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>
- electron/main.ts: check-prerequisites now returns hasHomebrew + platform
so the frontend can distinguish macOS-without-Homebrew from other scenarios
- electron/main.ts: remove untested tarball fallback (hardcoded Node version,
custom ~/.codepilot/node/bin PATH), replace with clean Homebrew-only path
that returns a clear error message when Homebrew is absent
- electron/main.ts: remove ~/.codepilot/node/bin from getExpandedShellPath()
since the tarball install target no longer exists
- InstallWizard.tsx: when Node.js is missing AND Homebrew is absent on macOS,
show a guided UI with the Homebrew install command, copy button, and
step-by-step instructions instead of a broken "Install" button
- InstallWizard.tsx: footer shows "Recheck" button (re-runs checkPrereqs)
instead of "Install" in the no-Homebrew case
- en.ts/zh.ts: add 8 new i18n keys for the Homebrew guidance UI
Root cause: the previous tarball fallback was untested, pinned to a specific
Node version (v22.12.0), and required maintaining a custom PATH entry. Guiding
users to install Homebrew first is more reliable and maintainable.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Problem:
- Install wizard on macOS failed with "Homebrew not found" when user
didn't have Homebrew installed, blocking Claude Code installation entirely
Fix (electron/main.ts):
- Add fallback: when Homebrew is not found, download official Node.js v22.12.0
binary tarball from nodejs.org and extract to ~/.codepilot/node/
- No Homebrew or sudo required — curl + tar only
- Detects architecture (arm64/x64) via process.arch
- Add ~/.codepilot/node/bin to getExpandedShellPath() so the downloaded
Node.js is found by subsequent install steps and server launcher
Install flow now: Homebrew found → brew install node (existing)
Homebrew missing → download tarball to ~/.codepilot/node/ (new)
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>
Session runtime mutex:
- Add session_runtime_locks table with TTL-based locking via SQLite
single-writer guarantee (transaction: DELETE expired + INSERT, PK
conflict = already locked → 409 SESSION_BUSY)
- POST /api/chat acquires lock before processing, releases in
collectStreamResponse finally block and error catch
- Add runtime_status/runtime_updated_at/runtime_error columns to
chat_sessions for tracking session state
Permission request persistence:
- Add permission_requests table with full lifecycle tracking
(pending → allow/deny/timeout/aborted)
- Dual-write in permission-registry: in-memory Map for real-time
resolution + DB for audit and recovery
- claude-client canUseTool now persists to DB before SSE event
- permission/route.ts validates against DB before resolving:
404 (not found), 409 (already resolved), 410 (waiter gone)
Immutable sdk_cwd:
- Add sdk_cwd column, snapshot from working_directory at session
creation time, never changes afterward
- route.ts uses sdk_cwd for SDK cwd to prevent resume breakage
when user modifies working_directory
- Backfill existing sessions via migration
Startup recovery (migrateDb):
- Reset running/waiting_permission sessions to idle with error msg
- Clear all runtime locks (stale from previous process)
- Abort pending permission requests (no in-memory waiter exists)
All DB writes are try/catch guarded — failure degrades gracefully
without breaking the in-memory hot path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Root cause: assistant messages use temporary IDs (temp-assistant-{timestamp})
in the frontend, which don't match real DB message IDs. The PUT update by
message_id always found 0 rows, so results were never persisted.
Fix — fallback search by session + prompt:
- db.ts: updateMessageContent now returns changes count; new
updateMessageBySessionAndHint() finds the latest assistant message
containing image-gen-request with matching prompt text and updates it
- /api/chat/messages PUT: tries message_id first, falls back to
session_id + prompt_hint search; returns 404 if neither finds a match;
response includes updated_message_id and fallback_used for debugging
- ImageGenConfirmation: always sends session_id and prompt_hint in PUT
request, regardless of whether messageId is a real or temp ID
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Root cause: after image generation, the message content in DB stayed as
`image-gen-request` (the options form). On app restart, MessageItem re-parsed
this as a generation form instead of showing the completed result. The result
only lived in React state and localStorage.
