The goal command now uses a session Stop hook as the durable completion mechanism and removes the separate evaluator path. Completion output is persisted as local command output so CLI streams, transcripts, and desktop history all see the same completed state.
Desktop keeps active goals in a compact header strip and lets completed goals render in the conversation flow, which avoids the old duplicate pinned card behavior while preserving visibility for running goals.
Constraint: /goal state has to survive transcript replay and desktop session restore.
Rejected: Keep the legacy evaluator alongside Stop hooks | duplicate completion paths made desktop state drift and hid the final card.
Confidence: high
Scope-risk: moderate
Directive: Keep goal completion events on the local_command transcript path unless desktop history restore is changed at the same time.
Tested: bun test src/goals/goalState.test.ts src/query/stopHooks.test.ts src/commands/goal/goal.test.tsx src/commands/headless.test.ts src/server/__tests__/ws-memory-events.test.ts src/server/__tests__/sessions.test.ts
Tested: bun run check:server
Tested: bun run check:desktop
Tested: real /tmp /goal CLI run 98fb4bb2-52da-4850-bc8e-e5e1cc0e4c51 with deepseek-v4-pro and WebUI screenshot verification
Not-tested: Remote release workflow
The e3b851a8 session showed the final assistant turn had completed all tracked tasks, but the transcript never received Goal marked complete. The remaining CLI process was consistent with the post-turn goal completion side query blocking, leaving desktop without any completion event to render.
This makes the goal evaluator complete locally when every tracked task is completed and the latest assistant message contains a clear completion summary. It also bounds the model-backed evaluator with a timeout so uncertain cases continue instead of hanging the session indefinitely.
Constraint: Desktop can only render a completed goal card after the CLI writes a completion event into the transcript.
Rejected: Broaden desktop history parsing only | the failing session had no completion event to parse, so UI parsing alone could not fix new sessions.
Confidence: high
Scope-risk: narrow
Directive: Keep goal completion checks bounded; never let an auxiliary evaluator block the main turn from finishing.
Tested: bun test src/goals/goalEvaluator.test.ts
Tested: bun run check:server
The goal evaluator now treats TaskCreate/TaskUpdate transcript state as a hard liveness gate, so a goal cannot complete while task entries remain pending or in_progress.
Background agent completion now notifies the parent before classifier or worktree cleanup, which keeps the main session from waiting forever when post-completion cleanup hangs. The desktop store also marks tabs idle on message_complete so completed transcripts do not leave stale running chrome.
Constraint: Desktop /goal relies on transcript task notifications to resume after background agents.
Rejected: Let optional cleanup run before notification | cleanup can hang and leaves the parent loop stuck.
Confidence: high
Scope-risk: moderate
Directive: Do not gate task-notification delivery on classifier or worktree cleanup without a timeout-backed liveness test.
Tested: bun test src/goals/goalEvaluator.test.ts src/tools/AgentTool/agentToolUtils.test.ts
Tested: bun run check:server
Tested: cd desktop && bun run test src/stores/chatStore.test.ts -t "marks the tab idle when a message completes"
The simplified /goal surface only supports setting a condition and clearing it. Removed subcommand names such as status were still valid free-form objectives, so a user trying the old query flow could overwrite the real goal with a goal named status and make the desktop state look stuck in progress.
Constraint: /goal should stay as /goal <condition> and /goal clear for the prelaunch simplified UX
Rejected: Reintroduce /goal status | it expands the command surface the product direction intentionally removed
Confidence: high
Scope-risk: narrow
Directive: Do not add pseudo subcommands back to the desktop picker unless the CLI command surface is deliberately expanded again
Tested: bun test src/commands/goal/goal.test.tsx src/goals/goalState.test.ts src/goals/goalEvaluator.test.ts src/server/__tests__/ws-memory-events.test.ts
Tested: cd desktop && bun run test -- --run src/components/chat/composerUtils.test.ts src/__tests__/pages.test.tsx src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx
The /goal feature has not shipped, so the desktop and CLI paths should only understand the current set/clear protocol instead of carrying transitional transcript formats. This removes Goal created/replaced and old status-block parsing from hydration, WebSocket forwarding, and desktop history mapping.
Constraint: Feature is still pre-release, so historical Goal created/replaced transcript compatibility is unnecessary.
Rejected: Keep old status-block hydration | it preserves a surface that users never received and makes the simplified /goal protocol harder to reason about.
Confidence: high
Scope-risk: narrow
Directive: Do not re-add legacy /goal status-block parsing unless a shipped transcript format requires it.
Tested: bun test src/commands/goal/goal.test.tsx src/goals/goalState.test.ts src/goals/goalEvaluator.test.ts src/server/__tests__/ws-memory-events.test.ts src/server/__tests__/sessions.test.ts src/server/__tests__/conversations.test.ts
Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx src/pages/ActiveSession.test.tsx src/components/chat/composerUtils.test.ts src/__tests__/pages.test.tsx
The previous /goal surface exposed management subcommands that made the CLI and desktop behavior hard to reason about. This keeps the user-facing command close to Claude Code's set/clear interaction while preserving historical transcript hydration and the existing evaluator loop.
