Load the authenticated Codex model catalog with a bundled fallback and carry model-native reasoning effort through the OpenAI OAuth transport. Keep desktop effort choices aligned with each model's advertised capabilities.
Constraint: Ultra remains a composite Codex delegation mode and is not exposed as a wire-level effort.
Confidence: high
Scope-risk: moderate
Tested: bun run check:server; bun run check:desktop; bun run check:persistence-upgrade; focused OAuth, WebSocket, and browser smoke checks
Not-tested: bun run verify
Run required server and contract suites in credential-free sandboxes, fail closed on incomplete coverage or test output, and preserve the desktop active-turn permission guard across stale tab interactions.\n\nTested: bun run check:policy (115 pass); bun run check:server (1605 pass before final runner evidence check); bun run check:desktop; bun run check:provider-contract; bun run check:chat-contract\nConfidence: high\nScope-risk: broad
Retry idle provider streams only before tool side effects, and reconcile desktop turn state after WebSocket gaps so completed or still-running work cannot leave a stale spinner.
Tested: 108 runtime/server focused tests, 128 desktop focused tests
Tested: disconnected-turn WebSocket integration test
Tested: bun run check:server (1489 pass)
Tested: desktop typecheck and production build
Not-tested: full desktop gate has one unrelated TraceSession polling assertion failure
Scope-risk: broad
Fix cross-issue regressions found during post-0.4.4 merge review:\n\n- preserve permission mode across clear and empty-session replacement flows\n- keep provider effort passthrough and context-window estimates aligned with runtime metadata\n- invalidate recent project caches and trace message signatures when sessions change\n- recognize Windows ARM64 unpacked package-smoke output\n\nTested: bun test scripts/quality-gate/package-smoke/index.test.ts scripts/quality-gate/runner.test.ts\nTested: bun run check:desktop\nTested: bun run check:server\nConfidence: high\nScope-risk: moderate
Make bypassPermissions skip permission-approval ask decisions while preserving explicit denies and tools that require user interaction. Keep desktop permission mode state authoritative by waiting for server/CLI confirmation and persisting CLI-originated mode broadcasts.
Tested:
- bun test src/utils/permissions/permissions.test.ts
- bun test src/server/__tests__/conversations.test.ts -t "permission switch|permission restart|permission-mode broadcasts|permission changes made before|bypass permissions back to default|runtime-only model switch"
- bun test src/server/__tests__/ws-memory-events.test.ts
- cd desktop && bun run test -- src/stores/chatStore.test.ts --run
- bun run check:server
Scope-risk: moderate
Materialize the active provider runtime for empty-session first prompts before the WebSocket prewarm and user message are sent. This keeps a clean install that adds a MiniMax provider from starting the first turn without the selected provider runtime.
Tested: bun test src/server/__tests__/conversations.test.ts -t "MiniMax provider turn"
Tested: bun test src/server/__tests__/websocket-handler.test.ts src/server/__tests__/conversations.test.ts -t "prewarm|active provider id|MiniMax provider turn|first-turn runtime synchronization"
Tested: cd desktop && bun run test -- --run src/pages/EmptySession.test.tsx -t "draft runtime|active provider runtime|creates a new session"
Tested: cd desktop && bun run test -- --run src/components/controls/ModelSelector.test.tsx -t "defaults blank provider-scoped runtime selections|selects provider-scoped runtime models"
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Not-tested: bun run check:desktop, unrelated full-suite failures in MessageList timestamp formatting and TabBar AbortSignal cleanup blocked the gate.
Confidence: medium
Scope-risk: narrow
Stream inspection transcript aggregation and avoid trace/message polling paths that repeatedly hydrate large session files.
Tested: bun run check:server
Tested: bun run check:desktop
Confidence: high
Scope-risk: moderate
Persist runtime provider metadata for desktop sessions so context estimates stay tied to the provider that launched the session. Infer a unique saved provider window for older sessions without runtime metadata, and keep Xiaomi MiMo custom providers on thinking-only capability mapping instead of max-effort passthrough.
Tested: bun test src/server/__tests__/conversations.test.ts -t "unique saved provider context window|pass the active provider id|provider model context windows"
Tested: bun test src/server/__tests__/providers.test.ts -t "Xiaomi MiMo custom providers|custom providers declare|model context windows"
Tested: bun test src/server/__tests__/sessions.test.ts src/server/__tests__/searchService.sessions.test.ts src/server/__tests__/ws-memory-events.test.ts
Tested: cd desktop && bun run test -- src/stores/chatStore.test.ts src/stores/providerStore.test.ts src/components/controls/ModelSelector.test.tsx
Not-tested: full bun run verify was not run for this local issue handoff.
