mirror of
https://github.com/lobehub/lobe-chat.git
synced 2026-06-17 04:55:51 +00:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 ONLY-yours
|
6f1380b07c |
@@ -1,8 +1,6 @@
|
||||
---
|
||||
name: add-provider-doc
|
||||
description: Guide for adding new AI provider documentation. Use when adding documentation for a new AI provider (like OpenAI, Anthropic, etc.), including usage docs, environment variables, Docker config, and image resources. Triggers on provider documentation tasks.
|
||||
disable-model-invocation: true
|
||||
argument-hint: '[provider-name]'
|
||||
---
|
||||
|
||||
# Adding New AI Provider Documentation
|
||||
|
||||
@@ -1,8 +1,6 @@
|
||||
---
|
||||
name: add-setting-env
|
||||
description: Guide for adding environment variables to configure user settings. Use when implementing server-side environment variables that control default values for user settings. Triggers on env var configuration or setting default value tasks.
|
||||
disable-model-invocation: true
|
||||
argument-hint: '[setting-name]'
|
||||
---
|
||||
|
||||
# Adding Environment Variable for User Settings
|
||||
|
||||
@@ -0,0 +1,298 @@
|
||||
---
|
||||
name: bot
|
||||
description: 'Bot platform architecture (Discord, Slack, Telegram, Feishu/Lark, QQ, WeChat). Use when working on inbound webhooks, Chat SDK message routing, agent execution from chat platforms, queue-mode callbacks, gateway lifecycle (websocket/polling), bot provider CRUD/credentials, or platform-specific clients/adapters/schemas. Triggers on bot, channel, webhook, mention, Chat SDK, agent bot provider, gateway, bot-callback, qstash bot.'
|
||||
---
|
||||
|
||||
# Bot System
|
||||
|
||||
> **Last updated: 2026-04-08.** Implementation evolves quickly — this doc is a map, not the source of truth. Always read the key files below to verify behavior, especially per-platform quirks. Update this doc when the architecture changes.
|
||||
|
||||
LobeChat agents can answer inside external chat platforms. Inbound messages flow through the Chat SDK (`chat` npm package), get routed to the right agent by `(platform, applicationId)`, executed via `AiAgentService`, and replied back through a per-platform `PlatformClient`. There are **two execution modes** (in-memory vs queue/QStash) and **three connection modes** (`webhook`, `websocket`, `polling`).
|
||||
|
||||
## Supported Platforms
|
||||
|
||||
| Platform | id | Default mode | Markdown | Edit | Notes |
|
||||
| -------- | ---------- | ------------------------------- | ----------------- | ------ | -------------------------------------------------------------------------------------- |
|
||||
| Discord | `discord` | `websocket` | yes | yes | Persistent gateway via Chat SDK adapter; reaction-thread quirks; native slash commands |
|
||||
| Slack | `slack` | `websocket` (Socket Mode) | yes (mrkdwn) | yes | Multi-mode — user can pick `webhook` per provider |
|
||||
| Telegram | `telegram` | `webhook` | yes (HTML) | yes | `setMyCommands` menu via `registerBotCommands` |
|
||||
| Feishu | `feishu` | `websocket` (Lark SDK WSClient) | **no** (stripped) | yes | Multi-mode; shared client with Lark |
|
||||
| Lark | `lark` | `websocket` | **no** | yes | Same client/schema as Feishu, different domain |
|
||||
| QQ | `qq` | `websocket` | **no** | **no** | All replies are final-only |
|
||||
| WeChat | `wechat` | `polling` (iLink long-poll) | **no** | **no** | 10-minute gateway window |
|
||||
|
||||
`supportsMarkdown=false` ⇒ outbound markdown is stripped to plain text via `stripMarkdown` and the AI is told not to use markdown. `supportsMessageEdit=false` ⇒ no progress edits — only the final reply is sent.
|
||||
|
||||
**Multi-mode connection** — Slack/Feishu/Lark/QQ ship as websocket but support `webhook` per-provider via `settings.connectionMode`. The runtime always merges schema defaults into stored settings before resolving the mode (`resolveBotProviderConfig` / `resolveConnectionMode` in `platforms/utils.ts`), so the schema's `field.default` is the source of truth — set it correctly when adding a new multi-mode platform.
|
||||
|
||||
## Inbound Flow (one webhook → reply)
|
||||
|
||||
```
|
||||
Platform server
|
||||
│ POST /api/agent/webhooks/[platform]/[appId]
|
||||
▼
|
||||
route.ts ── catch-all `[[...appId]]` route
|
||||
│
|
||||
▼
|
||||
BotMessageRouter (singleton)
|
||||
│ • lazy-loads bot per `platform:applicationId`
|
||||
│ • merges schema defaults + provider.settings (mergeWithDefaults)
|
||||
│ • builds Chat SDK Chat<any> with createIoRedisState (if Redis available)
|
||||
│ • registerHandlers: onNewMention / onSubscribedMessage / onNewMessage(/.dm)
|
||||
│ • registerCommands: /new (reset topic), /stop (interrupt)
|
||||
│
|
||||
▼
|
||||
chatBot.webhooks[platform](req) ← Chat SDK parses → fires events
|
||||
│
|
||||
▼
|
||||
AgentBridgeService.handleMention / handleSubscribedMessage
|
||||
│ • activeThreads guard (no duplicate runs per thread)
|
||||
│ • adds 👀 reaction (eyes), startTyping
|
||||
│ • merges debounced/queued skipped messages (mergeSkippedMessages)
|
||||
│ • extractFiles (buffer → fetchData → url)
|
||||
│ • formatPrompt (sanitize mention + speaker tag + referenced_message)
|
||||
│
|
||||
├── In-memory mode ──► AiAgentService.execAgent({ stepCallbacks })
|
||||
│ → onAfterStep edits progress message live
|
||||
│ → onComplete edits final reply, splits via splitMessage(charLimit)
|
||||
│
|
||||
└── Queue mode (isQueueAgentRuntimeEnabled) ──► execAgent({ stepWebhook, completionWebhook, webhookDelivery: 'qstash' })
|
||||
→ returns immediately, callbacks land at /api/agent/webhooks/bot-callback
|
||||
```
|
||||
|
||||
The router caches loaded bots in memory. Cache is **invalidated** by `BotMessageRouter.invalidateBot(platform, appId)` whenever the TRPC `update`/`delete` mutations run, so new credentials/settings take effect on the next webhook.
|
||||
|
||||
## Execution Modes
|
||||
|
||||
### In-memory (default)
|
||||
|
||||
`AgentBridgeService.executeWithInMemoryCallbacks` wraps `execAgent` with `stepCallbacks`. Lives in one process — Promise-based wait, 30-min timeout, edits the same `progressMessage` after every step. Topic title is summarized inline via `SystemAgentService`.
|
||||
|
||||
### Queue (`isQueueAgentRuntimeEnabled`)
|
||||
|
||||
`AgentBridgeService.executeWithWebhooks`:
|
||||
|
||||
1. Posts the `renderStart` placeholder, captures `progressMessageId`.
|
||||
2. Calls `execAgent` with `stepWebhook` and `completionWebhook` pointing at `${INTERNAL_APP_URL ?? APP_URL}/api/agent/webhooks/bot-callback`, plus `webhookDelivery: 'qstash'`.
|
||||
3. Returns immediately; the bridge `finally` block keeps the active-thread marker held until the `completion` callback fires.
|
||||
|
||||
`/api/agent/webhooks/bot-callback/route.ts` verifies the QStash signature and hands off to `BotCallbackService.handleCallback`:
|
||||
|
||||
- `type: 'step'` → `handleStep` re-renders `renderStepProgress`, edits `progressMessageId` (skipped if `displayToolCalls=false` or platform `supportsMessageEdit=false`).
|
||||
- `type: 'completion'` → `handleCompletion` writes the final reply (or error/interrupted message), removes the 👀 reaction, clears active-thread tracker, fires async `summarizeTopicTitle`.
|
||||
|
||||
`BotCallbackService.createMessenger` reloads provider + credentials from DB and rebuilds a `PlatformClient` per call (no in-memory state).
|
||||
|
||||
## Commands
|
||||
|
||||
Defined in `BotMessageRouter.buildCommands` and registered via two paths:
|
||||
|
||||
- **Native slash commands** (Slack/Discord): `bot.onSlashCommand('/<name>', ...)`
|
||||
- **Text-based fallback** (Telegram/Feishu/QQ/Lark/WeChat): `bot.onNewMessage(/^\/(new|stop)(\s|$|@)/, ...)` plus a per-mention `tryDispatch` so commands work even before subscribe.
|
||||
|
||||
Built-in commands:
|
||||
|
||||
- `/new` — clears `topicId` in thread state, next message starts a fresh topic.
|
||||
- `/stop` — interrupts the active execution (calls `AiAgentService.interruptTask` if `operationId` is known; otherwise queues a deferred stop via `requestStop`/`pendingStopThreads`, also aborts the startup phase via `startupControllers`).
|
||||
|
||||
To add a command, append to `buildCommands` — it auto-registers everywhere; on Telegram it also surfaces in the `/` menu via `client.registerBotCommands` → `setMyCommands`.
|
||||
|
||||
## Active-thread State (statics on `AgentBridgeService`)
|
||||
|
||||
- `activeThreads: Set<threadId>` — prevents duplicate runs per thread (must guard before stale-topic check, otherwise concurrent messages can drop).
