diff --git a/api/openapi.yaml b/api/openapi.yaml index 54eb954..dfc3ca0 100644 --- a/api/openapi.yaml +++ b/api/openapi.yaml @@ -131,15 +131,34 @@ paths: post: operationId: mergeTask description: > - Squashes the task's worktree, uncommitted changes included, into one commit on the project's - default branch, fast-forwards the project's checkout to it, then removes the worktree and branch. - Nothing is pushed. Refused while a turn is running or queued, and on merge conflicts. + Starts the same agent turn as merge-in. When that turn ends normally, byre squashes the task's worktree + into one commit on the project's default branch, fast-forwards the project's checkout to it, then removes + the worktree and branch and marks the task merged. Nothing is pushed. Refused while a turn is running or queued. responses: - "200": - description: The merged task. + "202": + description: The merge turn was started or queued. content: application/json: - schema: { $ref: "#/components/schemas/Task" } + schema: { $ref: "#/components/schemas/AgentSession" } + "400": { $ref: "#/components/responses/Error" } + "404": { $ref: "#/components/responses/Error" } + "409": { $ref: "#/components/responses/Error" } + + /api/tasks/{taskId}/merge-in: + parameters: + - { name: taskId, in: path, required: true, schema: { type: string } } + post: + operationId: mergeIn + description: > + Asks the task's agent to merge the project's default branch into the task branch, resolving any conflicts + and regenerating generated files. Sent to the task's idle session, or starts a session when it has none. + Refused while a turn is running or queued. + responses: + "202": + description: The merge turn was started or queued. + content: + application/json: + schema: { $ref: "#/components/schemas/AgentSession" } "400": { $ref: "#/components/responses/Error" } "404": { $ref: "#/components/responses/Error" } "409": { $ref: "#/components/responses/Error" } diff --git a/docs/operations.md b/docs/operations.md index 94b3669..d97202f 100644 --- a/docs/operations.md +++ b/docs/operations.md @@ -19,9 +19,11 @@ Schema changes are the `migrations` slice in `internal/store/store.go`: named en ## Closing a task -A task ends `merged` or `discarded`; either way its sessions are stopped, its worktree and branch are removed, its `open` inbox items become `dismissed` (resolved by whoever closed it), and its record and events remain. `GET /api/tasks/{id}/unmerged` reports what would be lost or merged: commits on the branch that aren't on the default branch, and files, lines and uncommitted paths that differ from the merge base. The UI shows it in the confirm dialog of both buttons. +A task ends `merged` or `discarded`; either way its sessions are stopped, its worktree and branch are removed, its `open` inbox items become `dismissed` (resolved by whoever closed it), and its record and events remain. `GET /api/tasks/{id}/unmerged` reports what would be lost or merged: commits on the branch that aren't on the default branch, and files, lines and uncommitted paths that differ from the merge base. The UI shows it in the confirm dialog of both buttons, which are disabled while the task's session is `running` or `queued`. -`POST /api/tasks/{id}/merge` squashes the worktree as it stands, uncommitted and untracked files included (captured through a temporary index, so the worktree isn't touched), onto the default branch with `git merge-tree --merge-base`, makes one commit with `git commit-tree` authored and committed by the merging user, and runs `git merge --ff-only` in the project's checkout, which must have the default branch checked out. The commit message is the task title. Nothing is pushed. It is refused (409) while a session is `running` or `queued`, on merge conflicts (the message lists the files; the task stays active), and if the default branch moved between the merge and the fast-forward. When the merge changes nothing, no commit is made. `POST /api/tasks/{id}/discard` removes everything without merging. +`POST /api/tasks/{id}/merge-in` (the transcript's **Merge main in** button, labelled with the default branch) brings the default branch into the task branch through the agent: it sends `mergeInPrompt` (`internal/agents/mergein.go`) as a `byre` message to the task's session, or starts a session with it when the task has none. The prompt has the agent run `git merge --no-ff --no-commit`, resolve conflicts, regenerate generated files rather than hand-merging them, check the build and tests, and leave the merge uncommitted; byre's end-of-turn commit concludes it as a merge commit. It is refused (409) while a session is `running` or `queued`. + +`POST /api/tasks/{id}/merge` starts the same turn and records, in memory, that the task is to be merged by the requesting user, who must have a git identity (400 otherwise). When that turn ends normally (not interrupted, not an error), byre squashes the worktree, now containing the default branch, onto it with `git merge-tree --merge-base`, makes one commit with `git commit-tree` authored and committed by the merging user, runs `git merge --ff-only` in the project's checkout (which must have the default branch checked out), then closes the task. The commit message is the task title. Nothing is pushed. When the merge changes nothing, no commit is made. If the squash fails, for example because the default branch moved again during the turn, byre files an error in the inbox and the task stays active. An interrupted or failed turn, or a byre restart during it, leaves the task active without squashing. `POST /api/tasks/{id}/discard` removes everything without merging. ## Running as a service diff --git a/internal/agents/manager.go b/internal/agents/manager.go index 89b27d3..f13aa80 100644 --- a/internal/agents/manager.go +++ b/internal/agents/manager.go @@ -46,6 +46,7 @@ type Manager struct { live map[string]*live closing bool rateLimits map[api.AgentSessionVendor]map[string]any + merges map[string]string deliverMu sync.Mutex capMu sync.Mutex @@ -80,6 +81,7 @@ func New(st *store.Store, limits Limits, worktreeRoot string) *Manager { worktreeRoot: worktreeRoot, live: map[string]*live{}, rateLimits: map[api.AgentSessionVendor]map[string]any{}, + merges: map[string]string{}, } } @@ -718,6 +720,11 @@ func (m *Manager) handle(ctx context.Context, l *live, ev claude.Event) error { go m.continueFromHandoff(l.id, res.Result) return nil } + mergeBy, merging := m.takeMerge(l.taskID) + if merging && finished { + go m.finishMerge(l, mergeBy) + return nil + } err = m.Deliver(ctx, l.id) if err != nil { slog.Error("deliver inbox responses", "session", l.id, "err", err) diff --git a/internal/agents/manager_test.go b/internal/agents/manager_test.go index eb496bf..656d9ba 100644 --- a/internal/agents/manager_test.go +++ b/internal/agents/manager_test.go @@ -530,6 +530,110 @@ func TestCompactCarriesHandoff(t *testing.T) { } } +func TestMergeIn(t *testing.T) { + t.Parallel() + e := newEnv(t) + m := e.manager() + + _, err := m.Create(e.ctx, e.task, e.user, `Create a file task.txt containing exactly the word task.`, testModel) + if err != nil { + t.Fatalf("create session: %v", err) + } + e.waitIdle() + + err = os.WriteFile(filepath.Join(e.repo, "main.txt"), []byte("main\n"), 0o644) + if err != nil { + t.Fatalf("write main.txt: %v", err) + } + gitOut(t, e.repo, "add", "main.txt") + gitOut(t, e.repo, "commit", "--message", "main change") + mainHead := gitOut(t, e.repo, "rev-parse", "HEAD") + + _, err = m.MergeIn(e.ctx, e.task, e.user, "main") + if err != nil { + t.Fatalf("merge in: %v", err) + } + e.waitIdle() + + parents := strings.Fields(gitOut(t, e.task.WorktreePath, "log", "-1", "--format=%P")) + if len(parents) != 2 || parents[1] != mainHead { + t.Fatalf("HEAD parents %v, want a merge of main %s", parents, mainHead) + } + for _, f := range []string{"task.txt", "main.txt"} { + _, err = os.Stat(filepath.Join(e.task.WorktreePath, f)) + if err != nil { + t.Fatalf("%s missing after merge: %v", f, err) + } + } + if status := gitOut(t, e.task.WorktreePath, "status", "--porcelain", "--untracked-files=all"); status != "" { + t.Fatalf("worktree dirty after the merge turn:\n%s", status) + } +} + +func TestMergeResolvesConflict(t *testing.T) { + t.Parallel() + e := newEnv(t) + m := e.manager() + + _, err := m.Create(e.ctx, e.task, e.user, `Create a file notes.txt containing exactly the line "task".`, testModel) + if err != nil { + t.Fatalf("create session: %v", err) + } + e.waitIdle() + err = os.WriteFile(filepath.Join(e.task.WorktreePath, "uncommitted"), []byte("three\n"), 0o644) + if err != nil { + t.Fatalf("write uncommitted: %v", err) + } + + err = os.WriteFile(filepath.Join(e.repo, "notes.txt"), []byte("main\n"), 0o644) + if err != nil { + t.Fatalf("write notes.txt: %v", err) + } + gitOut(t, e.repo, "add", "notes.txt") + gitOut(t, e.repo, "commit", "--message", "main change") + moved := gitOut(t, e.repo, "rev-parse", "HEAD") + + _, err = m.Merge(e.ctx, e.task, e.project, e.user) + if err != nil { + t.Fatalf("merge: %v", err) + } + e.waitFor("task merged", func(ev api.Event) bool { return ev.Kind == "task.merged" }) + + task, err := e.store.GetTask(e.ctx, e.task.Id) + if err != nil { + t.Fatalf("get task: %v", err) + } + if task.Status != api.TaskStatusMerged || task.MergeCommit == nil { + t.Fatalf("task after merge %+v", task) + } + if head := gitOut(t, e.repo, "rev-parse", "main"); head != *task.MergeCommit { + t.Fatalf("main at %s, want merge commit %s", head, *task.MergeCommit) + } + if parent := gitOut(t, e.repo, "rev-parse", "main^"); parent != moved { + t.Fatalf("merge commit parent %s, want %s", parent, moved) + } + if log := gitOut(t, e.repo, "log", "-1", "--format=%s|%an|%cn"); log != task.Title+"|"+gitName+"|"+gitName { + t.Fatalf("unexpected merge commit %s", log) + } + notes, err := os.ReadFile(filepath.Join(e.repo, "notes.txt")) + if err != nil { + t.Fatalf("read notes.txt: %v", err) + } + if !strings.Contains(string(notes), "task") || !strings.Contains(string(notes), "main") || strings.Contains(string(notes), "<<<<<<<") { + t.Fatalf("notes.txt on main doesn't hold both sides:\n%s", notes) + } + _, err = os.Stat(filepath.Join(e.repo, "uncommitted")) + if err != nil { + t.Fatalf("uncommitted file not on main: %v", err) + } + if status := gitOut(t, e.repo, "status", "--porcelain"); status != "" { + t.Fatalf("main checkout dirty after merge: %s", status) + } + if branches := gitOut(t, e.repo, "branch", "--list", e.task.Branch); branches != "" { + t.Fatalf("branch still exists: %s", branches) + } +} + func TestCreateTaskTool(t *testing.T) { t.Parallel() e := newEnv(t) diff --git a/internal/agents/mergein.go b/internal/agents/mergein.go new file mode 100644 index 0000000..24a482b --- /dev/null +++ b/internal/agents/mergein.go @@ -0,0 +1,113 @@ +package agents + +import ( + "context" + "fmt" + "log/slog" + + "g.fc.run/misc/byre/internal/api" + "g.fc.run/misc/byre/internal/git" +) + +func mergeInPrompt(target string) string { + return fmt.Sprintf("Merge %[1]s into this branch: run `git merge --no-ff --no-commit %[1]s`. "+ + "Resolve any conflicts keeping both sides' intent; regenerate generated files instead of hand-merging them. "+ + "Check that the build and tests pass. Leave the merge uncommitted: byre concludes it when the turn ends.", target) +} + +func (m *Manager) MergeIn(ctx context.Context, task api.Task, user api.User, target string) (api.AgentSession, error) { + sessions, err := m.store.ListSessions(ctx, task.Id) + if err != nil { + return api.AgentSession{}, err + } + + for _, sess := range sessions { + if sess.State != api.AgentSessionStateCompleted { + return m.Send(ctx, sess.Id, "byre", mergeInPrompt(target), "") + } + } + + return m.create(ctx, task, user, mergeInPrompt(target), "", "byre", nil) +} + +func (m *Manager) Merge(ctx context.Context, task api.Task, project api.Project, user api.User) (api.AgentSession, error) { + if user.GitName == "" || user.GitEmail == "" { + return api.AgentSession{}, ErrNoGitIdentity + } + + m.mu.Lock() + m.merges[task.Id] = user.Login + m.mu.Unlock() + + sess, err := m.MergeIn(ctx, task, user, project.DefaultBranch) + if err != nil { + m.mu.Lock() + delete(m.merges, task.Id) + m.mu.Unlock() + } + return sess, err +} + +func (m *Manager) takeMerge(taskID string) (string, bool) { + m.mu.Lock() + defer m.mu.Unlock() + login, ok := m.merges[taskID] + delete(m.merges, taskID) + return login, ok +} + +func (m *Manager) finishMerge(l *live, login string) { + ctx := context.Background() + err := m.squashAndClose(ctx, l.taskID, login) + if err == nil { + return + } + + slog.Error("finish merge", "task", l.taskID, "err", err) + m.fileError(l, "The agent merged the default branch in, but squashing onto it failed: "+err.Error()) + err = m.Deliver(ctx, l.id) + if err != nil { + slog.Error("deliver inbox responses", "session", l.id, "err", err) + } +} + +func (m *Manager) squashAndClose(ctx context.Context, taskID, login string) error { + task, err := m.store.GetTask(ctx, taskID) + if err != nil { + return err + } + project, err := m.store.GetProject(ctx, task.ProjectId) + if err != nil { + return err + } + user, err := m.store.GetUser(ctx, login) + if err != nil { + return err + } + + commit, err := git.SquashMerge(project.RepoPath, task.WorktreePath, project.DefaultBranch, task.Title, []string{ + "GIT_AUTHOR_NAME=" + user.GitName, + "GIT_AUTHOR_EMAIL=" + user.GitEmail, + "GIT_COMMITTER_NAME=" + user.GitName, + "GIT_COMMITTER_EMAIL=" + user.GitEmail, + }) + if err != nil { + return err + } + + err = m.RemoveTask(ctx, task, project, login) + if err != nil { + return err + } + + _, err = m.store.MergeTask(ctx, taskID, commit, login) + return err +} + +func (m *Manager) RemoveTask(ctx context.Context, task api.Task, project api.Project, actor string) error { + err := m.StopTask(ctx, task.Id, actor) + if err != nil { + return err + } + return git.RemoveWorktree(project.RepoPath, task.WorktreePath, task.Branch) +} diff --git a/internal/api/api.gen.go b/internal/api/api.gen.go index 0d7cb6c..ad97059 100644 --- a/internal/api/api.gen.go +++ b/internal/api/api.gen.go @@ -665,6 +665,9 @@ type ServerInterface interface { // (POST /api/tasks/{taskId}/merge) MergeTask(w http.ResponseWriter, r *http.Request, taskId string) + // (POST /api/tasks/{taskId}/merge-in) + MergeIn(w http.ResponseWriter, r *http.Request, taskId string) + // (GET /api/tasks/{taskId}/sessions) ListSessions(w http.ResponseWriter, r *http.Request, taskId string) @@ -1398,6 +1401,32 @@ func (siw *ServerInterfaceWrapper) MergeTask(w http.ResponseWriter, r *http.Requ handler.ServeHTTP(w, r) } +// MergeIn operation middleware +func (siw *ServerInterfaceWrapper) MergeIn(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.MergeIn(w, r, taskId) + })) + + for _, middleware := range siw.HandlerMiddlewares { + handler = middleware(handler) + } + + handler.ServeHTTP(w, r) +} + // ListSessions operation middleware func (siw *ServerInterfaceWrapper) ListSessions(w http.ResponseWriter, r *http.Request) { @@ -1606,6 +1635,7 @@ func HandlerWithOptions(si ServerInterface, options StdHTTPServerOptions) http.H m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/tasks/{taskId}", wrapper.GetTask) m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/tasks/{taskId}/unmerged", wrapper.GetUnmerged) m.HandleFunc(http.MethodPost+" "+options.BaseURL+"/api/tasks/{taskId}/merge", wrapper.MergeTask) + m.HandleFunc(http.MethodPost+" "+options.BaseURL+"/api/tasks/{taskId}/merge-in", wrapper.MergeIn) m.HandleFunc(http.MethodPost+" "+options.BaseURL+"/api/tasks/{taskId}/discard", wrapper.DiscardTask) m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/tasks/{taskId}/events", wrapper.ListTaskEvents) m.HandleFunc(http.MethodGet+" "+options.BaseURL+"/api/tasks/{taskId}/changes", wrapper.GetTaskChanges) @@ -1632,77 +1662,79 @@ func HandlerWithOptions(si ServerInterface, options StdHTTPServerOptions) http.H // 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{ - "5Dxrbxu3ln+FmF3ACTCW3dveBVb9lCZp4Yum640T5MPdQqCGRxLrGXJCcqxoDf/3i3PIeWk4kqxaTi76", - "Kco8Ds/7Pb5PMl2UWoFyNpneJwZsqZUF+s9bY7TBH5lWDpTDn7wsc5lxJ7W6+MNqhddstoKC46//NLBI", - "psl/XLRQL/xde+GhPTw8pIkAmxlZIpBk6o+ZJHgjPIugXi1BuRuwVvpDSqNLME561DID3IGYcUJqoU2B", - "vxLBHZw7WUCSJm5TQjJNrDNSLZOHtHlnvsF3BreliF4utIAc7/SRfg+fK7AOBKMHfmRQlG7DCuDKMrcC", - "dgdKaHNmmYAFr3I3iaFkdA4IG1RVJNN/JrIocyhAOTDJ75HnreMOhsh8rqBCTOhwzlxlFJOWrbl0Ui3Z", - "QhvG2cIAMJtrxyolwBCSmVZZZQyobMMyXlpEssFF5MhGDztJE1MphWikpDI5OBBDHNPkyzkCOL/jRvEC", - "hfXPnihvkIIrD3pw/X/rswZ33jeHD269brF5SBPH7e1sRJReJF1+ZzmvBERZ7R+eWX9SHCRKED5X0oDw", - "HEtaBJrjahWKgawlGjShp6NpV8lbDPX8D8gcYvjKOZ6timCYW/bBg25E2ABKzHKpoHNTKgdLMGQGBV9G", - "VIwuT5ngjrOP73+NavOtVKLL3YUkmoRcLJIaMP6XLw0vAquQBYqXdqVdkiaVyaPCKMAU3Iugj1YANmXv", - "/BPM6spkEEWv5G41hIBITpmBUp8byLmTd8Dwybi9onsb4rBYTNlSOmbgTqJomeFqGUeiJnZMR63jxu0Q", - "zy79Ru7tVVISUkydfsr1PKJI3vXP/OP341711J44Zms95B5nPE1s65NbgLVB/3efXz8YhX0XtUmeOX/k", - "gGCOPm23qzmO0bVFRmxhk2vevdeiXxqNP0c1FD73EJDK/dcP7eEH6eoWMxFkQDYNbGpR3CvKn2UOr1do", - "cRGeCyHRTG3cmuZScdNVwrnWOXCVUJKSw45XdS5mcY9iACOfmFKExUfYHBbaAP3f39zpn6JRv7Jdz8qF", - "oDhZaCEXkn4Suj5Q+/PDEbOMWBOJ1dtSoPOb09IO77rMaJg2Joo36O4Hgii5y1YjqhglO46cBxM7+krN", - "9ZcrB0VECQ4xr3mus1v8HVWGY4xv5KDtKEl5JGoOElxqg3GwxhXIS6WJ4Q5muSxkNOnq2/MgNSToU0bO", - "8otLWX0pZevVZkZ0g0iZpldsygxkuihACRAzfzFlvMk17IR5NKcMwbEXqNULqXjOgk9kelEnoW7FHSNI", - "TCHP8nzzcsJ61E0Z/TNhXRqnIX1OO1f9SU1ajTfO/Q2vsS/TAOn/VJLGvJrURrpNl/WB9iRNliELgzsJ", - "6yRNFhsZ5/Nu32jA6vzukXrSvDQSDns1mXRQ2H2lFtnC+/AaeWIPkxvDNz4L0fr/Qcwq5WR+OKZN+bH3", - "cMrM9+UrbmWAi8NT6w7zu3n2wLy7kJuw0si/Y+rdIFMn4h1L77J+1OV4Nouh1/mTYntNeFDyK9WVf/27", - "bUlucelgdG0sVLYmfjDGnRIkomXHOE0BubwD8zSuFmkYUz49XiB563iscaA3jKt5SJ0PFv0HfAHzeQvm", - "QNOoKQ0vhUPTnlD3JlIx/XsGNTlMSv2w5q9PmVYUbjAy1GHtzNahbKQA6wu3D9ffnbL1ChRBReSYAV6W", - "wA1BfJw2bKHtVmB8YkjB04JyzGm6QG4sivKRCrStJ42KELy9CvAhnFoHyyCK1BOR1Jykit4W0tpowOxE", - "gx4sQEhc2TXaeguDftuqBGNBjOQ673yaMaag1GewQ95jfcuksGxhdMGqEv0+XkuHUmDcMg+G8VyrpZUC", - "GqFNgrnZHcbeKvdI+/AdXqbGnFtJ65MlrgTLuQODWm0n7BPqoHRMyMUCTMAbsQih7sz63mPavcjsWrps", - "BbZbdNSJmbRE6+RwhX3HN2wOoblJRlHzxQBbyjtQEWBbikeQY+p27eP5s3R3Qxd2NjdcjRQiIy4Ii6mR", - "vKzQbuxWqWeHFTZkkXRG97UBws1xj2tzBBaP2coO2g4mYIB7DI/QsP0aNlsaXZTHWm2sAChKd0C96p+L", - "8qIp5wf9IXkHM0xsR3oOYj6bb5x/+oD+S86tm8Gdz44Pbdpg+jUjjkbkQc135GgG1oJlfnjg8g0L04FJ", - "FGZI3Eeo8hOGGfrAkSfaIrDX1OH5dY+BA073kf+wAvKv1g2LRwY8W4XiMtS3WBPfwgYEm2/CnUmssAyU", - "78LfWphluax5GnnAcfM4h7fdQWsBdNRkoAIdUaR9fesj2VeDbRq3RNaXT0zjP3B7O9T3ObcwCx31YTtm", - "3E9nubYNr/oi/lSnbUgUW3PLCjBLEEwbJqTNuBEgDk/innHKiGjOMl0UMkKWJ8LnjfZzxe2K+UeZ9uSG", - "YME8137sxmtM1oBYobRbSbVEr0kA403IPc3fYSuStCgJJIRUzjP6wPEgaof3ia9qWO2ldzXU9tKbFj66", - "bunyeAxba3PrDMBjAnG/xUCgG13chpi2Gtzpmj4mOiNNvnNt4+YRSciQH+d4r1GBRavxHlPKJIdqEZX3", - "QuaP6FB0Wu2RqImsGWL8wUBTo9UMpGC9YHAHZuOVEusA9MVLb5+7RUWsCefVJIzydyTlGNOb7eSVHosB", - "/6iCxkdmZkUdqvqseO1v1FbbFRl1SrkBdTZi1PHIumdI0Ui3jweK0fojfXHR1hZEE6sZ3AeYJpXytDkQ", - "zM8VLJMqyytyq1NV5Tn6OGWRGaNYdaAMcbvmbmXZWroVi5/WU6QYV7YkWEuj5kYPv/5ko4tYVOShIdMX", - "t5C2zPlmNppML6WbQcFlPnp39NVcL6Xar6X+sbSPSgd0F4cxwj6WImooR2O/heOByDyQAi10x0aT+cYA", - "7U8Yvw2UXE4uJ5e+PwSKlzKZJt9PLiff+wnRivC+4KW84KKQ6qKNWkug8Ir00Q7TlUimyS/gbmr33eva", - "/u3y8snWn8IJkf2nGzB3YNgKeO68766wWp/gsw+pp2Oe67mPEdpGEoQbpw0WPqE8p8ZCZQGthdfV/4Rh", - "AjzXYsOkX1EyfO2f/5GhV0JB4C0BDjK0ucYpUDZJmBWVdWwO7Pq3X1L2j+u3v6Tsl6ufMb36BPPrCXvl", - "WKGtY39n7+RPfhLT5/XHpoZLvHqAdT9psdniM6F1sZSLPoObFCzMIGOBwr/6RwnLY98t1dGvrmFePvbd", - "np04U8HDQA2/ezI1JM5HlBB1w6IWCYa6NkHj+sGrfwxcg1+91pcmP3z3/cFPbyn2xT3+cyUedploozM7", - "DfQvpjhDISInz6w32dTHUTTuwCIy8iDcHx4hLvSrhhfgwGDOfp9gVKqH8t7/J16GybY2px2atin4vVYD", - "KlG7HjrmIs+p6eMfnbC3WLHTf84skwI9FxJq4fOPfk0teDnaxsGE8x83//PbxP/XMr5wYNiv3LpzunJ+", - "9Ya90H4r0t/7XIHZsIbsl9TyNIDxFY3Ed1exTK4xini7G2eAF/7IJM7DFXBBuVXgYg+lJI0pxFjz5iEN", - "MAn1FiTR80hQv++1NAdfnJfbuSUy++q7V1m9XPyrvVgn1Vx/GVUFGijQWMambCWXK7CO1cNdtpDGOvai", - "WWpYcgcp82P9lC028iV1yxXTucAX6fkJ+1nmKBWmuDF6TUqgFQQVcJpxFgrDM8tomRZT9zPLEGxM7r9K", - "6wjREaFvCahXdY6zcES87ST80a/WQ+/DYkd3sj8GMVQDs7BhEEOqWas5QMl2B7rDp+q0GDQoWYdK+Y67", - "jOpRAu3dp1uBNKxBdMLe+MLMomZgApqySgV6/XtDdb7o0RlP4l7RNMz6maZhBfoXj4ZUdNFW80JSH33C", - "6ocNNS57XXB8tFnFURkCIecocqAcToWhKXrLehWimZ76yU6l6tFcTLvDykOt4ONZ3PFpSm+14qAU6Wtr", - "DsbeikqoVgkenUI9Iibj0/99RMLl1fEeUdyTcLXkn7As6vA4zlMawDdpTGuFp8lhPFuOy2F8ETzGzXdw", - "SjZSZ2KEgxnPczTxygJ9ZoOMqCJI+gZAwPPpTbrTYziBQR/LnNpkA3MeZ7GtVXUnXFENwIzgup29nN55", - "1cP1A1zXqzyv8xtbK0iIUH0ifC+1hnwaNelPrJ+5Om6YFlcWBeuaUU+gKxf34dceP9zl94ksZA/dfZqf", - "2uc2XDjO7cbYedEM0UeN8UMYe57eEmn6eWAG0ZYZREGKKtfWKd8U/9ORNNZbrm0mHGe2O5ZqJkBNc7El", - "eTjwiLmfD/6rsVP4ns686Jkdj9eRca+DjDxxQtk6qLBKZi/uw689Dqr+SveEDqr3NfBY+9LfPpGVNKw4", - "zkvFeEpY8bAAdyoExsz0lb31Nkp1YbtS6MtI/8nwiiuhFwv2Yql5njIBGX3eaFPamgG8wgUDJWxKhXBb", - "RaaMhm0vwxYjjRppydE/3F1YlJY1HxSTi+Ck8fXtMAy1vAgDUxpD0PokLb20RXqDLvedQN8LqqcfkTr2", - "tWf/qPr+7VnVt8ae2LTmloWdHqapF1mBmDxXjRhVVqkcGFOVX0dd3yrh1TWsnBGbhiHiqkbyGxFqwzSS", - "aPNxw9eVZDAJ+1UEeeON1hu513Vvv9L2J5W1A6hHjuinhgK/ASXCQviJkoL+uvlBecHz6hgxcdU6jG+0", - "8UQJ7cU9/rMnn2gyvBMlE7uSrU6i9dQZhKf8uPShz7yLrF0aiw5J3raLVVJ1M/Em/X7RbLqkYe2Kutj0", - "y+8gKGe4H6IgvZDRnxKZLKWTS6UNvMQwyxkCSymAcwOijcVFu6e2Y0FtLPdPMegRLCtVBn6T0X9uQL6h", - "JuPMMr1WTCoBXzCRUNoxp6tsFW9cB92qV+4GQtvKkOoNO6drAkMjUlmHiU8grCU1ZbZC6pAx1FCq2/D1", - "mHIFnNbborMYpDTZ41NPahM1XyKmcQ3mHDM6Svy+tdb2MxufCB+4Ry2PeoqKPsqn3TpUEq2A0mE2B7cG", - "UIzTgp23gqYWXvaUczKmvG/8X1M5YKoYlvgOJ3hsvujXLP80nCCQPw2n+csLX8tWmr9yMNbE4S5b/dVt", - "hHa0D8swjzl3LL18D4W+63ef2qVjJeoAhH5cV458t1RLH1XC8wYybXwQ9JsdzEDBZaTaCJvoXzNfaZbt", - "j8tcniaZ27e+02EudNdvOLPwOd3axbjGgDnfsJJbS58r0Gc71uGzbM6zW4qv+P4kuneB3Nq5cfME2zEj", - "nok+gemBKvgXWVRFMv3u8vKSPuUP/z1q5eYJmtH+bxMd0I3+WGLe47+RCkJ7USdpf7+8fPntJ8mUlz2/", - "B7qhD3TiLihluzboUyaV05Qu9D/vGU+TF9y684U2a25Cf6R9NltBdotOzmkmXdh7Mh3/GHGME/Zb+EpI", - "WlZWFhNp9h4WlcXkfoVJTPv3BcNXYW2DKiVIWLPTVwSZVotcZvHVOPqQ5Wt6zvBl2DN01p/Iyda9nJ1j", - "rZv6oedwJv3uxGETrmARvs1ck7QVA74d17Kvi6X6hIxV22gWFpSwDMvJ5qPkfqc63tH0faduO/PpW1z9", - "r7OfefR1SIurMxD497DVqvNxWDQl+kQTkYiqrHQuwrdZqBpjrp8JDVaduWid2HyadsqlmvqMscWacL+O", - "cpN/2wrn