Desktop sessions were missing a visible request_access approval path and could
mis-detect their own app window as an unapproved frontmost target, which caused
Computer Use clicks to fail even after opening the intended app. On macOS, text
entry was also split across inconsistent clipboard and keystroke paths, making
Electron inputs unreliable for Chinese and short strings.
This change adds a desktop approval bridge over the existing session websocket,
renders a dedicated desktop approval modal, threads the real desktop bundle id
into the Computer Use executor, and switches macOS clipboard typing onto the
native pasteboard plus system paste shortcut path. It also makes tool error
results expandable in the desktop chat UI so frontmost-gate failures are fully
visible during debugging.
Constraint: Desktop sessions run the CLI over the SDK websocket path, so Ink tool JSX dialogs are not visible there
Constraint: macOS IME and Electron text inputs are unreliable with pyautogui.write and generic hotkey synthesis
Rejected: Reuse CLI setToolJSX dialogs in desktop mode | no transport for mid-call Ink UI over the SDK bridge
Rejected: Keep shell pbcopy/pbpaste for clipboard typing | inconsistent with NSPasteboard path and less reliable for Chinese text
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep desktop Computer Use approvals and macOS text-entry behavior on a single bridge/path; avoid reintroducing separate CLI-only and desktop-only codepaths for the same action
Tested: python3 -m unittest runtime/test_helpers.py
Tested: bun test src/utils/computerUse/permissions.test.ts src/server/__tests__/conversation-service.test.ts
Tested: cd desktop && bun run test ComputerUsePermissionModal chatStore
Tested: cd desktop && bun run test chatBlocks
Tested: cd desktop && bun run lint
Not-tested: End-to-end manual Computer Use interaction against a live Electron target app on macOS
This introduces a persisted light/dark appearance setting, maps the desktop shell onto semantic theme tokens, and reworks the highest-traffic chat/settings surfaces so the new dark mode is usable without regressing the original light theme.
The same pass tightens markdown rendering for chat replies by improving inline code, table overflow handling, and safe external-link behavior so dark-mode content stays legible in real conversations.
Constraint: Preserve the existing light theme while adding a user-selectable dark theme in Settings > General
Constraint: Avoid introducing new dependencies for styling or markdown handling
Rejected: Replacing the light palette with a single dual-purpose palette | would risk broad visual regressions across the existing desktop UI
Rejected: Implementing dark mode only for shell chrome | leaves chat markdown, diffs, and permission flows visually broken
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: New desktop UI should use semantic theme variables instead of hard-coded color literals so both themes stay aligned
Tested: bun run lint; bun run test; bun run build; browser review of theme switching, provider/permission states, and chat surfaces
Not-tested: Prototype-style pages with remaining hard-coded colors (scheduled/session control mock surfaces) were not fully normalized in this change
The desktop app already had Tauri updater plumbing, but the
release pipeline was not emitting signed updater artifacts and
the UI exposed only a thin auto-check path. This change restores
a working updater release path, rotates to a new updater public
key, and adds a shared update flow with manual check/install
controls for testing.
Constraint: Original updater private key is unavailable, so a new public key had to be embedded and old installs cannot trust new signatures
Constraint: Must not add new dependencies or require main-branch rollout before validation
Rejected: Keep the old pubkey and skip signing | would leave release builds unable to publish valid updater artifacts
Rejected: Add a manual download fallback flow | user explicitly deferred that work
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Preserve the new updater private key and password outside the repo; losing them again will break future in-app updates for installed builds
Tested: desktop unit test for updater store; desktop TypeScript no-emit; desktop production build
Not-tested: end-to-end updater install against a real GitHub Release on this branch
The desktop chat store was dropping the previous assistant draft when a new user turn began because streaming text was cleared before it was flushed into message history. At the same time, the desktop OAuth flow was using an unregistered /api/haha-oauth/callback redirect URI, which caused provider authorization failures. This change flushes visible assistant drafts before starting a new turn, restores the OAuth redirect to the registered localhost callback, and adds a root callback handler while keeping the legacy API callback path compatible.