Confidence: high
Scope-risk: moderate
Show ExitPlanMode approvals as a rendered plan preview in desktop chat,
forward plan feedback and requested prompt permissions through the desktop
WebSocket permission response, and keep permission-mode restoration owned by
the CLI runtime.
Tested: bun run verify
Confidence: high
Scope-risk: moderate
Persist permission mode changes immediately, but defer restart-only permission transitions until the active desktop turn emits its terminal result.
Tested:
- bun test src/server/__tests__/conversations.test.ts -t "should defer bypass permission restarts until the active turn completes"
- bun test src/server/__tests__/conversations.test.ts -t "permission"
- bun run check:server
Scope-risk: narrow
Tested:
- cd desktop && bun run test -- --run src/pages/TraceList.test.tsx
- bun test src/server/__tests__/trace-capture.test.ts
- bun run check:desktop
- bun run check:server
Scope-risk: broad
Prevent desktop prewarm launches from inheriting interrupted-turn resume state, while leaving explicit user-message startup unchanged. Also stop server-side background schedulers during shutdown so app quit cannot leave scheduled task runners alive.
Tested:
- bun test src/server/__tests__/conversation-service.test.ts
- bun test src/server/__tests__/conversations.test.ts -t "prewarm"
- bun test src/server/__tests__/conversations.test.ts -t "permission"
- bun test src/server/__tests__/diagnostics-service.test.ts -t "keeps fatal startup errors visible on stderr while recording diagnostics"
- bun test desktop/electron/services/windows.test.ts desktop/electron/services/tray.test.ts desktop/electron/services/sidecarManager.test.ts src/server/__tests__/server-shutdown.test.ts
- bun run check:server
Avoid killing an in-flight desktop SDK turn when runtime config changes during tool execution. Persist the requested runtime immediately, then restart after the turn emits its terminal result.
Tested:
- bun run check:server
- real provider tool-turn model switch smoke
- bun run check:coverage (changed-line coverage passed; unrelated global lanes still fail)
Scope-risk: narrow
Use OS-assigned ports for server integration tests and publish the actual Bun server port after startup, preventing local port collisions from failing server checks.
Tested: bun test src/server/__tests__/e2e/business-flow.test.ts
Tested: bun test src/server/__tests__/e2e/full-flow.test.ts src/server/__tests__/conversations.test.ts src/server/__tests__/tasks.test.ts src/server/__tests__/haha-openai-oauth-api.test.ts
Tested: bun run check:server
Confidence: high
Scope-risk: narrow
Async title refresh runs after assistant output, so provider prompts can be biased by assistant language and English title examples. The title language now resolves from the first meaningful user message before consulting the response-language fallback, then retries once when a generated title violates that language.
Constraint: Desktop response-language settings still control assistant prose, not automatic title metadata when the first user message has a clear language
Rejected: Follow response-language setting for every generated title | Chinese sessions flip to English when replies are configured in English
Rejected: Persist mismatched generated titles after retry failure | preserves a bad UX over the safer first-message placeholder
Confidence: high
Scope-risk: moderate
Directive: Do not change automatic title language precedence without re-testing image/text first-turn sessions and English-response-language sessions
Tested: bun test src/server/__tests__/title-service.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts -t "refreshes the first-turn AI title"
Tested: git diff --check
Tested: real MiniMax-M3 /tmp session 58a47fcd-6f9d-4685-bc73-f9317e3f330e with temporary response language english; assistant replied English and final aiTitle was 标题语言验证
Not-tested: bun run check:server blocked before tests by expired quarantine entries server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
Desktop title generation previously upgraded the first sidebar title from the raw user prompt before assistant output existed. That made image-plus-text sessions vulnerable to keeping a title based only on the user's initial wording. This moves polished title generation to completed turns, reuses the CLI title prompt and transcript extractor, and routes title calls through the configured haiku model with a retry when disabled thinking is rejected.
Constraint: The first user message still needs an immediate placeholder title so the sidebar is responsive.
Rejected: Generate the AI title before assistant output | image-derived context is only available after the assistant turn completes.
Confidence: high
Scope-risk: moderate
Directive: Keep polished automatic titles tied to completed transcript turns, not pre-response user prompts.
Tested: bun test src/server/__tests__/title-service.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts -t "refreshes the first-turn AI title"
Tested: git diff --check
Tested: Real MiniMax-M3 /tmp session f89073ed-3467-492a-b63c-e1886c146a3a with image attachment wrote ai-title "Validate session title generation"
Not-tested: bun run check:server is blocked by existing expired quarantine manifest entries
Desktop chat can fall back to persisted transcript estimates when live inspection context is unavailable. That path previously only used built-in model windows, so custom provider settings such as MiniMax-M3 with a 1,000,000-token window still displayed the default 200,000-token estimate. Resolve transcript context windows from the session or active provider runtime env first, then fall back to built-ins.
Constraint: Provider model context windows are stored in provider runtime env, not always in the server process env.
