Assistant Workspace V2:
- Markdown indexing engine (incremental manifest + chunks JSONL)
- Keyword retrieval with CJK bigram support and hotset boosting
- Directory taxonomy inference and evolution suggestions
- Workspace config management (.assistant/config.json)
- Organize API: capture, classify, move, archive, suggest-evolution
Workspace switching:
- Inspect API (GET /api/workspace/inspect) for pre-switch validation
- Two-phase switching with confirmation dialogs (5 workspace statuses)
- Atomic save: init/reset runs before setSetting(), rollback on failure
- Auto-navigate to new/reused session after switch
- Mismatch banner in ChatView (only for former assistant sessions)
- Debounced path validation with visual indicators
Security hardening:
- Completion fence (onboarding-complete/checkin-complete) only processes
when session.workingDirectory === assistant_workspace_path (frontend)
AND session.working_directory === workspacePath (backend double-check)
- assertContained() in workspace-organizer: rejects absolute paths, ~/,
../ traversal, and symlink escapes for captureNote/moveFile
- organize API validates all path params at entry (validateRelativePath)
- captureDefault sanitized to relative path on onboarding write
- R_OK + W_OK validation on GET settings, session creation, and PUT
Bug fixes:
- hookTriggeredSessionId now read before auto-trigger; allows retry if
session has no messages (previous trigger failed silently)
- workspace-switched event listener matches oldPath (not just != newPath)
so normal project chats never show the mismatch banner
- Daily check-in card hidden when onboarding not complete
- Refresh docs now calls generateRootDocs() + generateDirectoryDocs()
- Banner "Open" button reuses latest session (checkin mode) instead of
always creating new onboarding session
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add "Assistant Workspace" feature that lets users designate a directory
(e.g. Obsidian vault) containing 4 Markdown files (soul.md, user.md,
memory.md, claude.md) to define AI personality, user profile, long-term
memory, and execution rules. These files are automatically injected into
the system prompt for assistant project sessions.
Core library (src/lib/assistant-workspace.ts):
- Workspace validation, initialization with template files
- File loading with 8000-char truncation, XML prompt assembly (40k limit)
- State management via .assistant/state.json
- Directory docs generation (README.ai.md + PATH.ai.md)
- Case-insensitive file name fallback (soul.md → SOUL.md)
System prompt injection (src/app/api/chat/route.ts):
- Scoped to sessions where working_directory === workspace path
- Workspace prompt prepended before session-level system prompt
- Onboarding/check-in instructions injected as <assistant-project-task>
- autoTrigger flag skips user message save and title update
Chat-based onboarding (10 questions) & daily check-in (3 questions):
- AI conducts conversation, outputs structured completion code blocks
- Frontend detects onboarding-complete/checkin-complete blocks
- Backend calls Claude API to generate file content from answers
- Fallback to raw answers if API call fails
Auto-trigger pipeline:
- Mount trigger (500ms delay) + focus fallback in MessageInput
- assistantTriggerFiredRef prevents duplicate triggers per mount
- hookTriggeredSessionId in state.json prevents cross-reload duplicates
- Daily check-in only triggers in the most recent workspace session
- hookTriggeredSessionId cleared via __clear__ sentinel after completion
API endpoints:
- GET/PUT /api/settings/workspace — path CRUD + file status
- POST /api/workspace/session — create (onboarding) or reuse (check-in)
- POST /api/workspace/onboarding — AI-generate soul.md + user.md
- POST /api/workspace/checkin — AI-update memory.md + user.md
- POST /api/workspace/hook-triggered — set/clear trigger guard
- GET /api/workspace/latest-session — latest session lookup
- POST /api/workspace/docs — refresh directory documentation
UI:
- Settings "Assistant" tab with workspace path, file status, controls
- Violet badge on workspace project group in ChatListPanel
- useAssistantWorkspace hook for state queries
Also includes:
- 102 passing tests (16 new regression tests for workspace logic)
- i18n keys for en.ts and zh.ts
- Handover documentation and execution plan
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When Claude's response includes tool calls (Read, Edit, Bash, etc.),
the response text is split into multiple content blocks — one before
each tool call and one after. These blocks were joined with an empty
string (.join('')), causing all paragraphs to concatenate without
any spacing in the final Telegram message.