|
||||
- `activeOperations: Map<threadId, operationId>` — needed by `/stop` once `execAgent` returns.
|
||||
- `startupControllers: Map<threadId, AbortController>` — cancels pre-`operationId` work (topic/tool prep).
|
||||
- `pendingStopThreads: Set<threadId>` — `/stop` arrived before `operationId` existed; consumed once available.
|
||||
|
||||
In **queue mode**, the bridge `finally` skips cleanup so the marker persists until `BotCallbackService.handleCompletion` calls `clearActiveThread`.
|
||||
|
||||
## Topic Lifecycle in Threads
|
||||
|
||||
- `handleMention` always treats the message as the start of a new conversation.
|
||||
- `handleSubscribedMessage` reads `topicId` from `thread.state`. If the topic is stale (`> 4 hours` since `updatedAt`), state is cleared and it retries as a fresh mention.
|
||||
- If `execAgent` fails with a Postgres FK violation on `topic_id` (cached topic was deleted), the bridge clears state and retries as a mention.
|
||||
- `subscribe()` is gated by `client.shouldSubscribe(threadId)` — Discord top-level channels return `false` so we don't follow up there.
|
||||
|
||||
## Attachments
|
||||
|
||||
`AgentBridgeService.extractFiles` resolves attachments in priority order:
|
||||
|
||||
1. `att.buffer` — already downloaded by the adapter (WeChat/Feishu inbound).
|
||||
2. `att.fetchData()` — adapter-provided lazy download with auth (Telegram, Slack, Feishu history). **Required** when URLs are token-protected — naive `fetch(url)` later in `ingestAttachment.ts` has no credentials.
|
||||
3. `att.url` — public CDN fallback (Discord, public QQ).
|
||||
|
||||
`inferMimeType` / `inferName` patch Telegram-style `photo` payloads (no `mimeType`/`name` from Bot API → defaults to `image/jpeg`) so vision models actually see them. Quoted-message attachments are also pulled from `raw.referenced_message.attachments` (Discord).
|
||||
|
||||
## Concurrency
|
||||
|
||||
`settings.concurrency` is `'queue'` or `'debounce'`:
|
||||
|
||||
- `debounce` → Chat SDK debounces inbound messages by `debounceMs`; `mergeSkippedMessages` joins skipped texts/attachments into the current message before handing to the agent.
|
||||
- `queue` → Chat SDK serializes per-thread; the bridge's own `activeThreads` set is still required because in queue mode the SDK lock releases before the agent finishes.
|
||||
|
||||
## Gateway (persistent platforms)
|
||||
|
||||
Webhook platforms run fine in serverless functions. Persistent platforms (`websocket`, `polling`) need a long-running listener — that's the **gateway**.
|
||||
|
||||
**`GatewayService.startClient(platform, appId, userId)`** (`src/server/services/gateway/index.ts`):
|
||||
|
||||
- On Vercel + persistent mode → `BotConnectQueue.push` (Redis hash) and mark runtime status `queued`. The cron picks it up.
|
||||
- On Vercel + webhook mode → start the client inline (one HTTP call).
|
||||
- Off-Vercel → `GatewayManager` singleton holds long-lived clients in process.
|
||||
|
||||
**`GET /api/agent/gateway/route.ts`** (cron, `Bearer ${CRON_SECRET}`):
|
||||
|
||||
- Iterates registered platforms and starts every enabled persistent provider with `durationMs = 10min`, then in `after(...)` polls `BotConnectQueue` every 30s for new connect requests, until the window expires.
|
||||
- `getEffectiveConnectionMode(platform, settings)` is the only place that resolves per-provider mode — respect it everywhere.
|
||||
|
||||
**`POST /api/agent/gateway/start/route.ts`** is the non-Vercel `ensureRunning` entry point (`Bearer ${KEY_VAULTS_SECRET}`).
|
||||
|
||||
**Runtime status** is stored in Redis at `bot:runtime-status:platform:appId` with TTL ≈ `durationMs + 60s`. States: `starting | connected | disconnected | failed | queued`. Updated by each `PlatformClient.start/stop` and by the gateway service.
|
||||
|
||||
## Platform Definitions
|
||||
|
||||
Each platform exposes a `PlatformDefinition` registered in `platforms/index.ts`:
|
||||
|
||||
```ts
|
||||
{
|
||||
id: 'discord',
|
||||
name: 'Discord',
|
||||
connectionMode: 'websocket', // recommended default
|
||||
schema: FieldSchema[], // applicationId + credentials + settings
|
||||
clientFactory: new DiscordClientFactory(),
|
||||
supportsMarkdown?: boolean, // default true
|
||||
supportsMessageEdit?: boolean, // default true
|
||||
documentation?: { portalUrl, setupGuideUrl },
|
||||
}
|
||||
```
|
||||
|
||||
`schema` drives both server validation (`mergeWithDefaults`, `extractDefaults`) **and** the auto-generated UI form. Top-level keys `applicationId` / `credentials` / `settings` map to DB columns. Common settings fields live in `platforms/const.ts` (`displayToolCallsField`, `makeServerIdField(platform?)`, `makeUserIdField(platform?)`). The `serverId` / `userId` factories take a platform identifier so the field's hint can render platform-specific "how to find this ID" guidance (Discord Developer Mode, Telegram @userinfobot, etc.); pass no argument to fall back to generic copy.
|
||||
|
||||
Each platform implements `PlatformClient` (see `platforms/types.ts`):
|
||||
|
||||
- Lifecycle: `start(opts?)`, `stop()`
|
||||
- Inbound: `createAdapter()` → Chat SDK adapter map
|
||||
- Outbound: `getMessenger(platformThreadId)` → `{ createMessage, editMessage, removeReaction, triggerTyping, updateThreadName? }`
|
||||
- Formatting: `formatMarkdown?`, `formatReply?` (usage-stats footer when `showUsageStats`)
|
||||
- Helpers: `extractChatId`, `parseMessageId`, `sanitizeUserInput`, `shouldSubscribe`, `resolveReactionThreadId`
|
||||
- Optional patches: `applyChatPatches(chatBot)` (Discord uses this for `forwardedInteractions` + `threadRecovery`)
|
||||
- Optional menu: `registerBotCommands(commands)` (Telegram `setMyCommands`)
|
||||
|
||||
`ClientFactory.validateCredentials` is called from the TRPC `testConnection` mutation — implement it to hit the platform API and return useful per-field errors.
|
||||
|
||||
## Database
|
||||
|
||||
**Schema** (`packages/database/src/schemas/agentBotProvider.ts`):
|
||||
|
||||
```ts
|
||||
agent_bot_providers (
|
||||
id uuid pk,
|
||||
agent_id text fk → agents.id (cascade),
|
||||
user_id text fk → users.id (cascade),
|
||||
platform varchar(50), // 'discord' | 'slack' | …
|
||||
application_id varchar(255),
|
||||
credentials text, // KeyVaults-encrypted JSON
|
||||
settings jsonb default '{}',
|
||||
enabled boolean default true,
|
||||
…timestamps
|
||||
)
|
||||
unique (platform, application_id)
|
||||
```
|
||||
|
||||
**Model** (`packages/database/src/models/agentBotProvider.ts`):
|
||||
|
||||
- User-scoped: `create / update / delete / query / findById / findByAgentId / findEnabledByApplicationId`. Credentials are encrypted/decrypted via the injected `KeyVaultsGateKeeper`.
|
||||
- Static (system-wide): `findByPlatformAndAppId`, `findEnabledByPlatform` — used by webhook routing & gateway sync, since they don't have a user context yet.
|
||||
|
||||
**TRPC router** (`src/server/routers/lambda/agentBotProvider.ts`):
|
||||
|
||||
| Procedure | Notes | |
|
||||
| -------------------------------------------- | ------------------------------------------------------------------------------------------- | ------------ |
|
||||
| `listPlatforms` | Returns `SerializedPlatformDefinition[]` (no `clientFactory`) | |
|
||||
| `create` / `update` / `delete` | Calls `BotMessageRouter.invalidateBot` + `GatewayService.stopClient` so changes take effect | |
|
||||
| `list` / `getByAgentId` / `getRuntimeStatus` | Decorate rows with Redis runtime status | |
|
||||
| `connectBot` | Returns \`{ status: 'started' | 'queued' }\` |
|
||||
| `testConnection` | Calls `clientFactory.validateCredentials` | |
|
||||
| `wechatGetQrCode` / `wechatPollQrStatus` | iLink onboarding flow | |
|
||||
|
||||
Client service: `src/services/agentBotProvider.ts`. Store actions: `src/store/agent/slices/bot/action.ts`. UI: `src/routes/(main)/agent/channel/{list,detail}` — settings form is auto-generated from each platform's `schema`.
|
||||
|
||||
## Reply Templates
|
||||
|
||||
`src/server/services/bot/replyTemplate.ts` exports `renderStart`, `renderStepProgress`, `renderFinalReply`, `renderError`, `renderStopped`, `splitMessage`. Step progress carries elapsed time, last LLM content, last tools, totals; final reply uses `client.formatMarkdown` then `client.formatReply` (which optionally appends `formatUsageStats`). `splitMessage(text, charLimit)` chunks at paragraph → line → hard cut.
|
||||
|
||||
`src/server/services/bot/ackPhrases/` provides randomized ack phrases.