Fix:
- db.ts: add updateMessageContent() to update a message's content by ID
- /api/chat/messages: add PUT handler for message content updates
- ImageGenConfirmation: accept messageId prop; on successful generation,
replace message content from image-gen-request to image-gen-result format
(with localPath references) via PUT API call
- MessageItem: pass message.id to ImageGenConfirmation
Now on restart, parseImageGenResult() matches the persisted image-gen-result
block and renders ImageGenCard directly with the saved image paths.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Auto-update flow rework:
- updater.ts: disable autoDownload, add manual `updater:download` IPC handler
so user explicitly triggers download via "Download & Install" button
- updater.ts: resolve system proxy via session.defaultSession.resolveProxy()
and inject into HTTPS_PROXY env var, fixing zero download speed behind VPN/proxy
- preload.ts + electron.d.ts: expose `downloadUpdate` method to renderer
UI improvements:
- UpdateDialog: add "Download & Install" button when update available but not
yet downloading; show progress bar during download; "Restart to Update" when ready
- GeneralSection UpdateCard: show "Download & Install" / "Restart to Update" button
next to "Check for Updates"; show download progress bar inline; add "View Details"
link to reopen update dialog
- AppShell: dismissUpdate no longer permanently hides update for that version
(removed localStorage persistence), just closes the dialog
- useUpdate: add downloadUpdate to context
i18n:
- Added `update.installUpdate` key (en: "Download & Install", zh: "下载并安装")
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gallery UI overhaul:
- GalleryGrid: replace equal-size grid with CSS columns masonry layout (6 columns),
pure image cards without text/date info, hover gray ring highlight,
favorited items show red heart badge
- GalleryDetail: left-right layout dialog (70% image / 30% info),
nearly full-screen size with minimal margins, black background for image area,
absolute-positioned image container for correct sizing across all aspect ratios,
favorite toggle button replaces tag manager, removed outer border
- Gallery page: added "favorites only" filter button, replaced load-more button
with IntersectionObserver infinite scroll, removed tag system references
Favorites system:
- db.ts: added `favorited` column to media_generations with migration
- New API: PUT /api/media/[id]/favorite for toggle
- gallery/route.ts: support favoritesOnly=1 filter, return favorited field
- i18n: added favorites-related translations (en/zh)
Other:
- Default image model changed from Nano Banana Pro to Nano Banana 2
- providers/models/route.ts: skip media provider types in chat model selector
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)
Foundation for the image generation feature:
- Install @google/genai SDK (Google Gemini API client for Nano Banana Pro)
- Add media_generations table to store image generation metadata
(id, type, status, provider, model, prompt, aspect_ratio, image_size,
local_path, tags, session_id, message_id, etc.)
- Add media_tags table for tag-based filtering in gallery
- Add DB migration for existing databases
- Add indexes for created_at, session_id, status on media_generations
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the manual "jump to GitHub Release" update flow with native
in-app auto-update powered by electron-updater. The app now silently
downloads updates in the background and prompts the user to restart
when ready. Browser mode (`npm run dev`) retains the existing polling
fallback via `/api/app/updates`.