4eFfAQAA//8=", + "7Fxbbxu5kv4rRO8CToC27DkzZ4HVPGWSzMAHk1lvnCAPZwcC1V2SOO4mOyTbitbwf19UkeyLmi3JGsvJ", + "wexTlL6wi1Vf3Yu+TzJVVkqCtCaZ3icaTKWkAfrPW62Vxh+ZkhakxZ+8qgqRcSuUvPjDKInXTLaCkuOv", + "f9ewSKbJv120q164u+bCrfbw8JAmOZhMiwoXSabuM5MEb/hncalXS5D2BowR7iOVVhVoKxxpmQZuIZ9x", + "ImqhdIm/kpxbOLeihCRN7KaCZJoYq4VcJg9p8858g+8Mbos8erlUORR4p0/0e/hcg7GQM3rgRwZlZTes", + "BC4NsytgdyBzpc8My2HB68JOYiRpVQCuDbIuk+k/E1FWBZQgLejk98jzxnILQ2I+11AjJfRxzmytJROG", + "rbmwQi7ZQmnG2UIDMFMoy2qZgyYiMyWzWmuQ2YZlvDJIZENLXiAb3dpJmuhaSiQjJcgUYCEf0pgmX85x", + "gfM7riUvUVj/7InyBndw5ZYeXP/v8K3BnffNxwe3XrfUPKSJ5eZ2NiJKJ5Iuv7OC1zlEWe0enhn3pfiS", + "KEH4XAsNueNY0hLQfC5AKLZkkKhHQg+jaRfkLYVq/gdkFil8ZS3PVqVXzC394B4bETaAzGeFkNC5KaSF", + "JWhSg5IvIxCjy1OWc8vZx/e/RtF8K2Te5e5C0J5ysVgkYWH8L19qXnpWIQskr8xK2SRNal1EhVGCLrkT", + "QZ8sv9iUvXNPMKNqnUGUvIrb1XAFJHLKNFTqXEPBrbgDhk/G9RXN25CGxWLKlsIyDXcCRcs0l8s4EWGz", + "Yxg1lmu7Qzy78I3c2wtSElIMTj8Vah4BkjP9M/f4/bhVPbUljulaj7jHKU/j2/rbLcEYj//d3w8PRte+", + "i+okz6z75GDDHG3ablNzHKODRkZ0YVMo3r3Xkl9phT9HEQqfewQIaf/jh/bjB2F1i5m4pCc29WxqSdwr", + "yp9FAa9XqHERnue5QDU1cW2aC8l1F4RzpQrgMqEgpYAdr6oin8Utigb0fPmUPCw+wuawUBro/+7mTvsU", + "9fq16VpWnufkJ0uVi4Wgn0Suc9Tu+/4Ts4xYE/HV21Kg7zdfSzu86zKjYdqYKN6guR8IouI2W41AMbrt", + "OHFumdinr+RcfbmyUEZAcIh6zQuV3eLvKBiOUb6RD217SYojETm44Upp9IOBViArlSaaW5gVohTRoKuv", + "z4PQkFafMjKWX2zKwqWUrVebGe0b8pQpesWkTEOmyhJkDvnMXUwZb2INM2GOzCnD5dgLRPVCSF4wbxOZ", + "WoQg1K64ZbQSk8izoti8nLDe7qaM/pmw7h6nPnxOO1fdl5qwGm+cuxsOsS9Tv9L/yCSNWTWhtLCbLuv9", + "3pM0WfooDO4ErJM0WWxEnM+7baMGo4q7R+KkeWnEHfZyMmGhNPtSLdKF9/41ssRuTa4137goRKn/hXxW", + "SyuKwylt0o+9H6fIfF+8YlcaeH54aN1hfjfOHqh3d+XGrTTy76h618mEQLyj6V3Wj5ocx+Z8aHX+pNhe", + "Ex0U/Ap55V7/bluSW1w6mFwTc5Wtih9McScFiaDsGKOZQyHuQD+NqcU9jIFPjSdITjseqxxoDeMw96Hz", + "waL/gC9gPG9AH6gaYaf+Jf/RtCfUvYFUDH/PAJPDpNR3a+76lClJ7gY9Q3BrZya4spEErC/c/rru7pSt", + "VyBpVSSOaeBVBVzTio9DwxbZdgXaBYbkPA1Iy6yiC2TGoiQfCaBtnDQQofX2AuCD/2pwll4UqdtEEjhJ", + "Gb0phTFRh9nxBr21AFfi0qxR19s16LepK9AG8pFY550LM8YASnUGM+Q95rdM5IYttCpZXaHdx2vpUAqM", + "G+aWYbxQcmlEDo3QJl7dzA5lb8E9Uj58h5epMGdXwrhgicucFdyCRlSbCfuEGBSW5WKxAO3pRiq8qzsz", + "rvaYdi8ysxY2W4HpJh0hMBOG9jo5HLDv+IbNwRc3SSkCXzSwpbgDGVlsC3i0cgxu186fP0t111dhZ3PN", + "5UgiMmKCMJkaictKZcduVWp2WGJDGknf6L42ILj53OPKHJ7FY7qyY28Hb2BAe4wOX7D9GjpbaVVWx2pt", + "LAEoK3tAvuqei/KiSecH9SFxBzMMbEdqDvl8Nt9Y9/QB9ZeCGzuDOxcdH1q0wfBrRhyNyIOK78jRDIwB", + "w1zzwBYb5rsDk+iaPnAf2ZXrMMzQBo480SaBvaIOL657DBxwuk/8hxWQfTV2mDwy4NnKJ5c+v8Wc+BY2", + "kLP5xt+ZxBJLv/Nd9BsDs6wQgaeRByzXjzN42xW0doEOTAYQ6Igi7eOtT2QfBtt73BJZXz4xxH/g5naI", + "9zk3MPMV9WE5ZtxOZ4UyDa/6Iv4UwjbcFFtzw0rQS8iZ0iwXJuM6h/zwIO4Zu4xI5ixTZSki23KbcHGj", + "+Vxzs2LuUabcdr2zYI5rP3b9NQZrQKyQyq6EXKLVpAXjRcg9xd9hKZJQlPgt+FDOMfrA9iCiw9nEV2Gt", + "9tK7sGp76U27PppuYYu4D1srfWs1wGMccb/EQEs3WNxeMW0R3KmaPsY7455c5drE1SMSkCE/zvFeA4FF", + "i3hHKUWSQ1hE5b0QxSMqFJ1Se8RrImuGFH/Q0ORogYHkrBcM7kBvHCgxD0BbvHT6uVtUxBr/vbCFUf6O", + "hBxjuNkOXumx2OIfpUd8pGdWBlfVZ8VrdyNobVdkVCnlGuTZiFLHPeueJkUj3T4dKEbjPumSiza3oD2x", + "wOD+gmlSS7c3CzlzfQXDhMyKmszqVNZFgTZOGmTGKFWdVYa0XXO7Mmwt7IrFv9YDUowrWxIM0gjc6NHX", + "72x0CYuK3Bdk+uLOhakKvpmNBtNLYWdQclGM3h19tVBLIfej1D2W9knpLN2lYWxjH6s8qihHU79F44HE", + "PBCAFqqjo8l8o4HmJ7SbBkouJ5eTS1cfAskrkUyT7yeXk+9dh2hFdF/wSlzwvBTyovVaSyD3ivujGaar", + "PJkmv4C9Cea7V7X92+Xlk40/+S9E5p9uQN+BZivghXW2u8ZsfYLPPqRuH/NCzZ2PUCYSINxYpTHx8ek5", + "FRZqA6gtPGT/E4YB8FzlGybciJLma/f8jwytEgoCb+VgIUOda4wCRZNEWVkby+bArn/7JWX/uH77S8p+", + "ufoZw6tPML+esFeWlcpY9nf2TvzkOjF9Xn9scrjEwQOM/Unlmy0+E1kXS7HoM7gJwXwPMuYo3Kt/VLA8", + "9t1KHv3qGubVY9/t6YnVNTwMYPjdk8GQOB8BIWLDIIpyhliboHL94OAfW66hL4z1pckP331/8NNbwL64", + "x3+u8oddKtpgZqeC/sWAMxQicvLMOJVNnR9F5fYsIiX3wv3hEeJCu6p5CRY0xuz3CXql0JR39j9xMky2", + "0Zx29rS9g98DDChF7VromIk8p6KPe3TC3mLGTv85M0zkaLlwowY+/+jG1LyVo2kcDDj/cfNfv03cfw3j", + "Cwua/cqNPacr51dv2AvlpiLdvc816A1rtv2SSp4a0L+ikrjqKqbJgaKItbuxGnjpPpnEebgCnlNs5bnY", + "IylJY4AYK948pH5NIr1dkvbzyKV+36tpFr5YJ7dzQ9vsw3cvWJ1c3Ks9XyfkXH0ZhQI1FKgtY1K2EssV", + "GMtCc5cthDaWvWiGGpbcQspcWz9li414SdVyyVSR44v0/IT9LAqUCpNca7UmECgJHgJWMc58YnhmGA3T", + "Yuh+ZhguG5P7r8JYInRE6FsC6mWd4ywcEW/bCX/0q6HpfZjv6Hb2x1b02cDMTxjEiGrGag4A2W5Hd3hX", + "nQaDBinrEJTvuM0oH6Wlnfm0KxCaNYRO2BuXmBlEBgagKaul3697bwjni94+40HcK+qGGdfT1KxE++LI", + "EJIumnpeCqqjT1h4WFPhslcFx0ebURyZ4SJkHPMCKIaTvmmK1jKMQjTdU9fZqWVozcXQ7UceAsDHo7jj", + "w5TeaMVBIdLXRg763ppSqBYEjw6hHuGT8en/PCLgcnC8RxL3BFzt9k+YFnV4HOcpNeCbMKbVwtPEMI4t", + "x8UwLgke4+Y7OCUbqTIxwsGMFwWqeG2AjtkgI+oIka4A4Ol8epXu1BhOoNDHMieorGfO4zS21apuhyuK", + "AIwIrtvey+mNV2iuH2C6XhVFiG9MAIj3UP1NuFpqWPk0MOl3rJ85O26YFgeLhHVg1BNg5eLe/9pjh7v8", + "PpGG7Nl3f89PbXMbLhxndmPsvGia6KPK+MG3PU+vidT9PDCCaNMM2kGKkGvzlG+K/+lIGOs01zQdjjPT", + "bUs1HaCmuNhuedjwiJmfD+7U2ClsT6df9MyGx2Fk3OogI08cULYGyo+SmYt7/2uPgQqndE9ooHqngcfK", + "l+72ibSkYcVxVirGU6KK+wG4UxEwpqavzK3TUcoL25FCl0a6I8MrLnO1WLAXS8WLlOWQ0fFGk9LUDOAV", + "njOQuUkpEW6zyJRRs+2ln2KkViMNObqHuwOLwrDmQDGZCE6ID7d9M9Tw0jdMqQ1B45M09NIm6Q253FUC", + "XS0odD8ieexrx/5R+P7tWeEbqCc2rblhfqaHKapF1pBPnitHjIJVSAta19XXgetbmTu4+pEzYtPQRVwF", + "Ir8RoTZMI4k2hxu+riS9SpivIsgbp7ROyR3Wnf4K0+9UBgMQWo5op4YCvwGZ+4HwEwUF/XHzg+KC58UY", + "MXHVGoxvtPBEAe3FPf6zJ55oIrwTBRO7gq1OoPXUEYTb+XHhQ595F1k7NBZtkrxtB6uE7EbiTfj9opl0", + "Sf3YFVWx6ZebQZBWc9dEwf1CRn9KZLIUViyl0vAS3SxnuFhKDpxryFtfXLZzajsG1MZi/xSdHq1lhMzA", + "TTK64wZkG8I2zgxTa8mEzOELBhJSWWZVna3ihWuPrTByNxDaVoQUJuysChv0hUhpLAY+fmPtVlNmatwd", + "MoYKSqEMH9qUK+A03hbtxeBOkz029aQ6EfgSUY1r0OcY0VHg962Vtp9Z+XJ/wD2qeVRTlHQon2brECRK", + "AoXDbA52DSAZpwE7pwVNLrzsgXMyBt437q+pHNBV9EN8h294rL/oxiz/9DpeIH96neYvL3wtXWn+ysFY", + "EYfbbPVX1xGa0T4swjzmu2Ph5Xso1V2/+tQOHcs8OCC046q2ZLuFXDqv4p/XkCntnKCb7GAaSi4i2Yaf", + "RP+a8UozbH9c5PI0wdy+8Z0Oc6E7fsOZgc/p1izGNTrM+YZV3Bg6rkDHdozFZ9mcZ7fkX/H9SXTuArm1", + "c+LmCaZjRiwTHYHpLVXyL6Ksy2T63eXlJR3l9/89auTmCYrR7m8THVCN/lhh3OPOSHmhvQhB2t8vL19+", + "+0EyxWXPb4F8gtsUrVxBzZ3w9eeRzoWMFsaaP5KSsvlGh7M+I9ZMSKsotOgfBRoPqRfc2POF0muufS2l", + "fTZbQXaLBtEqJqyfkdIdWxozolSJ4/q2pc8ft5qw3/xZI2FYVRsMx9l7WNQGU4QVhkLtXyn0Z8s6Za5I", + "5E7HXuJ29nmTbXc+Ym+N7ttOvi8CCp9fO5qys4ez1w4VGLsDwQ7xW6kkZaequEMEcblhmZKLQmTWjatr", + "WIIkHMkl8z8hd7XpCbvpnCH25HSL4ZSEmlCuCuWotT+Vv6ITdRKeAthX8v9h/RSwDtXOnY3fm/DQc7jb", + "Pu8P6wH3NCNsaStK+nac7746r+xvZKwehdpqyAcK2zm23+/lxGv+rjLbLfg/fRG4//cLnrk5fIgCd1pm", + "/xq6WneOT0aThk8UGkWgslJF7k8vIjRG3UWuwMgzG62kNIc3Tzl2Fr4xNnrm74ezjZN/2RrAw8P/BQAA", + "//8=", } // decodeSpec returns the embedded OpenAPI spec as raw JSON bytes, diff --git a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl index 516d168..b9701a7 100644 --- a/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl +++ b/internal/claude/testdata/transcripts/TestCommitIdentityHooksAndMCP.jsonl @@ -1,41 +1,36 @@ -{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_e2507dc4e295a3c1","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"10843dde-8955-421a-9ce0-340c8a134f3c","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":"10843dde-8955-421a-9ce0-340c8a134f3c","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_e2507dc4e295a3c1","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":81528,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":{"PostToolUse":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_9cb77f8b43f6be63","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"a6229ca5-1994-453a-83a3-8b3e05694cbe","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":"a6229ca5-1994-453a-83a3-8b3e05694cbe","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_9cb77f8b43f6be63","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":98363,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Create a file hello.txt containing exactly the word hi, then git add and git commit it with the message \"add hello\", then call the finish tool.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"4ba4f280-43fe-4b87-98d2-a55ef3cf03c4","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} -{"dir":"send","msg":{"response":{"request_id":"4ba4f280-43fe-4b87-98d2-a55ef3cf03c4","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"2c42f84c-f1c9-45ca-a941-1f42fbdf8af8","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} -{"dir":"send","msg":{"response":{"request_id":"2c42f84c-f1c9-45ca-a941-1f42fbdf8af8","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"finish","description":"Call this once the task is complete.","inputSchema":{"type":"object","properties":{}}}]}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__byre__finish"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"},{"name":"byre","status":"connected","source":"sdk"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"3c76debd-4a9d-4624-97d6-863f2ec9b9ed","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e/scratchpad","messaging_socket_path":"/tmp/cc-socks/81528.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"e0eeaefb-a84a-48ce-8087-02ae0d2fc3fa"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.13,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"45fed1ea-f6c0-4c7e-bdae-e75d37811f8e","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FtxAHJWsPKCwNRcJ37","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011W8vHUb98gd2hFYtKCpkjY","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001/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":15290,"cache_read_input_tokens":22425,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15290},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"35d5fe38-3951-447d-a661-8b6f77116653","timestamp":"2026-10-15T02:46:26.366Z","request_id":"req_011Cg3FtwrfoTwh1sj7Mtd43","wire_tool_inputs":{"toolu_011W8vHUb98gd2hFYtKCpkjY":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001/hello.txt","content":"hi"}}}} -{"dir":"recv","msg":{"type":"control_request","request_id":"9cc18669-5851-459d-87e7-70d05efbc0ff","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e/scratchpad","prompt_id":"609e9c5b-2859-4a37-9592-cd6563ac499d","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_011W8vHUb98gd2hFYtKCpkjY","duration_ms":4},"tool_use_id":"toolu_011W8vHUb98gd2hFYtKCpkjY"}}} -{"dir":"send","msg":{"response":{"request_id":"9cc18669-5851-459d-87e7-70d05efbc0ff","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011W8vHUb98gd2hFYtKCpkjY","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"75b515a3-f58f-4913-901c-6228006eea7e","timestamp":"2026-10-15T02:46:26.387Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_011W8vHUb98gd2hFYtKCpkjY","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"aaf295e3-3b0c-49c6-86a0-e29e3b7b3b7c"}} -{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"3a5994c1-ba0f-43a8-956c-a273b5318cd1"}} -{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":220,"estimated_tokens_delta":170,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"740e2142-82b7-47eb-8718-a8686f2f90a2"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Fu6U66xWr5vMA8Q8ZG","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37715,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"01e73675-e134-4ce6-91e6-bc4d516dc398","timestamp":"2026-10-15T02:46:28.575Z","request_id":"req_011Cg3Fu6By81CJgbe65SVYK","thinking_duration_ms":1234,"thinking_display":"updates"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Fu6U66xWr5vMA8Q8ZG","type":"message","role":"assistant","content":[{"type":"text","text":"Authorization for the add and commit, quoted from the current request: \"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":4714,"cache_read_input_tokens":37715,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"ce2c844f-c356-4336-b336-eb50e9973946","timestamp":"2026-10-15T02:46:28.577Z","request_id":"req_011Cg3Fu6By81CJgbe65SVYK"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Fu6U66xWr5vMA8Q8ZG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0171pJvHscx7V7eBTgqT9Y2b","name":"Bash","input":{"command":"git add hello.txt","description":"Stage hello.txt","timeout":15000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37715,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"919f9df7-bfdb-4dea-bd66-4874bf62bb03","timestamp":"2026-10-15T02:46:29.136Z","request_id":"req_011Cg3Fu6By81CJgbe65SVYK","wire_tool_inputs":{"toolu_0171pJvHscx7V7eBTgqT9Y2b":{"command":"git add hello.txt","description":"Stage hello.txt","timeout":15000}}}} -{"dir":"recv","msg":{"type":"control_request","request_id":"2cf42a39-faef-40f5-a9d0-c462c93ef5b2","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e/scratchpad","prompt_id":"609e9c5b-2859-4a37-9592-cd6563ac499d","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git add hello.txt","timeout":15000,"description":"Stage hello.txt"},"tool_response":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_use_id":"toolu_0171pJvHscx7V7eBTgqT9Y2b","duration_ms":83},"tool_use_id":"toolu_0171pJvHscx7V7eBTgqT9Y2b"}}} -{"dir":"send","msg":{"response":{"request_id":"2cf42a39-faef-40f5-a9d0-c462c93ef5b2","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0171pJvHscx7V7eBTgqT9Y2b","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"5a5e6105-ea27-4488-a273-ef52da563984","timestamp":"2026-10-15T02:46:29.241Z","tool_use_result":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"tool_result_meta":[{"id":"toolu_0171pJvHscx7V7eBTgqT9Y2b","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Fu6U66xWr5vMA8Q8ZG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013E9Mkzdh5SEf7HRhZJQPCc","name":"Bash","input":{"command":"git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Commit hello.txt","timeout":15000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37715,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"91abfa0f-77f3-4428-88f7-72ebcf91b948","timestamp":"2026-10-15T02:46:29.724Z","request_id":"req_011Cg3Fu6By81CJgbe65SVYK","wire_tool_inputs":{"toolu_013E9Mkzdh5SEf7HRhZJQPCc":{"command":"git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Commit hello.txt","timeout":15000}}}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.14,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"50b6a912-3913-4381-81a0-b6e6d90c2d37","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e"}} -{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001","uuid":"9b4e243f-0f89-4a30-a2a6-fe7b03a3bcb4","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"33b4eb03-642b-443e-808d-31982aaf6295","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e/scratchpad","prompt_id":"609e9c5b-2859-4a37-9592-cd6563ac499d","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":15000,"description":"Commit hello.txt"},"tool_response":{"stdout":"[main a2ec6ac] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"a2ec6ac","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_013E9Mkzdh5SEf7HRhZJQPCc","duration_ms":30},"tool_use_id":"toolu_013E9Mkzdh5SEf7HRhZJQPCc"}}} -{"dir":"send","msg":{"response":{"request_id":"33b4eb03-642b-443e-808d-31982aaf6295","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013E9Mkzdh5SEf7HRhZJQPCc","type":"tool_result","content":"[main a2ec6ac] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"cedfd6ec-c0b7-4502-81c7-958da80876b2","timestamp":"2026-10-15T02:46:29.772Z","tool_use_result":{"stdout":"[main a2ec6ac] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"a2ec6ac","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_013E9Mkzdh5SEf7HRhZJQPCc","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"9851c904-b4c0-4926-bf4b-705681cc178e"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FuM1i9dYkPJTL9NGBD","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01D9GCDrGh1LeRvRXPb3UbVv","name":"mcp__byre__finish","input":{},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":545,"cache_read_input_tokens":42429,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":545},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"3779920f-e91a-4b91-87ac-11a8f09f7877","timestamp":"2026-10-15T02:46:30.769Z","request_id":"req_011Cg3FuLhbTw3sDNa3wWWJx","wire_tool_inputs":{"toolu_01D9GCDrGh1LeRvRXPb3UbVv":{}},"tool_use_meta":[{"id":"toolu_01D9GCDrGh1LeRvRXPb3UbVv","display_name":"Finish","server_display_name":"byre"}]}} -{"dir":"recv","msg":{"type":"control_request","request_id":"9501a47e-d825-493f-a1e8-09b389cae471","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"finish","arguments":{},"_meta":{"claudecode/toolUseId":"toolu_01D9GCDrGh1LeRvRXPb3UbVv","progressToken":2}},"jsonrpc":"2.0","id":2}}}} -{"dir":"send","msg":{"response":{"request_id":"9501a47e-d825-493f-a1e8-09b389cae471","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"noted"}]}}},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"e9e34f03-582f-4348-89b3-91c6a61cbc50","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP1667272107/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP1667272107-001/b0447397-29cd-43a9-a25b-82ad4b77626e/scratchpad","prompt_id":"609e9c5b-2859-4a37-9592-cd6563ac499d","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__finish","tool_input":{},"tool_response":[{"type":"text","text":"noted"}],"tool_use_id":"toolu_01D9GCDrGh1LeRvRXPb3UbVv","duration_ms":3,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_01D9GCDrGh1LeRvRXPb3UbVv"}}} -{"dir":"send","msg":{"response":{"request_id":"e9e34f03-582f-4348-89b3-91c6a61cbc50","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01D9GCDrGh1LeRvRXPb3UbVv","type":"tool_result","content":[{"type":"text","text":"noted"}]}]},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"9810fed9-34b8-4086-938c-35e0efe0df27","timestamp":"2026-10-15T02:46:30.778Z","tool_use_result":[{"type":"text","text":"noted"}],"tool_result_meta":[{"id":"toolu_01D9GCDrGh1LeRvRXPb3UbVv","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"ac391ffc-d10c-4b23-a9c3-db1ce7559248"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FuRKQezBHM2bKBmfMr","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi`, staged it, and committed it to main as `a2ec6ac` with the message \"add hello\". I then called the finish tool. I didn't push."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":63,"cache_read_input_tokens":42974,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"output_tokens":61,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","uuid":"fdb8722c-9fad-4b21-9089-4838be3bd53d","timestamp":"2026-10-15T02:46:32.079Z","request_id":"req_011Cg3FuR1oYips1bkBDDdKv"}} -{"dir":"recv","msg":{"duration_api_ms":8261,"stop_reason":"end_turn","session_id":"b0447397-29cd-43a9-a25b-82ad4b77626e","total_cost_usd":0.10353799999999999,"usage":{"input_tokens":8,"cache_creation_input_tokens":20612,"cache_read_input_tokens":145543,"output_tokens":639,"output_tokens_details":{"thinking_tokens":105},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":20612,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":61,"cache_read_input_tokens":42974,"cache_creation_input_tokens":63,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1207,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001297,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":8,"outputTokens":639,"cacheReadInputTokens":145543,"cacheCreationInputTokens":20612,"webSearchRequests":0,"costUSD":0.1034083,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":105,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":5,"subtype":"success","api_error_status":null,"result":"I created `hello.txt` containing `hi`, staged it, and committed it to main as `a2ec6ac` with the message \"add hello\". I then called the finish tool. I didn't push.","ttft_ms":2045,"type":"result","duration_ms":7772,"uuid":"b120930c-6f1a-45f6-866d-87434bf6b851","ttft_stream_ms":1104,"time_to_request_ms":37,"first_content_frame_ms":1104,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"control_request","request_id":"06906118-7e10-4f24-b5da-c74d19ece14b","request":{"subtype":"mcp_message","server_name":"byre","message":{"jsonrpc":"2.0","method":"notifications/initialized"}}}} +{"dir":"send","msg":{"response":{"request_id":"06906118-7e10-4f24-b5da-c74d19ece14b","response":{"mcp_response":{"jsonrpc":"2.0","id":null,"result":{}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"6eacdcc3-72a7-4cf3-9680-26dcfaf5dc86","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/list","jsonrpc":"2.0","id":1}}}} +{"dir":"send","msg":{"response":{"request_id":"6eacdcc3-72a7-4cf3-9680-26dcfaf5dc86","response":{"mcp_response":{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"finish","description":"Call this once the task is complete.","inputSchema":{"type":"object","properties":{}}}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","tools":["Task","Artifact","ArtifactComments","ArtifactData","Bash","CronCreate","CronDelete","CronList","DesignSync","Edit","EnterWorktree","ExitWorktree","ListAgents","LSP","Monitor","NotebookEdit","PushNotification","Read","RemoteTrigger","ReportFindings","ScheduleWakeup","SendMessage","Skill","TaskStop","ToolSearch","WebFetch","WebSearch","Workflow","Write","mcp__byre__finish"],"mcp_servers":[{"name":"claude.ai Claude Docs","status":"pending","source":"claudeai"},{"name":"claude.ai Heliosian","status":"pending","source":"claudeai"},{"name":"claude.ai Fastmail","status":"pending","source":"claudeai"},{"name":"claude.ai Google Calendar","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Gmail","status":"needs-auth","source":"claudeai"},{"name":"claude.ai Google Drive","status":"needs-auth","source":"claudeai"},{"name":"byre","status":"connected","source":"sdk"}],"model":"claude-sonnet-5-5","permissionMode":"bypassPermissions","slash_commands":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","advisor","agents","auto-mode-setup","autocompact","clear","color","compact","config","output-style","context","effort","fast","focus","heapdump","init","mcp","import","model","__remote-workflow","workflow-launch-exec","reload-plugins","reload-skills","rename","ultrareview","security-review","usage-credits","extra-usage","usage","insights","recap","skill-doctor","goal","design-consent","design-revoke","list-agents","team-onboarding","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"terminal_slash_commands":["doctor","color","focus","reload-plugins"],"apiKeySource":"none","claude_code_version":"2.1.296","output_style":"default","agents":["claude","claude-code-guide","Explore","general-purpose","Plan","statusline-setup"],"skills":["deep-research","design","slides","design-sync","dataviz","artifact-diagramming","artifact-capabilities","update-config","verify","debug","code-review","simplify","batch","fewer-permission-prompts","doctor","loop","schedule","claude-api","workflow-authoring","run","run-skill-generator","plugin-authoring","anthropic-skills:docs","anthropic-skills:docx","anthropic-skills:google-workspace","anthropic-skills:import-memory","anthropic-skills:morning","anthropic-skills:pdf","anthropic-skills:pptx","anthropic-skills:skill-creator","anthropic-skills:xlsx"],"plugins":[{"name":"clangd-lsp","path":"/Users/flamingcow/.claude/plugins/cache/claude-plugins-official/clangd-lsp/1.0.0","source":"clangd-lsp@claude-plugins-official","version":"1.0.0"},{"name":"cc-plugin-agents-md","path":"builtin","source":"cc-plugin-agents-md@builtin"},{"name":"cc-plugin-telemetry","path":"builtin","source":"cc-plugin-telemetry@builtin"},{"name":"cc-plugin-plugin-authoring","path":"builtin","source":"cc-plugin-plugin-authoring@builtin"}],"capabilities":["interrupt_receipt_v1","interrupt_cancel_queued_v1","interrupt_send_now_v1","msg_lifecycle_v1","request_marker_lists_v1","sdk_mcp_tools_list_changed","sdk_mcp_manifests","mcp_read_resource_v1","mcp_tool_ui_meta_v1","ui_surface_v1"],"analytics_disabled":false,"product_feedback_disabled":false,"uuid":"82482951-e1f4-46fa-91ba-5451032b96e8","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","messaging_socket_path":"/tmp/cc-socks/98363.