Commit Graph
23 Commits
Author SHA1 Message Date
7418andClaude Opus 4.6 f76e4747cd feat: unified provider resolver with protocol-based dispatch
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>
2026-03-09 20:30:35 +08:00
7418andClaude Opus 4.6 94528edac9 fix: use local timezone for date-based features (check-in, usage stats)
Root cause: `new Date().toISOString().slice(0, 10)` returns UTC date,
causing date-based features to be off by up to ±1 day for non-UTC users.

Check-in / assistant workspace:
- Add `getLocalDateString()` utility, replace all UTC date comparisons
- Schema v2→v3 migration: normalize lastCheckInDate only when it matches
  UTC today (ambiguous window); leave past dates untouched so check-in
  triggers correctly after upgrade
- Runtime compat in `needsDailyCheckIn`: accept UTC today as fallback
  for edge cases the migration cannot catch
- `needsDailyCheckIn(state, now?)` accepts optional time for testability

Usage stats:
- Replace single-offset SQL bucketing (`DATE(datetime(..., '+N minutes'))`)
  with JS-side per-row aggregation using `getLocalDateString(new Date(utc))`
- Date methods account for historical DST offset at each message's timestamp
- `getTokenUsageStats(days, now?)` accepts optional time to pin window start
- Window boundary via `localDayStartAsUTC()` is already DST-aware

Tests (new file: timezone-boundaries.test.ts, 22 tests):
- getLocalDateString at UTC+9/UTC-5/UTC boundaries with fixed timestamps
- needsDailyCheckIn: compat suppression, clearly-past trigger, local match
- v2→v3 migration: targeted normalization, past-date preservation, null safe
- localDayStartAsUTC: UTC+8/UTC-5 midnight boundaries
- Usage stats bucketing: UTC+9 cross-day, summary window, DST spring-forward
- All usage stats tests use pinned `now` — no time-bomb from fixed test data

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 11:55:29 +08:00
7418andClaude Opus 4.6 6c02c135fe fix: composer UI polish and permission selector improvements
Slash command:
- Fix first-click bug: set textarea.value and cursor position before
  calling handleInputChange so selectionStart reads correctly
- Move slash button to right of + (attach) button
- Simplify icon from CommandLineIcon to plain "/" text

Composer action bar:
- Move Agent toggle and permission selector to left side (was centered)
- Adjust spacing: reduce input padding, increase bottom margin

Permission selector:
- Add dropdown arrow indicator (ArrowDown01Icon)
- Change full_access color from orange to red (icon + text + background)
- Check res.ok before updating UI state (prevent false success)
- Make sessionId optional to support /chat new session page
- Log warnings on PATCH failure instead of silent catch

New chat page (/chat):
- Add ChatPermissionSelector with local state before session exists
- Pass permission_profile in session creation payload
- Backend createSession() now accepts and writes permission_profile

Context usage indicator:
- Reduce circle size from 22px to 16px
- Change used-portion color to dark gray (zinc-600/400)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 16:03:19 +08:00
7418andClaude Opus 4.6 111fa8c92e feat: refactor composer to two-layer layout, add session permission & context indicator
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>
2026-03-07 14:55:38 +08:00
7418andClaude Opus 4.6 19aba25c8f feat: assistant workspace — persistent AI personality & memory via Markdown files (#165)
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>
2026-03-06 20:31:42 +08:00
7418andClaude Opus 4.6 c9f1b62809 fix: 模型切换串台 + 发送消息后滚动不到底部
1. page.tsx — loadSession 加 cancelled 竞态守卫,快速切换会话时
   丢弃过期的 fetch 结果,防止旧会话的 model/provider 覆盖新会话
2. ChatView.tsx — 去掉 if(modelName)/if(providerId) 守卫,改为
   无条件同步 props,空值走 localStorage → default fallback 链
3. ChatListPanel.tsx + types + route.ts + db.ts — 三个创建会话入口
   (handleFolderSelect/handleNewChat/handleCreateSessionInProject)
   统一从 localStorage 读取并传递 model + provider_id,DB 层写入
4. MessageList.tsx — ScrollOnStream 增加 messageCount prop,
   消息数增加时立即 scrollToBottom,覆盖乐观插入和 assistant 落地

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 12:01:10 +08:00
7418andClaude Opus 4.6 6ad821d3af feat: 多 IM 远程桥接系统 + Bridge 一级导航 + bug 修复
**Bridge 系统核心(src/lib/bridge/)**
- bridge-manager: 生命周期编排、adapter 事件循环、会话级并发控制
- channel-adapter: 抽象基类 + 注册式 adapter 工厂
- channel-router: IM 地址 → CodePilot session 自动映射
- conversation-engine: 服务端消费 streamClaude() SSE 流
- permission-broker: 权限请求转发到 IM 内联按钮
- delivery-layer: 出站分片、限流、重试退避、HTML 降级
- telegram-adapter: Telegram 长轮询 + offset 安全水位 + 幂等去重
- security/: 路径校验、危险输入检测、滑动窗口限流