Rejected: Change the built-in MiniMax-M3 window to 1,000,000 | upstream preset correctly keeps MiniMax-M3 at 204,800 by default, while user overrides must remain provider-specific.
Confidence: high
Scope-risk: moderate
Directive: Keep transcript estimates aligned with session/provider runtime env before consulting built-in model defaults.
Tested: git diff --check
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "active provider model context windows|Sonnet 4.6 transcript usage|low-trust media"
Tested: bun test src/server/__tests__/provider-presets.test.ts src/server/__tests__/provider-runtime-env.test.ts src/server/__tests__/providers.test.ts src/utils/__tests__/context.test.ts src/utils/__tests__/contextBudget.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts src/server/__tests__/conversation-service.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/provider-runtime-env.test.ts src/utils/__tests__/context.test.ts src/utils/__tests__/contextBudget.test.ts
Not-tested: bun run check:server blocked before execution by expired quarantine entries: server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
Unsupported image rejections from text-only compatible providers should not
poison the session, and low-trust multimodal usage spikes should not make
context indicators report a full window.
Constraint: Third-party Anthropic-compatible providers may report encoded media bytes as usage tokens.
Rejected: Trust all provider usage uniformly | third-party media responses can pin context to 100% incorrectly.
Confidence: high
Scope-risk: moderate
Directive: Do not remove the media-aware fallback without checking text-only provider recovery and desktop context indicators.
Tested: bun run check:server
Tested: focused media/context regression suite
Desktop reasoning effort now follows the selected session runtime instead of the General settings surface. Session metadata records provider, model, and effort so reconnects and prewarm restarts preserve the per-session runtime, while the default effort is max for new sessions.
Constraint: Existing transcript and localStorage runtime data must remain readable without a required migration.
Rejected: Keep effort as a General setting | it made one session change leak into every other session.
Confidence: high
Scope-risk: moderate
Directive: Do not reintroduce global desktop effort controls without proving multi-session isolation.
Tested: bun run check:server
Tested: bun run check:desktop
Tested: bun run check:native
Tested: bun run check:policy
Tested: bun run check:coverage
Tested: cd desktop && bun run test -- src/components/controls/ModelSelector.test.tsx src/stores/chatStore.test.ts
Tested: bun test src/server/__tests__/settings.test.ts --test-name-pattern "effort"
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "runtime"
Not-tested: Live provider smoke for domestic providers without local credentials.
Permission mode is a per-session runtime choice, while scheduled tasks cannot rely on a human approval loop. This removes the General settings permission surface, persists session permission metadata, and forces scheduled tasks to run with bypass permissions. Runtime permission changes now handle both directions across bypass boundaries, including startup/prewarm races, by persisting first and restarting only when the CLI launch mode must change.
Constraint: Scheduled tasks must be able to execute without a human standing by for authorization.
Constraint: The CLI only honors bypass permissions when launched with the skip-permissions flag, so switching to or from bypass requires a restart.
Rejected: Keep a global General permission default | it can leak across sessions and scheduled runs in ways the user cannot reason about.
Confidence: high
Scope-risk: broad
Directive: Do not reintroduce a global UI permission selector without proving it cannot affect unrelated sessions or automations.
Tested: bun test src/server/__tests__/conversations.test.ts -t "permission" --timeout 30000 (10 pass, 0 fail)
Tested: bun run check:server (858 pass, 0 fail)
Tested: cd desktop && bun run check:desktop (760 tests plus production build passed)
Tested: desktop/scripts/build-macos-arm64.sh and codesign verification passed
Tested: Real DeepSeek smoke validated plan, bypass, and scheduled task permission behavior
Not-tested: Did not repeat the full DeepSeek smoke after the final startup-race hardening; mock WebSocket permission regression and full server gate were rerun after that change.
Fixes#632
Desktop AskUserQuestion waits on the SDK permission bridge, and a transient renderer disconnect could previously let the short no-client cleanup kill the CLI. That turned a live user question into an AbortError and left history restore showing a stale interactive card.
Track live SDK permission requests, replay them to reconnecting clients, and give sessions waiting on user input a longer cleanup grace. Render aborted terminal results as completed history instead of an unanswered prompt.
Constraint: SDK permission requests are live in-memory control messages until answered or aborted.
Rejected: Only de-dupe history cards in MessageList | would not keep the CLI alive or restore the active permission request.
Rejected: Disable disconnect cleanup globally | would leak abandoned CLI processes for ordinary disconnected sessions.
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Do not shorten pending-permission cleanup without testing AskUserQuestion reconnect and abort paths.
Tested: bun run check:desktop
Tested: bun run check:server
Tested: git diff --check
Not-tested: Live Sub2API provider reconnect repro.
