Skills system:
- Replace `CommandBadge.isSkill: boolean` with `kind: SkillKind` (agent_skill | slash_command | sdk_command | codepilot_command)
- handleSubmit dispatches by kind: agent_skill retains skill name in prompt, slash/sdk commands pass through to SDK, codepilot commands expand via COMMAND_PROMPTS
- Popover groups commands into Commands / Slash Commands / Agent Skills
- API `/api/skills` returns `kind` field; `displayOverride` persisted through full chain (frontend → API → DB)
- Forward SDK `system:init` slash_commands/skills metadata to frontend via SSE
MCP management:
- Fix remote server (SSE/HTTP) creation: validate `url` instead of `command`
- Fix dual-config read/write asymmetry: PUT routes servers by `_source` to correct file (~/.claude.json vs ~/.claude/settings.json)
- DELETE checks both config files; POST checks both for name collision
- McpManager preserves `_source` tags on edit/rename; JSON editor only manages settings.json servers
Completion processing:
- Extract core logic into `onboarding-processor.ts` and `checkin-processor.ts` (shared by route handlers and server-side detection)
- Remove frontend `detectAssistantCompletion` from ChatView — server-side path in `finally` block is now the single source of truth
- Replace hard-coded `fetch("http://localhost:PORT/...")` with direct function imports
- Both processors are internally idempotent (check state before processing)
Other:
- `settingSources` always includes 'user' so SDK loads ~/.claude/skills/
- Add 24 unit tests for SkillKind dispatch logic
- Add onboarding-completion extraction tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract provider resolution logic into two new modules:
- provider-catalog.ts: vendor presets, default model catalogs, protocol definitions
- provider-resolver.ts: unified resolution for all consumers (Claude SDK, AI SDK, model listing)
DB migration:
- Add protocol, headers_json, env_overrides_json, role_models_json columns to api_providers
- Create provider_models table for per-provider model catalog
Consumer refactoring:
- claude-client.ts: replace inline env-building with toClaudeCodeEnv()
- text-generator.ts: replace inline config with toAiSdkConfig()
- conversation-engine.ts, onboarding, checkin, plan routes: use shared resolveProvider()
- /api/providers/models: read from catalog + provider_models table
UI improvements:
- Merge confusing "Custom API (Anthropic-compatible)" into "Anthropic Third-party API"
- Add 3-field model name mapping (sonnet/opus/haiku) in advanced options
- ProviderForm.tsx: support new fields (protocol, env_overrides, role_models)
Bug fixes:
- Protect auth credentials from being deleted by legacy extra_env empty-string overrides
- Fix env var names: ANTHROPIC_DEFAULT_SONNET → ANTHROPIC_DEFAULT_SONNET_MODEL (SDK convention)
Tests: 229/229 passed. Verified with aiberm (no mapping) and pipellm (with mapping).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Composer restructure:
- MessageInput internal footer now only contains: file button, model
selector, slash command button, and send button
- Removed mode toggle (Code/Plan) from composer area (logic preserved)
- New ChatComposerActionBar below input with three slots: left (Design
Agent), center (permission selector), right (context indicator)
New components:
- SlashCommandButton: inserts `/` at cursor, reuses existing slash
command detection and popover logic
- ChatPermissionSelector: session-level permission toggle (default /
full_access) with danger confirmation dialog
- ContextUsageIndicator: SVG donut chart showing context usage ratio
with HoverCard displaying model, tokens, cache stats
- ChatComposerActionBar: slot-based container for action bar items
Session permission (permission_profile):
- DB: new column on chat_sessions, default 'default'
- API: PATCH sessions supports updating permission_profile
- Chat API: bypassPermissions = global setting OR session full_access
- PermissionPrompt: auto-approves and hides when full_access
- Claude client: combines global and per-session bypass flags
Bridge integration:
- permission-broker: auto-approves permissions for full_access sessions
without sending IM notifications
- conversation-engine: passes bypassPermissions to SDK for full_access
- PATCH route: auto-approves pending bridge permissions on switch to
full_access
Other:
- ImageGenToggle relabeled to "Design Agent" / "设计 Agent"
- New model-context.ts with MODEL_CONTEXT_WINDOWS lookup
- Provider models API returns optional contextWindow field
- New useContextUsage hook for token usage calculation