|
||||
|
||||
## Key Files
|
||||
|
||||
```plaintext
|
||||
Webhook routes:
|
||||
src/app/(backend)/api/agent/webhooks/[platform]/[[...appId]]/route.ts — inbound catch-all
|
||||
src/app/(backend)/api/agent/webhooks/bot-callback/route.ts — qstash bot callback
|
||||
src/app/(backend)/api/agent/gateway/route.ts — cron gateway (10min window)
|
||||
src/app/(backend)/api/agent/gateway/start/route.ts — non-Vercel ensureRunning
|
||||
|
||||
Bot service:
|
||||
src/server/services/bot/index.ts — barrel
|
||||
src/server/services/bot/BotMessageRouter.ts — lazy bot loading + handler registration + commands
|
||||
src/server/services/bot/AgentBridgeService.ts — Chat SDK ↔ AiAgentService bridge, both exec modes
|
||||
src/server/services/bot/BotCallbackService.ts — qstash callback handler
|
||||
src/server/services/bot/formatPrompt.ts — speaker tag + referenced_message + sanitize
|
||||
src/server/services/bot/replyTemplate.ts — render*/splitMessage
|
||||
src/server/services/bot/ackPhrases/ — randomized acks
|
||||
src/server/services/bot/__tests__/ — unit tests for the above
|
||||
|
||||
Platform abstraction:
|
||||
src/server/services/bot/platforms/index.ts — registry singleton + exports
|
||||
src/server/services/bot/platforms/types.ts — PlatformClient/Definition/FieldSchema/ClientFactory
|
||||
src/server/services/bot/platforms/registry.ts — PlatformRegistry class
|
||||
src/server/services/bot/platforms/utils.ts — mergeWithDefaults, getEffectiveConnectionMode, formatUsageStats, runtimeKey
|
||||
src/server/services/bot/platforms/const.ts — shared FieldSchema fragments (displayToolCalls, serverId, userId)
|
||||
src/server/services/bot/platforms/stripMarkdown.ts — used by no-markdown platforms
|
||||
|
||||
Per-platform (each ships definition.ts, schema.ts, client.ts, const.ts, protocol-spec.md):
|
||||
src/server/services/bot/platforms/discord/ — websocket gateway + chat patches
|
||||
src/server/services/bot/platforms/slack/ — multi-mode (Socket Mode / webhook), markdownToMrkdwn
|
||||
src/server/services/bot/platforms/telegram/ — webhook, markdownToHTML, registerBotCommands
|
||||
src/server/services/bot/platforms/feishu/ — feishu + lark share client/schema (definitions/{feishu,lark,shared}.ts)
|
||||
src/server/services/bot/platforms/qq/ — websocket, no markdown, no edit
|
||||
src/server/services/bot/platforms/wechat/ — long-poll, no markdown, no edit
|
||||
|
||||
Gateway:
|
||||
src/server/services/gateway/index.ts — GatewayService (Vercel-aware startClient/stopClient)
|
||||
src/server/services/gateway/GatewayManager.ts — long-running client registry (non-Vercel)
|
||||
src/server/services/gateway/botConnectQueue.ts — Redis hash queue with TTL
|
||||
src/server/services/gateway/runtimeStatus.ts — Redis bot:runtime-status keys
|
||||
|
||||
Database:
|
||||
packages/database/src/schemas/agentBotProvider.ts — agent_bot_providers table
|
||||
packages/database/src/models/agentBotProvider.ts — encrypted CRUD + system-wide finders
|
||||
|
||||
TRPC + client:
|
||||
src/server/routers/lambda/agentBotProvider.ts — TRPC router
|
||||
src/services/agentBotProvider.ts — client wrapper
|
||||
src/store/agent/slices/bot/action.ts — Zustand actions
|
||||
|
||||
UI:
|
||||
src/routes/(main)/agent/channel/list.tsx — channel list
|
||||
src/routes/(main)/agent/channel/detail/ — auto-generated form (Header/Body/Footer)
|
||||
src/routes/(main)/agent/channel/const.ts — platform icons
|
||||
|
||||
Types & runtime status:
|
||||
src/types/botRuntimeStatus.ts — BOT_RUNTIME_STATUSES enum + snapshot type
|
||||
```
|
||||
|
||||
## Adding a New Platform
|
||||
|
||||
1. Create `src/server/services/bot/platforms/<id>/`:
|
||||
- `definition.ts` — `PlatformDefinition` registered in `platforms/index.ts`
|
||||
- `schema.ts` — `FieldSchema[]` (`applicationId` + `credentials` + `settings`); reuse fragments from `../const.ts`
|
||||
- `client.ts` — `class XClientFactory extends ClientFactory` returning a `PlatformClient` (lifecycle + adapter + messenger + helpers)
|
||||
- `const.ts` — `DEFAULT_X_CONNECTION_MODE`, history limits, etc.
|
||||
- `protocol-spec.md` — protocol notes (every existing platform has one)
|
||||
2. Pick the right `connectionMode` — webhook is much simpler if the platform supports it.
|
||||
3. If the platform can't render markdown, set `supportsMarkdown: false` and implement `formatMarkdown` via `stripMarkdown`.
|
||||
4. If it can't edit messages, set `supportsMessageEdit: false` — `BotCallbackService` will skip step edits and only send the final reply.
|
||||
5. Implement `validateCredentials` so the UI's "Test connection" button gives useful errors.
|
||||
6. Add the platform icon in `src/routes/(main)/agent/channel/const.ts` and register the platform in `src/server/services/bot/platforms/index.ts`.
|
||||
7. Add i18n keys under `channel.*` in `src/locales/default/setting.ts` (or wherever the channel namespace lives) — the schema's `label`/`description`/`placeholder`/`enumLabels` are i18n keys.
|
||||
@@ -1,130 +0,0 @@
|
||||
---
|
||||
name: builtin-tool
|
||||
description: Build a new builtin tool package under `packages/builtin-tool-<name>/`. Use when adding a new agent-callable toolset, designing its API surface (manifest / ApiName / Params / State), implementing the Executor + ExecutionRuntime, building the Inspector / Render / Placeholder / Streaming / Intervention / Portal UI, or wiring a tool into the central registries (`packages/builtin-tools/src/{index,identifiers,inspectors,renders,placeholders,streamings,interventions,portals}.ts` and `src/store/tool/slices/builtin/executors/index.ts`). Triggers on "new builtin tool", "add a tool", "tool inspector", "tool render", "tool placeholder", "tool streaming", "tool intervention", "BuiltinToolManifest", "BaseExecutor", "ExecutionRuntime".
|
||||
---
|
||||
|
||||
# Builtin Tool Authoring Guide
|
||||
|
||||
A builtin tool is a package the agent runtime can call. It ships **five faces**:
|
||||
|
||||
| Face | Lives in | Audience |
|
||||
| -------------------- | -------------------------------------------------------------------------------------- | ------------------------------------- |
|
||||
| **Manifest + types** | `src/{manifest,types,systemRole}.ts` | The LLM (tool spec + system prompt) |
|
||||
| **ExecutionRuntime** | `src/ExecutionRuntime/` | Server / desktop / any runtime caller |
|
||||
| **Executor** | `src/client/executor/` | Frontend (wraps stores/services) |
|
||||
| **Client UI** | `src/client/{Inspector,Render,…}/` | Chat UI |
|
||||
| **Registry wiring** | `packages/builtin-tools/src/*.ts` + `src/store/tool/slices/builtin/executors/index.ts` | Framework |
|
||||
|
||||
---
|
||||
|
||||
## Read These First
|
||||
|
||||
| Question | Doc |
|
||||
| ------------------------------------------------------------------------------------ | --------------------------------------------- |
|
||||
| Where do files live? What does each face do? Wiring? | [architecture.md](references/architecture.md) |
|
||||
| How do I name the tool, design APIs, write the manifest, executor, ExecutionRuntime? | [tool-design.md](references/tool-design.md) |
|
||||
| How do I build Inspector / Render / Placeholder / Streaming / Intervention / Portal? | [ui.md](references/ui.md) |
|
||||
|
||||
---
|
||||
|
||||
## When to Use This Skill
|
||||
|
||||
- Creating a new `packages/builtin-tool-<name>/` package
|
||||
- Adding a new API method to an existing builtin tool
|
||||
- Building or restyling any of the 6 client surfaces for a tool
|
||||
- Wiring a tool into the central registries
|
||||
- Debugging "tool not found / API not found / render not showing / placeholder stuck" errors
|
||||
|
||||
---
|
||||
|
||||
## Top-Level Design Principles
|
||||
|
||||
1. **`lobe-<domain>` identifier is permanent.** It's stored in message history. Renames need `@deprecated` aliases (see `packages/builtin-tools/src/inspectors.ts:88-89`). Get it right the first time.
|
||||
2. **ApiName is an `as const` object**, not a TS enum. It doubles as the runtime list `BaseExecutor` iterates over.
|
||||
3. **Three result fields, three audiences:**
|
||||
- `content: string` → the LLM reads it
|
||||
- `state: Record<…>` → the UI's `pluginState`; **result-domain only**, never echo all params back
|
||||
- `error: { type, message, body? }` → both LLM and UI; `type` is a stable code
|
||||
4. **Split execution from frontend wiring.**
|
||||
- `src/ExecutionRuntime/` — pure runtime, no React, no Zustand, accepts services via constructor. **The default place for new logic.**
|
||||
- `src/client/executor/` — `BaseExecutor` subclass that calls `ExecutionRuntime` (or stores/services directly when frontend-only).