Constraint: The OAuth provider only accepts the registered localhost /callback redirect URI
Rejected: Keep the desktop-specific /api/haha-oauth/callback path | provider rejects unsupported redirect URIs
Rejected: Rely on message_complete to persist visible assistant text | next user turn can begin before that event arrives
Confidence: high
Scope-risk: moderate
Directive: Any UI-visible assistant draft must be flushed into messages before a new user turn resets streaming state
Tested: bun test src/server/__tests__/haha-oauth-service.test.ts src/server/__tests__/haha-oauth-api.test.ts src/server/__tests__/conversation-service.test.ts
Tested: cd desktop && bun run test src/stores/chatStore.test.ts
Tested: cd desktop && bun run lint
Not-tested: Manual end-to-end desktop OAuth login after reinstall
Desktop auth was reporting stale local token files as logged in, could inherit a parent OAuth token after logout, and kept polling even when browser launch failed. This change validates stored tokens through the refresh path, clears inherited OAuth env before spawning the CLI, fetches subscription metadata on initial login, and moves polling start until after the browser opens. Regression tests cover the server and desktop store paths.
Constraint: Desktop CLI must bypass macOS Keychain by injecting env OAuth when available
Rejected: Keep status endpoint file-based only | reports expired sessions as logged in
Confidence: high
Scope-risk: moderate
Directive: Official desktop auth state must be derived from ensureFreshTokens rather than oauth.json presence alone
Tested: bun test src/server/__tests__/conversation-service.test.ts src/server/__tests__/haha-oauth-service.test.ts src/server/__tests__/haha-oauth-api.test.ts
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run test
Not-tested: Manual end-to-end desktop OAuth flow against the live provider
This bundles the pending desktop/server team-session fixes with the local adapter recovery changes already in the worktree. The team path now keeps teammate membership stable under concurrent spawns, surfaces real teammate identities in the desktop UI, and allows direct interaction with member transcripts. The adapter changes recover automatically when stale thinking signatures invalidate an existing session.
Constraint: Team config writes can happen concurrently while multiple reviewers spawn in parallel
Constraint: Desktop member views must follow mailbox/transcript semantics rather than hijacking teammate runtime sessions
Rejected: Keep relying on config.json alone for member discovery | in-process teammates can be lost after concurrent writes
Rejected: Open teammate sessionIds as normal desktop sessions | would attach a second CLI instead of the running teammate
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Preserve locked team-file mutation for any future teammate registration path and keep teammate labels sourced from member names before agent types
Tested: bun test src/server/__tests__/teams.test.ts src/server/__tests__/team-watcher.test.ts
Tested: cd desktop && bun run test --run src/stores/chatStore.test.ts src/pages/ActiveSession.test.tsx
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run build
Not-tested: Manual end-to-end validation against a live Agent Teams run in the desktop app
- security: XSS sanitization with DOMPurify in Markdown/Mermaid/PermissionDialog;
path whitelist in filesystem API; fake keys in test/config files
- perf: fine-grained Zustand selectors in Sidebar/StatusBar/ContentRouter;
50ms throttle on streaming deltas; React.memo + useMemo in MessageList;
useRef for frequent keyboard shortcut state; AbortController 30s timeout
- leaks: WS session TTL timers (5-min cleanup on close); batch splice for
sdkMessages/stderrLines; folderPath validation in cronScheduler
- quality: optimistic update rollback in settingsStore; error state in
providerStore/teamStore; i18n for all hardcoded English strings
- docs: desktop architecture and features docs updated; VitePress nav fixed
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the default macOS about dialog with a custom menu that emits
a Tauri event, navigating to the Settings > About tab within the React app.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Wires the new claude-sidecar adapters mode into the actual desktop UX:
* On app launch, Tauri main process now spawns the adapter sidecar right
after the server sidecar comes up. The sidecar reads ~/.claude/adapters.json
and connects whichever of Feishu / Telegram has credentials configured;
if neither does, it warns + skips + exits cleanly (treated as expected).
* When the user saves credentials in the existing AdapterSettings page,
the frontend store invokes restart_adapters_sidecar after the PUT
/api/adapters succeeds. Tauri kills the old child and spawns a new one,
which picks up the fresh config and establishes the WebSocket connection
to Feishu / Telegram immediately — no app restart needed.