- i18n: added composer.*, permission.*, context.* keys (en + zh)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
Skills.sh Marketplace:
- Add marketplace browser with search, detail panel, and install/uninstall
- Search API proxying skills.sh with lock file integration for installed state
- Install/remove APIs using `npx skills` CLI with SSE streaming progress
- SKILL.md content fetching via GitHub Git Trees API with in-memory caching
- MarketplaceSkillCard, MarketplaceSkillDetail, MarketplaceBrowser components
- InstallProgressDialog with real-time SSE log output
- SkillsManager gains "My Skills" / "Marketplace" segmented control
- Type definitions: MarketplaceSkill, SkillLockFile, SkillLockEntry
Navigation restructure:
- Split Extensions page into standalone /skills and /mcp top-level pages
- NavRail: replace single Extensions icon with separate Skills (ZapIcon) and MCP (Plug01Icon) entries
- /extensions page now redirects to /skills or /mcp based on ?tab param
- /plugins redirects updated to point to new routes
- Remove redundant source badges from SkillListItem (section headers suffice)
Other:
- Add WeChat user group QR code to README.md and README_CN.md
- i18n: add 19 marketplace-related keys in en.ts and zh.ts
- Bump version to 0.18.0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
P1: tool_result dedup changed from "first wins" to "last wins"
- claude-client.ts: remove emittedToolResultIds Set, both PostToolUse and
user message handler emit freely. PostToolUse provides immediate UI feedback;
user handler's potentially more complete result arrives second.
- route.ts: collectStreamResponse replaces existing contentBlock entry when
duplicate tool_use_id arrives (last wins for DB persistence).
- ChatView.tsx: onToolResult replaces existing state entry by tool_use_id
instead of skipping, ensuring most complete result is displayed.
P2: SDK task ID collision risk eliminated
- db.ts: syncSdkTasks now uses full sessionId in task ID
(`sdk-{fullSessionId}-{index}`) instead of truncated 8-char prefix,
eliminating cross-session primary key collisions.
P2: Todo ordering stabilized
- db.ts: add sort_order column migration, syncSdkTasks writes array index
as sort_order. getTasksBySession sorts by sort_order ASC, created_at ASC
so tasks with identical timestamps maintain insertion order.
P3: Documentation field mapping corrected
- agent-tooling-todo-bridge.md: fix field mapping table — actual implementation
maps activeForm (not priority) to description column. Updated dedup strategy
docs from "three-layer skip" to "two-layer last-wins replace".
Lint: fix prefer-const for finalPrompt in claude-client.ts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Image Generation Refactor:
- MessageInput: add onImageGenerate callback, remove skill fetch dependency
- ChatView: implement handleImageGenerate that creates image-gen-request
message for ImageGenConfirmation UI, then user selects params and generates
- New API route POST /api/chat/messages for DB-only message persistence
- image-gen-completed event now only persists notice to DB, no longer triggers model
- Reference images passed via module-level Map (imageGenRefStore) to avoid
DB bloat from base64 data; user message DB content stores metadata only
Bug Fixes:
- Fix useCallback dependency missing imageGen causing stale closure reads
- Fix React Hooks order violation in MessageItem (early return before hooks)
- Fix localStorage cache collision across sessions (key now includes sessionId)
- Fix empty src attribute in FileAttachmentDisplay for DB-restored messages
- Add JSON parse fallback for malformed image-gen-request blocks
Gallery Reference Images:
- /api/media/generate saves reference images to disk, stores paths in metadata
- /api/media/gallery extracts referenceImages from metadata in mapRow
- GalleryDetail displays reference image thumbnails
- ImageGenCard supports referenceImages prop for chat display
UI Changes:
- ImageGenToggle: replace paint brush icon with text label (en: Image, zh: 生图)
- Model selector button: remove provider name display to save space
- ImageGenConfirmation: support referenceImagesData prop for base64 preview
i18n:
- Add imageGen.toggleLabel key (en: Image, zh: 生图)
Full-featured desktop application built with Next.js + Electron:
- Streaming chat with Claude Code via Agent SDK
- Session management with SQLite persistence
- Project file tree and file preview
- MCP server and custom skills management
- Permission controls with Code/Plan/Ask modes
- Dark/light theme, token tracking
- macOS DMG packaging with electron-builder
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