|
||||
5. **UI defaults to "do nothing".** Inspector is required (the header strip). Render/Placeholder/Streaming/Intervention/Portal are added **only when there's something specific to show** — empty registries are fine.
|
||||
6. **Style with `createStaticStyles + cssVar.*`** (zero-runtime). Fall back to `createStyles + token` only when you genuinely need runtime values. Use `@lobehub/ui` components, not raw antd.
|
||||
7. **i18n keys live in `src/locales/default/plugin.ts`.** Inspector titles must come from `t('builtins.<identifier>.apiName.<api>')` so something renders while args stream.
|
||||
|
||||
---
|
||||
|
||||
## Package Layout (preferred, post-2026 convention)
|
||||
|
||||
```
|
||||
packages/builtin-tool-<name>/
|
||||
├── package.json
|
||||
└── src/
|
||||
├── index.ts # exports manifest + types + systemRole + Identifier (no React, no stores)
|
||||
├── manifest.ts # BuiltinToolManifest with JSON Schema for every API
|
||||
├── types.ts # ApiName const + Params/State interfaces per API
|
||||
├── systemRole.ts # System prompt teaching the model when/how to use the APIs
|
||||
├── ExecutionRuntime/ # ✅ Default home for runtime logic (server- or anywhere-callable)
|
||||
│ └── index.ts
|
||||
└── client/
|
||||
├── index.ts # Re-exports for the registries
|
||||
├── executor/ # ✅ Frontend executor — extends BaseExecutor, often delegates to ExecutionRuntime
|
||||
│ └── index.ts
|
||||
├── Inspector/ # required — header chip per API
|
||||
├── Render/ # optional — rich result card
|
||||
├── Placeholder/ # optional — skeleton during streaming/execution
|
||||
├── Streaming/ # optional — live output renderer (e.g. RunCommand, WriteFile)
|
||||
├── Intervention/ # optional — approval / edit-before-run UI
|
||||
├── Portal/ # optional — full-screen detail view
|
||||
└── components/ # shared subcomponents used by the surfaces above
|
||||
```
|
||||
|
||||
**Older packages** (`builtin-tool-task`, `builtin-tool-calculator`, etc.) still have `src/executor/` as a sibling of `src/client/`. That's grandfathered; **don't relocate without a deliberate refactor**. New packages and new APIs added to existing packages should follow the layout above.
|
||||
|
||||
`package.json` exports map:
|
||||
|
||||
```json
|
||||
"exports": {
|
||||
".": "./src/index.ts",
|
||||
"./client": "./src/client/index.ts",
|
||||
"./executor": "./src/client/executor/index.ts",
|
||||
"./executionRuntime": "./src/ExecutionRuntime/index.ts"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Authoring Checklist
|
||||
|
||||
Before opening the PR:
|
||||
|
||||
- [ ] Identifier follows `lobe-<domain>` and is **stable** (lives in message history).
|
||||
- [ ] Every `<Name>ApiName` value has: a manifest `api[]` entry, an executor method, an Inspector, an i18n `apiName.*` key.
|
||||
- [ ] `Params` interfaces match the JSON Schema; `State` interfaces match what the executor returns and what the UI surfaces read.
|
||||
- [ ] System prompt disambiguates confusable APIs and points to batch variants.
|
||||
- [ ] Runtime logic lives in `ExecutionRuntime/`; the `client/executor/` only wires stores/services and delegates.
|
||||
- [ ] Executor returns `{ success, content, state, error? }` via a single `toResult()` funnel — `content` always non-empty (default to `error.message`).
|
||||
- [ ] Inspector handles `isArgumentsStreaming`, `isLoading`, `partialArgs`, missing `pluginState`.
|
||||
- [ ] Render returns `null` until it has data; only created for APIs with rich results.
|
||||
- [ ] Placeholder added if the API has a perceivable execution lag (search, list, crawl).
|
||||
- [ ] Streaming added for APIs that emit incremental output (run command, write file, code execution).
|
||||
- [ ] Intervention added if `humanIntervention` is set in the manifest.
|
||||
- [ ] All registry files updated (see [architecture.md → Registry wiring](references/architecture.md#registry-wiring)).
|
||||
- [ ] i18n keys in `src/locales/default/plugin.ts` plus dev seeds in `en-US`/`zh-CN`.
|
||||
- [ ] `bunx vitest run --silent='passed-only' 'packages/builtin-tool-<name>'` passes.
|
||||
- [ ] `bun run type-check` passes.
|
||||
|
||||
---
|
||||
|
||||
## Reference Tools
|
||||
|
||||
Pick the closest neighbor and copy:
|
||||
|
||||
| If your tool is… | Read first |
|
||||
| ----------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
|
||||
| Pure-compute, no UI state | `packages/builtin-tool-calculator/` — `ExecutionRuntime` reuses executor (mathjs/nerdamer work everywhere) |
|
||||
| CRUD over a domain entity | `packages/builtin-tool-task/` — full Inspector + Render set, batch variants |
|
||||
| Heavy UI (Inspector/Render/Placeholder/Portal) | `packages/builtin-tool-web-browsing/` — search-style result UI, Portal for detail view |
|
||||
| Desktop / filesystem with all surfaces (incl. Streaming + Intervention) | `packages/builtin-tool-local-system/` — `ExecutionRuntime` injects an `ILocalSystemService`, executor calls it |
|
||||
| Server-side pure (no client executor) | `packages/builtin-tool-web-browsing/` — only `ExecutionRuntime` is exported; the chat client doesn't run it |
|
||||
| Needs human approval before running | `packages/builtin-tool-local-system/src/client/Intervention/` — per-API approval components |
|
||||
@@ -1,315 +0,0 @@
|
||||
# Builtin Tool Architecture
|
||||
|
||||
## The Five Faces
|
||||
|
||||
A builtin tool ships five distinct faces, each compiled into a different bundle:
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ ./ │
|
||||
│ Manifest + Types + systemRole │
|
||||
│ ─ Pure data, no React, no Node-only deps. │
|
||||
│ ─ Imported by: server (LLM tool spec), client (registries), │
|
||||
│ anyone who needs to know "what tools exist". │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
│
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ ./executionRuntime │
|
||||
│ src/ExecutionRuntime/index.ts │
|
||||
│ ─ Pure runtime logic. Accepts services via constructor — │
|
||||
│ never imports concrete services or stores directly. │
|
||||
│ ─ Imported by: server (BuiltinServerRuntimeOutput), tests, │
|
||||
│ and the client executor as a delegate. │
|
||||
│ ─ Returns: BuiltinServerRuntimeOutput { content, state, … } │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
│
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ ./executor │
|
||||
│ src/client/executor/index.ts │
|
||||
│ ─ BaseExecutor subclass. Wires Zustand stores and frontend │
|
||||
│ services into ExecutionRuntime, then funnels through │
|
||||
│ toResult() into BuiltinToolResult { content, state, error, │
|
||||
│ success }. │
|
||||
│ ─ Imported by: src/store/tool/slices/builtin/executors/ │
|
||||
│ index.ts (registered as a singleton). │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
│
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ ./client │
|
||||
│ src/client/{Inspector,Render,Placeholder,Streaming, │
|
||||
│ Intervention,Portal,components}/ │
|
||||
│ ─ React 'use client' surfaces. Read args + pluginState. │
|
||||
│ ─ Imported by: packages/builtin-tools/src/{inspectors, │
|
||||
│ renders,placeholders,streamings,interventions,portals}.ts. │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
│
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ Registry wiring │
|
||||
│ packages/builtin-tools/src/*.ts │
|
||||
│ src/store/tool/slices/builtin/executors/index.ts │
|
||||
│ ─ Aggregator maps: identifier → { apiName → component }. │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
The split exists so:
|
||||
|
||||
- Server bundles import only `./` and `./executionRuntime` and never touch React.
|
||||
- Frontend bundles import `./client` and never touch Node-only services.
|
||||
- The runtime is testable without React or Electron present.
|
||||
|
||||
---
|
||||
|
||||
## Why ExecutionRuntime is the Default Home for Logic
|
||||
|
||||
**Old pattern (grandfathered):** business logic in `src/executor/` directly. Examples: `builtin-tool-task`, older tools. Works, but the executor mixes runtime logic with frontend service plumbing — hard to reuse on the server.
|
||||
|
||||
**New pattern (preferred):** business logic in `src/ExecutionRuntime/`, frontend wiring in `src/client/executor/`. Examples: `builtin-tool-local-system`, `builtin-tool-web-browsing`, `builtin-tool-calculator`.