End-to-end behavior is now: install app → open → configure credentials in
settings → click save → IM bot is live.
Implementation
==============
* desktop/src-tauri/capabilities/default.json: replace the stale
binaries/claude-server allowlist with binaries/claude-sidecar across
shell:allow-execute, shell:allow-spawn, plus a new shell:allow-kill
entry needed for the restart path. (P2 changed externalBin to
claude-sidecar but missed updating capabilities, which is why the prior
bundle worked at all in dev mode but would have failed in production.)
* desktop/src-tauri/src/lib.rs:
- new AdapterState that holds an Option<CommandChild>
- start_adapters_sidecar() spawns `claude-sidecar adapters --feishu --telegram`
with ADAPTER_SERVER_URL env var pointing at the dynamic server port
(converted http://→ws:// since WsBridge does `new WebSocket(url)`
directly without protocol translation)
- spawn_and_track_adapters_sidecar() handles spawn + state insertion
- stop_adapters_sidecar() kills + clears state
- new #[tauri::command] restart_adapters_sidecar that calls stop+spawn
- sidecar Terminated events are info-logged, not treated as errors,
so the credential-missing path doesn't show up as a crash
- setup() spawns the adapter sidecar after server startup completes
- RunEvent::Exit cleanup also kills adapter sidecar
* desktop/src/stores/adapterStore.ts: after every successful PUT
/api/adapters, dynamic-import @tauri-apps/api/core and call
invoke('restart_adapters_sidecar'). Wrapped in try/catch so non-Tauri
test environments fall through quietly. Triggers on every config
change (including pairing code generation, paired-user removal) by
design — keeps the rule simple and guarantees any save takes effect.
* desktop/src/pages/AdapterSettings.tsx: removed the stale "Server URL"
text input. The field defaulted to ws://127.0.0.1:3456 but the actual
server uses a dynamic port chosen at startup. Even when filled in
correctly, loadConfig() in adapters/common/config.ts gives env var
priority over file value, so this UI control had zero effect inside
the desktop app. Standalone-mode adapter users can still edit the
field directly in adapters.json if they need to.
Bundle size: unchanged at 88 MB .app / 37 MB DMG. The Rust changes
add only a few KB to the desktop main binary.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Task card was expanded by default and overlapped the main chat area
whenever todos appeared. Start collapsed and reset expanded state on
clearTasks so new sessions also begin collapsed; users can click the
header to expand when needed.
This folds together the desktop-side fixes needed before broader rollout.
Session resume no longer deadlocks waiting on init, Mermaid and inline image
output render inside chat, task and sub-agent state stay visible during
execution, local build/release paths are safer, and Feishu/Telegram now expose
lightweight mobile commands (/help, /status, /clear) without adding a new
adapter-specific protocol.
Constraint: Desktop releases must publish updater artifacts from non-draft GitHub releases
Constraint: IM commands need short, phone-friendly responses and low operational complexity
Rejected: Add a dedicated IM command API surface | re-used existing slash commands and session/task REST endpoints to keep adapters thin
Rejected: Wait for task_update push events in WebUI | added low-risk polling because the current frontend ignores that event path
Confidence: medium
Scope-risk: broad
Reversibility: clean
Directive: Keep IM command replies terse and mobile-first, and merge local fallback slash commands when server-provided lists are partial
Tested: cd desktop && bun x vitest run src/components/chat/MermaidRenderer.test.tsx src/components/markdown/MarkdownRenderer.test.tsx
Tested: cd desktop && bun x vitest run src/components/chat/composerUtils.test.ts src/pages/ActiveSession.test.tsx src/stores/chatStore.test.ts
Tested: cd desktop && bun run lint
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "SDK init arrives only after the first user turn" --timeout 60000
Tested: cd adapters && bun test common/ feishu/ telegram/
Tested: cd adapters && bunx tsc --noEmit
Not-tested: Full GitHub Actions release run on all three desktop platforms
Not-tested: Local DMG packaging end-to-end on Apple Silicon
Not-tested: Real Feishu/Telegram device sessions against a live adapter process
Add a protocol-translating reverse proxy that allows using OpenAI-compatible
API providers (DeepSeek, OpenRouter, Groq, etc.) with Claude Code.
