, + }) + mux.Handle("/", http.FileServerFS(s.spa)) + return mux +} + +func (s *Server) identify(next http.Handler) http.Handler { + return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { + host, _, err := net.SplitHostPort(r.RemoteAddr) + if err != nil { + writeError(w, http.StatusForbidden, err) + return + } + ip := net.ParseIP(host) + if ip == nil || !ip.IsLoopback() { + writeError(w, http.StatusForbidden, fmt.Errorf("request from %s did not arrive via tailscale serve", host)) + return + } + + login := r.Header.Get("Tailscale-User-Login") + name := r.Header.Get("Tailscale-User-Name") + if login == "" || name == "" { + writeError(w, http.StatusUnauthorized, errors.New("missing Tailscale-User-Login or Tailscale-User-Name")) + return + } + + err = s.ensureUser(r.Context(), login, name) + if err != nil { + writeError(w, http.StatusInternalServerError, err) + return + } + + next.ServeHTTP(w, r.WithContext(context.WithValue(r.Context(), ctxKey{}, login))) + }) +} + +func (s *Server) ensureUser(ctx context.Context, login, name string) error { + s.usersMu.Lock() + defer s.usersMu.Unlock() + + if s.users[login] == name { + return nil + } + + _, err := s.store.EnsureUser(ctx, login, name) + if err != nil { + return err + } + s.users[login] = name + return nil +} + +func actor(r *http.Request) string { + return r.Context().Value(ctxKey{}).(string) +} + +func (s *Server) GetMe(w http.ResponseWriter, r *http.Request) { + u, err := s.store.GetUser(r.Context(), actor(r)) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, u) +} + +func (s *Server) UpdateMe(w http.ResponseWriter, r *http.Request) { + req := api.UserUpdate{} + if !readJSON(w, r, &req) { + return + } + + if strings.TrimSpace(req.GitName) == "" || !strings.Contains(req.GitEmail, "@") { + writeError(w, http.StatusBadRequest, errors.New("git_name and a valid git_email are required")) + return + } + + u, err := s.store.UpdateUserGit(r.Context(), actor(r), req.GitName, req.GitEmail) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, u) +} + +func (s *Server) ListProjects(w http.ResponseWriter, r *http.Request) { + projects, err := s.store.ListProjects(r.Context()) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, projects) +} + +func (s *Server) CreateProject(w http.ResponseWriter, r *http.Request) { + req := api.ProjectCreate{} + if !readJSON(w, r, &req) { + return + } + + if strings.TrimSpace(req.Name) == "" { + writeError(w, http.StatusBadRequest, errors.New("name is required")) + return + } + + info, err := git.Inspect(req.RepoPath) + if err != nil { + writeError(w, http.StatusBadRequest, err) + return + } + + p := api.Project{ + Id: store.NewID(), + Name: req.Name, + RepoPath: info.Root, + DefaultBranch: info.DefaultBranch, + Remote: info.Remote, + CreatedBy: actor(r), + CreatedAt: time.Now().UTC(), + } + + err = s.store.CreateProject(r.Context(), p) + if err != nil { + writeError(w, http.StatusBadRequest, err) + return + } + writeJSON(w, http.StatusCreated, p) +} + +func (s *Server) GetProject(w http.ResponseWriter, r *http.Request, projectID string) { + p, err := s.store.GetProject(r.Context(), projectID) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, p) +} + +func (s *Server) ListTasks(w http.ResponseWriter, r *http.Request, projectID string) { + _, err := s.store.GetProject(r.Context(), projectID) + if err != nil { + writeStoreError(w, err) + return + } + + tasks, err := s.store.ListTasks(r.Context(), projectID) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, tasks) +} + +func (s *Server) CreateTask(w http.ResponseWriter, r *http.Request, projectID string) { + req := api.TaskCreate{} + if !readJSON(w, r, &req) { + return + } + + if