Telegram and desktop can attach to the same session while a turn is streaming. The WebSocket handler now tracks output callbacks per client and broadcasts session messages instead of replacing the previous subscriber. Telegram thinking deltas are accumulated before editing the placeholder so the preview does not collapse to the latest tiny chunk.
Constraint: Desktop and IM adapters may observe the same active session concurrently
Rejected: Keep a single session output callback | a later desktop view can steal Telegram's live content and completion events
Confidence: high
Scope-risk: moderate
Directive: Do not collapse session output callbacks back to one callback without a multi-client streaming regression
Tested: bun run check:server (828 pass); bun run check:adapters (358 pass); git diff --check
Not-tested: Live Telegram Bot API smoke against the packaged app
The WebSocket runtime treated every active provider id as stale unless it existed in the saved custom-provider list. ChatGPT Official is an in-memory built-in provider, so restarting the desktop could activate Claude Official and rewrite the provider index back to null before a new session launched. Keep built-in OpenAI provider ids valid in runtime validation, while preserving the stale custom-provider cleanup path.
This also keeps the General network timeout UI aligned with the authoritative timeout behavior by allowing precise typed values and updating the user-facing hint.
Constraint: ChatGPT Official is a built-in provider id and is not stored in the custom providers array.
Rejected: Persist ChatGPT Official as a synthetic saved provider | it would mix token-backed built-ins with user-managed providers and complicate secret persistence.
Confidence: high
Scope-risk: moderate
Directive: Runtime provider validation must include built-in provider ids as well as saved custom provider ids.
Tested: bun test src/server/__tests__/conversations.test.ts -t "preserve ChatGPT Official"
Tested: bun test src/server/__tests__/conversations.test.ts -t "stale persisted|preserve ChatGPT Official"
Tested: bun run check:server
Tested: bun run check:desktop
Not-tested: Full bun run verify after the final interruption; user explicitly asked to stop verification and commit directly.
Not-tested: Manual desktop restart with a real ChatGPT OAuth account in the packaged app.
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.
Desktop sessions must treat the global Thinking toggle as the source of truth across active CLI sessions, title generation, and provider-compatible request bodies. DeepSeek-style streams can start with reasoning blocks before text, so the WebSocket bridge now keeps the UI in thinking state until text content actually starts.
Constraint: DeepSeek and MiniMax use Anthropic-compatible surfaces but expose thinking behavior through provider-specific request and stream shapes
Rejected: Keep provider-specific disabled-thinking env defaults | stale defaults kept overriding the user's global Thinking setting
Rejected: Treat every non-tool stream block as text | reasoning-only startup blocks created a blank streaming gap before the visible thinking bubble
Confidence: high
Scope-risk: moderate
Directive: Do not change thinking stream state transitions without replaying reasoning-before-text provider events
Tested: bun test src/server/__tests__/ws-memory-events.test.ts
Tested: bun run check:server
Tested: bun run verify
Not-tested: Live DeepSeek provider smoke with real quota
Virtualized chat rendering keeps inactive long-running sessions cheap without disconnecting their CLI process, while DeepSeek now relies on the shared Thinking setting instead of a provider-specific disabled-thinking override. Existing legacy DeepSeek managed env is normalized so old local settings do not keep suppressing reasoning output after upgrade.
Constraint: Multiple desktop tabs must keep live sessions running and remain quick to switch without reconnecting.
Rejected: Pause or disconnect hidden sessions | would delay tab switching and interrupt streaming/tool state visibility.
Rejected: Keep DeepSeek disabled-thinking preset | conflicts with the General Settings Thinking control.
Confidence: high
Scope-risk: moderate
Directive: Do not reintroduce provider-specific disabled-thinking defaults for DeepSeek without testing both General Settings toggle states.
Tested: bun test src/server/__tests__/conversations.test.ts -t "global Thinking setting control DeepSeek"
Tested: bun test src/server/__tests__/persistence-upgrade.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/title-service.test.ts src/utils/__tests__/thinking.test.ts src/utils/__tests__/providerManagedEnvCompat.test.ts
Tested: cd desktop && bun run test -- MessageList.test.tsx ContextUsageIndicator.test.tsx
Tested: bun run check:server
Continuing an already materialized worktree session should behave like a normal existing session. The launch path now checks whether the session has already moved into its worktree before showing the startup bubble or passing worktree creation flags again.
Constraint: Existing session metadata can retain repository.worktree after the worktree transcript becomes the active session file
Rejected: Frontend-only suppression | the server could still launch the CLI with duplicate worktree creation flags
Confidence: high
Scope-risk: narrow
Tested: bun run check:server
Tested: bun test src/server/__tests__/conversations.test.ts -t worktree --timeout 30000
Tested: bun test src/server/__tests__/sessions.test.ts -t "newest duplicate session file" --timeout 30000
Not-tested: bun run verify still fails on unrelated desktop Settings.tsx and MessageList.tsx gates from the broader worktree
Desktop repository launches now defer isolated worktree creation until the
first user turn so the CLI owns worktree setup, cwd initialization, and
session metadata. The chat UI surfaces the pre-startup Git phase so users see
when a session is creating a worktree or switching a branch before model
output begins.
Constraint: Desktop must preserve the selected source checkout until a user actually sends a message
Constraint: CLI setup is the canonical owner for worktree creation and cwd initialization
Rejected: Create the worktree eagerly in the desktop session picker | it diverges from CLI session startup and creates worktrees before a conversation exists
Confidence: high
Scope-risk: moderate
Directive: Keep repository session startup routed through CLI worktree flags; do not reintroduce eager desktop worktree creation without testing transcript cwd and cleanup behavior
Tested: bun test src/server/__tests__/sessions.test.ts src/server/__tests__/conversation-service.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "worktree startup status"
Tested: cd desktop && bun run test -- src/pages/EmptySession.test.tsx
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Tested: git diff --check
Tested: CLI init-only native worktree smoke from feature/rail
Tested: agent-browser UI flow with MiniMax-M2.7-highspeed in a /tmp repository
Desktop sessions can prewarm before the user-selected runtime reaches the server, and an empty-session draft could previously persist an inferred default runtime as if the user had explicitly selected it. The fix keeps new-session defaults implicit while preserving explicit draft selections, and waits for queued runtime restarts before the first turn is delivered to the CLI process.
Constraint: Runtime selection is session-scoped and may arrive while prewarm or first-turn startup is already in flight
Rejected: Always persist the current default provider/model into new sessions | this masks whether the user actually selected a runtime and can launch stale providers
Confidence: high
Scope-risk: moderate
Directive: Do not send user turns across pending runtime restarts without re-checking the session runtime override
Tested: bun test src/server/__tests__/conversations.test.ts
Tested: cd desktop && bun run test -- src/pages/EmptySession.test.tsx
Tested: git diff --check
Desktop sessions can run against different saved providers at the same time, so the runtime selection must remain scoped to the session from WebSocket startup through the CLI request path. This adds parallel-session regression coverage, a browser-driven fake-provider E2E, and refreshes idle connected sessions after provider saves so stale provider edits are reapplied without disturbing active turns.
Constraint: Desktop provider credentials must stay session-scoped and must not leak across concurrent CLI child processes
Rejected: Rely on provider test connectivity alone | it does not exercise the desktop WebSocket, session runtime, or CLI request path
Confidence: high
Scope-risk: moderate
Directive: Do not change runtime selection persistence or provider env injection without rerunning the parallel provider browser E2E
Tested: cd desktop && bun run test src/stores/providerStore.test.ts src/stores/chatStore.test.ts
Tested: CLAUDE_CONFIG_DIR=/Users/nanmi/.claude bun test src/server/__tests__/conversations.test.ts --timeout 30000
Tested: desktop/scripts/e2e-parallel-providers-agent-browser.sh
Tested: bun run quality:smoke --provider-model custom:main:custom-main --provider-model minimax:main:minimax-main
Tested: cd desktop && bun run lint
Tested: git diff --check
Not-tested: bun run verify passes fully; coverage lane still fails on the existing agent-utils ratchet below baseline
Runtime and permission changes can require a CLI restart, but the desktop UI should not interpret that maintenance restart as an active assistant turn. The restart path now stays out of the running chat state while preserving the stop/start behavior that applies model and bypass-permission changes.
Constraint: bypassPermissions changes require a CLI restart so startup args are applied.
Rejected: Hide the stop button in the frontend | the backend would still conflate configuration restarts with agent turns and quick-send races would remain untested.
Confidence: high
Scope-risk: narrow
Directive: Keep runtime and permission restart transitions serialized before user_message handling.
Tested: bun test src/server/__tests__/conversations.test.ts -t "in-flight runtime restart|in-flight permission restart"
Tested: bun run check:server
Not-tested: Browser screenshot; this change is the WebSocket state contract, not layout rendering.
Session titles need to appear immediately, but the async AI title pass can return fenced or escaped JSON fragments. Keep the first-message title path fast, preserve optimistic client titles during background refresh, and only accept structured title responses that parse cleanly.
Constraint: Desktop sessions should stop showing Untitled/New Session after the first user turn.
Rejected: Accept short raw model output as a fallback | malformed JSON fragments are short enough to leak into the UI.
Confidence: high
Scope-risk: moderate
Directive: Do not loosen generated title parsing without regression coverage for fenced, escaped, and truncated JSON responses.
Tested: bun test src/server/__tests__/title-service.test.ts
Tested: bun run check:server
Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/stores/sessionStore.test.ts src/pages/EmptySession.test.tsx
Tested: agent-browser smoke on http://127.0.0.1:1420/ confirmed sidebar and tab titles update without JSON fragments.