|
||||
|
||||
```
|
||||
ExecutionRuntime
|
||||
├─ accepts services via constructor (or `static create(opts)`)
|
||||
├─ returns BuiltinServerRuntimeOutput (content + state + success)
|
||||
└─ no React, no Zustand, no `@/services/...` direct imports
|
||||
|
||||
client/executor
|
||||
├─ extends BaseExecutor<typeof <Name>ApiName>
|
||||
├─ holds a `runtime = new <Name>ExecutionRuntime(realService)` instance
|
||||
├─ each ApiName method:
|
||||
│ 1. resolve scope / pull defaults from BuiltinToolContext
|
||||
│ 2. call runtime.<method>(args)
|
||||
│ 3. funnel through toResult() → BuiltinToolResult
|
||||
└─ exported singleton: export const <name>Executor = new <Name>Executor()
|
||||
```
|
||||
|
||||
### Service injection
|
||||
|
||||
`ExecutionRuntime` should declare a TypeScript interface for the services it needs and accept the implementation via constructor. Server callers wire in real implementations; tests wire in mocks. Example from `local-system`:
|
||||
|
||||
```ts
|
||||
export interface ILocalSystemService {
|
||||
readLocalFile: (params: any) => Promise<any>;
|
||||
writeFile: (params: any) => Promise<any>;
|
||||
/* … */
|
||||
}
|
||||
|
||||
export class LocalSystemExecutionRuntime extends ComputerRuntime {
|
||||
constructor(private service: ILocalSystemService) {
|
||||
super();
|
||||
}
|
||||
/* methods delegate to this.service.* */
|
||||
}
|
||||
```
|
||||
|
||||
The `client/executor` instantiates it once with the real service:
|
||||
|
||||
```ts
|
||||
import { localFileService } from '@/services/electron/localFileService';
|
||||
import { LocalSystemExecutionRuntime } from '../../ExecutionRuntime';
|
||||
|
||||
class LocalSystemExecutor extends BaseExecutor<typeof LocalSystemApiEnum> {
|
||||
private runtime = new LocalSystemExecutionRuntime(localFileService);
|
||||
/* … */
|
||||
}
|
||||
```
|
||||
|
||||
### When ExecutionRuntime is the only thing you ship
|
||||
|
||||
Some tools are server-only — there's no frontend executor. `builtin-tool-web-browsing` is the canonical example: only `./` and `./executionRuntime` are exported, no `./executor`, and the runtime is constructed by the server-side `ToolExecutionService`. Skip `client/executor/` entirely for those.
|
||||
|
||||
### When the executor reuses the runtime as-is
|
||||
|
||||
Pure-compute tools (`builtin-tool-calculator`) often have an executor whose ApiName methods call `executor.calculate(args)` and an `ExecutionRuntime` whose methods call `calculatorExecutor.calculate(args)` — same logic, two thin wrappers. That's fine; the duplication buys you the bundle split.
|
||||
|
||||
---
|
||||
|
||||
## The Result Contract
|
||||
|
||||
### `BuiltinServerRuntimeOutput` (what ExecutionRuntime returns)
|
||||
|
||||
```ts
|
||||
{
|
||||
content: string; // the LLM-facing text — never undefined; default to error message
|
||||
state?: any; // result-domain object the UI reads as pluginState
|
||||
success: boolean; // mandatory
|
||||
error?: any; // raw error; the executor will repackage
|
||||
}
|
||||
```
|
||||
|
||||
### `BuiltinToolResult` (what the executor returns to the runtime)
|
||||
|
||||
```ts
|
||||
{
|
||||
success: boolean;
|
||||
content?: string;
|
||||
state?: any;
|
||||
error?: { type: string; message: string; body?: any };
|
||||
metadata?: Record<string, any>; // rare; e.g. { agentCouncil: true }
|
||||
stop?: boolean; // rare; halt the orchestration step
|
||||
}
|
||||
```
|
||||
|
||||
### The `toResult` funnel (mandatory)
|
||||
|
||||
Every executor method returns through a single `toResult()` to enforce two invariants:
|
||||
|
||||
1. **`content` is never undefined.** A missing content collapses downstream into `''`, leaving the Debug pane blank while `pluginState` was already saved. See the `globLocalFiles` regression in `local-system/src/client/executor/index.ts:60-84`.
|
||||
2. **`state` survives failures.** Renderers can keep showing partial output even when `success: false`.
|
||||
|
||||
```ts
|
||||
private toResult(output: BuiltinServerRuntimeOutput): BuiltinToolResult {
|
||||
const errorMessage = typeof output.error?.message === 'string' ? output.error.message : undefined;
|
||||
const safeContent = output.content || errorMessage || 'Tool execution failed';
|
||||
|
||||
if (!output.success) {
|
||||
return {
|
||||
success: false,
|
||||
content: safeContent,
|
||||
state: output.state,
|
||||
error: output.error
|
||||
? { type: 'PluginServerError', message: errorMessage ?? safeContent, body: output.error }
|
||||
: undefined,
|
||||
};
|
||||
}
|
||||
return { success: true, content: safeContent, state: output.state };
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## `BaseExecutor` — How Method Dispatch Works
|
||||
|
||||
`BaseExecutor.invoke(apiName, params, ctx)` does:
|
||||
|
||||
```ts
|
||||
if (!this.hasApi(apiName)) return { error: { type: 'ApiNotFound', … }, success: false };
|
||||
return (this as any)[apiName](params, ctx); // method name MUST equal apiName value
|
||||
```
|
||||
|
||||
So:
|
||||
|
||||
- **Method names must equal `<Name>ApiName` values, exactly.** A typo silently routes to "ApiNotFound".
|
||||
- **Methods must be class fields, not class methods**, because `this` is lost when registry calls `executor.invoke(apiName, params, ctx)`. Always declare as `methodName = async (…) => { … }`.
|
||||
- **Always destructure `apiEnum` and `identifier` as `readonly` instance fields**, not getters — `BaseExecutor.hasApi/getApiNames` reads them synchronously.
|
||||
|
||||
---
|
||||
|
||||
## `BuiltinToolContext` — What the Executor Receives
|
||||
|
||||
The runtime hands every executor method an optional `BuiltinToolContext` as the second argument:
|
||||
|
||||
| Field | Use |
|
||||
| ----------------------------- | -------------------------------------------------------------- |
|
||||
| `agentId` | Default agent for "current agent" semantics (e.g. `listTasks`) |
|
||||
| `groupId` | Group chat scope |
|
||||
| `topicId` | Current topic — needed when creating messages/operations |
|
||||
| `taskId` | Current task identifier — fallback for "implicit" param |
|
||||
| `documentId` | Current page/document scope |
|
||||
| `messageId` | The tool message being created (for state attachments) |
|
||||
| `sourceMessageId` | The user message that triggered this tool turn |
|
||||
| `operationId` | Operation lineage (use for cancellation, tracing) |
|
||||
| `scope` | `'task' \| 'agent' \| …` — toggles default behaviors |
|
||||
| `signal: AbortSignal` | Honor for long-running ops |
|
||||
| `stepContext` | Cross-message runtime state (lobe-agent todos, etc.) |
|
||||
| `registerAfterCompletion(cb)` | Defer side-effects past message-update race |
|
||||
| `groupOrchestration` | Group orchestration callbacks |
|
||||
|
||||
**Use rule:** read with `?.`, fall back to explicit params, **never silently override** an explicit param with a context value.
|
||||
|
||||
---
|
||||
|
||||
## i18n Integration
|
||||
|
||||
Source of truth: `src/locales/default/plugin.ts`. Keys follow `builtins.<identifier>.<topic>.<…>`:
|
||||
|
||||
| Key | Use |
|
||||
| ------------------------------------- | ------------------------------------------------------------ |
|
||||
| `builtins.<identifier>.title` | Display title (overrides `manifest.meta.title` when present) |
|
||||
| `builtins.<identifier>.apiName.<api>` | Inspector header label (one per ApiName) |
|
||||
| `builtins.<identifier>.inspector.<…>` | Extra Inspector strings ("no results", chips, counters) |
|
||||
| `builtins.<identifier>.<feature>.<…>` | Render / Intervention strings, free-form per tool |
|
||||
|
||||
For dev preview, also seed `locales/zh-CN/plugin.json` and `locales/en-US/plugin.json`. Run `pnpm i18n` before opening a PR — it's slow, so do it once at the end. (See the **i18n** skill for the full workflow.)
|
||||
|
||||
---
|
||||
|
||||
## Registry Wiring
|
||||
|
||||
Five core files plus optional ones. Miss any and you'll see "tool not found", a missing chip, a blank result card, a stuck spinner, or an approval dialog that never appears.