strings.TrimSpace(req.Title) == "" { + writeError(w, http.StatusBadRequest, errors.New("title is required")) + return + } + + p, err := s.store.GetProject(r.Context(), projectID) + if err != nil { + writeStoreError(w, err) + return + } + + id := store.NewID() + t := api.Task{ + Id: id, + ProjectId: p.Id, + Title: req.Title, + Branch: "byre/" + id, + WorktreePath: filepath.Join(s.worktreeRoot, p.Id, id), + Status: api.Active, + CreatedBy: actor(r), + CreatedAt: time.Now().UTC(), + } + + t.BaseRef, err = git.AddWorktree(p.RepoPath, t.WorktreePath, t.Branch, p.DefaultBranch) + if err != nil { + writeError(w, http.StatusInternalServerError, err) + return + } + + err = s.store.CreateTask(r.Context(), t) + if err != nil { + writeError(w, http.StatusInternalServerError, err) + return + } + writeJSON(w, http.StatusCreated, t) +} + +func (s *Server) GetTask(w http.ResponseWriter, r *http.Request, taskID string) { + t, err := s.store.GetTask(r.Context(), taskID) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, t) +} + +func (s *Server) CompleteTask(w http.ResponseWriter, r *http.Request, taskID string) { + t, err := s.store.GetTask(r.Context(), taskID) + if err != nil { + writeStoreError(w, err) + return + } + + if t.Status != api.Active { + writeError(w, http.StatusConflict, fmt.Errorf("task %s is %s", t.Id, t.Status)) + return + } + + p, err := s.store.GetProject(r.Context(), t.ProjectId) + if err != nil { + writeStoreError(w, err) + return + } + + err = git.RemoveWorktree(p.RepoPath, t.WorktreePath, t.Branch) + if err != nil { + writeError(w, http.StatusInternalServerError, err) + return + } + + t, err = s.store.CompleteTask(r.Context(), taskID, actor(r)) + if err != nil { + writeStoreError(w, err) + return + } + writeJSON(w, http.StatusOK, t) +} + +func (s *Server) GetStatus(w http.ResponseWriter, r *http.Request) { + c, err := s.store.Counts(r.Context()) + if err != nil { + writeStoreError(w, err) + return + } + + dbBytes := int64(0) + for _, suffix := range []string{"", "-wal", "-shm"} { + fi, err := os.Stat(s.store.Path() + suffix) + if err == nil { + dbBytes += fi.Size() + } + } + + writeJSON(w, http.StatusOK, api.Status{ + StartedAt: s.startedAt, + DbBytes: dbBytes, + LastEventSeq: c.LastEventSeq, + Projects: c.Projects, + ActiveTasks: c.ActiveTasks, + SseClients: s.hub.count(), + }) +} + +func readJSON(w http.ResponseWriter, r *http.Request, v any) bool { + dec := json.NewDecoder(r.Body) + dec.DisallowUnknownFields() + err := dec.Decode(v) + if err != nil { + writeError(w, http.StatusBadRequest, fmt.Errorf("decode request: %w", err)) + return false + } + return true +} + +func writeJSON(w http.ResponseWriter, status int, v any) { + w.Header().Set("Content-Type", "application/json") + w.WriteHeader(status) + err := json.NewEncoder(w).Encode(v) + if err != nil { + slog.Warn("write response", "err", err) + } +} + +func writeError(w http.ResponseWriter, status int, err error) { + writeJSON(w, status, api.Error{Message: err.Error()}) +} + +func writeStoreError(w http.ResponseWriter, err error) { + if errors.Is(err, store.ErrNotFound) { + writeError(w, http.StatusNotFound, err) + return + } + writeError(w, http.StatusInternalServerError, err) +} diff --git a/internal/server/server_test.go b/internal/server/server_test.go new file mode 100644 index 0000000..98cff78 --- /dev/null +++ b/internal/server/server_test.go @@ -0,0 +1,352 @@ +package server_test + +import ( + "bufio" + "bytes" + "context" + "encoding/json" + "fmt" + "net/http" + "net/http/httptest" + "os" + "os/exec" + "path/filepath" + "strings" + "testing" + "testing/fstest" + "time" + + "g.fc.run/misc/byre/internal/api" + "g.fc.run/misc/byre/internal/server" +) + +const