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"df9da8f0-0c65-4ede-b6e0-5466e93d1f40"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"470c07e2-2518-4208-b65b-5a6a1264e4bb","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mazc5AwLTmBXXhF9g4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PTz61sYh9BChK8j25Ufgo6","name":"Write","input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/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":15288,"cache_read_input_tokens":22425,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15288},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"1bfa04d3-4d53-434a-aeaf-8f4d79a43914","timestamp":"2026-10-15T04:01:03.895Z","request_id":"req_011Cg3MazPBKSDDCkt2cTyYy","wire_tool_inputs":{"toolu_01PTz61sYh9BChK8j25Ufgo6":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi"}}}} +{"dir":"recv","msg":{"type":"control_request","request_id":"e871528f-5b0e-4825-8e78-becf403d7dea","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","prompt_id":"83f6996d-b89f-4bc4-b44f-7e33e389dd78","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Write","tool_input":{"file_path":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi"},"tool_response":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_use_id":"toolu_01PTz61sYh9BChK8j25Ufgo6","duration_ms":2},"tool_use_id":"toolu_01PTz61sYh9BChK8j25Ufgo6"}}} +{"dir":"send","msg":{"response":{"request_id":"e871528f-5b0e-4825-8e78-becf403d7dea","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PTz61sYh9BChK8j25Ufgo6","type":"tool_result","content":"File created successfully at: /private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt (file state is current in your context — no need to Read it back)"}]},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"1cc511cd-a275-4158-a560-22592a6690c4","timestamp":"2026-10-15T04:01:03.906Z","tool_use_result":{"type":"create","filePath":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001/hello.txt","content":"hi","structuredPatch":[],"originalFile":null,"userModified":false},"tool_result_meta":[{"id":"toolu_01PTz61sYh9BChK8j25Ufgo6","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"d08ba37d-7a1d-49b2-9f59-b269885dbe22"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":50,"estimated_tokens_delta":50,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"352b51a2-b363-4fdc-b326-dd52c56e15fe"}} +{"dir":"recv","msg":{"type":"system","subtype":"thinking_tokens","estimated_tokens":175,"estimated_tokens_delta":125,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"c1569831-922a-4213-a220-b169d7dfcf55"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb9niCnhu6pdEc7bqP","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4714,"cache_read_input_tokens":37713,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":9,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"8aa1070b-1b43-4de6-95f3-1b95bcd678b7","timestamp":"2026-10-15T04:01:05.644Z","request_id":"req_011Cg3Mb9VrfYwz8CvMJ45xd","thinking_duration_ms":651,"thinking_display":"updates"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb9niCnhu6pdEc7bqP","type":"message","role":"assistant","content":[{"type":"text","text":"Authorization for the commit, quoted 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":4714,"cache_read_input_tokens":37713,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":9,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"3af318ea-9049-4d28-b4a6-b6f1ef41e5d6","timestamp":"2026-10-15T04:01:05.645Z","request_id":"req_011Cg3Mb9VrfYwz8CvMJ45xd"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb9niCnhu6pdEc7bqP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","name":"Bash","input":{"command":"git add hello.txt \u0026\u0026 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","description":"Stage and 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":4714,"cache_read_input_tokens":37713,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4714},"output_tokens":9,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"b9c75e96-e56f-4804-b252-b0924f4bacd9","timestamp":"2026-10-15T04:01:06.329Z","request_id":"req_011Cg3Mb9VrfYwz8CvMJ45xd","wire_tool_inputs":{"toolu_01Kdth8WgpR7RU3So7ZfHqAx":{"command":"git add hello.txt \u0026\u0026 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":30000,"description":"Stage and commit hello.txt"}}}} +{"dir":"recv","msg":{"type":"system","subtype":"vcs_state_changed","kind":"commit","branch":"main","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","uuid":"d3d17884-f3bf-4d30-9e33-2d2bf6ab1319","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"693fcc91-eef3-4df1-8c9e-3faf01e28505","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","prompt_id":"83f6996d-b89f-4bc4-b44f-7e33e389dd78","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"git add hello.txt \u0026\u0026 git commit -m \"add hello\" -- hello.txt # USER EXPLICITLY AUTHORIZED THIS COMMIT IN THE IMMEDIATELY PRECEDING REQUEST","timeout":30000,"description":"Stage and commit hello.txt"},"tool_response":{"stdout":"[main 38d200e] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"38d200e","kind":"committed","branch":"main"}}},"tool_use_id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","duration_ms":73},"tool_use_id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx"}}} +{"dir":"send","msg":{"response":{"request_id":"693fcc91-eef3-4df1-8c9e-3faf01e28505","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","type":"tool_result","content":"[main 38d200e] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","is_error":false}]},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"6ad92344-fa35-4937-b216-1e648cca4536","timestamp":"2026-10-15T04:01:06.423Z","tool_use_result":{"stdout":"[main 38d200e] add hello\n 1 file changed, 1 insertion(+)\n create mode 100644 hello.txt","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false,"gitOperation":{"commit":{"sha":"38d200e","kind":"committed","branch":"main"}}},"tool_result_meta":[{"id":"toolu_01Kdth8WgpR7RU3So7ZfHqAx","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"5541f04e-7a98-4b33-ba21-ca8017d1c088"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbLTR9oKNbR6WJ5WEc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0193tN3xiKgw4xd3XKGsHavL","name":"mcp__byre__finish","input":{},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":333,"cache_read_input_tokens":42427,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":333},"output_tokens":24,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"59e07fbc-a065-495a-bb98-c1e58c546a5a","timestamp":"2026-10-15T04:01:07.549Z","request_id":"req_011Cg3MbLCHFaZhwoVvd6Pep","wire_tool_inputs":{"toolu_0193tN3xiKgw4xd3XKGsHavL":{}},"tool_use_meta":[{"id":"toolu_0193tN3xiKgw4xd3XKGsHavL","display_name":"Finish","server_display_name":"byre"}]}} +{"dir":"recv","msg":{"type":"control_request","request_id":"ac85329e-c81d-40d4-bf52-9be41e5d411d","request":{"subtype":"mcp_message","server_name":"byre","message":{"method":"tools/call","params":{"name":"finish","arguments":{},"_meta":{"claudecode/toolUseId":"toolu_0193tN3xiKgw4xd3XKGsHavL","progressToken":2}},"jsonrpc":"2.0","id":2}}}} +{"dir":"send","msg":{"response":{"request_id":"ac85329e-c81d-40d4-bf52-9be41e5d411d","response":{"mcp_response":{"jsonrpc":"2.0","id":2,"result":{"content":[{"type":"text","text":"noted"}]}}},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"8f0ebd1b-949b-498b-9309-3a05ae9918ac","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestCommitIdentityHooksAndMCP2708089900/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestCommitIdentityHooksAndMCP2708089900-001/d50a2e9d-312b-417d-b170-52615c3b7607/scratchpad","prompt_id":"83f6996d-b89f-4bc4-b44f-7e33e389dd78","permission_mode":"bypassPermissions","effort":{"level":"medium"},"hook_event_name":"PostToolUse","tool_name":"mcp__byre__finish","tool_input":{},"tool_response":[{"type":"text","text":"noted"}],"tool_use_id":"toolu_0193tN3xiKgw4xd3XKGsHavL","duration_ms":2,"mcp_server":{"name":"byre","source":"sdk"}},"tool_use_id":"toolu_0193tN3xiKgw4xd3XKGsHavL"}}} +{"dir":"send","msg":{"response":{"request_id":"8f0ebd1b-949b-498b-9309-3a05ae9918ac","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0193tN3xiKgw4xd3XKGsHavL","type":"tool_result","content":[{"type":"text","text":"noted"}]}]},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"899b48af-c55a-454e-a593-5bf601c24d7f","timestamp":"2026-10-15T04:01:07.559Z","tool_use_result":[{"type":"text","text":"noted"}],"tool_result_meta":[{"id":"toolu_0193tN3xiKgw4xd3XKGsHavL","permission_decision":{"decision":"accept","source":"config","reason_type":"mode"}}]}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"683ce938-eca8-4bc5-b464-479820dc7ade"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbRKMTqGWwKcK8UZCJ","type":"message","role":"assistant","content":[{"type":"text","text":"I created `hello.txt` containing `hi` and committed it to main as \"add hello\" (commit `38d200e`). I then called the finish tool."}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":63,"cache_read_input_tokens":42760,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"output_tokens":48,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","uuid":"401cbe37-6748-485b-87db-e67b17eeb4e0","timestamp":"2026-10-15T04:01:08.527Z","request_id":"req_011Cg3MbR4jXQdGy2FhTfPxf"}} +{"dir":"recv","msg":{"duration_api_ms":7264,"stop_reason":"end_turn","session_id":"d50a2e9d-312b-417d-b170-52615c3b7607","total_cost_usd":0.10104020000000001,"usage":{"input_tokens":8,"cache_creation_input_tokens":20398,"cache_read_input_tokens":145325,"output_tokens":477,"output_tokens_details":{"thinking_tokens":48},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":20398,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":48,"cache_read_input_tokens":42760,"cache_creation_input_tokens":63,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":63},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1207,"outputTokens":18,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001297,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":8,"outputTokens":477,"cacheReadInputTokens":145325,"cacheCreationInputTokens":20398,"webSearchRequests":0,"costUSD":0.1009105,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":48,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":4,"subtype":"success","api_error_status":null,"result":"I created `hello.txt` containing `hi` and committed it to main as \"add hello\" (commit `38d200e`). I then called the finish tool.","ttft_ms":2229,"type":"result","duration_ms":6876,"uuid":"473931ce-c34c-498e-a6ad-bde383ae9da7","ttft_stream_ms":1227,"time_to_request_ms":27,"first_content_frame_ms":1227,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestImageInput.jsonl b/internal/claude/testdata/transcripts/TestImageInput.jsonl index f39b796..55382e8 100644 --- a/internal/claude/testdata/transcripts/TestImageInput.jsonl +++ b/internal/claude/testdata/transcripts/TestImageInput.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_b7ae1940e644e81d","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_b7ae1940e644e81d","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":84647,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_f69e88afb0ab9ff3","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_f69e88afb0ab9ff3","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":98366,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":[{"source":{"data":"iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAAZElEQVR4nOzPUQkAIBTAQBH7V9YQfhwPdgm2c9dsWwf8akBrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0BrQGtAa0B7AQAA///jRQGCmaQfxwAAAABJRU5ErkJggg==","media_type":"image/png","type":"base64"},"type":"image"},{"text":"Without using any tools, what single colour fills the attached image? Reply with just the colour name.","type":"text"}],"role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestImageInput3452885842/001","session_id":"9427c7e7-455d-4edd-a89f-4a84a692cbad","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":"4d1560c5-885a-404e-bf66-9b612b2044ea","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput3452885842-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput3452885842-001/9427c7e7-455d-4edd-a89f-4a84a692cbad/scratchpad","messaging_socket_path":"/tmp/cc-socks/84647.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"9427c7e7-455d-4edd-a89f-4a84a692cbad","uuid":"5a918793-c9fd-4550-ba44-c6a279d007d5"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.15,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"80582691-eb6d-4494-977e-dac1cd8430e0","session_id":"9427c7e7-455d-4edd-a89f-4a84a692cbad"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3GmkVxw3Na4CsLv2XYA","type":"message","role":"assistant","content":[{"type":"text","text":"Red"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15356,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15356},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"9427c7e7-455d-4edd-a89f-4a84a692cbad","uuid":"19a2c5c7-5d40-4bdf-a4ea-4adf2d12ee92","timestamp":"2026-10-15T02:57:54.843Z","request_id":"req_011Cg3GmkGKx1MQWSD4krkZH"}} -{"dir":"recv","msg":{"duration_api_ms":1909,"stop_reason":"end_turn","session_id":"9427c7e7-455d-4edd-a89f-4a84a692cbad","total_cost_usd":0.0638324,"usage":{"input_tokens":2,"cache_creation_input_tokens":15356,"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":15356,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15356,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15356},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1192,"outputTokens":17,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001277,"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":15356,"webSearchRequests":0,"costUSD":0.0637047,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"Red","ttft_ms":1341,"type":"result","duration_ms":1361,"uuid":"c419b73f-0a69-4c34-8e78-37bab60565d8","ttft_stream_ms":1337,"time_to_request_ms":29,"first_content_frame_ms":1338,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestImageInput344995001/001","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","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":"cdf35a6a-4739-402b-8946-f1cc1cfa195c","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput344995001-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestImageInput344995001-001/4071b9c2-8eaa-4dc7-8728-d111bbfd6614/scratchpad","messaging_socket_path":"/tmp/cc-socks/98366.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","uuid":"4a0f0781-c467-4039-83de-41973b4331e6"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"4eae71b6-44db-4115-a35f-4725c09ff1ed","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MazeJKLj6L1nCEpvXJ","type":"message","role":"assistant","content":[{"type":"text","text":"Red"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15356,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15356},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","uuid":"f4e1de95-8aae-4a2f-ab81-a57df5a10d96","timestamp":"2026-10-15T04:01:02.851Z","request_id":"req_011Cg3MazRQhqgHAiYLrirtd"}} +{"dir":"recv","msg":{"duration_api_ms":1689,"stop_reason":"end_turn","session_id":"4071b9c2-8eaa-4dc7-8728-d111bbfd6614","total_cost_usd":0.0638324,"usage":{"input_tokens":2,"cache_creation_input_tokens":15356,"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":15356,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15356,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15356},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1192,"outputTokens":17,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001277,"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":15356,"webSearchRequests":0,"costUSD":0.0637047,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"Red","ttft_ms":1174,"type":"result","duration_ms":1197,"uuid":"be796010-891c-418d-a156-fdcd1805cc17","ttft_stream_ms":1173,"time_to_request_ms":32,"first_content_frame_ms":1173,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestInterrupt.jsonl b/internal/claude/testdata/transcripts/TestInterrupt.jsonl index bb282ad..5569d6e 100644 --- a/internal/claude/testdata/transcripts/TestInterrupt.jsonl +++ b/internal/claude/testdata/transcripts/TestInterrupt.jsonl @@ -1,18 +1,17 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_95cc4718c381813d","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_95cc4718c381813d","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":81527,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_93626c7c73aa88ff","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_93626c7c73aa88ff","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":98365,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Run the bash command `ping -c 120 127.0.0.1` in the foreground (not in the background) and wait for it to finish, then say done.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt1421965867/001","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","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":"631e698f-f7ef-41af-8664-71075f2017c0","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1421965867-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1421965867-001/4b593158-07f1-4deb-a1a3-dca27fa86f63/scratchpad","messaging_socket_path":"/tmp/cc-socks/81527.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","uuid":"953d662e-1dd8-42a2-9821-71e78d0ab671"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.13,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"2a9df3c9-f3ef-470c-9456-68f07f5022cf","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FtySRJENjoBYZk4QZd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SdAK4PtbwTeW2QjpwNADM2","name":"Bash","input":{"command":"ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":180000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15264,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15264},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","uuid":"0a42fec4-d566-4b1a-b63f-16b868cab3b7","timestamp":"2026-10-15T02:46:26.811Z","request_id":"req_011Cg3FtyC3C2xgVdYHZoR6G","wire_tool_inputs":{"toolu_01SdAK4PtbwTeW2QjpwNADM2":{"command":"ping -c 120 127.0.0.1","timeout":180000,"description":"Ping localhost 120 times"}}}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.14,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"550a9e79-c508-4245-a955-3b78761f683f","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63"}} -{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_5b1a4db7f3efd6b1","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_5b1a4db7f3efd6b1","response":{"still_queued":[]}}}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"The user doesn't want to proceed with this tool use. The tool use was rejected (eg. if it was a file edit, the new_string was NOT written to the file). STOP what you are doing and wait for the user to tell you how to proceed.\n\nNote: The user's next message may contain a correction or preference. Pay close attention — if they explain what went wrong or how they'd prefer you to work, consider saving that to memory for future sessions.","is_error":true,"tool_use_id":"toolu_01SdAK4PtbwTeW2QjpwNADM2"}]},"parent_tool_use_id":null,"session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","uuid":"37ac6f12-90fb-4585-a96b-3111b006a940","timestamp":"2026-10-15T02:46:28.823Z","tool_use_result":"User rejected tool use","tool_result_meta":[{"id":"toolu_01SdAK4PtbwTeW2QjpwNADM2","non_execution_kind":"user-rejected"}]}} -{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user for tool use]"}]},"parent_tool_use_id":null,"session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","uuid":"f29f636c-e5bd-4197-b590-3184a7053d39","timestamp":"2026-10-15T02:46:28.824Z"}} -{"dir":"recv","msg":{"duration_api_ms":2761,"stop_reason":"tool_use","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","total_cost_usd":0.0645672,"usage":{"input_tokens":2,"cache_creation_input_tokens":15264,"cache_read_input_tokens":22367,"output_tokens":114,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15264,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":114,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15264,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15264},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":114,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15264,"webSearchRequests":0,"costUSD":0.0644367,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"aborted_tools","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":true,"num_turns":3,"subtype":"error_during_execution","errors":["[ede_diagnostic] result_type=user last_content_type=n/a stop_reason=tool_use"],"type":"result","duration_ms":4193,"uuid":"533a3f01-e5e6-4e92-bad3-d2dfeb1cf106","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":"4b593158-07f1-4deb-a1a3-dca27fa86f63","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt1421965867/001","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","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":"5f9571e9-7d26-499d-9be3-3f4b9c38676b","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1421965867-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt1421965867-001/4b593158-07f1-4deb-a1a3-dca27fa86f63/scratchpad","messaging_socket_path":"/tmp/cc-socks/81527.