|
||||
|
||||
| File | Add what |
|
||||
| -------------------------------------------------- | ----------------------------------------------------------------------------------------- |
|
||||
| **Required** | |
|
||||
| `packages/builtin-tools/src/index.ts` | Import `<Name>Manifest`; push entry to `builtinTools`. Set `hidden`/`discoverable` flags. |
|
||||
| `packages/builtin-tools/src/identifiers.ts` | Add `<Name>Manifest.identifier` to `builtinToolIdentifiers`. |
|
||||
| `packages/builtin-tools/src/inspectors.ts` | Import `<Name>Inspectors, <Name>Manifest`; add to `BuiltinToolInspectors`. |
|
||||
| `src/store/tool/slices/builtin/executors/index.ts` | Import `<name>Executor`; add to `registerExecutors([…])`. |
|
||||
| **Conditional — add only if the surface exists** | |
|
||||
| `packages/builtin-tools/src/renders.ts` | Add to `BuiltinToolsRenders` if any API has a Render. |
|
||||
| `packages/builtin-tools/src/placeholders.ts` | Add to `BuiltinToolPlaceholders` if any API has a Placeholder. |
|
||||
| `packages/builtin-tools/src/streamings.ts` | Add to `BuiltinToolStreamings` if any API has a Streaming renderer. |
|
||||
| `packages/builtin-tools/src/interventions.ts` | Add to `BuiltinToolInterventions` if any API has an Intervention component. |
|
||||
| `packages/builtin-tools/src/portals.ts` | Add to `BuiltinToolsPortals` if the tool has a Portal. |
|
||||
| `packages/builtin-tools/src/displayControls.ts` | Add if Render must show/hide based on result content (rare; see ClaudeCode/Codex). |
|
||||
|
||||
### Optional flags in `packages/builtin-tools/src/index.ts`
|
||||
|
||||
```ts
|
||||
{
|
||||
identifier: TaskManifest.identifier,
|
||||
manifest: TaskManifest,
|
||||
type: 'builtin',
|
||||
hidden: true, // hide from chat-input Tools popover
|
||||
discoverable: false, // exclude from agent builder / skill discovery
|
||||
}
|
||||
```
|
||||
|
||||
Lists in the same file you may need to touch:
|
||||
|
||||
- `defaultToolIds` — added to the agent's tool list by default
|
||||
- `alwaysOnToolIds` — forced on regardless of user selection (use sparingly)
|
||||
- `runtimeManagedToolIds` — enable state controlled by runtime, not user UI; **must mirror the rules map** in `src/server/modules/Mecha/AgentToolsEngine/index.ts` and `src/helpers/toolEngineering/index.ts`
|
||||
|
||||
---
|
||||
|
||||
## File-Map at a Glance
|
||||
|
||||
```
|
||||
packages/builtin-tool-<name>/
|
||||
├── package.json # exports: ., ./client, ./executor, ./executionRuntime
|
||||
└── src/
|
||||
├── index.ts # export Manifest, Identifier, types, systemPrompt
|
||||
├── manifest.ts # BuiltinToolManifest + Identifier const
|
||||
├── types.ts # ApiName + Params/State per API
|
||||
├── systemRole.ts # System prompt (multiple variants OK: systemRole.desktop.ts)
|
||||
├── ExecutionRuntime/
|
||||
│ └── index.ts # <Name>ExecutionRuntime — pure runtime, service injection
|
||||
└── client/
|
||||
├── index.ts # exports for the registries
|
||||
├── executor/
|
||||
│ └── index.ts # <Name>Executor extends BaseExecutor; export <name>Executor
|
||||
├── Inspector/
|
||||
│ ├── index.ts # <Name>Inspectors record
|
||||
│ └── <ApiName>/index.tsx # one folder per API (or .tsx file when trivial)
|
||||
├── Render/
|
||||
│ ├── index.ts # <Name>Renders record
|
||||
│ └── <ApiName>/ # rich renders → folder with subcomponents
|
||||
├── Placeholder/
|
||||
│ ├── index.ts
|
||||
│ └── <ApiName>.tsx # usually a single skeleton file
|
||||
├── Streaming/
|
||||
│ ├── index.ts
|
||||
│ └── <ApiName>/ # live-output renderer
|
||||
├── Intervention/
|
||||
│ ├── index.ts
|
||||
│ └── <ApiName>/ # approval / edit-before-run UI
|
||||
├── Portal/
|
||||
│ ├── index.tsx # routing component (switch on apiName)
|
||||
│ └── <ApiName>/ # full-screen detail view
|
||||
└── components/ # FileItem, EngineAvatar, etc. — shared subcomponents
|
||||
```
|
||||
|
||||
Skip every `client/<surface>/` directory you don't need — empty registries are fine.
|
||||
@@ -1,478 +0,0 @@
|
||||
# Tool Design (Naming, Manifest, Executor, Runtime)
|
||||
|
||||
This doc covers everything that **isn't UI**: the tool's identifier, API surface, manifest, types, system prompt, ExecutionRuntime, and the executor that wires it into the frontend.
|
||||
|
||||
For UI surfaces (Inspector / Render / Placeholder / Streaming / Intervention / Portal), see [ui.md](ui.md).
|
||||
For where files live and how registries work, see [architecture.md](architecture.md).
|
||||
|
||||
---
|
||||
|
||||
## 1. Naming
|
||||
|
||||
| Thing | Convention | Example |
|
||||
| ----------------------- | -------------------------------------------------------------- | ------------------------------------------------------------ |
|
||||
| Package directory | `packages/builtin-tool-<kebab>/` | `builtin-tool-task` |
|
||||
| npm name | `@lobechat/builtin-tool-<kebab>` | `@lobechat/builtin-tool-task` |
|
||||
| Tool `identifier` | `lobe-<kebab-domain>` — **persisted in message history** | `lobe-task`, `lobe-calculator`, `lobe-knowledge-base` |
|
||||
| Identifier const | `<Name>Identifier` exported from `manifest.ts` (or `types.ts`) | `export const TaskIdentifier = 'lobe-task'` |
|
||||
| API name const | `<Name>ApiName` — `as const` object, **camelCase verbs** | `createTask`, `listTasks`, `runTask` |
|
||||
| Executor class | `<Name>Executor extends BaseExecutor<typeof <Name>ApiName>` | `TaskExecutor` |
|
||||
| Executor singleton | `<name>Executor` (camelCase) | `export const taskExecutor = new TaskExecutor()` |
|
||||
| ExecutionRuntime class | `<Name>ExecutionRuntime` | `LocalSystemExecutionRuntime`, `WebBrowsingExecutionRuntime` |
|
||||
| Inspector / Render etc. | `<ApiName>Inspector` / `<ApiName>Render` | `CreateTaskInspector`, `SearchInspector` |
|
||||
|
||||
### Identifier rules
|
||||
|
||||
- **`lobe-` prefix is mandatory** — many switches in the codebase key off it.
|
||||
- Pick a **domain noun**, not a verb (`lobe-task`, not `lobe-task-manager`).
|
||||
- The identifier is **persisted in message history** — renaming after release means the `@deprecated` alias trick (register the legacy identifier as a second key in `inspectors.ts` / `renders.ts` pointing at the new module). Get it right the first time.
|
||||
|
||||
### ApiName rules
|
||||
|
||||
- Verb + noun, camelCase: `createTask`, `viewTask`, `runTasks`.
|
||||
- **Plural variant for batch** (`createTasks`, `runTasks`) — describe in the manifest description that it's preferred over multiple single calls. The system prompt should also push the batch form.
|
||||
- Reserve **clear separation between mutating verbs** (`updateTaskStatus`, `editTask`) and **execution verbs** (`runTask`). The system prompt must warn the model when these are confusable — see `task` for the canonical "do NOT use updateTaskStatus(running) to start a task" warning.
|
||||
- Read-only verbs: `list*`, `view*`, `get*`, `search*`. Mutating: `create*`, `edit*`, `update*`, `delete*`. Triggers/effects: `run*`, `execute*`, `submit*`.
|
||||
|
||||
---
|
||||
|
||||
## 2. `types.ts` — ApiName + Params/State
|
||||
|
||||
Define `<Name>ApiName` as `as const` so it doubles as a runtime enum (used by `BaseExecutor`) and a literal type. Then declare `Params` and `State` per API.
|
||||
|
||||
```ts
|
||||
export const TaskIdentifier = 'lobe-task';
|
||||
|
||||
export const TaskApiName = {
|
||||
createTask: 'createTask',
|
||||
createTasks: 'createTasks',
|
||||
listTasks: 'listTasks',
|
||||
/* …one entry per API, group logically (CRUD then run-style) */
|
||||
} as const;
|
||||
|
||||
export type TaskApiNameType = (typeof TaskApiName)[keyof typeof TaskApiName];
|
||||
|
||||
// One block per API
|
||||
export interface CreateTaskParams {
|
||||
name: string;
|
||||
instruction: string; /* … */
|
||||
}
|
||||
export interface CreateTaskState {
|
||||
identifier?: string;
|
||||
success: boolean;
|
||||
}
|
||||
|
||||
export interface CreateTasksParams {
|
||||
tasks: CreateTaskParams[];
|
||||
}
|
||||
export interface CreateTasksItemResult {
|
||||
error?: string;
|
||||
identifier?: string;
|
||||
name: string;
|
||||
success: boolean;
|
||||
}
|
||||
export interface CreateTasksState {
|
||||
failed: number;
|
||||
results: CreateTasksItemResult[];
|
||||
succeeded: number;
|
||||
}
|
||||
```
|
||||
|
||||
**The result-domain rule for `State`** (memory: "pluginState is result-domain, not call-domain"):
|
||||
|
||||
- Include only fields the UI **renders after the call returns** — ids the LLM didn't have when calling, counts, summary numbers, server-assigned status.
|
||||
- **Don't echo all params.** The Inspector/Render gets `args` for free.
|
||||
- Keep batch results as `{ succeeded, failed, results }` so the Render can show a one-line summary plus a detail list.