login = "alice@example.com" + +type harness struct { + t *testing.T + url string +} + +func newHarness(t *testing.T) *harness { + srv, err := server.New(t.TempDir(), fstest.MapFS{"index.html": {Data: []byte("shell")}}) + if err != nil { + t.Fatalf("new server: %v", err) + } + t.Cleanup(func() { srv.Close() }) + + hs := httptest.NewServer(srv.Handler()) + t.Cleanup(hs.Close) + + return &harness{t: t, url: hs.URL} +} + +func (h *harness) do(method, path string, body any, out any) int { + h.t.Helper() + + buf := &bytes.Buffer{} + if body != nil { + err := json.NewEncoder(buf).Encode(body) + if err != nil { + h.t.Fatalf("encode: %v", err) + } + } + + req, err := http.NewRequest(method, h.url+path, buf) + if err != nil { + h.t.Fatalf("new request: %v", err) + } + req.Header.Set("Tailscale-User-Login", login) + req.Header.Set("Tailscale-User-Name", "Alice") + + resp, err := http.DefaultClient.Do(req) + if err != nil { + h.t.Fatalf("%s %s: %v", method, path, err) + } + defer resp.Body.Close() + + if out != nil && resp.StatusCode < 300 { + err = json.NewDecoder(resp.Body).Decode(out) + if err != nil { + h.t.Fatalf("decode %s %s: %v", method, path, err) + } + } + return resp.StatusCode +} + +func (h *harness) createProject(name string) api.Project { + h.t.Helper() + p := api.Project{} + code := h.do("POST", "/api/projects", api.ProjectCreate{Name: name, RepoPath: repoWithOrigin(h.t)}, &p) + if code != http.StatusCreated { + h.t.Fatalf("create project: %d", code) + } + return p +} + +func TestIdentityRequired(t *testing.T) { + h := newHarness(t) + + resp, err := http.Get(h.url + "/api/me") + if err != nil { + t.Fatalf("get: %v", err) + } + resp.Body.Close() + if resp.StatusCode != http.StatusUnauthorized { + t.Fatalf("want 401 without tailscale headers, got %d", resp.StatusCode) + } + + resp, err = http.Get(h.url + "/") + if err != nil { + t.Fatalf("get spa: %v", err) + } + resp.Body.Close() + if resp.StatusCode != http.StatusOK { + t.Fatalf("want spa shell without auth, got %d", resp.StatusCode) + } +} + +func TestMe(t *testing.T) { + h := newHarness(t) + + me := api.User{} + h.do("GET", "/api/me", nil, &me) + if me.Login != login || me.DisplayName != "Alice" || me.GitEmail != "" { + t.Fatalf("unexpected user %+v", me) + } + + code := h.do("PUT", "/api/me", api.UserUpdate{GitName: "Alice", GitEmail: "nope"}, nil) + if code != http.StatusBadRequest { + t.Fatalf("want 400 for bad email, got %d", code) + } + + code = h.do("PUT", "/api/me", api.UserUpdate{GitName: "Alice A", GitEmail: "alice@example.org"}, &me) + if code != http.StatusOK || me.GitName != "Alice A" || me.GitEmail != "alice@example.org" { + t.Fatalf("update failed: %d %+v", code, me) + } +} + +func TestProjectAndTaskLifecycle(t *testing.T) { + h := newHarness(t) + p := h.createProject("demo") + + if p.DefaultBranch != "main" || !strings.HasSuffix(p.Remote, "origin.git") { + t.Fatalf("unexpected project %+v", p) + } + + code := h.do("POST", "/api/projects", api.ProjectCreate{Name: "demo", RepoPath: p.RepoPath}, nil) + if code != http.StatusBadRequest { + t.Fatalf("want 400 for duplicate project, got %d", code) + } + + task := api.Task{} + code = h.do("POST", "/api/projects/"+p.Id+"/tasks", api.TaskCreate{Title: "first"}, &task) + if code != http.StatusCreated { + t.Fatalf("create task: %d", code) + } + + _, err := os.Stat(filepath.Join(task.WorktreePath, "README")) + if err != nil { + t.Fatalf("worktree not checked out: %v", err) + } + head := gitOut(t, task.WorktreePath, "rev-parse", "--abbrev-ref", "HEAD") + if head != task.Branch { + t.Fatalf("worktree on %s, want %s", head, task.Branch) + } + if task.BaseRef != gitOut(t, p.RepoPath, "rev-parse", "main") { + t.Fatalf("base