Desktop context inspection could send get_context_usage while a prewarmed CLI process existed but before the SDK socket was connected. That first control request sat in the pending outbound queue and could time out, leaving the composer spinner or a misleading empty-state context display. The server now waits for the SDK socket before sending control requests, and the UI renders the actual initial context snapshot instead of masking empty active-session data.
Constraint: CLI /context and desktop get_context_usage must stay on the shared collectContextData/analyzeContextUsage path
Rejected: Hide zero-token active snapshots in the component | that masks backend timing bugs and prevents showing real initial system/tool context
Confidence: high
Scope-risk: narrow
Directive: Do not queue control requests before the SDK socket is connected; let user messages keep the pending outbound behavior
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "not queue control|context-only|prewarmed empty session|structured session inspection"
Tested: cd desktop && bun run test -- pages.test.tsx --test-name-pattern "EmptySession shows draft context|first-paint spinner|empty live session|live context usage|runtime model"
Tested: bun run check:server
Tested: cd desktop && bun run lint
Tested: real dev API prewarmed empty session returned 31,190 / 262,144 (12%) on first context-only inspection and 16ms on repeat
Tested: browser at http://127.0.0.1:5174/ showed 上下文用量 12% for an empty active session
The live desktop context path already routes through the CLI get_context_usage control request and the shared analyzeContextUsage implementation. The offline transcript fallback was still using its own prompt-token-only estimate, so disconnected sessions could report a lower context total than the live /context path. The fallback now reuses the same current-context total helper and includes output tokens as next-turn context.
Constraint: Desktop must still show context estimates when the CLI process is not running
Rejected: Keep transcript fallback prompt-only | it diverges from the live CLI /context total and can drop after responses
Confidence: high
Scope-risk: narrow
Directive: Transcript context fallback must stay aligned with calculateCurrentContextTokenTotal
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "context-only|structured session inspection|reconstruct Sonnet 4.6 transcript usage"
Tested: bun test src/utils/__tests__/context.test.ts
Tested: bun run check:server
The desktop composer now treats draft and not-yet-running sessions as pending
until a real CLI context snapshot exists. Context inspection has a lightweight
context-only path so the composer and /context panel do not wait on unrelated
usage or MCP status work, and desktop boot no longer blocks the first shell
render on tab restoration.
Constraint: Empty composer state has no live CLI context to inspect until a session starts
Rejected: Display 0% before live context exists | it implied one user message consumed the fixed prompt/tool baseline
Confidence: high
Scope-risk: moderate
Directive: Do not show numeric context usage without a real context snapshot
Tested: cd desktop && bun run test -- pages.test.tsx
Tested: cd desktop && bun run lint
Tested: bun run check:desktop
Tested: bun run check:server
Tested: Browser reload at http://127.0.0.1:5174 with cleared open-tabs showed pending context and no /inspection request
Bring the provider context-window, auth-secret masking, and explicit auth-strategy worktree commits onto main after local verification. The merge keeps main's notification and docs history intact while preserving the provider fixes as separate commits.
Constraint: main has diverged with local desktop notification and docs commits, so this cannot be fast-forwarded safely.
Confidence: high
Scope-risk: moderate
Directive: Keep provider auth behavior configured through preset authStrategy rather than implicit env-name guesses.
Tested: ALLOW_CLI_CORE_CHANGE=1 bun run quality:pr
Tested: bun run quality:gate --mode baseline --allow-live --provider-model minimax:main:minimax-main
# Conflicts:
# desktop/src/pages/Settings.tsx
Teach provider presets and saved providers to carry per-model context windows so auto-compact uses provider-specific limits instead of a blanket fallback. The desktop provider form now keeps these limits in an advanced context section and syncs the generated settings preview with model changes.
Constraint: Third-party provider APIs do not consistently expose machine-readable model context windows.
Rejected: Keep a single 100K/200K fallback | modern provider windows vary from 128K to 1M+ and the fallback caused late or early compaction.
Confidence: high
Scope-risk: moderate
Directive: Do not change provider compact thresholds without re-running real provider long-context checks.
Tested: bun test src/services/compact/autoCompact.test.ts; bun test src/server/__tests__/provider-presets.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/providers-real.test.ts; bun run check:server; bun run check:desktop; bun run check:policy; bun run check:native; MiniMax/Kimi/DeepSeek live long-context probes; agent-browser provider form flow.
Not-tested: quality:pr policy gate still requires explicit allow-cli-core-change for CLI core edits.
Rewinding a desktop session can race with a still-exiting CLI process,
leaving late transcript entries after the trim point. Desktop placeholder
sessions also need to preserve canonical launch metadata so a zero-message
rewind can restart from the real workspace instead of reconstructing it from
a lossy sanitized project directory name.