The proxy intercepts Anthropic Messages API requests from the CLI, transforms
them to OpenAI Chat Completions or Responses API format, forwards to the
upstream provider, and transforms streaming/non-streaming responses back.
Key features:
- Request transform: Anthropic Messages → OpenAI Chat/Responses
- Response transform: OpenAI → Anthropic (streaming SSE + non-streaming)
- Provider-agnostic reasoning support (reasoning_content, thinking_blocks,
reasoning fields from DeepSeek, OpenAI o-series, GLM-5, Groq, etc.)
- Event queue pattern for correct Anthropic SSE event ordering
- Two-step test: ① connectivity check ② full proxy pipeline validation
- Desktop UI: API format selector, two-step test results display
- License attribution for cc-switch (MIT, Jason Young)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Instead of close tab → delete session → create session → open tab (which
causes visual flicker and tab jumping), create the new session first then
replace the tab's sessionId in-place via a new replaceTabSession method.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Update AgentDefinition type with agentType, source, isActive, modelDisplay fields
- Refactor agentStore to support activeAgents/allAgents with cwd parameter
- Add i18n strings for agent browser UI (source labels, summary, status)
- Update server agents API with serialization helpers and override resolution
- Update tests to match new agent data structure
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Server: GET /api/skills (list) and GET /api/skills/detail (tree + files)
- Desktop: Skills tab with grouped list, file tree navigation, Markdown/code preview
- i18n: EN/ZH support
- Types, API client, Zustand store
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add API client, Zustand store, and i18n for agents list
- Display installed agents from ~/.claude/agents/ with detail view
- Render agent system prompt as Markdown via MarkdownRenderer
- Include error state with retry and empty state guidance
- Add 11 component tests covering all UI states and navigation
- Server: GET /api/skills (list) and GET /api/skills/detail (tree + files)
- Desktop: type definitions, API client, Zustand store
- i18n: EN/ZH translation keys for Skills tab
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Tab drag-and-drop reordering with visual drop indicator
- Add moveTab action to tabStore with localStorage persistence
- Context menu: add "Close Left" and "Close All" options
- Add i18n translations for new menu items (en/zh)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Settings and Scheduled Tasks now open as special tabs in the TabBar,
matching IDE conventions (closeable, icon-prefixed, persistent)
- New Session directly creates a session with the current workDir
- ChatInput shows DirectoryPicker before first message, locks after
- Remove connection status from StatusBar (unnecessary noise)
- ContentRouter routes by tab type instead of activeView
- Settings page no longer has a back-button header
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Update all components, hooks, and tests to use the new per-session
chatStore API where state is keyed by sessionId under `sessions` and
all action methods require sessionId as the first parameter.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The desktop chat view flattened Agent tool activity, which made sub-agent work
hard to follow and separated key evidence from the main conversation. This
change threads parent tool linkage through the server bridge and desktop store,
renders dispatched sub-agents as grouped cards with nested tool activity, and
moves long final outputs into a markdown preview dialog so the main transcript
stays readable on narrow layouts.
Constraint: Existing sessions and live websocket events both needed to preserve parent-child relationships
Rejected: Add brand-new subagent websocket event types | unnecessary protocol expansion when parent linkage already existed upstream
Rejected: Inline full sub-agent markdown in the card body | too cramped for narrow desktop chat layouts
Confidence: medium
Scope-risk: moderate
Reversibility: clean
Directive: Keep Agent card summaries compact; route long-form sub-agent output through the preview dialog unless the main chat layout is widened substantially
Tested: cd desktop && bun run test -- MessageList.test.tsx chatStore.test.ts
Tested: cd desktop && bun run lint
Tested: bun test src/server/__tests__/sessions.test.ts -t should\ reconstruct\ parent\ agent\ tool\ linkage\ from\ parentUuid\ chains
Not-tested: Full end-to-end visual verification against live CLI sessions with sub-agent text/thinking nested inline
Previously, creating a new session without selecting a project directory
defaulted to process.cwd(), which in the desktop app resolves to the app
installation path. Now it defaults to os.homedir().