Main process (electron/updater.ts — new):
- Wrap electron-updater's autoUpdater, forward lifecycle events
(checking / available / downloading / downloaded / error) to the
renderer via IPC channel `updater:status`
- Register `updater:check` and `updater:quit-and-install` IPC handlers
- Auto-check 10s after launch, then every 4 hours
- Only initialized in packaged mode (!isDev)
Preload bridge (electron/preload.ts):
- Expose `updater` namespace with checkForUpdates, quitAndInstall,
and onStatus callback (same pattern as install.onProgress)
Type declarations (src/types/electron.d.ts):
- Add UpdateStatusEvent, ElectronUpdaterAPI interfaces
- Add optional `updater` field to ElectronAPI
Update hook (src/hooks/useUpdate.ts):
- Extend UpdateInfo with downloadProgress, readyToInstall, isNativeUpdate
- Add quitAndInstall to UpdateContextValue
Renderer — dual-mode logic (src/components/layout/AppShell.tsx):
- Detect `window.electronAPI?.updater` to choose between native IPC
subscription (Electron) and HTTP polling (browser)
- Map IPC events to UpdateInfo state, including download progress
UI components:
- UpdateDialog: three footer states — View Release (browser), progress
bar + disabled button (downloading), Restart to Update (ready)
- UpdateBanner (new): persistent top banner when update is downloaded,
shown even after dialog is dismissed
- NavRail: settings dot turns green + pulse when readyToInstall
- GeneralSection: UpdateCard shows download %, restart button, or
View Release depending on mode
Build & CI:
- electron-builder.yml: add `publish` config (github provider) to
generate latest-mac.yml / latest.yml metadata + blockmap files
- build.yml: change --publish never to --publish always with GH_TOKEN;
release job now uses `gh release edit` instead of create
i18n:
- Add 6 translation keys (en + zh) for update UI strings
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ErrorBoundary (PR #49 follow-up):
- Replace inline SVG with lucide-react CircleAlert icon for consistency
- Add i18n support: extract fallback UI into functional ErrorFallback
component so it can use useTranslation hook
- Remove unused withErrorBoundary HOC
- Add error.* translation keys to en.ts and zh.ts
ProviderManager:
- Add Claude Code default config entry in connected providers section
with cc switch hint explaining configurations may not be readable
- Update GLM preset descriptions: "GLM" → "GLM Code Plan / 编程套餐"
- Update MiniMax preset descriptions: "MiniMax API" → "MiniMax Code Plan / 编程套餐"
- Add provider.ccSwitchHint translation key to en.ts and zh.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Completely rewrites the Provider management page in Settings to follow
the OpenCode reference design with two clear sections.
ProviderManager.tsx — full rewrite:
- Top section "Connected Providers": shows all configured providers as a
clean list with brand icons from @lobehub/icons, name, badge, edit and
disconnect buttons. Environment variables also shown here.
- Bottom section "Add Provider": preset list with icon + name + description
+ Connect button. Clicking Connect opens a dialog with only the fields
needed for that preset.
- First 3 presets: Custom API (all fields), Anthropic Third-party API
(name + URL + key), Anthropic Official (key only).
- Other presets (GLM, Kimi, Moonshot, MiniMax, etc.) simplified to key-only.
- Bedrock/Vertex show environment variable config.
- Removed the top-right "Add Provider" button entirely.
- Added PresetConnectDialog component: shows brand icon in title, only
relevant fields, advanced options fold for extra_env, Cancel/Connect footer.
package.json:
- Add @lobehub/icons dependency for AI brand icons
- Bump version to 0.15.0
i18n (en.ts, zh.ts):
- Add translations: connectedProviders, noConnected, connect, disconnect,
disconnectProvider, disconnectConfirm, addProviderSection, addProviderDesc,
disconnecting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Refactors the provider/model selection system so users can switch providers
directly from the chat input model selector, instead of having to go to
Settings to activate/deactivate providers.
