Tested:
- bun test src/services/api/claudeEffort.test.ts src/server/__tests__/proxy-transform.test.ts src/utils/__tests__/thinking.test.ts
- bun run check:server
- git diff --check
Not-tested:
- bun run verify / coverage
Confidence: high
Scope-risk: narrow
Forbid style tags and inline style attributes in rendered assistant markdown so model text blocks cannot inject global CSS into the desktop UI.
Tested: cd desktop && bun run test -- src/components/markdown/MarkdownRenderer.test.tsx --run
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Not-tested: bun run check:desktop still fails on unrelated existing MessageList timestamp and TabBar deleteSession test issues.
Confidence: high
Scope-risk: narrow
Fixes#909.
Tested:
- cd desktop && bun run test -- src/components/chat/ChatInput.test.tsx src/pages/EmptySession.test.tsx -t "/model"
- cd desktop && bun run test -- src/components/chat/composerUtils.test.ts src/components/controls/ModelSelector.test.tsx src/components/chat/ChatInput.test.tsx src/pages/EmptySession.test.tsx
- cd desktop && bun run build
- git diff --check
Not-tested:
- Full bun run check:desktop remains blocked by an unrelated MessageList timestamp assertion and existing TabBar AbortSignal rejections.
Confidence: high
Scope-risk: narrow
Use transcript activity timestamps for session list ordering instead of JSONL mtime, and skip duplicate runtime metadata appends.
Tested: bun test src/server/__tests__/sessions.test.ts --test-name-pattern "metadata-only writes|duplicate runtime metadata"
Tested: bun test src/server/__tests__/sessions.test.ts
Tested: bun run check:server
Confidence: high
Scope-risk: moderate
Tested: cd desktop && bun run test -- src/pages/ActiveSession.test.tsx --run
Tested: cd desktop && bun run test -- src/stores/workspacePanelStore.test.ts --run
Tested: git diff --check
Not-tested: bun run check:desktop remains blocked by an unrelated MessageList timestamp assertion and existing TabBar unhandled rejections.
Confidence: high
Scope-risk: narrow
Add a provider-level disableExperimentalBetas setting that writes CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 into managed provider runtime env, keeps stale parent env isolated, and exposes the toggle in desktop provider settings.
Tested: bun test src/server/__tests__/provider-runtime-env.test.ts --test-name-pattern "experimental betas|stale proxy"
Tested: bun test src/server/__tests__/providers.test.ts --test-name-pattern "experimental betas|POST /api/providers should create a provider|PUT /api/providers/:id should update a provider"
Tested: bun test src/server/__tests__/conversation-service.test.ts --test-name-pattern "experimental beta kill switch"
Tested: cd desktop && bun run test -- --run src/__tests__/generalSettings.test.tsx -t "experimental beta headers|Tool Search"
Tested: cd desktop && bun run test -- --run src/lib/__tests__/providerSettingsJson.test.ts
Tested: bun run check:server
Tested: cd desktop && bun run build
Not-tested: bun run verify
Confidence: high
Scope-risk: moderate
Preserve user-invoked skill command metadata during session restore,
WebSocket replay, and session search while continuing to hide malformed
command breadcrumbs.
Tested:
- bun test src/server/__tests__/sessions.test.ts
- bun test src/server/__tests__/ws-memory-events.test.ts
- bun test src/server/__tests__/searchService.sessions.test.ts
- cd desktop && bun run test -- --run src/stores/chatStore.test.ts
- bun run check:server
- cd desktop && bun run build
- git diff --check
Not-tested:
- bun run check:desktop did not complete because an existing MessageList timestamp assertion fails independently of this change.
Confidence: high
Scope-risk: narrow
Fixes#887.
Emit terminal SDK bookends for auto-dream completion, failure, and stop paths so the desktop task state can close instead of remaining running.
Keep dream background task events out of the transcript while preserving lifecycle tracking in the background task drawer.