|
||||
|
||||
---
|
||||
|
||||
## 3. `manifest.ts` — JSON Schema for the LLM
|
||||
|
||||
```ts
|
||||
import type { BuiltinToolManifest } from '@lobechat/types';
|
||||
|
||||
import { systemPrompt } from './systemRole';
|
||||
import { TaskApiName, TaskIdentifier } from './types';
|
||||
|
||||
export const TaskManifest: BuiltinToolManifest = {
|
||||
identifier: TaskIdentifier,
|
||||
type: 'builtin',
|
||||
systemRole: systemPrompt,
|
||||
meta: {
|
||||
avatar: '📋',
|
||||
title: 'Task Tools',
|
||||
description: 'Create, list, edit, delete tasks with dependencies',
|
||||
readme: 'Optional long description shown in tool detail pages',
|
||||
},
|
||||
api: [
|
||||
{
|
||||
name: TaskApiName.createTask,
|
||||
description:
|
||||
'Create a new task. Optionally attach as a subtask via parentIdentifier. ' +
|
||||
'Prefer createTasks when planning a batch.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
required: ['name', 'instruction'],
|
||||
properties: {
|
||||
name: { type: 'string', description: 'Short, descriptive name.' },
|
||||
instruction: {
|
||||
type: 'string',
|
||||
description: 'Detailed instruction for what the task should accomplish.',
|
||||
},
|
||||
parentIdentifier: {
|
||||
type: 'string',
|
||||
description:
|
||||
'Identifier of the parent task (e.g. "TASK-1"). If provided, the new task becomes a subtask.',
|
||||
},
|
||||
priority: {
|
||||
type: 'number',
|
||||
description: 'Priority level: 0=none, 1=urgent, 2=high, 3=normal, 4=low. Default is 0.',
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
/* …one entry per ApiName */
|
||||
],
|
||||
};
|
||||
```
|
||||
|
||||
### Manifest writing checklist
|
||||
|
||||
- **Every API in `<Name>ApiName` has exactly one entry in `api[]`.** Easy to drift after a refactor.
|
||||
- **`description` on each API is the model's only docs.** Make it long enough for the LLM to pick the right tool. Mention edge cases ("If you provide any filter, omitted filters are not applied implicitly"), defaults, and the relationship to sibling APIs ("To START a task, use runTask — updateTaskStatus only flips a flag").
|
||||
- **`parameters` is JSON Schema** (`LobeChatPluginApi`). Use `enum`, `required`, `items`, `oneOf`, `additionalProperties: false` etc. — these survive into the LLM's tool spec.
|
||||
- **Use `additionalProperties: false`** on parameter objects so the model can't sneak unknown fields past validation.
|
||||
- **Number parameters with semantic values** (`priority: 0=none, 1=urgent, …`) should describe the mapping in the description. Don't rely on `enum` alone for numbers — the model often fills the wrong one.
|
||||
- **`enum` arrays for known string sets** (statuses, categories, engines). Spread from a constants module (`enum: [...TASK_STATUSES]`) so the manifest stays in sync.
|
||||
|
||||
### Optional manifest fields
|
||||
|
||||
```ts
|
||||
{
|
||||
/* Where this tool can run.
|
||||
'client' → Agent Gateway dispatches to the desktop client (filesystem, Electron only)
|
||||
'server' → ToolExecutionService runs it on the server
|
||||
omitted → server only */
|
||||
executors: ['client', 'server'],
|
||||
|
||||
/* Default human intervention policy for all APIs that don't specify one.
|
||||
Pair with an Intervention component (see ui.md). */
|
||||
humanIntervention: 'never' | 'always' | { /* extended config */ },
|
||||
}
|
||||
```
|
||||
|
||||
Per-API `humanIntervention` and `renderDisplayControl` go inside each `api[]` entry.
|
||||
|
||||
---
|
||||
|
||||
## 4. `systemRole.ts` — Operator Instructions for the Model
|
||||
|
||||
This is appended to the agent system prompt whenever the tool is enabled. Treat it as a **how-to-use guide for the LLM**, not marketing copy.
|
||||
|
||||
```ts
|
||||
export const systemPrompt = `You have access to Task management tools. Use them to:
|
||||
|
||||
- **createTask**: Create a new task. Use parentIdentifier to make it a subtask.
|
||||
- **createTasks**: Prefer this over multiple createTask calls when planning a batch
|
||||
(e.g. all subtasks under one parent, or all chapters of an outline).
|
||||
- **runTask**: Actually START a task — kicks off the agent in a new (or continued)
|
||||
topic. Do NOT use updateTaskStatus(running) to start a task; that only flips a
|
||||
flag without executing. The task must have an assigneeAgentId.
|
||||
- **updateTaskStatus**: Change a task's status (completed/cancelled/paused/failed).
|
||||
If you mark a task as failed, include an error message explaining why.
|
||||
- ...
|
||||
|
||||
When planning work:
|
||||
1. Create tasks for each major piece (use parentIdentifier to organize as subtasks).
|
||||
2. Use editTask with addDependencies to control execution order.
|
||||
3. Use updateTaskStatus to mark the current task completed when done.`;
|
||||
```
|
||||
|
||||
### Patterns that work well
|
||||
|
||||
- **Bulleted list, bold the API name, one line per API.** The model picks tools by skimming.
|
||||
- **Disambiguate confusable APIs explicitly** (`runTask` vs `updateTaskStatus`).
|
||||
- **Push toward batched APIs** ("Prefer this when…").
|
||||
- **End with a numbered workflow** if the tool has a typical sequence.
|
||||
- **For tools with multiple environments** (e.g. desktop vs cloud), keep variants in `systemRole.ts` and `systemRole.desktop.ts` and pick at the manifest level. See `builtin-tool-local-system`.
|
||||
|
||||
### Dynamic system prompts
|
||||
|
||||
If the prompt depends on runtime state (current date, available models), export a function and call it in the manifest:
|
||||
|
||||
```ts
|
||||
// systemRole.ts
|
||||
export const systemPrompt = (today: string) => `Today is ${today}. You have web search tools…`;
|
||||
|
||||
// manifest.ts
|
||||
import dayjs from 'dayjs';
|
||||
systemRole: systemPrompt(dayjs(new Date()).format('YYYY-MM-DD')),
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. `ExecutionRuntime/index.ts` — Pure Runtime
|
||||
|
||||
This is **the default home for new tool logic** going forward. The runtime is a class that:
|
||||
|
||||
- Has no React, no Zustand, no `@/services/...` direct imports.
|
||||
- Receives services as **constructor injection** (or as method args).
|
||||
- Returns `BuiltinServerRuntimeOutput` from each method.
|
||||
- Is unit-testable by passing in mocks.
|
||||
|
||||
### Pattern A: Inject a service interface
|
||||
|
||||
Use when the runtime calls out to IPC, network, or DB.
|
||||
|
||||
```ts
|
||||
// ExecutionRuntime/index.ts
|
||||
import type { BuiltinServerRuntimeOutput } from '@lobechat/types';
|
||||
|
||||
export interface IWebBrowsingService {
|
||||
search: (q: SearchQuery) => Promise<UniformSearchResponse>;
|
||||
crawlPages: (urls: string[]) => Promise<CrawlResults>;
|
||||
}
|
||||
|
||||
export interface WebBrowsingRuntimeOptions {
|
||||
searchService: IWebBrowsingService;
|
||||
documentService?: WebBrowsingDocumentService;
|
||||
agentId?: string;
|
||||
topicId?: string;
|
||||
}
|
||||
|
||||
export class WebBrowsingExecutionRuntime {
|
||||
constructor(private opts: WebBrowsingRuntimeOptions) {}
|
||||
|
||||
async search(
|
||||
args: SearchQuery,
|
||||
options?: { signal?: AbortSignal },
|
||||
): Promise<BuiltinServerRuntimeOutput> {
|
||||
try {
|
||||
const data = await this.opts.searchService.search(args, options);
|
||||
if (data.errorDetail) {
|
||||
return {
|
||||
success: false,
|
||||
content: data.errorDetail,
|
||||
error: { message: data.errorDetail },
|
||||
state: data,
|
||||
};
|
||||
}
|
||||
return {
|
||||
success: true,
|
||||
content: searchResultsPrompt(data.results.slice(0, 10)),
|
||||
state: data,
|
||||
};
|
||||
} catch (e) {
|
||||
return { success: false, content: (e as Error).message, error: e };
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Pattern B: Reuse the executor
|
||||
|
||||
Use when the same logic runs in browser and Node (e.g. mathjs, nerdamer). The runtime is a thin wrapper that imports the executor and re-types the state per API. See `builtin-tool-calculator/src/ExecutionRuntime/index.ts` for the canonical example.
|
||||
|
||||
### Pattern C: Extend a shared base
|
||||
|
||||
When you're implementing a domain that already has a base runtime (file ops via `ComputerRuntime`), extend and only override `callService` + result normalization. See `builtin-tool-local-system/src/ExecutionRuntime/index.ts`.
|
||||
|
||||
### Runtime contract
|
||||
|
||||
Every method returns:
|
||||
|
||||
```ts
|
||||
{
|
||||
content: string; // LLM-facing — never undefined; default to error message
|
||||
state?: any; // result-domain — what the UI's pluginState becomes
|
||||
success: boolean; // mandatory
|
||||
error?: any; // raw error object; the executor will repackage
|
||||
}
|
||||
```
|
||||
|
||||
Use `@lobechat/prompts` formatters (`searchResultsPrompt`, `crawlResultsPrompt`, `formatTaskCreated`, etc.) to produce structured `content`. They emit XML/markdown that's already tuned for token efficiency.
|
||||
|
||||
---
|
||||
|
||||
## 6. `client/executor/index.ts` — Frontend Wiring
|
||||
|
||||
The executor's job is to **resolve frontend defaults** (current agent, current task, scope) and **call the runtime**. It then funnels through `toResult()` into the `BuiltinToolResult` shape.