Constraint: Rewind must work after trimming back to an empty transcript.
Constraint: Session project directory names are sanitized and not reversible.
Rejected: Add retries around CLI startup | would leave corrupted transcript state in place.
Rejected: Delete desktop placeholder files before first CLI launch | drops the only reliable workDir metadata.
Confidence: high
Scope-risk: moderate
Directive: Do not change rewind process stopping without rechecking late CLI output and transcript metadata preservation.
Tested: Real DeepSeek deepseek-v4-pro rewind smoke, bun test src/server/__tests__/sessions.test.ts --timeout 30000, bun test src/server/__tests__/conversations.test.ts --timeout 30000, bun run check:server, bun run check:native, bun run quality:pr, git diff --check
Not-tested: Native Windows desktop binary smoke for the original reporter environment.
Bring the detached quality-gate worktree into local main while preserving the existing main-only desktop diagnostics commits. This merge lands the PR/release quality gate, live model baselines, provider selector docs, AGENTS automation rules, and repository hygiene for generated artifacts.
Constraint: Local main had commits not present in the detached worktree, so fast-forward merge was not possible.
Rejected: Rebase the detached worktree | rewriting the already-verified local commits would discard the exact release-gate evidence SHA chain.
Confidence: high
Scope-risk: broad
Directive: Keep quality reports and local Superpowers plans out of future commits; use report summaries as evidence, not tracked artifacts.
Tested: bun run quality:gate --mode release --allow-live --provider-model codingplan:main:codingplan-main --provider-model minimax:main:minimax-main
Not-tested: post-merge full rerun on main; merge had no content conflicts.
The desktop product needs a repeatable local gate that can prove the core Coding Agent loop still works after changes, not only that unit tests pass. This adds a quality-gate runner with PR, baseline, and release modes, structured reports, explicit quarantine metadata, and fixture-based live baseline cases that can run across provider/model targets.
Constraint: Existing check:pr and CI policy behavior must remain usable while the stronger baseline grows around it
Constraint: Default PR gates must not require real model credentials or provider quota
Rejected: Build a standalone QA platform first | too heavy before the baseline task shape is proven
Rejected: Keep unstable server exclusions hardcoded in run-server-tests | hides quarantine policy from reports and future review
Confidence: medium
Scope-risk: moderate
Directive: Expand baseline cases by adding focused fixtures and verifiers; do not make normal PR checks depend on live providers
Tested: bun test scripts/quality-gate/*.test.ts scripts/quality-gate/baseline/*.test.ts
Tested: bun run check:server
Tested: bun run quality:gate --mode baseline --allow-live --provider-model 2944f963-ce75-45b7-bac1-6e4f57df0970:kimi-k2.6:volc-kimi-k2.6 --provider-model 9c78d3df-7fb5-44c7-8436-3a41c3a59231:MiniMax-M2.7-highspeed:minimax-m2.7
Not-tested: desktop UI browser smoke and native release mode in this commit
Desktop failures were previously hard to debug from issue reports because server-side and CLI startup details were only partially visible in the UI. This adds a dedicated cc-haha diagnostics store with sanitized structured events, runtime error summaries, a Settings diagnostics view, and an exportable bundle that users can attach to reports.
Constraint: Diagnostic exports must not include chat content, file contents, full environment variables, API keys, bearer tokens, cookies, or OAuth tokens.
Rejected: Export raw server logs | easier to debug but too likely to leak secrets and private workspace data.
Rejected: Keep diagnostics only in transient UI errors | still leaves maintainers unable to diagnose later GitHub issues.
Confidence: high
Scope-risk: moderate
Directive: Do not add raw transcript, prompt, attachment, or environment dumps to diagnostics without a separate privacy review.
Tested: ANTHROPIC_API_KEY=test-key bun test src/server/__tests__/diagnostics-service.test.ts
Tested: ANTHROPIC_API_KEY=test-key bun test src/server/__tests__/conversation-service.test.ts
Tested: ANTHROPIC_API_KEY=test-key bun test src/server/__tests__/conversations.test.ts
Tested: cd desktop && bun run test src/__tests__/diagnosticsSettings.test.tsx --run
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Tested: agent-browser E2E on local server/dev UI for CLI startup failure, provider test failure, diagnostics tab, copy summary, export bundle, and tar/secret scan
Not-tested: Destructive clear-logs button in browser E2E; local deletion was intentionally not clicked.
Large desktop histories were making session discovery parse every JSONL
before pagination, while automatic title updates could still overwrite
manual names during resumed sessions. This keeps listing bounded to the
requested page, preserves custom titles, and blocks deleted placeholder
sessions from being recreated by prewarm startup.