Tested: bun test src/tasks/DreamTask/DreamTask.test.ts
Tested: cd desktop && bun run test src/stores/chatStore.test.ts --run
Tested: cd desktop && bun run test src/components/chat/MessageList.test.tsx --run -t auto-dream
Tested: bun run check:server
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Not-tested: full bun run verify / coverage gates; this is a scoped local issue fix.
Confidence: high
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
Treat pages as PDF-only during validation and execution so model-supplied pages on images or text files do not loop on invalid parameter errors.
Tested:
- bun test src/tools/FileReadTool/FileReadTool.test.ts
- bun run check:server
Confidence: high
Scope-risk: narrow
Add per-session zoom state, route the zoom factor through the desktop preview bridge, and apply it to the Electron WebContentsView before preview capture so screenshot and annotation coordinates stay on the native preview surface.
Tested:
- cd desktop && bun run test -- src/components/browser/BrowserSurface.test.tsx src/stores/browserPanelStore.test.ts src/components/workbench/WorkbenchPanel.webview.test.tsx src/lib/previewBridge.test.ts src/lib/desktopHost/electronHost.test.ts
- cd desktop && bun test electron/services/preview.test.ts
- cd desktop && bun run lint
- cd desktop && bun run build
- cd desktop && bun run check:electron
Not-tested:
- cd desktop && bun run check:desktop (blocked by existing MessageList relative-time assertion and TabBar AbortSignal errors)
Confidence: medium
Scope-risk: moderate
Add a General settings control for the default permission mode used by newly created desktop chat sessions, while preserving per-session overrides.
Tested: cd desktop && bun run check:desktop
Not-tested: bun run verify and coverage gates were not run for this local desktop-scoped handoff.
Confidence: high
Scope-risk: narrow
Add Windows ARM64 desktop release packaging, verify architecture-specific sidecar/native files in package smoke, and give the Electron sidecar more startup time plus early diagnostics for slow Windows ARM launches.
Tested: bun test electron/services/sidecarManager.test.ts
Tested: bun test scripts/quality-gate/package-smoke/index.test.ts scripts/release-update-metadata.test.ts scripts/pr/release-workflow.test.ts
Tested: bun run check:native
Tested: bun run check:policy
Not-tested: full bun run verify / coverage; this was a local issue-fix handoff, not PR-ready validation.
Confidence: high
Scope-risk: moderate
Tested: bun run scripts/release.ts 0.4.4 --dry
Tested: bun run verify (artifacts/quality-runs/2026-07-01T12-34-24-275Z/report.md)
Confidence: high
Scope-risk: broad
Constraint: providers-real remains a live MiniMax connectivity check, so it stays quarantined from non-live gates.
Tested: bun run check:quarantine
Tested: bun run check:policy
Confidence: high
Scope-risk: narrow
Keep task-notification-only follow-up turns out of the live desktop transcript so background command completion notices do not render as repeated thinking, assistant text, or completed-duration rows.
Refs: #886
Tested: cd desktop && bun run test -- src/stores/chatStore.test.ts && bun run lint
Confidence: high
Scope-risk: narrow
Preserve background task visibility after the foreground turn completes and move task progress into an official-style background task drawer.
Keep tabs/sidebar active while background tasks run, delay foreground completion rows until background work is settled, and avoid hiding resumed agents after clearing prior finished entries.
Tested: bun run check:desktop
Confidence: high
Scope-risk: moderate
Tested:
- bun test src/server/__tests__/provider-presets.test.ts src/server/__tests__/provider-runtime-env.test.ts src/utils/model/modelContextWindows.test.ts src/utils/__tests__/thinking.test.ts src/server/__tests__/conversation-service.test.ts src/server/__tests__/settings.test.ts
- bun run check:server
- git diff --check
Not-tested:
- bun run verify
- coverage gates
Confidence: high
Scope-risk: moderate
Emit a visible Goal continuing local-command marker before managed /goal continuations, then preserve it through server events, session history, and desktop history restore.