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Use rejection sampling to ensure uniform distribution across the
safe alphabet. Values >= 232 are rejected and resampled.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After the first assistant response, derive a quick placeholder title from
the user message, then asynchronously call the provider's Haiku model to
generate a polished 3-7 word title. Titles update again at message 3 with
fuller conversation context. Updates push to frontend in real-time via
WebSocket `session_title_updated` event.
- extractTitle now reads `ai-title` JSONL entries (priority: custom > ai > first message)
- New titleService with deriveTitle + generateTitle using active provider config
- Handler tracks per-session message count and triggers generation on result
- Frontend sessionStore receives live title updates for sidebar + header
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement IM adapters allowing users to chat with Claude Code from Telegram
and Feishu/Lark. Includes persistent session management (chatId→sessionId
mapping), project selection via /projects command, and a web UI settings page
for configuring bot tokens, allowed users, and default project directory.
Key changes:
- adapters/: Telegram and Feishu adapter scripts with shared common modules
(WsBridge, MessageBuffer, SessionStore, HttpClient, config, formatting)
- Backend: adapterService + REST API (GET/PUT /api/adapters) with secret masking
- Frontend: AdapterSettings page in Settings tab with i18n support
- DirectoryPicker: use React Portal for dropdown to fix overflow clipping
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add 7 frequency modes (every N min/hours, daily, weekdays, specific days, monthly, custom cron) with progressive disclosure UI
- Add "Run Now" button with confirmation popover and fire-and-forget API
- Add execution logs panel (TaskRunsPanel) with auto-polling and accordion behavior
- Add task edit mode with cron reverse-parsing (parseCron) to populate form
- Add server-side extractAssistantText to store meaningful AI responses instead of raw NDJSON
- Fix session linking: pass --session-id to CLI subprocess so "View conversation" navigates to actual content
- Fix MACRO undefined error by adding --preload to Bun.spawn
- Add confirmation popovers for all destructive actions (run/disable/delete)
- Add DayOfWeekPicker component for specific-days scheduling
- Add cronDescribe utility with i18n support and unit tests
- Display task creation time and last run time
- Add ~50 i18n keys (en/zh) for all new UI elements
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add a lightweight custom i18n system supporting English (default)
and Chinese, with a language switcher in Settings > General.
All 35+ UI components internationalized with ~270 translation keys,
including 189 Chinese spinner verbs and server error code mapping.
When all tasks were completed and the user continued chatting, the inline
task summary was shown correctly. But on page refresh, loadHistory and
fetchSessionTasks would re-populate the task store, making the sticky bar
reappear.
- Add completedAndDismissed flag to cliTaskStore
- Detect user messages after last task tool call in history (V1 + V2)
- SessionTaskBar skips render when allCompleted && completedAndDismissed
- refreshTasks/setTasksFromTodos reset the flag for new task activity
- Fix InlineTaskSummary width to match parent container
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The CLI subprocess runs in --print (non-interactive) mode, which disabled
V2 task tools (TaskCreate/TaskUpdate). Only TodoWrite was available, but
the frontend only tracked V2 tool names for task refresh — so the Tasks
bar never appeared for new WebApp sessions.