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","uuid":"5011abeb-bf05-49c4-85cc-5ab5361e8e83"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FuGxsYnqSWLYTh6WPh","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37631,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","uuid":"f1629f35-a252-4c14-b09e-117b4ed8f235","timestamp":"2026-10-15T02:46:30.039Z","request_id":"req_011Cg3FuGgVwEtHtm9CJhXAr"}} -{"dir":"recv","msg":{"duration_api_ms":3990,"stop_reason":"end_turn","session_id":"4b593158-07f1-4deb-a1a3-dca27fa86f63","total_cost_usd":0.0874623,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37631,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":4772,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37631,"cache_creation_input_tokens":4772,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001305,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":118,"cacheReadInputTokens":59998,"cacheCreationInputTokens":20036,"webSearchRequests":0,"costUSD":0.0873318,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1212,"type":"result","duration_ms":1240,"uuid":"5b593093-695a-4e9f-871b-24f958b93bb4","ttft_stream_ms":1211,"time_to_request_ms":9,"first_content_frame_ms":1211,"queued_turn_count":0,"result_index":1}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt3118307443/001","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","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":"98fbe535-615a-4c35-b98a-b8a450c82d23","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/3e98ea6f-403d-4428-95b5-929359d3d2ee/scratchpad","messaging_socket_path":"/tmp/cc-socks/98365.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"8b9b397a-d89b-4e72-b9af-bba331c763e3"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"5dc4a698-6327-4edf-a518-133fbb837d0c","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mazh2n47jmF6uFm5sc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DAXvVXxANNsftpBUGzT6K5","name":"Bash","input":{"command":"ping -c 120 127.0.0.1","description":"Ping localhost 120 times","timeout":180000},"caller":{"type":"direct"}}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15263,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15263},"output_tokens":16,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"a4f7ffa9-8d8f-4930-bfc2-7e6915578427","timestamp":"2026-10-15T04:01:03.741Z","request_id":"req_011Cg3MazS9YHo9yTp56KQ6A","wire_tool_inputs":{"toolu_01DAXvVXxANNsftpBUGzT6K5":{"command":"ping -c 120 127.0.0.1","timeout":180000,"description":"Ping localhost 120 times"}}}} +{"dir":"send","msg":{"request":{"subtype":"interrupt"},"request_id":"req_40eed33f6f637dfa","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_40eed33f6f637dfa","response":{"still_queued":[]}}}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"The user doesn't want to proceed with this tool use. The tool use was rejected (eg. if it was a file edit, the new_string was NOT written to the file). STOP what you are doing and wait for the user to tell you how to proceed.\n\nNote: The user's next message may contain a correction or preference. Pay close attention — if they explain what went wrong or how they'd prefer you to work, consider saving that to memory for future sessions.","is_error":true,"tool_use_id":"toolu_01DAXvVXxANNsftpBUGzT6K5"}]},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"ae028585-0fc4-4e1d-bc98-f6346bdc1843","timestamp":"2026-10-15T04:01:05.753Z","tool_use_result":"User rejected tool use","tool_result_meta":[{"id":"toolu_01DAXvVXxANNsftpBUGzT6K5","non_execution_kind":"user-rejected"}]}} +{"dir":"recv","msg":{"type":"user","message":{"role":"user","content":[{"type":"text","text":"[Request interrupted by user for tool use]"}]},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"711a87e7-910e-4ac8-8cd3-574f52e3194e","timestamp":"2026-10-15T04:01:05.754Z"}} +{"dir":"recv","msg":{"duration_api_ms":2781,"stop_reason":"tool_use","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","total_cost_usd":0.0645662,"usage":{"input_tokens":2,"cache_creation_input_tokens":15263,"cache_read_input_tokens":22367,"output_tokens":114,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15263,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":114,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15263,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15263},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":25,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001335,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":114,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15263,"webSearchRequests":0,"costUSD":0.06443270000000001,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"aborted_tools","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":true,"num_turns":3,"subtype":"error_during_execution","errors":["[ede_diagnostic] result_type=user last_content_type=n/a stop_reason=tool_use"],"type":"result","duration_ms":4076,"uuid":"7c04e01d-49dc-49e5-bb3e-5caebac96264","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":"3e98ea6f-403d-4428-95b5-929359d3d2ee","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestInterrupt3118307443/001","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","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":"5accde2b-ad81-4a85-b942-5bc6b0aca562","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestInterrupt3118307443-001/3e98ea6f-403d-4428-95b5-929359d3d2ee/scratchpad","messaging_socket_path":"/tmp/cc-socks/98365.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"a612b0d0-f118-44c2-909b-96448602c4ea"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbHjxDqDpHhr8US96b","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37630,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","uuid":"0e9faebc-ed7b-4210-a6d7-206864da3e11","timestamp":"2026-10-15T04:01:06.862Z","request_id":"req_011Cg3MbHT6R72nc4tBQxyPq"}} +{"dir":"recv","msg":{"duration_api_ms":3894,"stop_reason":"end_turn","session_id":"3e98ea6f-403d-4428-95b5-929359d3d2ee","total_cost_usd":0.0874612,"usage":{"input_tokens":2,"cache_creation_input_tokens":4772,"cache_read_input_tokens":37630,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":4772,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":37630,"cache_creation_input_tokens":4772,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":4772},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1210,"outputTokens":25,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001335,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":118,"cacheReadInputTokens":59997,"cacheCreationInputTokens":20035,"webSearchRequests":0,"costUSD":0.08732770000000001,"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":1104,"type":"result","duration_ms":1122,"uuid":"fae28eac-fe54-42e9-b54a-dab434fb98fb","ttft_stream_ms":1104,"time_to_request_ms":8,"first_content_frame_ms":1104,"queued_turn_count":0,"result_index":1}} diff --git a/internal/claude/testdata/transcripts/TestResume-first.jsonl b/internal/claude/testdata/transcripts/TestResume-first.jsonl index 2f0f877..21fea57 100644 --- a/internal/claude/testdata/transcripts/TestResume-first.jsonl +++ b/internal/claude/testdata/transcripts/TestResume-first.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_fb8bf868bfd263bb","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_fb8bf868bfd263bb","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":81531,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_79a3affeb81ca6cc","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_79a3affeb81ca6cc","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":98361,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Remember the codeword AZURE-17. Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume2536316200/001","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","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":"efe725b0-d0cd-4d5c-b620-1af00f6e8f59","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2536316200-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2536316200-001/8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f/scratchpad","messaging_socket_path":"/tmp/cc-socks/81531.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","uuid":"e483c3cb-7302-45f3-83e3-e8c80238dca3"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.13,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"615dbbce-4bab-4d99-a0f4-a0bdaa00239e","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Ftx83jWNReLz3SwfCX","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":15240,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15240},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","uuid":"df992dfe-7d50-4861-bc12-0fdbe1562588","timestamp":"2026-10-15T02:46:25.867Z","request_id":"req_011Cg3Ftwsue8M6UqKyiAkhz"}} -{"dir":"recv","msg":{"duration_api_ms":2219,"stop_reason":"end_turn","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","total_cost_usd":0.06337,"usage":{"input_tokens":2,"cache_creation_input_tokens":15240,"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":15240,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15240,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15240},"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":15240,"webSearchRequests":0,"costUSD":0.0632407,"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":1560,"type":"result","duration_ms":1581,"uuid":"579795c4-0e6f-4016-adcf-4422bbfd1397","ttft_stream_ms":1558,"time_to_request_ms":42,"first_content_frame_ms":1558,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume329762661/001","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","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":"2553ecd4-6e0d-463a-b8d8-98b88d68abc5","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/8d41cb35-d2d6-4384-a660-f3269b91d3fa/scratchpad","messaging_socket_path":"/tmp/cc-socks/98361.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"dc081894-65c6-4b68-b8d8-a57d004c1d71"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"bc240332-8e40-469f-b278-8bfdb3566a9b","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mazd3tsVvEfJ3XYgdP","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15230,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15230},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"50cce199-27c9-4cfd-b5b6-e5e9cceb5f23","timestamp":"2026-10-15T04:01:03.384Z","request_id":"req_011Cg3MazNvngW2CLGMcm6B2"}} +{"dir":"recv","msg":{"duration_api_ms":2309,"stop_reason":"end_turn","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","total_cost_usd":0.06333,"usage":{"input_tokens":2,"cache_creation_input_tokens":15230,"cache_read_input_tokens":22367,"output_tokens":4,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15230,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":4,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15230,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15230},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":21,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012930000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":4,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15230,"webSearchRequests":0,"costUSD":0.0632007,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"ok","ttft_ms":1714,"type":"result","duration_ms":1757,"uuid":"42e1b61e-4004-4970-a87f-c725f0a2e3ba","ttft_stream_ms":1711,"time_to_request_ms":26,"first_content_frame_ms":1711,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl index b36860c..fa2542d 100644 --- a/internal/claude/testdata/transcripts/TestResume-resumed.jsonl +++ b/internal/claude/testdata/transcripts/TestResume-resumed.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_8ea3c1bcf9cebb7d","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_8ea3c1bcf9cebb7d","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":82138,"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":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume2536316200/001","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","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":"374ecda4-4d27-4c0a-aaf9-2a9adfa71a8e","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2536316200-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume2536316200-001/8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f/scratchpad","messaging_socket_path":"/tmp/cc-socks/82138.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","uuid":"2873de37-a06a-470d-8cde-691c99828b7f"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FuBicVNtT3RgUPGGcu","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":7024,"cache_read_input_tokens":30630,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7024},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13150}},"context_management":null},"parent_tool_use_id":null,"session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","uuid":"abcb4af1-7e7a-48b8-b67c-dd2819346b8a","timestamp":"2026-10-15T02:46:28.955Z","request_id":"req_011Cg3FuBUy6TvXaTLFe7nFr"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.14,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"0f623ae5-1fb8-48bf-b006-8053d4b0c3ef","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f"}} -{"dir":"recv","msg":{"duration_api_ms":3587,"stop_reason":"end_turn","session_id":"8e4c92b0-79e0-4ed0-bf1d-ac4ae3f5de7f","total_cost_usd":0.094613,"usage":{"input_tokens":2,"cache_creation_input_tokens":7024,"cache_read_input_tokens":30630,"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":7024,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":8,"cache_read_input_tokens":30630,"cache_creation_input_tokens":7024,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7024},"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":52997,"cacheCreationInputTokens":22264,"webSearchRequests":0,"costUSD":0.0944837,"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":1386,"type":"result","duration_ms":1406,"uuid":"6096d7b5-5c47-4fec-8b87-e87106f8a23c","ttft_stream_ms":1383,"time_to_request_ms":37,"first_content_frame_ms":1384,"queued_turn_count":0,"result_index":0}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_7faf36c3a900d24a","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_7faf36c3a900d24a","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":99041,"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":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","type":"user"}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestResume329762661/001","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","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":"a204c748-dc92-43a1-91d2-8c04fa4e55d8","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestResume329762661-001/8d41cb35-d2d6-4384-a660-f3269b91d3fa/scratchpad","messaging_socket_path":"/tmp/cc-socks/99041.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"67920b18-eeaf-487d-a245-8af0fd3f8af3"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MbEw2gyH73f6h7CkRh","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":30628,"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":13150}},"context_management":null},"parent_tool_use_id":null,"session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","uuid":"1ec5bc63-058f-4472-b247-18c19cab9e67","timestamp":"2026-10-15T04:01:06.986Z","request_id":"req_011Cg3MbEgA9kCbtrnAGZ65v"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"9ce1779b-6b8b-482c-89f2-397a0abe7a15","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa"}} +{"dir":"recv","msg":{"duration_api_ms":4207,"stop_reason":"end_turn","session_id":"8d41cb35-d2d6-4384-a660-f3269b91d3fa","total_cost_usd":0.0945408,"usage":{"input_tokens":2,"cache_creation_input_tokens":7016,"cache_read_input_tokens":30628,"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":30628,"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":52995,"cacheCreationInputTokens":22246,"webSearchRequests":0,"costUSD":0.0944115,"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":1913,"type":"result","duration_ms":1931,"uuid":"08d749fd-b929-42dd-a5f3-fa114688fbeb","ttft_stream_ms":1907,"time_to_request_ms":33,"first_content_frame_ms":1908,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl index 2062ad1..9044a88 100644 --- a/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl +++ b/internal/claude/testdata/transcripts/TestStopHookBlocks.jsonl @@ -1,17 +1,16 @@ -{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_cefc5fc5334d98a8","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_cefc5fc5334d98a8","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":81529,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":{"Stop":[{"hookCallbackIds":["hook_0"],"matcher":""}]},"subtype":"initialize"},"request_id":"req_02d1ad1c4ac551df","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_02d1ad1c4ac551df","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":98364,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","hooks_applied":true,"feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Reply with the single word ok.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks756518558/001","session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","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":"ba887e12-7e33-4e62-b497-27847599ca0c","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks756518558-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks756518558-001/5943cd94-5f17-40f4-b84f-8c3f4036e488/scratchpad","messaging_socket_path":"/tmp/cc-socks/81529.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","uuid":"5bf6f856-e13a-455d-86eb-6cd06ab96e13"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.13,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"7ea26460-d52d-4eb0-8226-06f468f77df4","session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FtxDVxrXVCu2PHGFEN","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":15234,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15234},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","uuid":"22d0127e-f977-4976-8aab-f611c3327508","timestamp":"2026-10-15T02:46:26.112Z","request_id":"req_011Cg3FtwvPDMPDy7NasqYVv"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"7ff49ffa-6ccd-43cf-b4ac-edebe9cde0ea","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks756518558-001/5943cd94-5f17-40f4-b84f-8c3f4036e488.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks756518558/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks756518558-001/5943cd94-5f17-40f4-b84f-8c3f4036e488/scratchpad","prompt_id":"bf4bcb7b-436e-41f5-b6d0-d4050d42cde1","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":"229a0d34-85e8-43ba-a535-8a8c0f5649cb"}}} -{"dir":"send","msg":{"response":{"request_id":"7ff49ffa-6ccd-43cf-b4ac-edebe9cde0ea","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":"5943cd94-5f17-40f4-b84f-8c3f4036e488","uuid":"3ea3cf7b-9660-48cc-aef5-3dcc41703796","timestamp":"2026-10-15T02:46:26.137Z","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":"5943cd94-5f17-40f4-b84f-8c3f4036e488","uuid":"7e371315-b224-44e0-a554-6f568354a219"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","uuid":"c9f049ed-9344-40d9-9c76-8376c3ed595b"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Fu5NcYWJARqkbXbxGv","type":"message","role":"assistant","content":[{"type":"text","text":"PINEAPPLE"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7060,"cache_read_input_tokens":30621,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13144}},"context_management":null},"parent_tool_use_id":null,"session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","uuid":"400fea2a-4cc3-40cf-b113-1d92f1b72350","timestamp":"2026-10-15T02:46:27.621Z","request_id":"req_011Cg3Fu58irwauizyTvX5Qk"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.14,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"f0658b1d-bfcb-49f3-8e7b-9afd91c764dd","session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488"}} -{"dir":"recv","msg":{"type":"control_request","request_id":"69738bae-c8ef-4f8f-a133-facd632112d4","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks756518558-001/5943cd94-5f17-40f4-b84f-8c3f4036e488.