Render the marker as a compact divider so a new assistant continuation after end_turn is visually separated from the previous assistant output.
Related: #901
Tested: bun test src/query/stopHooks.test.ts src/server/__tests__/ws-memory-events.test.ts src/server/__tests__/sessions.test.ts && cd desktop && bun run test MessageList.test.tsx chatStore.test.ts
Tested: bun run check:server
Tested: bun run check:desktop
Not-tested: live release build and Windows v0.4.3 repro path; keep issue open until release validation.
Scope-risk: moderate
Confidence: high
Goal prompt-hook evaluator failures now become blocking continuation feedback instead of non-blocking hook errors, so an active goal is treated as incomplete and the loop keeps working.
Tested: bun test src/utils/hooks/execPromptHook.test.ts src/query/stopHooks.test.ts src/goals/goalState.test.ts
Tested: bun run check:server
Scope-risk: moderate
Confidence: high
Reproduce: pasted a cc-switch-style settings JSON with PROXY_MANAGED auth, claude-* request model env vars, and Qwen3Coder *_MODEL_NAME display labels into the Provider form test path.
Fix: derive the Provider main model from ANTHROPIC_MODEL or the Sonnet model env fallback, and keep *_MODEL_NAME values as display labels only. Treat both proxy-managed and PROXY_MANAGED placeholders as non-secret display placeholders.
Tested: bun test desktop/src/lib/__tests__/providerSettingsJson.test.ts
Tested: cd desktop && bun run test generalSettings.test.tsx
Tested: bun run check:desktop
Confidence: high
Scope-risk: narrow
Reduce repeated /api/sessions?limit=400 scans by caching per-file JSONL list summaries keyed by mtime and size. This targets #894 diagnostics where sidebar refreshes reported client_api_request_failed timeouts on session list and inspection paths.
Tested: bun test src/server/__tests__/sessions.test.ts
Tested: bun run check:server
Tested: temporary source server /api/sessions?limit=400 first call 0.80s; after waiting past the 5s list cache TTL, second call 0.03s with identical 399 session IDs.
Not-tested: Windows release build retest for #894 diagnostics timeout.
Confidence: high
Scope-risk: narrow
ExitPlanMode can be interrupted while a real plan approval preview is still rendered elsewhere. In that path the tool result had no plan input and displayed an extra empty plan card, which made plan mode look duplicated. Render the plan preview in rejected tool cards only when real plan, file path, or permission data exists.
Tested: cd desktop && bun run test PlanModePermissionDialog.test.tsx
Tested: bun run check:desktop
Tested: Computer Use dev Electron smoke via desktop/scripts/electron-dev.ts; original #869 repro no longer showed the empty '暂无计划内容' card after HMR.
Not-tested: release build post-install retest; GitHub issue remains open until release.
Confidence: high
Scope-risk: narrow
Map CLI result cache_read_input_tokens/cache_creation_input_tokens into the desktop websocket usage payload, and count cache read/write tokens in the active session header token badge.
Fixes locally: #842
Tested: bun test src/server/__tests__/websocket-handler.test.ts
Tested: cd desktop && bun run test -- src/pages/ActiveSession.test.tsx --run
Tested: bun run check:server
Tested: bun run check:desktop
Not-tested: live Windows v0.4.3 reproduction; GitHub issues remain open until release and retest.
Confidence: high
Scope-risk: narrow
Adds an idempotent DELETE /api/traces/:sessionId path that removes only the local trace JSONL file and invalidates trace read cache. The Trace list now exposes a trash action behind a confirmation dialog that states chat history is not deleted.
Tested: bun test src/server/__tests__/trace-capture.test.ts
Tested: cd desktop && bun run test -- src/pages/TraceList.test.tsx --run
Tested: bun run check:server
Tested: bun run check:desktop
Tested: Browser smoke with temporary CLAUDE_CONFIG_DIR verified the Trace list delete button and confirmation dialog on ?traceWindow=1.
Constraint: GitHub issue #868 remains open until a release ships and post-release retest passes.