Changes:
- Set CLAUDE_CODE_ENABLE_TASKS=1 in CLI subprocess env to enable V2 tasks
- Add TodoWrite to TASK_TOOL_NAMES for backward compat with V1 sessions
- Parse TodoWrite input.todos directly into TaskBar state (no disk read)
- Extract last TodoWrite from history on session load for V1 sessions
- Inline completed task summary into message flow when user continues chat
(sticky TaskBar converts to scrollable inline summary)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Tauri sidecar architecture: Rust shell spawns claude-server binary,
dynamic port allocation, health-check wait loop, graceful shutdown
- Fix CORS middleware to accept `tauri://localhost` and `https://tauri.localhost`
origins from Tauri WebView, and add CORS headers to /health endpoint
- Enable native macOS window decorations (traffic lights) with Overlay title bar,
add data-tauri-drag-region on sidebar for window dragging
- Conditionally apply desktop-only padding (44px for traffic lights) vs web (12px)
- Generate brand identity: light-background app icon, horizontal logo, full icon
set (icns/ico/png) for Tauri bundle
- Add brand mark + GitHub link in sidebar, replace mascot SVG with app icon
in EmptySession page
- Update README (zh/en) and docs hero image with new branding
- Add sidecar build scripts and launcher entry points
- Gitignore Rust target/, Tauri gen/, and brand-assets candidates
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the separate Tasks sidebar page (wrong concept — was showing
scheduled tasks). Instead, display CLI task progress as a sticky bar
at the bottom of the active session, matching the official desktop app
behavior. Tasks are refreshed in real-time by detecting TaskCreate/
TaskUpdate tool_result messages over WebSocket.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Settings: new Providers tab with full CRUD, activation, and connectivity
test; Model tab shows active provider name; General tab simplified
- Tasks: new CLI Tasks page displaying task lists from ~/.claude/tasks/
with status, owner, and dependency (blocks/blockedBy) visualization
- NewTaskModal: add Advanced options (model, permission mode, working dir)
- Backend: fix TaskService to parse CLI V2 task format; extend /api/tasks
with /lists endpoint for grouped queries
- Fix ModelInfo.context type from number to string
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace project-grouped session list with a flat time-grouped layout
(Today / Yesterday / Last 7 days / Last 30 days / Older) matching
the original Claude Code desktop design. Add ProjectFilter component
with multi-select dropdown for filtering by project. Deduplicate
sessions by ID in the store to fix duplicate-key React errors caused
by the same session appearing across multiple project directories.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Server marks assistant messages with tool_use blocks as type='tool_use'
(not 'assistant'), and user messages with tool_result blocks as
type='tool_result' (not 'user'). mapHistoryMessagesToUiMessages now
handles both type variants when parsing content arrays, so tool calls
are properly restored after page refresh.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two bugs fixed:
1. Intermediate assistant text (e.g. "项目已经有 node_modules，直接启动") was
lost between tool calls because content_start didn't flush streamingText.
Now we flush accumulated text as assistant_text before switching to the
next content block.
2. History reload (page refresh) now restores thinking blocks alongside
tool_use, tool_result, and text blocks. Previously thinking blocks were
intentionally dropped — now they're preserved for full conversation replay.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Store statusVerb from server 'status' WebSocket messages
- StreamingIndicator now shows the real CLI verb (Canoodling, Thinking, etc.)
plus elapsed time and output token count
- Only show StreamingIndicator during tool_executing (not during thinking,
where ThinkingBlock already provides feedback)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The desktop app now keeps the composer stable while turns are active,
reduces low-signal tool noise in the transcript, restores project context
under the composer after session creation, and relies on the CLI's own
permission requests instead of injecting broader desktop-side Bash asks.
This also brings in the supporting desktop app source tree and the server
routes/session metadata needed for git info, filesystem browsing, session
resume, slash commands, and SDK-backed permission bridging so the UI can
operate as a coherent feature instead of a partial patch.
Constraint: Desktop transcript needs to stay usable during long multi-tool sessions without hiding file-change diffs
Constraint: Permission prompts must mirror CLI behavior closely enough that read-only commands do not get desktop-only prompts
Rejected: Keep rendering Read/Bash bodies inline | too noisy and unlike the intended transcript model
Rejected: Commit only the touched desktop files | would leave the newly introduced desktop app incomplete in git history
Confidence: medium
Scope-risk: broad
Reversibility: messy
Directive: Treat non-writing tools as summary-first transcript events; do not re-expand them by default without validating the UX against long sessions
Tested: cd desktop && bun run lint
Tested: cd desktop && bun run test -- --run
Tested: bun test src/server/__tests__/conversations.test.ts
Not-tested: Manual visual regression against the exact screenshots in a live desktop session
Not-tested: Full root TypeScript check (repository still has unrelated extracted-native parse failures)