Constraint: Desktop must see a live goal event before the model reaches the next tool call.\nRejected: Keep status/pause/resume/complete slash subcommands | requested UX is only set and clear.\nConfidence: high\nScope-risk: moderate\nDirective: Keep /goal user-facing syntax compact; extend internals without expanding the slash picker unless product explicitly asks.\nTested: bun test src/commands/goal/goal.test.tsx src/goals/goalState.test.ts src/goals/goalEvaluator.test.ts src/server/__tests__/ws-memory-events.test.ts src/server/__tests__/conversations.test.ts\nTested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx src/pages/ActiveSession.test.tsx src/components/chat/composerUtils.test.ts\nTested: bun run check:server\nTested: cd desktop && bun run lint\nTested: cd desktop && bun run build\nTested: ./bin/claude-haha -p '/goal smoke verify immediate goal output' --output-format stream-json --include-partial-messages --max-turns 1 --no-session-persistence --verbose emitted immediate system.local_command_output before model stream\nTested: ./bin/claude-haha -p '/goal clear' --output-format stream-json --include-partial-messages --max-turns 1 --no-session-persistence --verbose exited with duration_api_ms=0 and No active goal\nNot-tested: Browser click smoke was blocked by Chrome DevTools transport closing and Computer Use cgWindowNotFound on this machine.
Resumed desktop sessions keep the /goal lifecycle in transcript files, but the CLI status command only checked the in-memory goal map. The desktop history mapper also treated the local command breadcrumb as internal state, so the original /goal prompt disappeared when reopening a session.
This hydrates /goal command state from the current transcript before lifecycle operations and renders historical /goal command breadcrumbs as visible user messages. Query-only negative status output is kept informational so an old broken "No active goal." response cannot erase an earlier completed goal.
Constraint: Goal state is process memory at runtime, while session resume relies on persisted JSONL transcript records.
Rejected: Persist a second goal database | the transcript already contains the authoritative command lifecycle and avoids a new storage migration.
Confidence: high
Scope-risk: narrow
Directive: Treat /goal status output as a query result, not as lifecycle mutation; only explicit clear output should remove restored state.
Tested: bun test src/commands/goal/goal.test.tsx src/goals/goalState.test.ts src/goals/goalEvaluator.test.ts
Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx src/pages/ActiveSession.test.tsx
Tested: bun run check:desktop
Tested: real transcript hydrate for 3e9117d5-b792-43c9-bf57-7aec2b124f7e returned Goal: complete
Tested: bun test src/server/__tests__/h5-access-auth.test.ts -t 'blocks remote browser SDK requests even under explicit server auth'
Not-tested: Full check:server completed 726/727 tests; one unrelated H5 auth hook timed out in the full suite and passed on isolated rerun.
The goal flow needs to drive the agent loop and remain visible after desktop reconnects, so this change treats /goal output as a structured lifecycle signal across CLI, server, and desktop history restoration.
Constraint: The current TypeScript CLI does not share Codex's Rust app-server thread-goal database, so persistence is reconstructed from the existing session transcript.
Rejected: UI-only goal badges | would leave the CLI self-loop unable to recover active or completed goals after process restart.
Rejected: Add a new persisted store | larger migration surface than needed for the existing transcript-backed session model.
Confidence: high
Scope-risk: moderate
Directive: Keep future goal state changes mirrored in transcript-visible local command output or introduce a real migration-backed store.
Tested: bun test src/goals/goalEvaluator.test.ts src/goals/goalState.test.ts
Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/pages/ActiveSession.test.tsx src/components/chat/MessageList.test.tsx
Tested: bun run verify
Not-tested: Live provider baseline with a real model-driven goal loop.
Coding sessions need a native way to keep working until a stated completion condition is actually met. This adds a CLI /goal command, goal state and evaluator logic, and a headless-safe command filter so interactive and print-mode runs can both start a goal and continue when the evaluator says more work remains.
Constraint: The evaluator must work with saved third-party provider runtimes that may reject structured output schemas.
Constraint: Completion evidence must come from visible transcript text, not hidden goal prompts or assistant thinking blocks.
Rejected: Implement /goal as a bundled skill only | it would not own the query loop or support native continuation semantics.
Rejected: Expose all local-jsx commands to headless mode | interactive UI commands would become available in print mode.
Confidence: high
Scope-risk: moderate
Directive: Keep /goal evaluator evidence scoped to visible transcript text before adding richer completion signals.
Tested: bun test src/commands/headless.test.ts src/goals/goalState.test.ts src/goals/goalEvaluator.test.ts
Tested: bun run check:server
Tested: bun run verify
Tested: Real provider /goal smoke with MiniMax-M2.7-highspeed, including a two-turn continuation that logged Goal continuation #1 and completed with GOAL_SMOKE_LOOP_DONE.
Not-tested: Durable cross-process goal persistence for resumed sessions.