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks756518558/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks756518558-001/5943cd94-5f17-40f4-b84f-8c3f4036e488/scratchpad","prompt_id":"bf4bcb7b-436e-41f5-b6d0-d4050d42cde1","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":"68da64c8-6f2b-4dd4-b450-e3b0715614d2"}}} -{"dir":"send","msg":{"response":{"request_id":"69738bae-c8ef-4f8f-a133-facd632112d4","response":{},"subtype":"success"},"type":"control_response"}} -{"dir":"recv","msg":{"duration_api_ms":3872,"stop_reason":"end_turn","session_id":"5943cd94-5f17-40f4-b84f-8c3f4036e488","total_cost_usd":0.0947472,"usage":{"input_tokens":4,"cache_creation_input_tokens":22294,"cache_read_input_tokens":52988,"output_tokens":14,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":22294,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30621,"cache_creation_input_tokens":7060,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1174,"outputTokens":14,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001244,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":14,"cacheReadInputTokens":52988,"cacheCreationInputTokens":22294,"webSearchRequests":0,"costUSD":0.0946228,"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":1783,"type":"result","duration_ms":3323,"uuid":"74883093-b07c-49b9-9b5a-23f8ccd847d2","ttft_stream_ms":1778,"time_to_request_ms":46,"first_content_frame_ms":1779,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks582294929/001","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","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":"b2b436bc-fe36-4809-a1ad-824239b4408a","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003/scratchpad","messaging_socket_path":"/tmp/cc-socks/98364.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"18cf8903-3877-4d59-b9e3-6b87b7cf1559"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"5c9914da-3ac9-4e6f-b863-5708567463e0","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MazufpKaWg1rWUNvs5","type":"message","role":"assistant","content":[{"type":"text","text":"ok"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15233,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15233},"output_tokens":4,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"cc712600-aad9-43a5-a7cb-57ab2fb9600b","timestamp":"2026-10-15T04:01:03.441Z","request_id":"req_011Cg3MazXMngPm6MEkboQhL"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"1581cbd8-4d8b-4459-bdee-5931bf7efc3e","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks582294929/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003/scratchpad","prompt_id":"8e4c4b7c-16fc-4b76-9352-f889570d8de2","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":"b32ba246-fa7c-45dd-b67c-b0a441ec331a"}}} +{"dir":"send","msg":{"response":{"request_id":"1581cbd8-4d8b-4459-bdee-5931bf7efc3e","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":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"91ccf118-5b3b-42a3-9d6f-400ac2cee0fe","timestamp":"2026-10-15T04:01:03.467Z","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":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"24bfc79c-50b4-4be6-8ddd-942cc626f607"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"f87132cf-6c29-404a-be79-1287757e5519"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3Mb7x5cs8by4chcpqws","type":"message","role":"assistant","content":[{"type":"text","text":"PINEAPPLE"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7060,"cache_read_input_tokens":30620,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":{"cache_miss_reason":{"type":"messages_changed","cache_missed_input_tokens":13144}},"context_management":null},"parent_tool_use_id":null,"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","uuid":"dfe97aca-77da-494e-9255-ac5939df1d2c","timestamp":"2026-10-15T04:01:05.136Z","request_id":"req_011Cg3Mb7fTzGgZZFbTLvAwk"}} +{"dir":"recv","msg":{"type":"control_request","request_id":"3925aa2e-872e-456e-8e2e-9331f00b3285","request":{"subtype":"hook_callback","callback_id":"hook_0","input":{"session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","transcript_path":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003.jsonl","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestStopHookBlocks582294929/001","scratchpad_dir":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestStopHookBlocks582294929-001/3a5eb510-b78c-4f3b-bc01-b15807f70003/scratchpad","prompt_id":"8e4c4b7c-16fc-4b76-9352-f889570d8de2","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":"c75ff38d-8b07-4e8a-bf60-e90c21d81367"}}} +{"dir":"send","msg":{"response":{"request_id":"3925aa2e-872e-456e-8e2e-9331f00b3285","response":{},"subtype":"success"},"type":"control_response"}} +{"dir":"recv","msg":{"duration_api_ms":4175,"stop_reason":"end_turn","session_id":"3a5eb510-b78c-4f3b-bc01-b15807f70003","total_cost_usd":0.0947431,"usage":{"input_tokens":4,"cache_creation_input_tokens":22293,"cache_read_input_tokens":52987,"output_tokens":14,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":22293,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":10,"cache_read_input_tokens":30620,"cache_creation_input_tokens":7060,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":7060},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1174,"outputTokens":14,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.0001244,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":4,"outputTokens":14,"cacheReadInputTokens":52987,"cacheCreationInputTokens":22293,"webSearchRequests":0,"costUSD":0.0946187,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":2,"subtype":"success","api_error_status":null,"result":"PINEAPPLE","ttft_ms":1748,"type":"result","duration_ms":3466,"uuid":"a6060220-2220-4305-bcb0-b12291b5904d","ttft_stream_ms":1742,"time_to_request_ms":31,"first_content_frame_ms":1743,"queued_turn_count":0,"result_index":0}} diff --git a/internal/claude/testdata/transcripts/TestTextDeltas.jsonl b/internal/claude/testdata/transcripts/TestTextDeltas.jsonl index f90f7e9..9437e54 100644 --- a/internal/claude/testdata/transcripts/TestTextDeltas.jsonl +++ b/internal/claude/testdata/transcripts/TestTextDeltas.jsonl @@ -1,8 +1,8 @@ -{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_501b5535c51fca92","type":"control_request"}} -{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_501b5535c51fca92","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":81530,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} +{"dir":"send","msg":{"request":{"hooks":null,"subtype":"initialize"},"request_id":"req_21a0463a8f168dbc","type":"control_request"}} +{"dir":"recv","msg":{"type":"control_response","response":{"subtype":"success","request_id":"req_21a0463a8f168dbc","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":98362,"claude_code_version":"2.1.296","current_permission_mode":"bypassPermissions","feedback_mode":{"kind":"post"},"analytics_disabled":false,"remote_control_auto_enable":false,"remote_control_auto_connect_default":false,"remote_control_available":true,"remote_control_auto_on_by_default":false,"ide_rc_auto_enable_gate":true,"fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","session_state":"idle","capabilities":["ui_surface_v1"]},"pending_permission_requests":[],"pending_user_dialog_requests":[]}}} {"dir":"send","msg":{"message":{"content":"Without using any tools, count from one to twenty in words, separated by spaces.","role":"user"},"parent_tool_use_id":null,"session_id":"","type":"user"}} -{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestTextDeltas3246909673/001","session_id":"c8dcc254-f534-4fb5-af48-c18d21086690","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":"608957b7-9400-46b7-9efc-470103a5a74d","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas3246909673-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas3246909673-001/c8dcc254-f534-4fb5-af48-c18d21086690/scratchpad","messaging_socket_path":"/tmp/cc-socks/81530.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} -{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"c8dcc254-f534-4fb5-af48-c18d21086690","uuid":"6bc02c1b-9162-4019-9c77-93dceff2c509"}} -{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792036200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.13,"resetsAt":1792036200},"seven_day":{"utilization":0.33,"resetsAt":1792270800}}},"uuid":"10326f12-60a6-442d-baed-3de26448a683","session_id":"c8dcc254-f534-4fb5-af48-c18d21086690"}} -{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3FtwsR3k6sGom8o4a3e","type":"message","role":"assistant","content":[{"type":"text","text":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15243,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15243},"output_tokens":8,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"c8dcc254-f534-4fb5-af48-c18d21086690","uuid":"fccb87bd-a37c-4a7f-b870-5cf993c2e25d","timestamp":"2026-10-15T02:46:26.123Z","request_id":"req_011Cg3FtwdnK76UzZnzoYejM"}} -{"dir":"recv","msg":{"duration_api_ms":2420,"stop_reason":"end_turn","session_id":"c8dcc254-f534-4fb5-af48-c18d21086690","total_cost_usd":0.063871,"usage":{"input_tokens":2,"cache_creation_input_tokens":15243,"cache_read_input_tokens":22367,"output_tokens":53,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15243,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":53,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15243,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15243},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012830000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":53,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15243,"webSearchRequests":0,"costUSD":0.0637427,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty","ttft_ms":1837,"type":"result","duration_ms":1858,"uuid":"8b40d8a0-5b8a-4086-bdab-3946d7d9982b","ttft_stream_ms":1174,"time_to_request_ms":39,"first_content_frame_ms":1174,"queued_turn_count":0,"result_index":0}} +{"dir":"recv","msg":{"type":"system","subtype":"init","cwd":"/private/var/folders/r4/m529kfnd537_x0xfbgcgqfs40000gn/T/TestTextDeltas4122698565/001","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","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":"9518a43e-d524-445b-bf36-98778bc0b54e","memory_paths":{"auto":"/Users/flamingcow/.claude/projects/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas4122698565-001/memory/"},"scratchpad_path":"/private/tmp/claude-501/-private-var-folders-r4-m529kfnd537-x0xfbgcgqfs40000gn-T-TestTextDeltas4122698565-001/3810dedc-a024-4c36-8e67-709b70a35ca1/scratchpad","messaging_socket_path":"/tmp/cc-socks/98362.sock","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","per_turn_effort_active":true,"view_mode":"default"}} +{"dir":"recv","msg":{"type":"system","subtype":"status","status":"requesting","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","uuid":"6e521520-557c-4e08-9f14-4264a9ebcf67"}} +{"dir":"recv","msg":{"type":"rate_limit_event","rate_limit_info":{"status":"allowed","resetsAt":1792054200,"rateLimitType":"five_hour","overageStatus":"rejected","overageDisabledReason":"org_level_disabled","isUsingOverage":false,"unifiedWindows":{"five_hour":{"utilization":0.01,"resetsAt":1792054200},"seven_day":{"utilization":0.34,"resetsAt":1792270800}}},"uuid":"6ca939e1-49c7-4c92-89c7-0def6b066465","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1"}} +{"dir":"recv","msg":{"type":"assistant","message":{"model":"claude-sonnet-5-5","id":"msg_011Cg3MazUdfUdYYNqPGyMsW","type":"message","role":"assistant","content":[{"type":"text","text":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty"}],"container":null,"stop_reason":null,"stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":15243,"cache_read_input_tokens":22367,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15243},"output_tokens":2,"service_tier":"standard","inference_geo":"global"},"input_transformations":[],"diagnostics":null,"context_management":null},"parent_tool_use_id":null,"session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","uuid":"87c3e680-b78e-4869-9187-1676d99c86ae","timestamp":"2026-10-15T04:01:03.458Z","request_id":"req_011Cg3MazEjVz7knkKKpTZoZ"}} +{"dir":"recv","msg":{"duration_api_ms":2369,"stop_reason":"end_turn","session_id":"3810dedc-a024-4c36-8e67-709b70a35ca1","total_cost_usd":0.063871,"usage":{"input_tokens":2,"cache_creation_input_tokens":15243,"cache_read_input_tokens":22367,"output_tokens":53,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":15243,"ephemeral_5m_input_tokens":0},"inference_geo":"global","iterations":[{"input_tokens":2,"output_tokens":53,"cache_read_input_tokens":22367,"cache_creation_input_tokens":15243,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":15243},"type":"message"}],"speed":"standard","fallback_credit":null},"modelUsage":{"claude-haiku-5-5":{"inputTokens":1188,"outputTokens":19,"cacheReadInputTokens":0,"cacheCreationInputTokens":0,"webSearchRequests":0,"costUSD":0.00012830000000000003,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-haiku-5-5","provider":"firstParty","costBasis":"list"},"claude-sonnet-5-5":{"inputTokens":2,"outputTokens":53,"cacheReadInputTokens":22367,"cacheCreationInputTokens":15243,"webSearchRequests":0,"costUSD":0.0637427,"contextWindow":1000000,"maxOutputTokens":128000,"thinkingTokens":0,"canonicalModel":"claude-sonnet-5-5","provider":"firstParty","costBasis":"list"}},"permission_denials":[],"terminal_reason":"completed","fast_mode_state":"off","fast_mode_disabled_reason":"sdk_opt_in_required","subagent_stats":{"spawned":0,"requested":{"background":0,"foreground":0,"unset":0},"started_in_background":0,"max_depth":0,"spawned_by_subagents":0,"completed":0,"failed":0,"killed":{"parent":0,"user":0,"system":0},"refused":{"depth_limit":0,"concurrency_limit":0,"budget":0},"by_type":{}},"safety_stops":0,"is_error":false,"num_turns":1,"subtype":"success","api_error_status":null,"result":"one two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty","ttft_ms":1816,"type":"result","duration_ms":1833,"uuid":"13a1f2b5-5a4c-4007-821d-3e7894e8e5a5","ttft_stream_ms":1103,"time_to_request_ms":28,"first_content_frame_ms":1104,"queued_turn_count":0,"result_index":0}} diff --git a/internal/server/server.go b/internal/server/server.go index 335f47e..acdc681 100644 --- a/internal/server/server.go +++ b/internal/server/server.go @@ -291,49 +291,33 @@ func (s *Server) MergeTask(w http.ResponseWriter, r *http.Request, taskID string writeStoreError(w, err) return } - if u.GitName == "" || u.GitEmail == "" { - writeError(w, http.StatusBadRequest, errors.New("set your git name and email (PUT /api/me) before merging")) + + sess, err := s.agents.Merge(r.Context(), t, p, u) + if err != nil { + writeAgentError(w, err) + return + } + writeJSON(w, http.StatusAccepted, sess) +} + +func (s *Server) MergeIn(w http.ResponseWriter, r *http.Request, taskID string) { + t, p, ok := s.activeTask(w, r, taskID) + if !ok { return } - sessions, err := s.store.ListSessions(r.Context(), t.Id) + u, err := s.store.GetUser(r.Context(), actor(r)) if err != nil { writeStoreError(w, err) return } - for _, sess := range sessions { - if sess.State == api.AgentSessionStateRunning || sess.State == api.AgentSessionStateQueued { - writeError(w, http.StatusConflict, fmt.Errorf("session %s is %s; wait for the turn to end or interrupt it", sess.Id, sess.State)) - return - } - } - commit, err := git.SquashMerge(p.RepoPath, t.WorktreePath, p.DefaultBranch, squashMessage(t), []string{ - "GIT_AUTHOR_NAME=" + u.GitName, - "GIT_AUTHOR_EMAIL=" + u.GitEmail, - "GIT_COMMITTER_NAME=" + u.GitName, - "GIT_COMMITTER_EMAIL=" + u.GitEmail, - }) - conflict := &git.ConflictError{} - if errors.As(err, &conflict) { - writeError(w, http.StatusConflict, err) - return - } + sess, err := s.agents.MergeIn(r.Context(), t, u, p.DefaultBranch) if err != nil { - writeError(w, http.StatusInternalServerError, err) + writeAgentError(w, err) return } - - if !s.removeTask(w, r, t, p) { - return - } - - t, err = s.store.MergeTask(r.Context(), taskID, commit, actor(r)) - if err != nil { - writeStoreError(w, err) - return - } - writeJSON(w, http.StatusOK, t) + writeJSON(w, http.StatusAccepted, sess) } func (s *Server) DiscardTask(w http.ResponseWriter, r *http.Request, taskID string) { @@ -342,11 +326,13 @@ func (s *Server) DiscardTask(w http.ResponseWriter, r *http.Request, taskID stri return } - if !s.removeTask(w, r, t, p) { + err := s.agents.RemoveTask(r.Context(), t, p, actor(r)) + if err != nil { + writeError(w, http.StatusInternalServerError, err) return } - t, err := s.store.DiscardTask(r.Context(), taskID, actor(r)) + t, err = s.store.DiscardTask(r.Context(), taskID, actor(r)) if err != nil { writeStoreError(w, err) return @@ -354,10 +340,6 @@ func (s *Server) DiscardTask(w http.ResponseWriter, r *http.Request, taskID stri writeJSON(w, http.StatusOK, t) } -func squashMessage(t api.Task) string { - return t.Title -} - func (s *Server) activeTask(w http.ResponseWriter, r *http.Request, taskID string) (api.Task, api.Project, bool) { t, err := s.store.GetTask(r.Context(), taskID) if err != nil { @@ -378,21 +360,6 @@ func (s *Server) activeTask(w http.ResponseWriter, r *http.Request, taskID strin return t, p, true } -func (s *Server) removeTask(w http.ResponseWriter, r *http.Request, t api.Task, p api.Project) bool { - err := s.agents.StopTask(r.Context(), t.Id, actor(r)) - if err != nil { - writeError(w, http.StatusInternalServerError, err) - return false - } - - err = git.RemoveWorktree(p.RepoPath, t.WorktreePath, t.Branch) - if err != nil { - writeError(w, http.StatusInternalServerError, err) - return false - } - return true -} - func (s *Server) GetStatus(w http.ResponseWriter, r *http.Request) { c, err := s.store.Counts(r.Context()) if err != nil { diff --git a/internal/server/server_test.go b/internal/server/server_test.go index 179f7ce..c37223d 100644 --- a/internal/server/server_test.go +++ b/internal/server/server_test.go @@ -259,80 +259,11 @@ func TestMergeTask(t *testing.T) { if code != http.StatusBadRequest { t.Fatalf("want 400 merging without a git identity, got %d", code) } - h.do("PUT", "/api/me", api.UserUpdate{GitName: "Alice", GitEmail: "alice@example.org"}, nil) - - writeFile(t, filepath.Join(task.WorktreePath, "committed"), "one\ntwo\n") - gitOut(t, task.WorktreePath, "add", "committed") - gitOut(t, task.WorktreePath, "commit", "--message", "wip") - writeFile(t, filepath.Join(task.WorktreePath, "uncommitted"), "three\n") - - writeFile(t, filepath.Join(p.RepoPath, "other"), "main moved\n") - gitOut(t, p.RepoPath, "add", "other") - gitOut(t, p.RepoPath, "commit", "--message", "main moved") - moved := gitOut(t, p.RepoPath, "rev-parse", "main") - - unmerged := api.Unmerged{} - h.do("GET", "/api/tasks/"+task.Id+"/unmerged", nil, &unmerged) - if unmerged != (api.Unmerged{Commits: 1, Files: 2, Insertions: 3, Deletions: 0, Uncommitted: 1}) { - t.Fatalf("unexpected unmerged %+v", unmerged) - } - - merged := api.Task{} - code = h.do("POST", "/api/tasks/"+task.Id+"/merge", nil, &merged) - if code != http.StatusOK || merged.Status != api.TaskStatusMerged || merged.ClosedAt == nil || merged.MergeCommit == nil { - t.Fatalf("merge: %d %+v", code, merged) - } - - head := gitOut(t, p.RepoPath, "rev-parse", "main") - if head != *merged.MergeCommit { - t.Fatalf("main at %s, want merge commit %s", head, *merged.MergeCommit) - } - if parent := gitOut(t, p.RepoPath, "rev-parse", "main^"); parent != moved { - t.Fatalf("merge commit parent %s, want %s", parent, moved) - } - if log := gitOut(t, p.RepoPath, "log", "-1", "--format=%s|%an|%cn"); log != "Add notes|Alice|Alice" { - t.Fatalf("unexpected merge commit %s", log) - } - for _, name := range []string{"committed", "uncommitted", "other"} { - _, err := os.Stat(filepath.Join(p.RepoPath, name)) - if err != nil { - t.Fatalf("%s not checked out on main: %v", name, err) - } - } - if status := gitOut(t, p.RepoPath, "status", "--porcelain"); status != "" { - t.Fatalf("main checkout dirty after merge: %s", status) - } - if branches := gitOut(t, p.RepoPath, "branch", "--list", task.Branch); branches != "" { - t.Fatalf("branch still exists: %s", branches) - } -} - -func TestMergeConflict(t *testing.T) { - h := newHarness(t) - p := h.createProject("demo") - h.do("PUT", "/api/me", api.UserUpdate{GitName: "Alice", GitEmail: "alice@example.org"}, nil) - - task := api.Task{} - h.do("POST", "/api/projects/"+p.Id+"/tasks", api.TaskCreate{Title: "Edit readme"}, &task) - writeFile(t, filepath.Join(task.WorktreePath, "README"), "task\n") - - writeFile(t, filepath.Join(p.RepoPath, "README"), "main\n") - gitOut(t, p.RepoPath, "commit", "--all", "--message", "main edit") - head := gitOut(t, p.RepoPath, "rev-parse", "main") - - code := h.do("POST", "/api/tasks/"+task.Id+"/merge", nil, nil) - if code != http.StatusConflict { - t.Fatalf("want 409 on conflict, got %d", code) - } got := api.Task{} h.do("GET", "/api/tasks/"+task.Id, nil, &got) - if got.Status != api.TaskStatusActive || gitOut(t, p.RepoPath, "rev-parse", "main") != head { - t.Fatalf("conflicted merge changed state: %+v", got) - } - _, err := os.Stat(task.WorktreePath) - if err != nil { - t.Fatalf("worktree removed after conflict: %v", err) + if got.Status != api.TaskStatusActive { + t.Fatalf("refused merge changed the task: %+v", got) } } diff --git a/web/dist/task.js b/web/dist/task.js index 09fd54e..96631e3 100644 --- a/web/dist/task.js +++ b/web/dist/task.js @@ -87,15 +87,32 @@ export function mountTranscript(root) { } const sess = currentSession(task.id); if (task.status !== "active") { - replace(head, h("div", { class: "meta" }, h("code", {}, task.branch)), h("div", { class: "head-actions" }, task.status)); + replace(head, h("div", { class: "head-actions" }, task.status)); return; } const target = state.projects.find((p) => p.id === task.project_id)?.default_branch ?? "the default branch"; - const merge = h("button", { title: `Squash into one commit on ${target}; nothing is pushed` }, "Merge"); - merge.onclick = () => closeTask(task, (u) => `Merge "${task.title}" into ${target}? ${changesText(u)} become one commit on ${target}. Nothing is pushed.`, "/api/tasks/{taskId}/merge"); - const discard = h("button", { class: "danger", title: "Delete the worktree and branch without merging" }, "Discard"); - discard.onclick = () => closeTask(task, (u) => `Discard "${task.title}"? ${changesText(u)} that aren't on ${target} will be deleted. This can't be undone.`, "/api/tasks/{taskId}/discard"); - replace(head, h("div", { class: "meta" }, h("code", {}, task.branch)), h("div", { class: "head-actions" }, sess && contextMeter(context.get(sess.id)), sess && compactButton(sess.id, sess.state), merge, discard)); + const busy = sess?.state === "running" || sess?.state === "queued"; + const merge = h("button", { disabled: busy, title: `The agent merges ${target} in, then byre squashes into one commit on ${target}; nothing is pushed` }, "Merge"); + merge.onclick = () => confirmChanges(task, (u) => `Merge "${task.title}" into ${target}? The agent first merges ${target} in and resolves any conflicts; when that turn ends, ${changesText(u)} become one commit on ${target} and the task closes. Nothing is pushed.