ref %s is not main's head", task.BaseRef) + } + + tasks := []api.Task{} + h.do("GET", "/api/projects/"+p.Id+"/tasks", nil, &tasks) + if len(tasks) != 1 || tasks[0].Id != task.Id { + t.Fatalf("unexpected task list %+v", tasks) + } + + err = os.WriteFile(filepath.Join(task.WorktreePath, "dirty"), []byte("x"), 0o644) + if err != nil { + t.Fatalf("write: %v", err) + } + + done := api.Task{} + code = h.do("POST", "/api/tasks/"+task.Id+"/complete", nil, &done) + if code != http.StatusOK || done.Status != api.Completed || done.CompletedAt == nil { + t.Fatalf("complete: %d %+v", code, done) + } + + _, err = os.Stat(task.WorktreePath) + if !os.IsNotExist(err) { + t.Fatalf("worktree still exists: %v", err) + } + branches := gitOut(t, p.RepoPath, "branch", "--list", task.Branch) + if branches != "" { + t.Fatalf("branch still exists: %s", branches) + } + + code = h.do("POST", "/api/tasks/"+task.Id+"/complete", nil, nil) + if code != http.StatusConflict { + t.Fatalf("want 409 completing twice, got %d", code) + } + + code = h.do("GET", "/api/tasks/nope", nil, nil) + if code != http.StatusNotFound { + t.Fatalf("want 404 for unknown task, got %d", code) + } +} + +func TestEventStreamResume(t *testing.T) { + h := newHarness(t) + + stream := h.openStream(nil) + p := h.createProject("demo") + first := stream.next() + if first.Kind != "project.created" || *first.ProjectId != p.Id { + t.Fatalf("unexpected first event %+v", first) + } + stream.close() + + task := api.Task{} + h.do("POST", "/api/projects/"+p.Id+"/tasks", api.TaskCreate{Title: "while away"}, &task) + h.do("PUT", "/api/me", api.UserUpdate{GitName: "Alice", GitEmail: "alice@example.org"}, nil) + + resumed := h.openStream(&first.Seq) + missed := resumed.next() + if missed.Kind != "task.created" || *missed.TaskId != task.Id || missed.Seq != first.Seq+1 { + t.Fatalf("unexpected replayed event %+v", missed) + } + if next := resumed.next(); next.Kind != "user.updated" { + t.Fatalf("unexpected second replayed event %+v", next) + } + + h.do("POST", "/api/tasks/"+task.Id+"/complete", nil, nil) + if live := resumed.next(); live.Kind != "task.completed" { + t.Fatalf("unexpected live event %+v", live) + } + + status := api.Status{} + h.do("GET", "/api/admin/status", nil, &status) + if status.LastEventSeq != 4 || status.Projects != 1 || status.ActiveTasks != 0 || status.SseClients < 1 { + t.Fatalf("unexpected status %+v", status) + } +} + +type stream struct { + t *testing.T + cancel context.CancelFunc + resp *http.Response + r *bufio.Reader +} + +func (h *harness) openStream(lastEventID *int64) *stream { + h.t.Helper() + + ctx, cancel := context.WithCancel(context.Background()) + req, err := http.NewRequestWithContext(ctx, "GET", h.url+"/api/events", nil) + if err != nil { + h.t.Fatalf("new request: %v", err) + } + req.Header.Set("Tailscale-User-Login", login) + req.Header.Set("Tailscale-User-Name", "Alice") + if lastEventID != nil { + req.Header.Set("Last-Event-ID", fmt.Sprint(*lastEventID)) + } + + resp, err := http.DefaultClient.Do(req) + if err != nil { + h.t.Fatalf("open stream: %v", err) + } + if resp.StatusCode != http.StatusOK { + h.t.Fatalf("open stream: %d", resp.StatusCode) + } + + s := &stream{t: h.t, cancel: cancel, resp: resp, r: bufio.NewReader(resp.Body)} + h.t.Cleanup(s.close) + return s +} + +func (s *stream) next() api.Event { + s.t.Helper() + + type result struct { + ev api.Event + err error + } + ch := make(chan result, 1) + + go func() { + id := "" + data := "" + for { + line, err := s.r.ReadString('\n') + if err != nil { + ch <- result{err: err} + return + } + line = strings.TrimRight(line, "\n") + switch { + case strings.HasPrefix(line, "id: "): + id = strings.TrimPrefix(line, "id: ") + case strings.HasPrefix(line, "data: "): + data = strings.TrimPrefix(line, "data: ") + case line == "" && data != "": + ev := api.Event{} + err := json.Unmarshal([]byte(data), &ev) + if err == nil && fmt.Sprint(ev.Seq) != id { + err = fmt.Errorf("sse id %s does not match seq %d", id, ev.Seq) + } + ch <- result{ev: ev, err: err} + return + } + } + }() + + select { + case res := <-ch: + if res.err != nil { + s.t.Fatalf("read event: %v", res.err) + } + return res.ev + case <-time.After(5 * time.Second): + s.t.Fatalf("timed out waiting for event") + return api.Event{} + } +} + +func (s *stream) close() { + s.cancel() + s.resp.Body.Close() +} + +func repoWithOrigin(t *testing.T) string { + dir := t.TempDir() + origin := filepath.Join(dir, "origin.git") + repo := filepath.Join(dir, "repo") + + gitOut(t, dir, "init", "--bare", "--initial-branch=main", origin) + gitOut(t, dir, "init", "--initial-branch=main", repo) + gitOut(t, repo, "remote", "add", "origin", origin) + err := os.WriteFile(filepath.Join(repo, "README"), []byte("hi\n"), 0o644) + if err != nil { + t.Fatalf("write readme: %v", err) + } + gitOut(t, repo, "add", "README") + gitOut(t, repo, "commit", "--message", "root") + gitOut(t, repo, "push", "origin", "main") + return repo +} + +func gitOut(t *testing.T, dir string, args ...string) string { + t.Helper() + cmd := exec.Command("git", args...) + cmd.Dir = dir + cmd.Env = append(os.Environ(), + "GIT_AUTHOR_NAME=Test", + "GIT_AUTHOR_EMAIL=test@example.com", + "GIT_COMMITTER_NAME=Test", + "GIT_COMMITTER_EMAIL=test@example.com", + ) + out, err := cmd.CombinedOutput() + if err != nil { + t.Fatalf("git %v: %v\n%s", args, err, out) + } + return strings.TrimSpace(string(out)) +} diff --git a/internal/server/sse.go b/internal/server/sse.go new file mode 100644 index 0000000..3d58fd6 --- /dev/null +++ b/internal/server/sse.go @@ -0,0 +1,91 @@ +package server + +import ( + "encoding/json" + "fmt" + "net/http" + "time" + + "g.fc.run/misc/byre/internal/api" +) + +const backfillPage = 500 + +func (s *Server) StreamEvents(w http.ResponseWriter, r *http.Request, params api.StreamEventsParams) { + last := int64(0) + if params.After != nil { + last = *params.After + } + if params.LastEventID != nil { + last = *params.LastEventID + } + + rc := http.NewResponseController(w) + w.Header().Set("Content-Type", "text/event-stream") + w.Header().Set("Cache-Control", "no-cache") + w.WriteHeader(http.StatusOK) + + live := s.hub.subscribe() + defer s.hub.unsubscribe(live) + + for { + events, err := s.store.EventsAfter(r.Context(), last, backfillPage) + if err != nil { + return + } + for _, ev := range events { + if !writeEvent(w, ev) { + return + } + last = ev.Seq + } + if len(events) < backfillPage { + break + } + } + + if rc.Flush() != nil { + return + } + + ping := time.NewTicker(30 * time.Second) + defer ping.Stop() + + for { + select { + case ev, ok := <-live: + if !ok { + return + } + if ev.Seq <= last { + continue + } + if !writeEvent(w, ev) { + return + } + last = ev.Seq + + case <-ping.C: + _, err := fmt.Fprint(w, ": ping\n\n") + if err != nil { + return + } + + case <-r.Context().Done(): + return + } + + if rc.Flush() != nil { + return + } + } +} + +func writeEvent(w http.ResponseWriter, ev api.Event) bool { + data, err := json.Marshal(ev) + if err != nil { + return false + } + _, err = fmt.Fprintf(w, "id: %d\ndata: %s\n\n", ev.Seq, data) + return err == nil +} diff --git a/internal/store/store.go b/internal/store/store.go new file mode 100644 index 0000000..9b214da --- /dev/null +++ b/internal/store/store.go @@ -0,0 +1,405 @@ +package store + +import ( + "context" + "crypto/rand" + "database/sql" + "encoding/hex" + "encoding/json" + "errors" + "fmt" + "sync" + "time" + + _ "modernc.org/sqlite" + + "g.fc.run/misc/byre/internal/api" +) + +var ErrNotFound = errors.New("not found") + +const schema = ` +CREATE TABLE IF NOT EXISTS users ( + login TEXT PRIMARY KEY, + display_name TEXT NOT NULL, + git_name TEXT NOT NULL DEFAULT '', + git_email TEXT NOT NULL DEFAULT '', + created_at TEXT NOT NULL +); + +CREATE TABLE IF NOT EXISTS projects ( + id TEXT PRIMARY KEY, + name TEXT NOT NULL UNIQUE, + repo_path TEXT NOT NULL UNIQUE, + default_branch TEXT NOT NULL, + remote TEXT NOT NULL, + created_by TEXT NOT NULL REFERENCES users(login), + created_at TEXT NOT NULL +); + +CREATE TABLE IF NOT EXISTS tasks ( + id TEXT PRIMARY KEY, + project_id TEXT NOT NULL REFERENCES projects(id), + title TEXT NOT NULL, + branch TEXT NOT NULL, + worktree_path TEXT NOT NULL, + base_ref TEXT NOT NULL, + status TEXT NOT NULL, + created_by TEXT NOT NULL REFERENCES users(login), + created_at TEXT NOT NULL, + completed_at TEXT +); + +CREATE INDEX IF NOT EXISTS tasks_project ON tasks(project_id, created_at); + +CREATE TABLE IF NOT EXISTS events ( + seq INTEGER PRIMARY KEY AUTOINCREMENT, + kind TEXT NOT NULL, + project_id TEXT, + task_id TEXT, + actor TEXT NOT NULL, + payload TEXT NOT NULL, + created_at TEXT NOT NULL +); +` + +type Store struct { + db *sql.DB + path string + writeMu sync.Mutex + onEvent func(api.Event) +} + +func Open(path string, onEvent func(api.Event)) (*Store, error) { + dsn := "file:" + path + "?_pragma=journal_mode(WAL)&_pragma=busy_timeout(5000)&_pragma=foreign_keys(1)&_txlock=immediate" + db, err := sql.Open("sqlite", dsn) + if err != nil { + return nil, err + } + + _, err = db.Exec(schema) + if err != nil { + db.Close() + return nil, fmt.Errorf("apply schema: %w", err) + } + + return &Store{db: db, path: path, onEvent: onEvent}, nil +} + +func (s *Store) Close() error { + return s.db.Close() +} + +func (s *Store) Path() string { + return s.path +} + +func NewID() string { + b := make([]byte, 6) + rand.Read(b) + return hex.EncodeToString(b) +} + +func (s *Store) EnsureUser(ctx context.Context, login, displayName string) (api.User, error) { + _, err := s.db.ExecContext(ctx, ` + INSERT INTO users (login, display_name, created_at) VALUES (?, ?, ?) + ON CONFLICT (login) DO UPDATE SET display_name = excluded.display_name + `, login, displayName, now()) + if err != nil { + return api.User{}, err + } + return s.GetUser(ctx, login) +} + +func (s *Store) GetUser(ctx context.Context, login string) (api.User, error) { + u := api.User{} + err := s.db.QueryRowContext(ctx, `SELECT login, display_name, git_name, git_email FROM users WHERE login = ?`, login). + Scan(&u.Login, &u.DisplayName, &u.GitName, &u.GitEmail) + if errors.Is(err, sql.ErrNoRows) { + return u, ErrNotFound + } + return u, err +} + +func (s *Store) UpdateUserGit(ctx context.Context, login, gitName, gitEmail string) (api.User, error) { + err := s.write(ctx, func(tx *sql.Tx, emit emitFunc) error { + _, err := tx.ExecContext(ctx, `UPDATE users SET git_name = ?, git_email = ? WHERE login = ?`, gitName, gitEmail, login) + if err != nil { + return err + } + return emit(api.Event{Kind: "user.updated", Actor: login, Payload: map[string]any{"login": login}}) + }) + if err != nil { + return api.User{}, err + } + return s.GetUser(ctx, login) +} + +func (s *Store) CreateProject(ctx context.Context, p api.Project) error { + return s.write(ctx, func(tx *sql.Tx, emit emitFunc) error { + _, err := tx.ExecContext(ctx, ` + INSERT INTO projects (id, name, repo_path, default_branch, remote, created_by, created_at) + VALUES (?, ?, ?, ?, ?, ?, ?) + `, p.Id, p.Name, p.RepoPath, p.DefaultBranch, p.Remote, p.CreatedBy, formatTime(p.CreatedAt)) + if err != nil { + return err + } + return emit(api.Event{Kind: "project.created", ProjectId: &p.Id, Actor: p.CreatedBy, Payload: toPayload(p)}) + }) +} + +func (s *Store) ListProjects(ctx context.Context) ([]api.Project, error) { + rows, err := s.db.QueryContext(ctx, `SELECT `+projectColumns+` FROM projects ORDER BY name`) + if err != nil { + return nil, err + } + defer rows.Close() + + projects := []api.Project{} + for rows.Next() { + p, err := scanProject(rows) + if err != nil { + return nil, err + } + projects = append(projects, p) + } + return projects, rows.Err() +} + +func (s *Store) GetProject(ctx context.Context, id string) (api.Project, error) { + p, err := scanProject(s.db.QueryRowContext(ctx, `SELECT `+projectColumns+` FROM projects WHERE id = ?`, id)) + if errors.Is(err, sql.ErrNoRows) { + return p, ErrNotFound + } + return p, err +} + +func (s *Store) CreateTask(ctx context.Context, t api.Task) error { + return s.write(ctx, func(tx *sql.Tx, emit emitFunc) error { + _, err := tx.ExecContext(ctx, ` + INSERT INTO tasks (id, project_id, title, branch, worktree_path, base_ref, status, created_by, created_at) + VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?) + `, t.Id, t.ProjectId, t.Title, t.Branch, t.WorktreePath, t.BaseRef, string(t.Status), t.CreatedBy, formatTime(t.CreatedAt)) + if err != nil { + return err + } + return emit(api.Event{Kind: "task.created", ProjectId: &t.ProjectId, TaskId: &t.Id, Actor: t.CreatedBy, Payload: toPayload(t)}) + }) +} + +func (s *Store) ListTasks(ctx context.Context, projectID string) ([]api.Task, error) { + rows, err := s.db.QueryContext(ctx, `SELECT `+taskColumns+` FROM tasks WHERE project_id = ? ORDER BY created_at DESC`, projectID) + if err != nil { + return nil, err + } + defer rows.Close() + + tasks := []api.Task{} + for rows.Next() { + t, err := scanTask(rows) + if err != nil { + return nil, err + } + tasks = append(tasks, t) + } + return tasks, rows.Err() +} + +func (s *Store) GetTask(ctx context.Context, id string) (api.Task, error) { + t, err := scanTask(s.db.QueryRowContext(ctx, `SELECT `+taskColumns+` FROM tasks WHERE id = ?`, id)) + if errors.Is(err, sql.ErrNoRows) { + return t, ErrNotFound + } + return t, err +} + +func (s *Store) CompleteTask(ctx context.Context, id, actor string) (api.Task, error) { + err := s.write(ctx, func(tx *sql.Tx, emit emitFunc) error { + res, err := tx.ExecContext(ctx, `UPDATE tasks SET status = ?, completed_at = ? WHERE id = ? AND status = ?`, + string(api.Completed), now(), id, string(api.Active)) + if err != nil { + return err + } + n, err := res.RowsAffected() + if err != nil { + return err + } + if n == 0 { + return ErrNotFound + } + + projectID := "" + err = tx.QueryRowContext(ctx, `SELECT project_id FROM tasks WHERE id = ?`, id).Scan(&projectID) + if err != nil { + return err + } + return emit(api.Event{Kind: "task.completed", ProjectId: &projectID, TaskId: &id, Actor: actor, Payload: map[string]any{"id": id}}) + }) + if err != nil { + return api.Task{}, err + } + return s.GetTask(ctx, id) +} + +func (s *Store) EventsAfter(ctx context.Context, after int64, limit int) ([]api.Event, error) { + rows, err := s.db.QueryContext(ctx, ` + SELECT seq, kind, project_id, task_id, actor, payload, created_at + FROM events WHERE seq > ? ORDER BY seq LIMIT ? + `, after, limit) + if err != nil { + return nil, err + } + defer rows.Close() + + events := []api.Event{} + for rows.Next() { + ev := api.Event{} + payload := "" + createdAt := "" + err := rows.Scan(&ev.Seq, &ev.Kind, &ev.ProjectId, &ev.TaskId, &ev.Actor, &payload, &createdAt) + if err != nil { + return nil, err + } + err = json.Unmarshal([]byte(payload), &ev.Payload) + if err != nil { + return nil, err + } + ev.CreatedAt, err = parseTime(createdAt) + if err != nil { + return nil, err + } + events = append(events, ev) + } + return events, rows.Err() +} + +type Counts struct { + LastEventSeq int64 + Projects int + ActiveTasks int +} + +func (s *Store) Counts(ctx context.Context) (Counts, error) { + c := Counts{} + err := s.db.QueryRowContext(ctx, ` + SELECT + (SELECT COALESCE(MAX(seq), 0) FROM events), + (SELECT COUNT(*) FROM projects), + (SELECT COUNT(*) FROM tasks WHERE status = ?) + `, string(api.Active)).Scan(&c.LastEventSeq, &c.Projects, &c.ActiveTasks) + return c, err +} + +type emitFunc func(api.Event) error + +func (s *Store) write(ctx context.Context, fn func(tx *sql.Tx, emit emitFunc) error) error { + s.writeMu.Lock() + defer s.writeMu.Unlock() + + tx, err := s.db.BeginTx(ctx, nil) + if err != nil { + return err + } + defer tx.Rollback() + + events := []api.Event{} + emit := func(ev api.Event) error { + ev.CreatedAt = time.Now().UTC() + payload, err := json.Marshal(ev.Payload) + if err != nil { + return err + } + err = tx.QueryRowContext(ctx, ` + INSERT INTO events (kind, project_id, task_id, actor, payload, created_at) + VALUES (?, ?, ?, ?, ?, ?) RETURNING seq + `, ev.Kind, ev.ProjectId, ev.TaskId, ev.Actor, string(payload), formatTime(ev.CreatedAt)).Scan(&ev.Seq) + if err != nil { + return err + } + events = append(events, ev) + return nil + } + + err = fn(tx, emit) + if err != nil { + return err + } + + err = tx.Commit() + if err != nil { + return err + } + + for _, ev := range events { + s.onEvent(ev) + } + return nil +} + +const projectColumns = `id, name, repo_path, default_branch, remote, created_by, created_at` + +const taskColumns = `id, project_id, title, branch, worktree_path, base_ref, status, created_by, created_at, completed_at` + +type scanner interface { + Scan(dest ...any) error +} + +func scanProject(row scanner) (api.Project, error) { + p := api.Project{} + createdAt := "" + err := row.Scan(&p.Id, &p.Name, &p.RepoPath, &p.DefaultBranch, &p.Remote, &p.CreatedBy, &createdAt) + if err != nil { + return p, err + } + p.CreatedAt, err = parseTime(createdAt) + return p, err +} + +func scanTask(row scanner) (api.Task, error) { + t := api.Task{} + status := "" + createdAt := "" + completedAt := sql.NullString{} + err := row.Scan(&t.Id, &t.ProjectId, &t.Title, &t.Branch, &t.WorktreePath, &t.BaseRef, &status, &t.CreatedBy, &createdAt, &completedAt) + if err != nil { + return t, err + } + t.Status = api.TaskStatus(status) + t.CreatedAt, err = parseTime(createdAt) + if err != nil { + return t, err + } + if completedAt.Valid { + ct, err := parseTime(completedAt.String) + if err != nil { + return t, err + } + t.CompletedAt = &ct + } + return t, nil +} + +func toPayload(v any) map[string]any { + b, err := json.Marshal(v) + if err != nil { + panic(err) + } + m := map[string]any{} + err = json.Unmarshal(b, &m) + if err != nil { + panic(err) + } + return m +} + +func now() string { + return formatTime(time.Now()) +} + +func formatTime(t time.Time) string { + return t.UTC().Format(time.RFC3339Nano) +} + +func parseTime(s string) (time.Time, error) { + return time.Parse(time.RFC3339Nano, s) +} diff --git a/web/embed.go b/web/embed.go new file mode 100644 index 0000000..38ca34f --- /dev/null +++ b/web/embed.go @@ -0,0 +1,6 @@ +package web + +import "embed" + +//go:embed index.html +var FS embed.FS diff --git a/web/index.html b/web/index.html new file mode 100644 index 0000000..d9cbc6b --- /dev/null +++ b/web/index.html @@ -0,0 +1,42 @@ + + + + + +byre + + + +

byre

+

Me


+
Projects

+
Events

+
+
+