types/index.ts:
- Add ProviderModelGroup interface for grouped provider+model data
- Extend SendMessageRequest, ClaudeStreamOptions, ChatSession with provider_id
db.ts:
- Migration: add provider_id column to chat_sessions
- Migration: convert is_active=1 provider to default_provider_id setting
- New helpers: updateSessionProviderId, getDefaultProviderId, setDefaultProviderId
providers/models/route.ts:
- Rewrite to return { groups, default_provider_id } instead of flat model list
- Each configured provider becomes a group; env vars become "Environment" group
- Deduplicate models within a group (e.g. GLM sonnet/opus both → "GLM-4.7" once)
chat/route.ts:
- Accept provider_id from request body
- Resolution chain: request → session → default_provider_id → env vars
- provider_id='env' is sentinel for environment variable fallback
- Pass resolved provider object to streamClaude()
claude-client.ts:
- Use options.provider ?? getActiveProvider() so explicit provider takes priority
ChatView.tsx:
- Track currentProviderId state, pass provider_id in fetch body
- New handleProviderModelChange callback
MessageInput.tsx:
- New props: providerId, onProviderModelChange
- Replace dynamicModels/activeProviderName with providerGroups/defaultProviderId
- Model selector UI: grouped by provider with section headers, ✓ for active item
- Persist both model and provider ID to localStorage
chat/page.tsx, chat/[id]/page.tsx:
- Track and pass provider_id through the component chain
ProviderManager.tsx:
- Remove handleActivate/handleDeactivate, activatingId, Apply/Disable buttons
- Remove Active badge and green border styling
- Simplify env variable banner
- Add provider-changed event dispatch to save/delete handlers
providers/route.ts:
- GET response now includes default_provider_id field
i18n (en.ts, zh.ts):
- Add provider.default, provider.setDefault, provider.environment translations
Backward compatible: old sessions without provider_id default to '' which
triggers the fallback chain. is_active column preserved but no longer written.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add useEffect cleanup to abort in-flight fetch when ChatView unmounts
(e.g., session switch via key={id} remount). This triggers the existing
server-side cleanup chain: saves partial message to DB, auto-denies
pending permissions. Also resets streamingSessionId and
pendingApprovalSessionId global state to prevent stale UI.
- Add beforeunload handler during streaming to show browser confirmation
dialog when user attempts to close the window/tab, preventing accidental
data loss. Listener is automatically removed when streaming ends.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- New API route: src/app/api/skills/search/route.ts
- POST endpoint receives query + skill list + model alias
- resolveApiConfig() resolves credentials: active provider → settings → env
- Supports Anthropic direct, OpenRouter (Bearer auth), custom base URLs
- Bedrock/Vertex silently return empty results (unsupported)
- 5s hard timeout, all errors return { suggestions: [] }
- LLM returns JSON array of matching skill names, validated against input
- Modified: src/components/chat/MessageInput.tsx
- Extend substring matching to search both label and description fields
- Add debounced AI search (500ms) when skill mode has < 2 non-built-in
substring matches and filter length >= 2 characters
- AbortController cancellation on new input or popover close
- "AI Suggested" section with BrainIcon and spinner in popover UI
- Unified keyboard navigation across filteredItems + aiSuggestions
using allDisplayedItems for ArrowUp/Down, Enter/Tab, and visibility
- Modified: src/i18n/en.ts, src/i18n/zh.ts
- Added 'messageInput.aiSuggested' translation key (EN/ZH)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The `electron:dev` script requires `dist-electron/main.js` to exist,
but the README does not mention running `node scripts/build-electron.mjs`
beforehand. Without this step, `electron .` fails with:
"Cannot find module '/path/to/dist-electron/main.js'"
Add the build command to both the Quick Start and Development sections
in all three README files (EN, CN, JA).
New "Usage" tab in Settings showing token consumption analytics:
- **Data cards**: Total Tokens, Total Cost, Sessions, Cache Hit Rate
- **Bar chart**: Daily token usage with model/provider color grouping
using recharts v3, with custom tooltip and continuous date x-axis
- **Provider tracking**: Each session now records the active provider
name (e.g. "Kimi Coding Plan") so the chart distinguishes usage
across different providers, not just model names
Backend changes (db.ts):
- Added `provider_name` column to chat_sessions with auto-migration
- Added `getTokenUsageStats(days)` with summary + daily aggregation
- SQL uses `json_valid()` guard to prevent malformed JSON crashes
- Fixed off-by-one: 7D now shows exactly 7 calendar days, not 8
- Provider-qualified grouping: shows provider name when set,
plain model name when using direct Anthropic
API changes (route.ts):
- Persists effectiveModel and activeProvider name on every message
- Captures model from SDK init event for accurate tracking
- New GET /api/usage/stats endpoint
Frontend fixes:
- SettingsLayout: replaced useEffect+setState with useSyncExternalStore
to fix react-hooks/set-state-in-effect lint error
- UsageStatsSection: AbortController prevents request race on rapid
range switching; cache hit rate formula corrected to
cache_read/(cache_read+input); date gaps filled with zeros for
continuous x-axis
- Full i18n support (en + zh)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