**Telegram 通知 Bot(src/lib/telegram-bot.ts)**
- 独立通知模式,与 bridge 模式互斥
- bridgeModeActive 使用 globalThis 存储,避免 HMR 重置导致轮询冲突

**API 路由**
- /api/bridge: GET 状态查询 + POST start/stop/auto-start
- /api/bridge/channels: 活跃通道列表
- /api/bridge/settings: bridge 设置读写
- /api/settings/telegram: 凭据管理(含 allowed_users 白名单)
- /api/settings/telegram/verify: 连接验证 + chat ID 自动检测

**UI 重构:Bridge 提升为一级导航**
- NavRail 新增 Bridge 图标导航项
- /bridge 页面:BridgeLayout hash 路由,Bridge + Telegram 两个子 tab
- BridgeSection: 总开关、状态、启停、通道开关、适配器状态、默认设置
- TelegramBridgeSection: 凭据配置 + 白名单 + Setup Guide(6 步)
- Settings 移除 Telegram 和 Bridge tab,只保留 4 个核心 tab

**Bug 修复**
- bridge-manager: runAdapterLoop 在 state.running=true 之前被调用,
  while 条件同步求值为 false 导致消费者循环不启动。修复为先设 running
  再启动 loop
- telegram-bot: bridgeModeActive 改用 globalThis 防止 HMR 丢失状态
- settings/telegram route: TELEGRAM_KEYS 补充 telegram_bridge_allowed_users

**Electron**
- 窗口关闭时 bridge 活跃则最小化到系统托盘而非退出
- 启动时通过 auto-start API 恢复桥接
- preload 暴露 bridge 相关 IPC

**文档**
- docs/bridge-system.md: 完整架构文档
- docs/chat-sdk-integration-feasibility.md: Chat SDK 集成调研
- CLAUDE.md 添加 bridge 文档链接

chore: bump v0.21.0

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 00:18:19 +08:00
7418andClaude Opus 4.6 0c379e5607 fix: address tool_result dedup, SDK task ID collision, and doc accuracy
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>
2026-02-27 13:22:10 +08:00
7418andClaude Opus 4.6 c13ff54638 feat: fix tool call chain and Tasks panel integration
Phase 1: RightPanel Files/Tasks tab toggle
- RightPanel.tsx: add Files/Tasks toggle buttons, conditionally render
  FileTree vs TaskList based on panelContent state
- en.ts/zh.ts: add panel.tasks translation

Phase 2: TodoWrite SDK mapping
- types/index.ts: add source field to TaskItem, add task_update SSE event type
- db.ts: add source column migration, syncSdkTasks() replace-all function
  that syncs SDK TodoWrite output to local tasks table (user tasks untouched)
- claude-client.ts: PostToolUse hook detects TodoWrite tool, emits task_update
  SSE with mapped todo items
- route.ts: collectStreamResponse handles task_update, calls syncSdkTasks()
- useSSEStream.ts: add onTaskUpdate callback and task_update case
- ChatView.tsx: onTaskUpdate dispatches tasks-updated CustomEvent
- TaskList.tsx: listens for tasks-updated event to auto-refresh
- tasks/route.ts: add PUT bulk sync endpoint for testing

Phase 3: tool_result three-layer deduplication
- claude-client.ts: emittedToolResultIds Set prevents PostToolUse and user
  message handler from emitting duplicate tool_result for same tool_use_id
- route.ts: seenToolResultIds Set in collectStreamResponse skips duplicate
  DB writes
- ChatView.tsx: onToolResult checks existing tool_use_id before state update

Phase 4: Agent SDK upgrade
- Upgrade @anthropic-ai/claude-agent-sdk from v0.2.33 to v0.2.62
  (29 versions, zero TypeScript errors, all integration points compatible)

Phase 5: Documentation
- docs/agent-tooling-todo-bridge.md: architecture overview, TodoWrite field
  mapping, status mapping, idempotency strategy, three-layer dedup, SSE event
  types, troubleshooting guide
- CLAUDE.md: add Architecture Docs section with reference