`, async () => { + await post("/api/tasks/{taskId}/merge", { path: { taskId: task.id } }); + }); + const mergeIn = h("button", { disabled: busy, title: `Ask the agent to merge ${target} into this branch and resolve any conflicts` }, `Merge ${target} in`); + mergeIn.onclick = async () => { + mergeIn.disabled = true; + try { + await post("/api/tasks/{taskId}/merge-in", { path: { taskId: task.id } }); + } + catch (err) { + alert(errorText(err)); + mergeIn.disabled = false; + } + }; + const discard = h("button", { class: "danger", disabled: busy, title: "Delete the worktree and branch without merging" }, "Discard"); + discard.onclick = () => confirmChanges(task, (u) => `Discard "${task.title}"? ${changesText(u)} that aren't on ${target} will be deleted. This can't be undone.`, async () => { + await post("/api/tasks/{taskId}/discard", { path: { taskId: task.id } }); + location.hash = "#/"; + }); + replace(head, h("div", { class: "head-actions session-actions" }, sess && contextMeter(context.get(sess.id)), sess && compactButton(sess.id, sess.state), mergeIn), h("div", { class: "head-actions" }, merge, discard)); }; let composerModel = ""; const renderComposer = () => { @@ -610,14 +627,13 @@ function messageImages(ids) { return h("a", { href: src, target: "_blank", rel: "noopener" }, h("img", { src, alt: "attached image", loading: "lazy" })); })); } -async function closeTask(task, prompt, path) { +async function confirmChanges(task, prompt, act) { try { const u = await get("/api/tasks/{taskId}/unmerged", { path: { taskId: task.id } }); if (!confirm(prompt(u))) { return; } - await post(path, { path: { taskId: task.id } }); - location.hash = "#/"; + await act(); } catch (err) { alert(errorText(err)); diff --git a/web/dist/task.js.map b/web/dist/task.js.map index b36246d..799c15e 100644 --- a/web/dist/task.js.map +++ b/web/dist/task.js.map @@ -1 +1 @@ -{"version":3,"file":"task.js","sourceRoot":"","sources":["../src/task.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAE,IAAI,EAA4C,MAAM,UAAU,CAAC;AAC/E,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,MAAM,eAAe,CAAC;AACzC,OAAO,EAAE,cAAc,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAErE,MAAM,MAAM,GAAG,CAAC,iBAAiB,EAAE,mBAAmB,EAAE,kBAAkB,EAAE,kBAAkB,CAAC,CAAC;AAmBhG,MAAM,UAAU,eAAe,CAAC,IAAiB;IAC/C,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACnD,MAAM,UAAU,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IACrD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,CAAC,CAAC;IAEjD,MAAM,cAAc,GAAG,IAAI,GAAG,EAAmB,CAAC;IAClD,MAAM,KAAK,GAAG,IAAI,GAAG,EAAU,CAAC;IAChC,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,QAAQ,CAAC,eAAe,KAAK,SAAS,EAAE,CAAC;YAC3C,OAAO;QACT,CAAC;QACD,MAAM,GAAG,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,cAAc,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;QACzH,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACrB,OAAO;QACT,CAAC;QACD,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;YACrB,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QAChB,CAAC;QACD,IAAI,CAAC,sBAAsB,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,SAAkB,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,EAAE,EAAE;YAChI,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;gBACrB,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;YACnB,CAAC;YACD,OAAO,CAAC,KAAK,CAAC,qBAAqB,EAAE,GAAG,CAAC,CAAC;QAC5C,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IACF,MAAM,QAAQ,GAAG,IAAI,oBAAoB,CACvC,CAAC,OAAO,EAAE,EAAE;QACV,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACxB,MAAM,EAAE,GAAI,CAAC,CAAC,MAAsB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAC1D,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,cAAc,EAAE,CAAC;gBACrB,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;YACnC,CAAC;iBAAM,CAAC;gBACN,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YAClC,CAAC;QACH,CAAC;QACD,UAAU,EAAE,CAAC;IACf,CAAC,EACD,EAAE,IAAI,EAAE,UAAU,EAAE,SAAS,EAAE,GAAG,EAAE,CACrC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAQ,EAAE;QACvB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,OAAO;YACL,KAAK,EAAE,IAAI,GAAG,EAAE;YAChB,GAAG,EAAE,SAAS;YACd,WAAW,EAAE,SAAS;YACtB,SAAS,EAAE,SAAS;YACpB,IAAI,EAAE,IAAI,EAAE,aAAa,IAAI,EAAE;YAC/B,WAAW,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,EAAE;gBAC1B,EAAE,CAAC,OAAO,CAAC,WAAW,CAAC,GAAG,MAAM,CAAC;gBACjC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;YACvB,CAAC;SACF,CAAC;IACJ,CAAC,CAAC;IACF,IAAI,GAAG,GAAG,MAAM,EAAE,CAAC;IACnB,IAAI,OAAO,GAAG,IAAI,GAAG,EAA2D,CAAC;IAEjF,MAAM,OAAO,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;IAChI,MAAM,UAAU,GAAG,CAAC,OAAgB,EAAE,EAAE;QACtC,UAAU,CAAC,SAAS,CAAC,MAAM,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QAChD,IAAI,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;YAChC,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,OAAO,CAAC,MAAM,GAAG,CAAC,OAAO,CAAC;QAC1B,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,EAAe,EAAE,EAAE;QAC9B,IAAI,OAAO,CAAC,UAAU,KAAK,UAAU,EAAE,CAAC;YACtC,UAAU,CAAC,YAAY,CAAC,EAAE,EAAE,OAAO,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,UAAU,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,UAAU,CAAC,IAAI,KAAK,SAAS,IAAI,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,KAAK,SAAS,CAAC,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,IAAI,CAAC,CAAC;YACd,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,IAAI,CAAC,MAAM,KAAK,QAAQ,EAAE,CAAC;YAC7B,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;YACzH,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,EAAE,cAAc,IAAI,oBAAoB,CAAC;QAC5G,MAAM,KAAK,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,6BAA6B,MAAM,qBAAqB,EAAE,EAAE,OAAO,CAAC,CAAC;QACxG,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CACnB,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,UAAU,IAAI,CAAC,KAAK,UAAU,MAAM,KAAK,WAAW,CAAC,CAAC,CAAC,yBAAyB,MAAM,sBAAsB,EAAE,2BAA2B,CAAC,CAAC;QACpK,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,gDAAgD,EAAE,EAAE,SAAS,CAAC,CAAC;QACrH,OAAO,CAAC,OAAO,GAAG,GAAG,EAAE,CACrB,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,YAAY,IAAI,CAAC,KAAK,MAAM,WAAW,CAAC,CAAC,CAAC,mBAAmB,MAAM,yCAAyC,EAAE,6BAA6B,CAAC,CAAC;QACtK,OAAO,CACL,IAAI,EACJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,EACvD,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,IAAI,IAAI,YAAY,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,IAAI,IAAI,aAAa,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAAE,KAAK,EAAE,OAAO,CAAC,CAC5I,CAAC;IACJ,CAAC,CAAC;IAEF,IAAI,aAAa,GAAG,EAAE,CAAC;IACvB,MAAM,cAAc,GAAG,GAAG,EAAE;QAC1B,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,QAAQ,CAAC,CAAC;YAClB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,KAAK,WAAW,EAAE,CAAC;YACxC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;YACtC,OAAO;QACT,CAAC;QACD,aAAa,GAAG,IAAI,CAAC,KAAK,IAAI,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC;QAChE,OAAO,CAAC,QAAQ,EAAE,WAAW,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,EAAE,aAAa,CAAC,CAAC,CAAC;IAC9E,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,EAAe,EAAE,IAAsB,EAAE,EAAE;QAC3D,MAAM,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC;QACpB,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,GAAG,CAAC,GAAG,GAAG,EAAE,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;YACrE,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,OAAO;QACT,CAAC;QACD,IAAI,IAAI,EAAE,CAAC;YACT,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACvB,CAAC;QACD,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC;YACf,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;YAC7B,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,CAAC,CAAC;YACpD,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC;YACnE,GAAG,CAAC,KAAK,CAAC,WAAW,CAAC,KAAK,CAAC,CAAC;YAC7B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACvB,IAAI,GAAG,CAAC,KAAK,CAAC,SAAS,CAAC,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;gBAC5C,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;YACjC,CAAC;YACD,GAAG,CAAC,KAAK,GAAG,EAAE,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC;QAC3C,CAAC;QACD,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QAC1B,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;IACpD,CAAC,CAAC;IAEF,IAAI,MAAoE,CAAC;IACzE,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,OAAO;QACT,CAAC;QACD,oBAAoB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACnC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC;QACnB,MAAM,GAAG,SAAS,CAAC;IACrB,CAAC,CAAC;IACF,MAAM,WAAW,GAAG,CAAC,EAAa,EAAE,EAAE;QACpC,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,MAAM,GAAG,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;YACtE,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;QACD,MAAM,CAAC,IAAI,IAAI,MAAM,CAAC,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;QAChD,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;YACjB,OAAO;QACT,CAAC;QACD,MAAM,CAAC,KAAK,GAAG,qBAAqB,CAAC,GAAG,EAAE;YACxC,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO;YACT,CAAC;YACD,MAAM,CAAC,KAAK,GAAG,CAAC,CAAC;YACjB,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;YAC7F,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC,CAAC;YACrD,IAAI,MAAM,EAAE,CAAC;gBACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;YACjD,CAAC;QACH,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,KAAkB,EAAE,GAAgB,EAAE,EAAE;QACxD,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;QAC7B,OAAO,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;QAChD,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC,CAAC;QAC7D,IAAI,IAAI,GAAqB,KAAK,CAAC;QACnC,OAAO,IAAI,IAAI,IAAI,KAAK,OAAO,EAAE,CAAC;YAChC,MAAM,IAAI,GAAqB,IAAI,CAAC,WAAW,CAAC;YAChD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;YAClB,IAAI,GAAG,IAAI,CAAC;QACd,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,YAAY,GAAG,CAAC,MAAmB,EAAE,EAAE;QAC3C,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,IAAI,cAAc,GAAG,KAAK,CAAC;QAC3B,KAAK,MAAM,EAAE,IAAI,MAAM,EAAE,CAAC;YACxB,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;YAChD,IAAI,EAAE,CAAC,IAAI,KAAK,eAAe,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC1F,UAAU,EAAE,CAAC;YACf,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,IAAI,EAAE,CAAC,gBAAgB,EAAE,CAAC;gBACzD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,CAAC,CAAC;gBAC9C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,CAAC;gBACxD,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC;gBACvG,cAAc,GAAG,IAAI,CAAC;gBACtB,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,EAAE,CAAC;gBAClC,QAAQ,CAAC,cAAc,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBACxG,SAAS;YACX,CAAC;YACD,MAAM,EAAE,GAAG,WAAW,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC;YAChC,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,gBAAgB,EAAE,CAAC;gBACjC,QAAQ,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;gBACxB,SAAS;YACX,CAAC;YACD,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,IAAI,GAAG,CAAC,SAAS,EAAE,UAAU,KAAK,UAAU,EAAE,CAAC;gBAClG,QAAQ,CAAC,GAAG,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;gBAC5B,GAAG,CAAC,SAAS,GAAG,SAAS,CAAC;gBAC1B,SAAS;YACX,CAAC;YACD,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC/B,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC;YACrB,CAAC;QACH,CAAC;QACD,IAAI,cAAc,EAAE,CAAC;YACnB,UAAU,EAAE,CAAC;YACb,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,cAAc,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;YACrF,IAAI,IAAI,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC,KAAK,aAAa,EAAE,CAAC;gBACjF,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC;QACD,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,SAAS,GAAG,GAAG,EAAE;QACrB,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,cAAc,CAAC,KAAK,EAAE,CAAC;QACvB,UAAU,EAAE,CAAC;QACb,GAAG,GAAG,MAAM,EAAE,CAAC;QACf,OAAO,GAAG,IAAI,GAAG,EAAE,CAAC;QACpB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC,KAAK,CAAC,cAAc,EAAE,CAAC;YAC1B,cAAc,EAAE,CAAC;YACjB,OAAO,CAAC,UAAU,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,2DAA2D,CAAC,CAAC,CAAC;YAC/G,OAAO;QACT,CAAC;QACD,OAAO,CAAC,UAAU,EAAE,OAAO,CAAC,CAAC;QAC7B,YAAY,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;QAC/B,cAAc,EAAE,CAAC;IACnB,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG;QACX,MAAM,CAAC,CAAC,WAAW,CAAC,EAAE,SAAS,CAAC;QAChC,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,EAAE;YACrB,UAAU,EAAE,CAAC;YACb,cAAc,EAAE,CAAC;QACnB,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE;YAC9B,IAAI,MAAM,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;gBACpC,UAAU,EAAE,CAAC;gBACb,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,YAAY,CAAC,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAoB,CAAC,CAAC;QACrE,MAAM,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,EAAE,EAAE,EAAE,CAAC,WAAW,CAAC,EAAe,CAAC,CAAC;QACxD,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,UAAU,CAAC;KAC9B,CAAC;IACF,QAAQ,CAAC,gBAAgB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;IAE1D,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC,CAAC;IAClF,SAAS,EAAE,CAAC;IACZ,OAAO,GAAG,EAAE;QACV,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;QACD,QAAQ,CAAC,mBAAmB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;QAC7D,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,UAAU,EAAE,CAAC;IACf,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,cAAc,GAAG,IAAI,GAAG,EAAkB,CAAC;AAEjD,SAAS,SAAS,CAAC,KAA0B,EAAE,GAAW;IACxD,KAAK,CAAC,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;IAC5C,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,GAAG,EAAE;QACnC,IAAI,KAAK,CAAC,KAAK,EAAE,CAAC;YAChB,cAAc,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QAC7B,CAAC;IACH,CAAC,CAAC,CAAC;IACH,OAAO,GAAG,EAAE,CAAC,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;AAC1C,CAAC;AAID,MAAM,WAAW,GAAG,IAAI,GAAG,EAA0B,CAAC;AAEtD,MAAM,UAAU,GAAG,CAAC,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,YAAY,CAAC,CAAC;AAC1E,MAAM,aAAa,GAAG,CAAC,IAAI,EAAE,CAAC;AAE9B,SAAS,SAAS,CAAC,IAAqB,EAAE,KAA0B,EAAE,GAAW;IAC/E,MAAM,EAAE,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,gBAAgB,EAAE,CAAC,CAAC;IACjD,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;QACxC,EAAE,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,KAAK,CAAC,CAAC;QAC9B,OAAO,CACL,EAAE,EACF,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YAClB,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,GAAG,CAAC,CAAC;YAC5F,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE;gBACpB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;gBAC7B,MAAM,IAAI,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC;gBACnE,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;gBAC7B,CAAC;qBAAM,CAAC;oBACN,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;gBAC1B,CAAC;gBACD,MAAM,EAAE,CAAC;YACX,CAAC,CAAC;YACF,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC;QACjG,CAAC,CAAC,CACH,CAAC;IACJ,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,KAAqB,EAAE,EAAE;QACpC,MAAM,KAAK,GAAmB,EAAE,CAAC;QACjC,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;YACtB,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC;gBACjC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,WAAW,wCAAwC,CAAC,CAAC;gBACxE,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,IAAI,GAAG,aAAa,EAAE,CAAC;gBAC3B,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,YAAY,YAAY,aAAa,IAAI,EAAE,OAAO,CAAC,CAAC;gBACvE,SAAS;YACX,CAAC;YACD,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,GAAG,EAAE,GAAG,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QACvD,CAAC;QACD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,KAAK,CAAC;QACf,CAAC;QACD,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,EAAE,GAAG,KAAK,CAAC,CAAC,CAAC;QAClE,MAAM,EAAE,CAAC;QACT,OAAO,IAAI,CAAC;IACd,CAAC,CAAC;IAEF,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,CAAC,CAAC,EAAE,EAAE;QACpC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC;QAC7F,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,UAAU,EAAE,CAAC,CAAC,EAAE,EAAE;QACtC,IAAI,CAAC,CAAC,YAAY,EAAE,KAAK,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;YAC5C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;QACjC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,EAAE;QACvC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,aAA4B,CAAC,EAAE,CAAC;YACnD,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QACpC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,MAAM,EAAE,CAAC,CAAC,EAAE,EAAE;QAClC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,YAAY,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,MAAM,EAAE,CAAC;IACT,OAAO;QACL,EAAE;QACF,IAAI,EAAE,GAAG,EAAE;YACT,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;YACxC,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;YACxB,MAAM,EAAE,CAAC;YACT,OAAO,IAAI,CAAC;QACd,CAAC;QACD,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE;YAChB,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,IAAI,EAAE,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YACnE,CAAC;YACD,MAAM,EAAE,CAAC;QACX,CAAC;KACF,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,YAAY,CAAC,IAAoB;IAC9C,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,YAAY,EAAE,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC;QAC1D,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACpB,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,aAAa,CAAC,IAAoB;IACzC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED,SAAS,SAAS,CAAC,MAAc;IAC/B,MAAM,MAAM,GAAG,CAAC,CAAC,UAAU,EAAE,EAAE,WAAW,EAAE,gEAAgE,EAAE,IAAI,EAAE,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACzI,MAAM,UAAU,GAAG,SAAS,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,KAAK,GAAG,WAAW,CAAC,SAAS,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IACzD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,aAAa,CAAC,CAAC,CAAC,CAAC;IAC5H,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC;QAC3B,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,MAAM,CAAC,KAAK,GAAG,EAAE,CAAC;QAClB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC;YACtH,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,SAAS,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC7C,MAAM,CAAC,KAAK,GAAG,KAAK,CAAC;YACrB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;IAC5B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,MAAM,YAAY,GAAG,IAAI,GAAG,EAAkB,CAAC;AAE/C,SAAS,WAAW,CAAC,GAAW,EAAE,OAAe;IAC/C,MAAM,OAAO,GAAG,OAAO,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;IACrF,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,yBAAyB,EAAE,EAAE,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IACtH,MAAM,CAAC,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,IAAI,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IAChE,MAAM,CAAC,QAAQ,GAAG,GAAG,EAAE;QACrB,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC;IACtC,CAAC,CAAC;IACF,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,WAAW,CAAC,MAAc,EAAE,SAAiB,EAAE,YAAoB,EAAE,YAAoB;IAChG,MAAM,IAAI,GAAG,CAAC,CAAC,UAAU,EAAE;QACzB,WAAW,EAAE,YAAY,KAAK,MAAM,CAAC,CAAC,CAAC,yDAAyD,CAAC,CAAC,CAAC,2CAA2C;QAC9I,IAAI,EAAE,CAAC;KACR,CAAC,CAAC;IACH,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC;IACxF,MAAM,SAAS,GAAG,CAAC,CACjB,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,SAAS,IAAI,YAAY,KAAK,QAAQ,EAAE,EACtG,YAAY,KAAK,QAAQ,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,WAAW,CAC/D,CAAC;IACF,SAAS,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QAC7B,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,qCAAqC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC7E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,WAAW,CAAC,WAAW,SAAS,EAAE,EAAE,YAAY,CAAC,CAAC;IAChE,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,IAAI,CAAC,CAAC,CAAC;IAC3F,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC;QACzB,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,CAAC,EAAE,CAAC;YAC3D,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,IAAI,CAAC,KAAK,GAAG,EAAE,CAAC;QAChB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,oCAAoC,EAAE;gBAC/C,IAAI,EAAE,EAAE,SAAS,EAAE;gBACnB,IAAI,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,KAAK,YAAY,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,EAAE;aAC7F,CAAC,CAAC;YACH,YAAY,CAAC,MAAM,CAAC,WAAW,SAAS,EAAE,CAAC,CAAC;YAC5C,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC/C,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;YACnB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IAC1B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,KAA0B,EAAE,IAAqB;IACtE,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC;YACvD,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,aAAa,EAAE,CAAC;QACvB,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,SAAS,aAAa,CAAC,SAAiB,EAAE,YAAoB;IAC5D,MAAM,CAAC,GAAG,CAAC,CACT,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,KAAK,EAAE,kFAAkF,EAAE,EAChJ,SAAS,CACV,CAAC;IACF,CAAC,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QACrB,CAAC,CAAC,QAAQ,GAAG,IAAI,CAAC;QAClB,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,mCAAmC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC3E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;YACtB,CAAC,CAAC,QAAQ,GAAG,KAAK,CAAC;QACrB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,CAAC,CAAC;AACX,CAAC;AAED,SAAS,YAAY,CAAC,CAA8D;IAClF,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QACxB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC;IACrD,MAAM,KAAK,GAAG,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC;IAC/D,MAAM,KAAK,GAAG,YAAY,CAAC,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC,MAAM,CAAC,cAAc,EAAE,UAAU,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;IAC5H,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,KAAK,EAAE,EAAE,KAAK,EAAE,EAAE,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;AACtF,CAAC;AAED,SAAS,cAAc,CAAC,CAA0B,EAAE,GAAQ;IAC1D,MAAM,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,qBAAqB,EAAE,EAAE,UAAU,CAAC,CAAC;IACtE,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;IACvC,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,MAAM,EAAE,EACjB,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAChJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EACtE,MAAM,CACP,CAAC;AACJ,CAAC;AAED,SAAS,UAAU,CAAC,KAAa;IAC/B,MAAM,MAAM,GAAG,IAAI,GAAG,EAAqC,CAAC;IAC5D,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,MAAM,GAAG,GAAG,GAAG,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,MAAM,EAAE,CAAC;QACrC,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,EAAE,CAAC;YACV,KAAK,CAAC,CAAC,EAAE,CAAC;QACZ,CAAC;aAAM,CAAC;YACN,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,UAAU,CAAC,CAAC;IACxD,CAAC;IACD,MAAM,KAAK,GAA6B,EAAE,CAAC;IAC3C,KAAK,MAAM,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,MAAM,CAAC,MAAM,EAAE,EAAE,CAAC;QAC1C,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACnB,CAAC;QACD,KAAK,CAAC,IAAI,CACR,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CACpM,CAAC;IACJ,CAAC;IACD,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,GAAG,KAAK,CAAC,CAAC;AACjC,CAAC;AAED,SAAS,WAAW,CAAC,EAAa,EAAE,GAAQ;IAC1C,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;IAChD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,QAAQ,EAAE,EAAE,CAAC,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC,UAAU,EAAE,EAAE,GAAG,CAAC,EAAE,CAAC,UAAU,CAAC,CAAC,CAAC;IAE9F,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;QAChB,KAAK,cAAc;YACjB,GAAG,CAAC,WAAW,GAAG,SAAS,CAAC;YAC5B,IAAI,EAAE,CAAC,KAAK,KAAK,MAAM,EAAE,CAAC;gBACxB,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC;gBAC/B,MAAM,CAAC,KAAK,EAAE,GAAG,IAAI,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;gBAC1C,IAAI,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;oBAChC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;gBACtD,CAAC;gBACD,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAAE,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YACnH,CAAC;YACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,UAAU,EAAE,EACrB,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAC/C,aAAa,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAC1B,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,IAAI,CAC/E,CAAC;QAEJ,KAAK,eAAe;YAClB,GAAG,CAAC,WAAW,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YAC3F,OAAO,GAAG,CAAC,WAAW,CAAC;QAEzB,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;QAEnH,KAAK,mBAAmB,CAAC,CAAC,CAAC;YACzB,MAAM,MAAM,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;YACvD,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,EAAE,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;YACpD,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,oBAAoB,EAAE,EAAE,IAAI,CAAC,CAAC;YACzD,CAAC;YACD,MAAM,CAAC,SAAS,GAAG,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,mBAAmB,CAAC,CAAC,CAAC,aAAa,CAAC;YACvE,OAAO,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YACtB,IAAI,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC;gBAClB,MAAM,CAAC,OAAO,CAAC,cAAc,CAAC,EAAE,SAAS,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;gBACzD,MAAM,CAAC,OAAO,CAAC,oBAAoB,CAAC,EAAE,SAAS,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;YACjE,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,YAAY;YACf,IAAI,OAAO,CAAC,CAAC,eAAe,CAAC,KAAK,QAAQ,IAAI,CAAC,CAAC,eAAe,CAAC,IAAI,GAAG,CAAC,WAAW,EAAE,CAAC;gBACpF,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC;YACvD,CAAC;YACD,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,EAAE,CAAC;gBAC1B,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,oEAAoE,EAAE,IAAI,CAAC,CAAC;YACjH,CAAC;YACD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,eAAe,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAE1J,KAAK,iBAAiB;YACpB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,cAAc,CAAC,CAAC,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEtI,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,0BAA0B,CAAC,CAAC,OAAO,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;QAE/F,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,WAAW,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAEvG,KAAK,eAAe,CAAC,CAAC,CAAC;YACrB,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC;YACvB,IAAI,IAAI,KAAK,UAAU,EAAE,CAAC;gBACxB,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,QAAQ,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAChH,CAAC;YACD,IAAI,IAAI,KAAK,eAAe,IAAI,IAAI,KAAK,cAAc,EAAE,CAAC;gBACxD,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC/D,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,aAAa;YAChB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,mBAAmB,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,OAAO,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEzI,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,sBAAsB,EAAE,IAAI,CAAC,CAAC;IAChF,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,GAAY;IACjC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC5C,OAAO,IAAI,CAAC;IACd,CAAC;IACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,YAAY,EAAE,EACvB,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QAChB,MAAM,GAAG,GAAG,cAAc,kBAAkB,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;QAC3D,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC;IAC7H,CAAC,CAAC,CACH,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,SAAS,CAAC,IAAU,EAAE,MAA+B,EAAE,IAAiE;IACrI,IAAI,CAAC;QACH,MAAM,CAAC,GAAG,MAAM,GAAG,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACnF,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,CAAC,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QAChD,QAAQ,CAAC,IAAI,GAAG,IAAI,CAAC;IACvB,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;IACxB,CAAC;AACH,CAAC;AAED,SAAS,WAAW,CAAC,CAAW;IAC9B,MAAM,MAAM,GAAG,CAAC,CAAS,EAAE,IAAY,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC;IAChF,MAAM,WAAW,GAAG,CAAC,CAAC,WAAW,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,WAAW,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC;IAC9E,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,MAAM,CAAC,CAAC,CAAC,KAAK,EAAE,cAAc,CAAC,MAAM,CAAC,CAAC,UAAU,KAAK,CAAC,CAAC,SAAS,GAAG,WAAW,GAAG,CAAC;AAClI,CAAC;AAED,SAAS,SAAS,CAAC,KAAc,EAAE,IAAY;IAC7C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,CAAC,GAAG,KAAgC,CAAC;IAC3C,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,aAAa,CAAC,IAAI,EAAE,CAAC;IACpH,MAAM,IAAI,GAAG,QAAQ,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,IAAI,CAAC,CAAC;IAC3C,OAAO,IAAI,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC;AAC7D,CAAC;AAED,SAAS,UAAU,CAAC,KAAc,EAAE,IAAY;IAC9C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,IAAI,GAAI,KAAiC,CAAC,WAAW,CAAC,CAAC;IAC7D,OAAO,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AAC9D,CAAC;AAED,SAAS,QAAQ,CAAC,IAAY,EAAE,IAAY;IAC1C,OAAO,IAAI,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;AAClF,CAAC;AAED,SAAS,UAAU,CAAC,OAAgB;IAClC,IAAI,OAAO,OAAO,KAAK,QAAQ,EAAE,CAAC;QAChC,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,IAAI,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;QAC3B,OAAO,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,QAAQ,IAAI,CAAC,KAAK,IAAI,IAAI,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAClI,CAAC;IACD,OAAO,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;AAC1C,CAAC"} \ No newline at end of file +{"version":3,"file":"task.js","sourceRoot":"","sources":["../src/task.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,GAAG,EAAE,IAAI,EAA4C,MAAM,UAAU,CAAC;AAC/E,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,MAAM,eAAe,CAAC;AACzC,OAAO,EAAE,cAAc,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAErE,MAAM,MAAM,GAAG,CAAC,iBAAiB,EAAE,mBAAmB,EAAE,kBAAkB,EAAE,kBAAkB,CAAC,CAAC;AAmBhG,MAAM,UAAU,eAAe,CAAC,IAAiB;IAC/C,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;IACnD,MAAM,UAAU,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,CAAC;IACrD,MAAM,QAAQ,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,CAAC,CAAC;IAEjD,MAAM,cAAc,GAAG,IAAI,GAAG,EAAmB,CAAC;IAClD,MAAM,KAAK,GAAG,IAAI,GAAG,EAAU,CAAC;IAChC,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,QAAQ,CAAC,eAAe,KAAK,SAAS,EAAE,CAAC;YAC3C,OAAO;QACT,CAAC;QACD,MAAM,GAAG,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,cAAc,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;QACzH,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACrB,OAAO;QACT,CAAC;QACD,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;YACrB,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QAChB,CAAC;QACD,IAAI,CAAC,sBAAsB,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,SAAkB,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,GAAG,EAAE,EAAE;YAChI,KAAK,MAAM,EAAE,IAAI,GAAG,EAAE,CAAC;gBACrB,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;YACnB,CAAC;YACD,OAAO,CAAC,KAAK,CAAC,qBAAqB,EAAE,GAAG,CAAC,CAAC;QAC5C,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IACF,MAAM,QAAQ,GAAG,IAAI,oBAAoB,CACvC,CAAC,OAAO,EAAE,EAAE;QACV,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACxB,MAAM,EAAE,GAAI,CAAC,CAAC,MAAsB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAC1D,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,cAAc,EAAE,CAAC;gBACrB,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;YACnC,CAAC;iBAAM,CAAC;gBACN,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YAClC,CAAC;QACH,CAAC;QACD,UAAU,EAAE,CAAC;IACf,CAAC,EACD,EAAE,IAAI,EAAE,UAAU,EAAE,SAAS,EAAE,GAAG,EAAE,CACrC,CAAC;IAEF,MAAM,MAAM,GAAG,GAAQ,EAAE;QACvB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,OAAO;YACL,KAAK,EAAE,IAAI,GAAG,EAAE;YAChB,GAAG,EAAE,SAAS;YACd,WAAW,EAAE,SAAS;YACtB,SAAS,EAAE,SAAS;YACpB,IAAI,EAAE,IAAI,EAAE,aAAa,IAAI,EAAE;YAC/B,WAAW,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,EAAE;gBAC1B,EAAE,CAAC,OAAO,CAAC,WAAW,CAAC,GAAG,MAAM,CAAC;gBACjC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;YACvB,CAAC;SACF,CAAC;IACJ,CAAC,CAAC;IACF,IAAI,GAAG,GAAG,MAAM,EAAE,CAAC;IACnB,IAAI,OAAO,GAAG,IAAI,GAAG,EAA2D,CAAC;IAEjF,MAAM,OAAO,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;IAChI,MAAM,UAAU,GAAG,CAAC,OAAgB,EAAE,EAAE;QACtC,UAAU,CAAC,SAAS,CAAC,MAAM,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QAChD,IAAI,OAAO,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;YAChC,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,OAAO,CAAC,MAAM,GAAG,CAAC,OAAO,CAAC;QAC1B,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,EAAe,EAAE,EAAE;QAC9B,IAAI,OAAO,CAAC,UAAU,KAAK,UAAU,EAAE,CAAC;YACtC,UAAU,CAAC,YAAY,CAAC,EAAE,EAAE,OAAO,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,UAAU,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,UAAU,CAAC,IAAI,KAAK,SAAS,IAAI,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,KAAK,SAAS,CAAC,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,IAAI,CAAC,CAAC;YACd,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,IAAI,CAAC,MAAM,KAAK,QAAQ,EAAE,CAAC;YAC7B,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;YAChE,OAAO;QACT,CAAC;QACD,MAAM,MAAM,GAAG,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,UAAU,CAAC,EAAE,cAAc,IAAI,oBAAoB,CAAC;QAC5G,MAAM,IAAI,GAAG,IAAI,EAAE,KAAK,KAAK,SAAS,IAAI,IAAI,EAAE,KAAK,KAAK,QAAQ,CAAC;QACnE,MAAM,KAAK,GAAG,CAAC,CACb,QAAQ,EACR,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,oBAAoB,MAAM,8CAA8C,MAAM,qBAAqB,EAAE,EAC9H,OAAO,CACR,CAAC;QACF,KAAK,CAAC,OAAO,GAAG,GAAG,EAAE,CACnB,cAAc,CACZ,IAAI,EACJ,CAAC,CAAC,EAAE,EAAE,CACJ,UAAU,IAAI,CAAC,KAAK,UAAU,MAAM,4BAA4B,MAAM,wDAAwD,WAAW,CAAC,CAAC,CAAC,yBAAyB,MAAM,0CAA0C,EACvN,KAAK,IAAI,EAAE;YACT,MAAM,IAAI,CAAC,2BAA2B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACzE,CAAC,CACF,CAAC;QACJ,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,0BAA0B,MAAM,6CAA6C,EAAE,EAAE,SAAS,MAAM,KAAK,CAAC,CAAC;QAC5J,OAAO,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;YAC3B,OAAO,CAAC,QAAQ,GAAG,IAAI,CAAC;YACxB,IAAI,CAAC;gBACH,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;YAC5E,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;gBACtB,OAAO,CAAC,QAAQ,GAAG,KAAK,CAAC;YAC3B,CAAC;QACH,CAAC,CAAC;QACF,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,gDAAgD,EAAE,EAAE,SAAS,CAAC,CAAC;QACrI,OAAO,CAAC,OAAO,GAAG,GAAG,EAAE,CACrB,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,YAAY,IAAI,CAAC,KAAK,MAAM,WAAW,CAAC,CAAC,CAAC,mBAAmB,MAAM,yCAAyC,EAAE,KAAK,IAAI,EAAE;YACnJ,MAAM,IAAI,CAAC,6BAA6B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;YACzE,QAAQ,CAAC,IAAI,GAAG,IAAI,CAAC;QACvB,CAAC,CAAC,CAAC;QACL,OAAO,CACL,IAAI,EACJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,8BAA8B,EAAE,EAAE,IAAI,IAAI,YAAY,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,IAAI,IAAI,aAAa,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAAE,OAAO,CAAC,EACpJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,KAAK,EAAE,OAAO,CAAC,CACpD,CAAC;IACJ,CAAC,CAAC;IAEF,IAAI,aAAa,GAAG,EAAE,CAAC;IACvB,MAAM,cAAc,GAAG,GAAG,EAAE;QAC1B,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC/E,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,OAAO,CAAC,QAAQ,CAAC,CAAC;YAClB,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACrC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,KAAK,WAAW,EAAE,CAAC;YACxC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;YACtC,OAAO;QACT,CAAC;QACD,aAAa,GAAG,IAAI,CAAC,KAAK,IAAI,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC;QAChE,OAAO,CAAC,QAAQ,EAAE,WAAW,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,EAAE,aAAa,CAAC,CAAC,CAAC;IAC9E,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,EAAe,EAAE,IAAsB,EAAE,EAAE;QAC3D,MAAM,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC;QACpB,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,GAAG,CAAC,GAAG,GAAG,EAAE,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;YACrE,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,OAAO;QACT,CAAC;QACD,IAAI,IAAI,EAAE,CAAC;YACT,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACvB,CAAC;QACD,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC;YACf,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;YAC7B,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,CAAC,CAAC;YACpD,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC;YACnE,GAAG,CAAC,KAAK,CAAC,WAAW,CAAC,KAAK,CAAC,CAAC;YAC7B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACvB,IAAI,GAAG,CAAC,KAAK,CAAC,SAAS,CAAC,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;gBAC5C,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;YACjC,CAAC;YACD,GAAG,CAAC,KAAK,GAAG,EAAE,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC;QAC3C,CAAC;QACD,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QAC1B,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC;IACpD,CAAC,CAAC;IAEF,IAAI,MAAoE,CAAC;IACzE,MAAM,UAAU,GAAG,GAAG,EAAE;QACtB,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,OAAO;QACT,CAAC;QACD,oBAAoB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACnC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC;QACnB,MAAM,GAAG,SAAS,CAAC;IACrB,CAAC,CAAC;IACF,MAAM,WAAW,GAAG,CAAC,EAAa,EAAE,EAAE;QACpC,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,MAAM,GAAG,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;YACtE,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;QACD,MAAM,CAAC,IAAI,IAAI,MAAM,CAAC,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;QAChD,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;YACjB,OAAO;QACT,CAAC;QACD,MAAM,CAAC,KAAK,GAAG,qBAAqB,CAAC,GAAG,EAAE;YACxC,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO;YACT,CAAC;YACD,MAAM,CAAC,KAAK,GAAG,CAAC,CAAC;YACjB,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;YAC7F,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC,CAAC;YACrD,IAAI,MAAM,EAAE,CAAC;gBACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;YACjD,CAAC;QACH,CAAC,CAAC,CAAC;IACL,CAAC,CAAC;IAEF,MAAM,QAAQ,GAAG,CAAC,KAAkB,EAAE,GAAgB,EAAE,EAAE;QACxD,MAAM,OAAO,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC;QAC7B,OAAO,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;QAChD,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,CAAC,CAAC;QAC7D,IAAI,IAAI,GAAqB,KAAK,CAAC;QACnC,OAAO,IAAI,IAAI,IAAI,KAAK,OAAO,EAAE,CAAC;YAChC,MAAM,IAAI,GAAqB,IAAI,CAAC,WAAW,CAAC;YAChD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;YAClB,IAAI,GAAG,IAAI,CAAC;QACd,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,YAAY,GAAG,CAAC,MAAmB,EAAE,EAAE;QAC3C,MAAM,MAAM,GAAG,UAAU,CAAC,YAAY,GAAG,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,GAAG,EAAE,CAAC;QAC7F,IAAI,cAAc,GAAG,KAAK,CAAC;QAC3B,KAAK,MAAM,EAAE,IAAI,MAAM,EAAE,CAAC;YACxB,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;YAChD,IAAI,EAAE,CAAC,IAAI,KAAK,eAAe,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC1F,UAAU,EAAE,CAAC;YACf,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,IAAI,EAAE,CAAC,gBAAgB,EAAE,CAAC;gBACzD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,CAAC,CAAC;gBAC9C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,IAAI,IAAI,EAAE,MAAM,IAAI,CAAC,CAAC;gBACxD,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,gBAAgB,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC;gBACvG,cAAc,GAAG,IAAI,CAAC;gBACtB,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,iBAAiB,EAAE,CAAC;gBAClC,QAAQ,CAAC,cAAc,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;gBACxG,SAAS;YACX,CAAC;YACD,MAAM,EAAE,GAAG,WAAW,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC;YAChC,IAAI,CAAC,EAAE,EAAE,CAAC;gBACR,SAAS;YACX,CAAC;YACD,IAAI,EAAE,CAAC,IAAI,KAAK,gBAAgB,EAAE,CAAC;gBACjC,QAAQ,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;gBACxB,SAAS;YACX,CAAC;YACD,GAAG,CAAC,GAAG,GAAG,SAAS,CAAC;YACpB,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,IAAI,GAAG,CAAC,SAAS,EAAE,UAAU,KAAK,UAAU,EAAE,CAAC;gBAClG,QAAQ,CAAC,GAAG,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;gBAC5B,GAAG,CAAC,SAAS,GAAG,SAAS,CAAC;gBAC1B,SAAS;YACX,CAAC;YACD,GAAG,CAAC,EAAE,CAAC,CAAC;YACR,IAAI,EAAE,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;gBAC/B,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC;YACrB,CAAC;QACH,CAAC;QACD,IAAI,cAAc,EAAE,CAAC;YACnB,UAAU,EAAE,CAAC;YACb,MAAM,IAAI,GAAG,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,cAAc,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;YACrF,IAAI,IAAI,IAAI,CAAC,IAAI,CAAC,KAAK,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,KAAK,IAAI,EAAE,CAAC,KAAK,aAAa,EAAE,CAAC;gBACjF,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC;QACD,IAAI,MAAM,EAAE,CAAC;YACX,UAAU,CAAC,SAAS,GAAG,UAAU,CAAC,YAAY,CAAC;QACjD,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,SAAS,GAAG,GAAG,EAAE;QACrB,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,cAAc,CAAC,KAAK,EAAE,CAAC;QACvB,UAAU,EAAE,CAAC;QACb,GAAG,GAAG,MAAM,EAAE,CAAC;QACf,OAAO,GAAG,IAAI,GAAG,EAAE,CAAC;QACpB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC,KAAK,CAAC,cAAc,EAAE,CAAC;YAC1B,cAAc,EAAE,CAAC;YACjB,OAAO,CAAC,UAAU,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,2DAA2D,CAAC,CAAC,CAAC;YAC/G,OAAO;QACT,CAAC;QACD,OAAO,CAAC,UAAU,EAAE,OAAO,CAAC,CAAC;QAC7B,YAAY,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;QAC/B,cAAc,EAAE,CAAC;IACnB,CAAC,CAAC;IAEF,MAAM,IAAI,GAAG;QACX,MAAM,CAAC,CAAC,WAAW,CAAC,EAAE,SAAS,CAAC;QAChC,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,EAAE;YACrB,UAAU,EAAE,CAAC;YACb,cAAc,EAAE,CAAC;QACnB,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE;YAC9B,IAAI,MAAM,KAAK,KAAK,CAAC,cAAc,EAAE,CAAC;gBACpC,UAAU,EAAE,CAAC;gBACb,cAAc,EAAE,CAAC;YACnB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,CAAC,CAAC,YAAY,CAAC,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAoB,CAAC,CAAC;QACrE,MAAM,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,EAAE,EAAE,EAAE,CAAC,WAAW,CAAC,EAAe,CAAC,CAAC;QACxD,MAAM,CAAC,CAAC,OAAO,CAAC,EAAE,UAAU,CAAC;KAC9B,CAAC;IACF,QAAQ,CAAC,gBAAgB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;IAE1D,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC,CAAC;IAClF,SAAS,EAAE,CAAC;IACZ,OAAO,GAAG,EAAE;QACV,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,GAAG,EAAE,CAAC;QACR,CAAC;QACD,QAAQ,CAAC,mBAAmB,CAAC,kBAAkB,EAAE,UAAU,CAAC,CAAC;QAC7D,QAAQ,CAAC,UAAU,EAAE,CAAC;QACtB,UAAU,EAAE,CAAC;IACf,CAAC,CAAC;AACJ,CAAC;AAED,MAAM,cAAc,GAAG,IAAI,GAAG,EAAkB,CAAC;AAEjD,SAAS,SAAS,CAAC,KAA0B,EAAE,GAAW;IACxD,KAAK,CAAC,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;IAC5C,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,GAAG,EAAE;QACnC,IAAI,KAAK,CAAC,KAAK,EAAE,CAAC;YAChB,cAAc,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACvC,CAAC;aAAM,CAAC;YACN,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QAC7B,CAAC;IACH,CAAC,CAAC,CAAC;IACH,OAAO,GAAG,EAAE,CAAC,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;AAC1C,CAAC;AAID,MAAM,WAAW,GAAG,IAAI,GAAG,EAA0B,CAAC;AAEtD,MAAM,UAAU,GAAG,CAAC,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,YAAY,CAAC,CAAC;AAC1E,MAAM,aAAa,GAAG,CAAC,IAAI,EAAE,CAAC;AAE9B,SAAS,SAAS,CAAC,IAAqB,EAAE,KAA0B,EAAE,GAAW;IAC/E,MAAM,EAAE,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,gBAAgB,EAAE,CAAC,CAAC;IACjD,MAAM,MAAM,GAAG,GAAG,EAAE;QAClB,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;QACxC,EAAE,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,KAAK,CAAC,CAAC;QAC9B,OAAO,CACL,EAAE,EACF,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YAClB,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,KAAK,EAAE,cAAc,EAAE,EAAE,GAAG,CAAC,CAAC;YAC5F,MAAM,CAAC,OAAO,GAAG,GAAG,EAAE;gBACpB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;gBAC7B,MAAM,IAAI,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC;gBACnE,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;gBAC7B,CAAC;qBAAM,CAAC;oBACN,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;gBAC1B,CAAC;gBACD,MAAM,EAAE,CAAC;YACX,CAAC,CAAC;YACF,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC;QACjG,CAAC,CAAC,CACH,CAAC;IACJ,CAAC,CAAC;IACF,MAAM,GAAG,GAAG,CAAC,KAAqB,EAAE,EAAE;QACpC,MAAM,KAAK,GAAmB,EAAE,CAAC;QACjC,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;YACtB,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC;gBACjC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,WAAW,wCAAwC,CAAC,CAAC;gBACxE,SAAS;YACX,CAAC;YACD,IAAI,CAAC,CAAC,IAAI,GAAG,aAAa,EAAE,CAAC;gBAC3B,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,YAAY,YAAY