Changed .join('') to .join('\n\n') so paragraph breaks between text
blocks are preserved, matching how they appear in the desktop UI.
* feat: add "View Plan" button with fullscreen modal to ExitPlanMode UI
When Claude writes a plan in plan mode, the plan content is written to a
file on disk but the ExitPlanMode UI only shows Approve/Reject buttons —
the user never sees the actual plan without manually finding the file.
Add a "View Plan" button that opens a fullscreen Dialog modal showing
the plan content rendered as markdown. The plan content is extracted from
the tool uses array (the Write tool's input for the plan file), so no
new API endpoints are needed.
Changes in StreamingMessage.tsx:
- extractPlanContent(): walks toolUses backwards to find the last Write
to a plans/*.md file and returns its content
- ExitPlanModeUI: accepts toolUses prop, renders "View Plan" button
(hidden if no plan content found), opens Radix Dialog modal with
MessageResponse markdown renderer
- Modal is 80vh tall, max-w-4xl, scrollable, with Close button
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add "Do this instead" feedback textbox to plan approval UI
When rejecting a plan, users can now type feedback and click "Do this
instead" (or press Enter) to send a custom deny message to the SDK.
This matches the Claude Code CLI behavior where users can provide
alternative instructions when rejecting a plan.
Previously, the deny message was hardcoded to "User denied permission"
— the API already supported custom messages but the client never sent
them.
Changes:
- StreamingMessage.tsx: add feedback textbox + "Do this instead" button
to ExitPlanModeUI, wire onDenyWithMessage callback
- ChatView.tsx: pass denyMessage through handlePermissionResponse
- MessageList.tsx: update onPermissionResponse type signature
- stream-session-manager.ts: add denyMessage param to
respondToPermission(), use it in the deny decision body
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: fetch plan content from disk so View Plan always shows latest version
Previously extractPlanContent read the Write tool's input.content, which
showed stale content when Claude later edited the plan via the Edit tool.
Now extractPlanFilePath finds the plan file path (matching both Write and
Edit tools, with Windows backslash support), and the View Plan button
fetches the file from disk on each click via /api/files/preview.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The stream idle timer (330s) fires during long-running Claude Code tool
executions because the SDK's keep_alive heartbeat messages are silently
dropped. This causes a false "Stream idle timeout" error even though
Claude is still actively working.
Root cause: claude-client.ts only handles 6 SDK message types in its
switch statement and has no default case, so keep_alive messages from
the SDK are never forwarded to the frontend. The idle timer in
stream-session-manager.ts never gets reset by markActive().
Fix: thread keep_alive through the existing 3-layer event pipeline:
- claude-client.ts: forward keep_alive as SSE event (via default case)
- useSSEStream.ts: add onKeepAlive callback to SSECallbacks interface
- stream-session-manager.ts: call markActive() on keep_alive to reset
the idle timer
No visible UI change — keep_alive only resets the timer silently.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: preserve paragraph breaks between text blocks in bridge responses
When Claude's response includes tool calls (Read, Edit, Bash, etc.),
the response text is split into multiple content blocks — one before
each tool call and one after. These blocks were joined with an empty
string (.join('')), causing all paragraphs to concatenate without
any spacing in the final Telegram message.
Changed .join('') to .join('\n\n') so paragraph breaks between text
blocks are preserved, matching how they appear in the desktop UI.
* fix: sanitize __NEXT_PRIVATE_* env vars from child processes
The bundled Next.js standalone server sets __NEXT_PRIVATE_STANDALONE_CONFIG
and __NEXT_PRIVATE_ORIGIN in process.env at runtime. These leak into every
child process spawned by the Electron main process (Claude Code CLI,
node version checks, package installs, etc.), which in turn pollutes
tmux/terminal sessions.
When other Next.js projects detect __NEXT_PRIVATE_STANDALONE_CONFIG in their
environment, they skip normal next.config loading and use CodePilot's baked-in
config instead — silently breaking builds and dev servers system-wide.
Fix: strip all __NEXT_PRIVATE_* variables when constructing env objects for
child processes. The standalone server.js already sets these internally, so
they don't need to be passed from the parent.
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
jasonjaclyn2017