Constraint: Desktop session storage remains JSONL-compatible with the CLI
Rejected: Virtualize the sidebar in this patch | does not fix backend JSONL parsing cost
Rejected: Disable title generation globally | would regress useful titles for unnamed sessions
Confidence: high
Scope-risk: moderate
Directive: Do not reintroduce all-file JSONL parsing on /api/sessions list paths without a heavy-session benchmark
Tested: ANTHROPIC_API_KEY=test-key bun test src/server/__tests__/title-service.test.ts src/server/__tests__/sessions.test.ts
Tested: ANTHROPIC_API_KEY=test-key bun test src/server/__tests__/conversations.test.ts
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Tested: heavy local preview with 240 sessions, 320 messages each, and 40 restored tabs
Not-tested: native packaged desktop runtime under Windows with the same heavy fixture
Related: https://github.com/NanmiCoder/cc-haha/issues/237
Related: https://github.com/NanmiCoder/cc-haha/issues/248
Desktop users can now disable thinking for new sessions, and Anthropic-compatible providers that opt in receive explicit disabled-thinking requests across main turns, side queries, and AI title generation.
Constraint: DeepSeek/Kimi/GLM Anthropic-compatible endpoints need a non-thinking path without scattering provider-specific logic through the CLI.
Rejected: Per-model if/else branches | centralized provider preset env keeps the native CLI surface smaller and easier to audit.
Confidence: high
Scope-risk: moderate
Tested: bun test src/utils/__tests__/thinking.test.ts src/server/__tests__/title-service.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/conversations.test.ts
Tested: cd desktop && bun run test -- generalSettings.test.tsx
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Tested: agent-browser DeepSeek desktop E2E with transparent proxy captured main and title requests with thinking.type=disabled
Desktop sessions can carry persisted runtime provider selections long after the provider index changes. The server now validates those session-level and active provider ids before launching the CLI, falls back to a valid default path, and includes non-secret launch diagnostics in startup failure messages so future issue reports expose the server-side context.
Constraint: Desktop users often report only the visible chat error, not sidecar console logs
Rejected: Frontend-only cleanup of stale localStorage selections | does not protect API or reconnect paths and loses server-side evidence
Confidence: high
Scope-risk: narrow
Directive: Do not pass session-scoped provider ids into CLI startup without validating they still exist in providers.json
Tested: bun test src/server/__tests__/conversations.test.ts
Tested: bun test src/server/__tests__/providers.test.ts
Tested: bun test src/server/__tests__/conversation-service.test.ts
The session inspector now asks the resumed CLI for a fast structural context estimate instead of forcing the full token-counting API path. This preserves live CLI state for system prompt, tools, MCP tools, skills, and messages while avoiding the 20s timeout that made historical sessions appear stuck or fall back to transcript-only estimates.
Constraint: Inspector requests must return quickly for third-party providers and historical resumed sessions.
Rejected: Increase the server timeout | the slow path can still block on provider token counting and keeps the UI feeling broken.
Confidence: high
Scope-risk: narrow
Directive: Keep interactive inspector context on the estimateOnly control path unless the UI explicitly supports a slow precise refresh.
Tested: bun test src/server/__tests__/conversations.test.ts -t 'structured session inspection|Sonnet 4.6 transcript usage'
Tested: cd desktop && bun run test -- --run src/i18n/index.test.tsx
Tested: cd desktop && bun run build
Tested: direct /api/sessions/:id/inspection?includeContext=1 returned live context in 0.046867s with System prompt, System tools, MCP tools, Messages
Tested: agent-browser automation verified no loading/error and visible System prompt/System tools/MCP tools/Messages
Not-tested: bare root tsc --noEmit, because current tsconfig scans existing desktop/src-tauri/target generated binary assets unrelated to this change
Session inspection was coupling quick status and usage rendering to live context control requests, so a slow get_context_usage path could leave the desktop inspector stuck on a loading state. The desktop panel now loads basic inspection data first, renders a transcript-based context estimate immediately, and only asks for live context details as a background refinement.
The translation hook now returns a stable function per locale so effects that depend on translation do not reset and re-fetch after every render.
Constraint: Third-party provider sessions may not expose reliable live context capabilities through the control request path.
Rejected: Keep waiting on live get_context_usage for the context tab | it recreates the user-visible loading stall.
Rejected: Hardcode provider-specific context windows | provider capabilities are not always known from the desktop session record.
Confidence: high
Scope-risk: moderate
Directive: Do not make the inspector first render depend on live CLI control requests without a transcript or cached fallback.
Tested: bun test src/server/__tests__/conversations.test.ts -t "structured session inspection|Sonnet 4.6 transcript usage"
Tested: cd desktop && bun run test -- --run src/i18n/index.test.tsx
Tested: cd desktop && bun run build
Tested: git diff --check
Tested: agent-browser verified /context renders transcript estimate without Loading context data
Not-tested: Provider-specific true context-window discovery for every third-party vendor