,aAAa,IAAI,EAAE,OAAO,CAAC,CAAC;gBACvE,SAAS;YACX,CAAC;YACD,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,GAAG,EAAE,GAAG,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QACvD,CAAC;QACD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,OAAO,KAAK,CAAC;QACf,CAAC;QACD,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,EAAE,GAAG,KAAK,CAAC,CAAC,CAAC;QAClE,MAAM,EAAE,CAAC;QACT,OAAO,IAAI,CAAC;IACd,CAAC,CAAC;IAEF,KAAK,CAAC,gBAAgB,CAAC,OAAO,EAAE,CAAC,CAAC,EAAE,EAAE;QACpC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC;QAC7F,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,UAAU,EAAE,CAAC,CAAC,EAAE,EAAE;QACtC,IAAI,CAAC,CAAC,YAAY,EAAE,KAAK,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;YAC5C,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;QACjC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,EAAE;QACvC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,aAA4B,CAAC,EAAE,CAAC;YACnD,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QACpC,CAAC;IACH,CAAC,CAAC,CAAC;IACH,IAAI,CAAC,gBAAgB,CAAC,MAAM,EAAE,CAAC,CAAC,EAAE,EAAE;QAClC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC;QAClC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,YAAY,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,GAAG,CAAC,KAAK,CAAC,CAAC;QACb,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,MAAM,EAAE,CAAC;IACT,OAAO;QACL,EAAE;QACF,IAAI,EAAE,GAAG,EAAE;YACT,MAAM,IAAI,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;YACxC,WAAW,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;YACxB,MAAM,EAAE,CAAC;YACT,OAAO,IAAI,CAAC;QACd,CAAC;QACD,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE;YAChB,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpB,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,IAAI,EAAE,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YACnE,CAAC;YACD,MAAM,EAAE,CAAC;QACX,CAAC;KACF,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,YAAY,CAAC,IAAoB;IAC9C,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,MAAM,IAAI,GAAG,MAAM,IAAI,CAAC,YAAY,EAAE,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC;QAC1D,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACpB,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,aAAa,CAAC,IAAoB;IACzC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACvB,GAAG,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED,SAAS,SAAS,CAAC,MAAc;IAC/B,MAAM,MAAM,GAAG,CAAC,CAAC,UAAU,EAAE,EAAE,WAAW,EAAE,gEAAgE,EAAE,IAAI,EAAE,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC;IACzI,MAAM,UAAU,GAAG,SAAS,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,KAAK,GAAG,WAAW,CAAC,SAAS,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IACzD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,aAAa,CAAC,CAAC,CAAC,CAAC;IAC5H,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC;QAC3B,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,MAAM,CAAC,KAAK,GAAG,EAAE,CAAC;QAClB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC;YACtH,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,SAAS,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC7C,MAAM,CAAC,KAAK,GAAG,KAAK,CAAC;YACrB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;IAC5B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,MAAM,YAAY,GAAG,IAAI,GAAG,EAAkB,CAAC;AAE/C,SAAS,WAAW,CAAC,GAAW,EAAE,OAAe;IAC/C,MAAM,OAAO,GAAG,OAAO,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;IACrF,MAAM,MAAM,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,yBAAyB,EAAE,EAAE,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IACtH,MAAM,CAAC,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,IAAI,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC;IAChE,MAAM,CAAC,QAAQ,GAAG,GAAG,EAAE;QACrB,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAC;IACtC,CAAC,CAAC;IACF,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,WAAW,CAAC,MAAc,EAAE,SAAiB,EAAE,YAAoB,EAAE,YAAoB;IAChG,MAAM,IAAI,GAAG,CAAC,CAAC,UAAU,EAAE;QACzB,WAAW,EAAE,YAAY,KAAK,MAAM,CAAC,CAAC,CAAC,yDAAyD,CAAC,CAAC,CAAC,2CAA2C;QAC9I,IAAI,EAAE,CAAC;KACR,CAAC,CAAC;IACH,MAAM,UAAU,GAAG,SAAS,CAAC,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,MAAM,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,EAAE,MAAM,CAAC,CAAC;IACxF,MAAM,SAAS,GAAG,CAAC,CACjB,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,SAAS,IAAI,YAAY,KAAK,QAAQ,EAAE,EACtG,YAAY,KAAK,QAAQ,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,WAAW,CAC/D,CAAC;IACF,SAAS,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QAC7B,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,qCAAqC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC7E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IAEF,MAAM,KAAK,GAAG,WAAW,CAAC,WAAW,SAAS,EAAE,EAAE,YAAY,CAAC,CAAC;IAChE,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,IAAI,EAAE,WAAW,MAAM,EAAE,CAAC,CAAC;IACxD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,iBAAiB,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,IAAI,CAAC,CAAC,CAAC;IAC3F,IAAI,CAAC,QAAQ,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;QAC1B,CAAC,CAAC,cAAc,EAAE,CAAC;QACnB,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC;QACzB,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,CAAC,EAAE,CAAC;YAC3D,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QACzB,IAAI,CAAC,KAAK,GAAG,EAAE,CAAC;QAChB,UAAU,EAAE,CAAC;QACb,IAAI,CAAC;YACH,MAAM,MAAM,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,oCAAoC,EAAE;gBAC/C,IAAI,EAAE,EAAE,SAAS,EAAE;gBACnB,IAAI,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,CAAC,KAAK,KAAK,YAAY,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,EAAE;aAC7F,CAAC,CAAC;YACH,YAAY,CAAC,MAAM,CAAC,WAAW,SAAS,EAAE,CAAC,CAAC;YAC5C,aAAa,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,cAAc,CAAC,GAAG,CAAC,WAAW,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;YAC/C,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;YACnB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACnB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;QACxB,CAAC;IACH,CAAC,CAAC;IACF,aAAa,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IAC1B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,KAA0B,EAAE,IAAqB;IACtE,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,EAAE,EAAE;QACtB,IAAI,CAAC,CAAC,GAAG,KAAK,OAAO,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC;YACvD,CAAC,CAAC,cAAc,EAAE,CAAC;YACnB,IAAI,CAAC,aAAa,EAAE,CAAC;QACvB,CAAC;IACH,CAAC,CAAC;AACJ,CAAC;AAED,SAAS,aAAa,CAAC,SAAiB,EAAE,YAAoB;IAC5D,MAAM,CAAC,GAAG,CAAC,CACT,QAAQ,EACR,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,YAAY,KAAK,MAAM,EAAE,KAAK,EAAE,kFAAkF,EAAE,EAChJ,SAAS,CACV,CAAC;IACF,CAAC,CAAC,OAAO,GAAG,KAAK,IAAI,EAAE;QACrB,CAAC,CAAC,QAAQ,GAAG,IAAI,CAAC;QAClB,IAAI,CAAC;YACH,MAAM,IAAI,CAAC,mCAAmC,EAAE,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC,CAAC;QAC3E,CAAC;QAAC,OAAO,GAAG,EAAE,CAAC;YACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;YACtB,CAAC,CAAC,QAAQ,GAAG,KAAK,CAAC;QACrB,CAAC;IACH,CAAC,CAAC;IACF,OAAO,CAAC,CAAC;AACX,CAAC;AAED,SAAS,YAAY,CAAC,CAA8D;IAClF,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QACxB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC;IACrD,MAAM,KAAK,GAAG,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC;IAC/D,MAAM,KAAK,GAAG,YAAY,CAAC,CAAC,IAAI,CAAC,cAAc,EAAE,OAAO,CAAC,CAAC,MAAM,CAAC,cAAc,EAAE,UAAU,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;IAC5H,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,iBAAiB,KAAK,EAAE,EAAE,KAAK,EAAE,EAAE,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;AACtF,CAAC;AAED,SAAS,cAAc,CAAC,CAA0B,EAAE,GAAQ;IAC1D,MAAM,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,qBAAqB,EAAE,EAAE,UAAU,CAAC,CAAC;IACtE,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;IACvC,OAAO,CAAC,CACN,SAAS,EACT,EAAE,KAAK,EAAE,MAAM,EAAE,EACjB,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAChJ,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EACtE,MAAM,CACP,CAAC;AACJ,CAAC;AAED,SAAS,UAAU,CAAC,KAAa;IAC/B,MAAM,MAAM,GAAG,IAAI,GAAG,EAAqC,CAAC;IAC5D,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,MAAM,GAAG,GAAG,GAAG,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,MAAM,EAAE,CAAC;QACrC,MAAM,KAAK,GAAG,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,KAAK,EAAE,CAAC;YACV,KAAK,CAAC,CAAC,EAAE,CAAC;QACZ,CAAC;aAAM,CAAC;YACN,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC;QACrC,CAAC;IACH,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,UAAU,CAAC,CAAC;IACxD,CAAC;IACD,MAAM,KAAK,GAA6B,EAAE,CAAC;IAC3C,KAAK,MAAM,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,MAAM,CAAC,MAAM,EAAE,EAAE,CAAC;QAC1C,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACnB,CAAC;QACD,KAAK,CAAC,IAAI,CACR,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CACpM,CAAC;IACJ,CAAC;IACD,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,GAAG,KAAK,CAAC,CAAC;AACjC,CAAC;AAED,SAAS,WAAW,CAAC,EAAa,EAAE,GAAQ;IAC1C,MAAM,CAAC,GAAG,EAAE,CAAC,OAAkC,CAAC;IAChD,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,QAAQ,EAAE,EAAE,CAAC,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC,UAAU,EAAE,EAAE,GAAG,CAAC,EAAE,CAAC,UAAU,CAAC,CAAC,CAAC;IAE9F,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;QAChB,KAAK,cAAc;YACjB,GAAG,CAAC,WAAW,GAAG,SAAS,CAAC;YAC5B,IAAI,EAAE,CAAC,KAAK,KAAK,MAAM,EAAE,CAAC;gBACxB,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC;gBAC/B,MAAM,CAAC,KAAK,EAAE,GAAG,IAAI,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;gBAC1C,IAAI,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC;oBAChC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;gBACtD,CAAC;gBACD,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAAE,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YACnH,CAAC;YACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,UAAU,EAAE,EACrB,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,EAC/C,aAAa,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAC1B,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,IAAI,CAC/E,CAAC;QAEJ,KAAK,eAAe;YAClB,GAAG,CAAC,WAAW,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,WAAW,EAAE,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;YAC3F,OAAO,GAAG,CAAC,WAAW,CAAC;QAEzB,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,SAAS,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,SAAS,EAAE,EAAE,EAAE,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;QAEnH,KAAK,mBAAmB,CAAC,CAAC,CAAC;YACzB,MAAM,MAAM,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;YACvD,MAAM,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,EAAE,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;YACpD,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,oBAAoB,EAAE,EAAE,IAAI,CAAC,CAAC;YACzD,CAAC;YACD,MAAM,CAAC,SAAS,GAAG,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,mBAAmB,CAAC,CAAC,CAAC,aAAa,CAAC;YACvE,OAAO,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YACtB,IAAI,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC;gBAClB,MAAM,CAAC,OAAO,CAAC,cAAc,CAAC,EAAE,SAAS,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;gBACzD,MAAM,CAAC,OAAO,CAAC,oBAAoB,CAAC,EAAE,SAAS,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;YACjE,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,YAAY;YACf,IAAI,OAAO,CAAC,CAAC,eAAe,CAAC,KAAK,QAAQ,IAAI,CAAC,CAAC,eAAe,CAAC,IAAI,GAAG,CAAC,WAAW,EAAE,CAAC;gBACpF,GAAG,CAAC,WAAW,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC;YACvD,CAAC;YACD,IAAI,CAAC,CAAC,SAAS,CAAC,KAAK,IAAI,EAAE,CAAC;gBAC1B,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,oEAAoE,EAAE,IAAI,CAAC,CAAC;YACjH,CAAC;YACD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,eAAe,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAE1J,KAAK,iBAAiB;YACpB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,cAAc,CAAC,CAAC,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEtI,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,0BAA0B,CAAC,CAAC,OAAO,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;QAE/F,KAAK,eAAe;YAClB,OAAO,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,WAAW,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAEvG,KAAK,eAAe,CAAC,CAAC,CAAC;YACrB,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC;YACvB,IAAI,IAAI,KAAK,UAAU,EAAE,CAAC;gBACxB,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,EAAE,QAAQ,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAChH,CAAC;YACD,IAAI,IAAI,KAAK,eAAe,IAAI,IAAI,KAAK,cAAc,EAAE,CAAC;gBACxD,MAAM,CAAC,GAAG,CAAC,CAAC,SAAS,CAA4B,CAAC;gBAClD,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC/D,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,KAAK,aAAa;YAChB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,mBAAmB,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,OAAO,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,CAAC;QAEzI,KAAK,gBAAgB;YACnB,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,sBAAsB,EAAE,IAAI,CAAC,CAAC;IAChF,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,GAAY;IACjC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC5C,OAAO,IAAI,CAAC;IACd,CAAC;IACD,OAAO,CAAC,CACN,KAAK,EACL,EAAE,KAAK,EAAE,YAAY,EAAE,EACvB,GAAG,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QAChB,MAAM,GAAG,GAAG,cAAc,kBAAkB,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;QAC3D,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,UAAU,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,gBAAgB,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC;IAC7H,CAAC,CAAC,CACH,CAAC;AACJ,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,IAAU,EAAE,MAA+B,EAAE,GAAwB;IACjG,IAAI,CAAC;QACH,MAAM,CAAC,GAAG,MAAM,GAAG,CAAC,8BAA8B,EAAE,EAAE,IAAI,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACnF,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,OAAO;QACT,CAAC;QACD,MAAM,GAAG,EAAE,CAAC;IACd,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAC;IACxB,CAAC;AACH,CAAC;AAED,SAAS,WAAW,CAAC,CAAW;IAC9B,MAAM,MAAM,GAAG,CAAC,CAAS,EAAE,IAAY,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC;IAChF,MAAM,WAAW,GAAG,CAAC,CAAC,WAAW,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,WAAW,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC;IAC9E,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,MAAM,CAAC,CAAC,CAAC,KAAK,EAAE,cAAc,CAAC,MAAM,CAAC,CAAC,UAAU,KAAK,CAAC,CAAC,SAAS,GAAG,WAAW,GAAG,CAAC;AAClI,CAAC;AAED,SAAS,SAAS,CAAC,KAAc,EAAE,IAAY;IAC7C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,CAAC,GAAG,KAAgC,CAAC;IAC3C,MAAM,KAAK,GAAG,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,aAAa,CAAC,IAAI,EAAE,CAAC;IACpH,MAAM,IAAI,GAAG,QAAQ,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,IAAI,CAAC,CAAC;IAC3C,OAAO,IAAI,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC;AAC7D,CAAC;AAED,SAAS,UAAU,CAAC,KAAc,EAAE,IAAY;IAC9C,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAChD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,IAAI,GAAI,KAAiC,CAAC,WAAW,CAAC,CAAC;IAC7D,OAAO,OAAO,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AAC9D,CAAC;AAED,SAAS,QAAQ,CAAC,IAAY,EAAE,IAAY;IAC1C,OAAO,IAAI,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;AAClF,CAAC;AAED,SAAS,UAAU,CAAC,OAAgB;IAClC,IAAI,OAAO,OAAO,KAAK,QAAQ,EAAE,CAAC;QAChC,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,IAAI,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;QAC3B,OAAO,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,QAAQ,IAAI,CAAC,KAAK,IAAI,IAAI,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAClI,CAAC;IACD,OAAO,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;AAC1C,CAAC"} \ No newline at end of file diff --git a/web/src/api.gen.ts b/web/src/api.gen.ts index 32e8f50..d2258d1 100644 --- a/web/src/api.gen.ts +++ b/web/src/api.gen.ts @@ -121,7 +121,7 @@ export interface paths { }; get?: never; put?: never; - /** @description Squashes the task's worktree, uncommitted changes included, into one commit on the project's default branch, fast-forwards the project's checkout to it, then removes the worktree and branch. Nothing is pushed. Refused while a turn is running or queued, and on merge conflicts. */ + /** @description Starts the same agent turn as merge-in. When that turn ends normally, byre squashes the task's worktree into one commit on the project's default branch, fast-forwards the project's checkout to it, then removes the worktree and branch and marks the task merged. Nothing is pushed. Refused while a turn is running or queued. */ post: operations["mergeTask"]; delete?: never; options?: never; @@ -129,6 +129,25 @@ export interface paths { patch?: never; trace?: never; }; + "/api/tasks/{taskId}/merge-in": { + parameters: { + query?: never; + header?: never; + path: { + taskId: string; + }; + cookie?: never; + }; + get?: never; + put?: never; + /** @description Asks the task's agent to merge the project's default branch into the task branch, resolving any conflicts and regenerating generated files. Sent to the task's idle session, or starts a session when it has none. Refused while a turn is running or queued. */ + post: operations["mergeIn"]; + delete?: never; + options?: never; + head?: never; + patch?: never; + trace?: never; + }; "/api/tasks/{taskId}/discard": { parameters: { query?: never; @@ -893,13 +912,38 @@ export interface operations { }; requestBody?: never; responses: { - /** @description The merged task. */ - 200: { + /** @description The merge turn was started or queued. */ + 202: { headers: { [name: string]: unknown; }; content: { - "application/json": components["schemas"]["Task"]; + "application/json": components["schemas"]["AgentSession"]; + }; + }; + 400: components["responses"]["Error"]; + 404: components["responses"]["Error"]; + 409: components["responses"]["Error"]; + }; + }; + mergeIn: { + parameters: { + query?: never; + header?: never; + path: { + taskId: string; + }; + cookie?: never; + }; + requestBody?: never; + responses: { + /** @description The merge turn was started or queued. */ + 202: { + headers: { + [name: string]: unknown; + }; + content: { + "application/json": components["schemas"]["AgentSession"]; }; }; 400: components["responses"]["Error"]; diff --git a/web/src/task.ts b/web/src/task.ts index 4970252..a411308 100644 --- a/web/src/task.ts +++ b/web/src/task.ts @@ -111,20 +111,45 @@ export function mountTranscript(root: HTMLElement): () => void { } const sess = currentSession(task.id); if (task.status !== "active") { - replace(head, h("div", { class: "meta" }, h("code", {}, task.branch)), h("div", { class: "head-actions" }, task.status)); + replace(head, h("div", { class: "head-actions" }, task.status)); return; } const target = state.projects.find((p) => p.id === task.project_id)?.default_branch ?? "the default branch"; - const merge = h("button", { title: `Squash into one commit on ${target}; nothing is pushed` }, "Merge"); + const busy = sess?.state === "running" || sess?.state === "queued"; + const merge = h( + "button", + { disabled: busy, title: `The agent merges ${target} in, then byre squashes into one commit on ${target}; nothing is pushed` }, + "Merge", + ); merge.onclick = () => - closeTask(task, (u) => `Merge "${task.title}" into ${target}? ${changesText(u)} become one commit on ${target}. Nothing is pushed.`, "/api/tasks/{taskId}/merge"); - const discard = h("button", { class: "danger", title: "Delete the worktree and branch without merging" }, "Discard"); + confirmChanges( + task, + (u) => + `Merge "${task.title}" into ${target}? The agent first merges ${target} in and resolves any conflicts; when that turn ends, ${changesText(u)} become one commit on ${target} and the task closes. Nothing is pushed.`, + async () => { + await post("/api/tasks/{taskId}/merge", { path: { taskId: task.id } }); + }, + ); + const mergeIn = h("button", { disabled: busy, title: `Ask the agent to merge ${target} into this branch and resolve any conflicts` }, `Merge ${target} in`); + mergeIn.onclick = async () => { + mergeIn.disabled = true; + try { + await post("/api/tasks/{taskId}/merge-in", { path: { taskId: task.id } }); + } catch (err) { + alert(errorText(err)); + mergeIn.disabled = false; + } + }; + const discard = h("button", { class: "danger", disabled: busy, title: "Delete the worktree and branch without merging" }, "Discard"); discard.onclick = () => - closeTask(task, (u) => `Discard "${task.title}"? ${changesText(u)} that aren't on ${target} will be deleted. This can't be undone.`, "/api/tasks/{taskId}/discard"); + confirmChanges(task, (u) => `Discard "${task.title}"? ${changesText(u)} that aren't on ${target} will be deleted. This can't be undone.`, async () => { + await post("/api/tasks/{taskId}/discard", { path: { taskId: task.id } }); + location.hash = "#/"; + }); replace( head, - h("div", { class: "meta" }, h("code", {}, task.branch)), - h("div", { class: "head-actions" }, sess && contextMeter(context.get(sess.id)), sess && compactButton(sess.id, sess.state), merge, discard), + h("div", { class: "head-actions session-actions" }, sess && contextMeter(context.get(sess.id)), sess && compactButton(sess.id, sess.state), mergeIn), + h("div", { class: "head-actions" }, merge, discard), ); }; @@ -706,14 +731,13 @@ function messageImages(ids: unknown): HTMLElement | null { ); } -async function closeTask(task: Task, prompt: (u: Unmerged) => string, path: "/api/tasks/{taskId}/merge" | "/api/tasks/{taskId}/discard") { +async function confirmChanges(task: Task, prompt: (u: Unmerged) => string, act: () => Promise) { try { const u = await get("/api/tasks/{taskId}/unmerged", { path: { taskId: task.id } }); if (!confirm(prompt(u))) { return; } - await post(path, { path: { taskId: task.id } }); - location.hash = "#/"; + await act(); } catch (err) { alert(errorText(err)); } diff --git a/web/style.css b/web/style.css index 618301d..9964caf 100644 --- a/web/style.css +++ b/web/style.css @@ -432,20 +432,6 @@ textarea { display: none; } -.meta { - display: flex; - flex-direction: column; - min-width: 0; - font-size: 11px; - color: var(--muted); -} - -.meta code { - overflow: hidden; - text-overflow: ellipsis; - white-space: nowrap; -} - .head-actions { display: flex; gap: 8px; @@ -453,6 +439,10 @@ textarea { flex-shrink: 0; } +.session-actions { + margin-right: auto; +} + .context-meter { font-size: 11px; }