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 13:12:59 +08:00
7418andClaude Opus 4.6 2a7dbd45c2 feat: add context sharing and storage consistency (P0)
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>
2026-02-27 12:20:01 +08:00
7418andClaude Opus 4.6 40a78ea0fc fix: image gen result persistence with fallback for temp message IDs, bump v0.17.3
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>
2026-02-27 11:51:31 +08:00
7418andClaude Opus 4.6 20a5934cfc fix: persist image generation results to DB for reload survival, bump v0.17.2
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>
2026-02-27 11:32:00 +08:00
7418andClaude Opus 4.6 a5e2cedc12 feat: gallery masonry layout, favorites system, left-right detail dialog, bump v0.17.0
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>
2026-02-27 11:00:58 +08:00
7418andClaude Opus 4.6 d5dd9cfe34 feat: unify reference image data structure, add Nano Banana 2 model
Reference Image 统一重构:
- 新增 ReferenceImage 类型 (src/types/index.ts),统一承载 base64 和 localPath 两种来源
- 重写 image-ref-store.ts:单一 Map<string, ReferenceImage[]> 替代原来的
  imageGenRefStore + lastGeneratedImagePaths 双通路
  - sessionStorage 持久化 last-generated 路径,解决页面刷新后数据丢失
  - buildReferenceImages() 作为唯一的 merge 入口,消除各组件手写拼接逻辑
- ImageGenConfirmation props 从两个 (referenceImagePaths + referenceImagesData)
  合并为单一 referenceImages?: ReferenceImage[]
  - 预览渲染改为单循环,根据 data/localPath 决定 img src,上传图和结果图同时显示
  - API 调用时再拆分回 base64 和路径两个字段,后端无需改动
- StreamingMessage / MessageItem 各自 5 行手动 merge 逻辑替换为一行
  buildReferenceImages() 调用
- ChatView 改用 setLastGeneratedImages() 和 transferPendingToMessage()
  替代直接操作 Map
- MessageInput 改用 setRefImages() / deleteRefImages() 替代直接操作 Map

新增 Gemini 3.1 Flash Image 模型:
- 新增 Nano Banana 2 (gemini-3.1-flash-image-preview) 作为默认图片生成模型
- 模型列表: Nano Banana 2 > Nano Banana Pro > Nano Banana
- 更新 ProviderManager、image-generator.ts、media/generate route 的默认值

其他已有改动一并提交:
- batch image generation 功能文件
- 依赖更新 (package.json / package-lock.json)
- i18n、db schema、AppShell、uploads route 等相关改动

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 00:55:24 +08:00
7418andClaude Opus 4.6 97dc9d3a8c chore: add @google/genai SDK and media_generations DB schema
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>
2026-02-26 12:18:26 +08:00
7418andClaude Opus 4.6 448738d4f3 feat: provider/model system refactor — switch provider from chat input
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>
2026-02-26 00:22:18 +08:00
7418andClaude Opus 4.6 52f5bb5f86 feat: add token usage statistics page in Settings
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>
2026-02-25 00:07:41 +08:00
7418andClaude Opus 4.6 916b8889b7 fix: require valid project directory for session creation
- Backend: POST /api/chat/sessions now validates working_directory
  exists (400 MISSING_DIRECTORY / INVALID_DIRECTORY)
- db.ts: remove process.cwd() fallback in createSession
- ChatListPanel: validate last-working-directory before use,
  open FolderPicker when invalid; add SSR guard for localStorage
- NewChatPage: block sending without a project directory selected

Bump version to 0.10.5.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 15:37:51 +08:00
7418andClaude Opus 4.6 af2830db9b feat: add cursor-based message pagination (P0-3)
Backend returns paginated messages with hasMore flag. Frontend shows
"Load earlier messages" button with scroll anchor preservation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 01:24:27 +08:00
liuxiaopai-ai 746cea1eb7 fix: add graceful database shutdown to prevent WAL file leaks
The SQLite database connection was never explicitly closed when the
process exits. In WAL mode, this can leave behind -wal and -shm files
and risk data loss if the WAL hasn't been checkpointed.

Changes:
- Add closeDb() export for explicit database closure
- Register process shutdown handlers (exit, SIGTERM, SIGINT, SIGHUP)
  that call closeDb() before the process terminates
- Idempotent: multiple calls to closeDb() are safe
- After closeDb(), getDb() transparently re-opens the database
- Add 6 unit tests covering close, idempotency, reopen, data
  persistence, and WAL cleanup (all passing)
2026-02-08 21:37:35 +08:00
7418andClaude Opus 4.6 4e81eaa60b feat: fix slash commands, add badge UI, multi-provider management
Slash commands:
- Fix skills not appearing (removed non-existent `enabled` filter)
- Add badge/capsule UI for prompt-type commands (/compact, /review, etc.)
- SDK-native commands sent directly; CLI-only commands expanded to prompts
- /clear now resets SDK session and clears database messages
- /cost shows actual aggregated token usage statistics
- Keyboard: Backspace/Escape to remove badge, arrow keys auto-scroll popover
- Add /memory command for editing CLAUDE.md

Multi-provider management:
- CRUD API for API providers with SQLite storage
- ProviderManager UI with quick presets (GLM, Kimi, MiniMax, etc.)
- Dynamic model labels based on active provider
- Environment variable injection with conflict resolution

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-08 20:03:18 +08:00
7418andClaude Opus 4.6 262b295f63 fix: use stable ~/.codepilot/ data directory to persist across updates
Previously the database path depended on app.getPath('userData') which
varies with app name changes (CodePilot vs codepilot vs Claude GUI).
Now uses a fixed ~/.codepilot/ directory for both dev and production.

Includes automatic migration: on first launch, if the DB doesn't exist
at the new path, it checks old locations (Application Support variants
and the old dev-mode data/ folder) and copies the database over.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 13:07:08 +08:00
7418andClaude Opus 4.6 ff1fb38735 feat: CodePilot - desktop GUI for Claude Code
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>
2026-02-06 21:04:05 +08:00