Confidence: high
Scope-risk: moderate
Provider connectivity tests now pass the actual upstream URL and loopback no-proxy rules into proxy fetch option resolution, including IPv6 loopback. This closes the local test/connectivity gap in the #896 proxy compatibility work without closing GitHub issues before release.
Tested: bun test src/utils/proxy.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/network-settings.test.ts src/services/api/client.test.ts
Tested: bun run check:server
Not-tested: Windows dev-sidecar real-machine retest and release build confirmation for #896.
Confidence: medium
Scope-risk: narrow
Preserve loopback NO_PROXY entries when Electron or manual network settings inject proxy environment variables, and make the Anthropic client skip Bun proxy fetch options for local desktop provider proxy base URLs.
Tested: bun test src/utils/proxy.test.ts src/services/api/client.test.ts src/server/__tests__/network-settings.test.ts src/server/__tests__/conversation-service.test.ts
Tested: cd desktop && bun run test -- electron/services/sidecarManager.test.ts --run
Tested: bun run check:server
Tested: bun run check:native
Not-tested: Windows dev-sidecar real-machine retest for #896; current Mac can only prove loopback proxy bypass behavior and native packaging.
Confidence: medium
Scope-risk: moderate
Trace direct provider calls from the effective Request metadata so headers carried by Request input are sanitized and persisted instead of being dropped when init.headers is empty.
Tested: bun test src/server/__tests__/trace-capture.test.ts src/server/__tests__/proxy-network-settings.test.ts
Tested: bun run check:server
Confidence: high
Scope-risk: narrow
Batch J follows the v0.4.3 validation pass. It closes the remaining Settings tab persistence gap after renderer recreation and prevents MCP settings from exposing sensitive command args/env/header values in visible UI or input values while preserving unchanged raw values on save.
Tested: cd desktop && bun run test -- --run src/stores/uiStore.test.ts src/__tests__/mcpSettings.test.tsx
Tested: cd desktop && bun run lint
Tested: bun run check:desktop
Not-tested: live Electron MCP settings smoke after restart; trace header revalidation is deferred because inspected trace files predate the header fix.
Confidence: high
Scope-risk: narrow
Allow MCP server names to use Unicode letters and numbers while continuing to reject spaces and separators.
Tested: bun test src/server/__tests__/mcp.test.ts
Tested: bun run check:server
Confidence: high
Scope-risk: narrow
Fixes#827, #857, #860, #885.
Reproduced #827 with a delayed pasted-image FileReader result that reappeared after send; fixed by invalidating stale paste callbacks after submit or session switch.
Reproduced #857 with TCP accepting while /health stayed unhealthy; fixed Electron sidecar readiness to require HTTP /health status ok before continuing.
Reproduced #860 through OpenAI-compatible sampling param pass-through and missing GLM-5.2 context metadata; fixed sampling params to be opt-in and added GLM-5.2 context windows for preset and core resolution.
Reproduced #885 with a truncated long sidebar title lacking a row tooltip; fixed by exposing the full title on the session row.
Tested: cd desktop && bun run test -- src/components/chat/ChatInput.test.tsx src/components/layout/Sidebar.test.tsx --run
Tested: cd desktop && bun test electron/services/sidecarManager.test.ts
Tested: bun test src/server/__tests__/proxy-transform.test.ts src/server/__tests__/provider-presets.test.ts src/services/compact/autoCompact.test.ts
Tested: bun run check:server
Tested: bun run check:desktop
Tested: bun run check:native
Confidence: high
Scope-risk: moderate
Fixes#893.
Reproduced the stuck session-list refresh by keeping the automatic fetch promise pending, then clicking the manual refresh button. Also covered the existing-sessions loading state so a background refresh does not leave the control disabled or spinning forever.
Tested: cd desktop && bun run test -- src/components/layout/Sidebar.test.tsx --run
Tested: bun run check:desktop
Confidence: high
Scope-risk: narrow