|
||||
|
||||
```ts
|
||||
import { BaseExecutor, type BuiltinToolContext, type BuiltinToolResult } from '@lobechat/types';
|
||||
import debug from 'debug';
|
||||
|
||||
import { taskService } from '@/services/task';
|
||||
import { getTaskStoreState } from '@/store/task';
|
||||
|
||||
import { TaskIdentifier } from '../../manifest';
|
||||
import { TaskApiName, type CreateTaskParams } from '../../types';
|
||||
|
||||
const log = debug('lobe-task:executor');
|
||||
|
||||
class TaskExecutor extends BaseExecutor<typeof TaskApiName> {
|
||||
readonly identifier = TaskIdentifier;
|
||||
protected readonly apiEnum = TaskApiName;
|
||||
|
||||
// ⚠ class FIELD, not a method — preserves `this` when invoked via registry
|
||||
createTask = async (
|
||||
params: CreateTaskParams,
|
||||
ctx?: BuiltinToolContext,
|
||||
): Promise<BuiltinToolResult> => {
|
||||
try {
|
||||
log('createTask params=%o', params);
|
||||
const task = await getTaskStoreState().createTask({
|
||||
name: params.name,
|
||||
instruction: params.instruction,
|
||||
// Default assignee from context — never silently override an explicit value
|
||||
assigneeAgentId:
|
||||
params.assigneeAgentId ?? (ctx?.scope === 'task' ? undefined : ctx?.agentId),
|
||||
parentTaskId: params.parentIdentifier?.trim() || undefined,
|
||||
priority: params.priority,
|
||||
});
|
||||
|
||||
if (!task) return this.errorResult('Failed to create task', 'CreateFailed');
|
||||
|
||||
return {
|
||||
success: true,
|
||||
content: formatTaskCreated({ identifier: task.identifier, name: task.name /* … */ }),
|
||||
state: { identifier: task.identifier, success: true },
|
||||
};
|
||||
} catch (error) {
|
||||
return this.errorResult(error, 'CreateTaskFailed');
|
||||
}
|
||||
};
|
||||
|
||||
private errorResult(err: unknown, type: string): BuiltinToolResult {
|
||||
const message = err instanceof Error ? err.message : String(err) || 'Unknown error';
|
||||
return { success: false, content: `Failed: ${message}`, error: { type, message } };
|
||||
}
|
||||
}
|
||||
|
||||
export const taskExecutor = new TaskExecutor();
|
||||
```
|
||||
|
||||
### Hard rules
|
||||
|
||||
1. **Methods are class fields** (`name = async (…) => {…}`), not class methods. The registry calls `(executor as any)[apiName](params, ctx)`; arrow-function fields keep `this` bound.
|
||||
2. **`identifier` and `apiEnum` are `readonly` instance fields**, not getters — `BaseExecutor.hasApi/getApiNames` reads them synchronously at registration time.
|
||||
3. **Default missing params from `ctx`**, but never silently override explicit values. Use `params.foo ?? ctx?.foo`, not `ctx?.foo ?? params.foo`.
|
||||
4. **One funnel for all returns.** Either always return through `toResult(runtime.x())` (when delegating) or through `errorResult(…)` for the catch arm. Never inline `{ success: false, content: '' }` — `content: ''` collapses the Debug pane to blank.
|
||||
5. **`debug('lobe-<name>:executor')`.** Match the namespace to the identifier minus `lobe-` when convenient.
|
||||
6. **Singleton export.** `export const <name>Executor = new <Name>Executor()` — the registry imports the instance, not the class.
|
||||
|
||||
### When the executor delegates to ExecutionRuntime
|
||||
|
||||
```ts
|
||||
class LocalSystemExecutor extends BaseExecutor<typeof LocalSystemApiEnum> {
|
||||
readonly identifier = LocalSystemIdentifier;
|
||||
protected readonly apiEnum = LocalSystemApiEnum;
|
||||
private runtime = new LocalSystemExecutionRuntime(localFileService);
|
||||
|
||||
readLocalFile = async (params: LocalReadFileParams): Promise<BuiltinToolResult> => {
|
||||
try {
|
||||
const result = await this.runtime.readFile({
|
||||
path: params.path,
|
||||
startLine: params.loc?.[0],
|
||||
endLine: params.loc?.[1],
|
||||
});
|
||||
return this.toResult(result);
|
||||
} catch (error) {
|
||||
return this.errorResult(error);
|
||||
}
|
||||
};
|
||||
|
||||
private toResult(out: BuiltinServerRuntimeOutput): BuiltinToolResult {
|
||||
const errMsg = typeof out.error?.message === 'string' ? out.error.message : undefined;
|
||||
const safe = out.content || errMsg || 'Tool execution failed';
|
||||
if (!out.success) {
|
||||
return {
|
||||
success: false,
|
||||
content: safe,
|
||||
state: out.state, // ← preserve partial state on failure
|
||||
error: out.error
|
||||
? { type: 'PluginServerError', message: errMsg ?? safe, body: out.error }
|
||||
: undefined,
|
||||
};
|
||||
}
|
||||
return { success: true, content: safe, state: out.state };
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The `toResult` funnel is **mandatory**: it enforces never-undefined `content` and partial-state preservation. Both invariants caught real production bugs (`globLocalFiles` Response empty, `editLocalFile` partial state lost).
|
||||
|
||||
---
|
||||
|
||||
## 7. `index.ts` — Package Entry Point
|
||||
|
||||
Keep it pure data + the manifest. **No React, no stores, no Node-only imports.**
|
||||
|
||||
```ts
|
||||
export { TaskIdentifier, TaskManifest } from './manifest';
|
||||
export { systemPrompt } from './systemRole';
|
||||
export {
|
||||
TaskApiName,
|
||||
type TaskApiNameType,
|
||||
type CreateTaskParams,
|
||||
type CreateTaskState,
|
||||
/* …all Params/State types */
|
||||
} from './types';
|
||||
|
||||
// Optional helpers used by both the runtime and the UI
|
||||
export { TASK_STATUSES, UNFINISHED_TASK_STATUSES } from './constants';
|
||||
```
|
||||
|
||||
This entry is what `packages/builtin-tools/src/index.ts` and `identifiers.ts` import — it must be importable from server bundles.
|
||||
|
||||
---
|
||||
|
||||
## 8. `package.json`
|
||||
|
||||
```json
|
||||
{
|
||||
"dependencies": {
|
||||
"@lobechat/prompts": "workspace:*"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@lobechat/types": "workspace:*"
|
||||
},
|
||||
"exports": {
|
||||
".": "./src/index.ts",
|
||||
"./client": "./src/client/index.ts",
|
||||
"./executor": "./src/client/executor/index.ts",
|
||||
"./executionRuntime": "./src/ExecutionRuntime/index.ts"
|
||||
},
|
||||
"main": "./src/index.ts",
|
||||
"name": "@lobechat/builtin-tool-<name>",
|
||||
"peerDependencies": {
|
||||
"@lobehub/ui": "^5",
|
||||
"antd": "^6",
|
||||
"antd-style": "*",
|
||||
"lucide-react": "*",
|
||||
"react": "*",
|
||||
"react-i18next": "*"
|
||||
},
|
||||
"private": true,
|
||||
"version": "1.0.0"
|
||||
}
|
||||
```
|
||||
|
||||
**Why peer not direct deps for client libs:** the `./` and `./executionRuntime` entry points must be importable from server code. Listing React etc. as peer deps prevents bundlers from following them when only the runtime is consumed.
|
||||
|
||||
**Skip `./executor`** if the package has no frontend executor (server-only tools like `builtin-tool-web-browsing`).
|
||||
|
||||
---
|
||||
|
||||
## 9. Common Pitfalls
|
||||
|
||||
| Symptom | Likely cause |
|
||||
| ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
|
||||
| "ApiNotFound" at runtime | Method name in executor doesn't match `ApiName` value (typo, wrong case) |
|
||||
| Method works once, then "this is undefined" | Method declared as `async fn() {}` instead of `fn = async () => {}` — `this` lost when registry invokes |
|
||||
| Debug "Response" pane blank but `pluginState` populated | Returning `content: ''` or letting `output.content` be undefined — use the `toResult` funnel |
|
||||
| Partial result vanishes on failure | `toResult` discarded `state` when `success: false`; preserve it |
|
||||
| Tool shows up but doesn't run on desktop | `executors` in manifest doesn't include `'client'` (or vice versa for server-only) |
|
||||
| Same tool registered twice / legacy identifier ghost | Identifier collision; check `@deprecated` aliases in `inspectors.ts`/`renders.ts` |
|
||||
| Manifest test fails after adding API | Forgot to add the corresponding i18n `apiName.<api>` key |
|
||||
| TypeScript error on `BaseExecutor<typeof X>` | `X` declared with `enum` instead of `as const` object — must be the const-object form |
|
||||
@@ -1,721 +0,0 @@
|
||||
# Tool UI Surfaces
|
||||
|
||||
A builtin tool can ship up to **six client-side surfaces**, each with a different role in the chat UI. Only `Inspector` is required; the other five are added on demand and registered in their own central files.
|
||||
|
||||
| Surface | Required? | When the chat shows it | Registered in |
|
||||
| ------------ | --------- | --------------------------------------------------------------------- | --------------------------------------------- |
|
||||
| Inspector | ✅ Always | Header strip of every tool call (one-line chip) | `packages/builtin-tools/src/inspectors.ts` |
|
||||
| Render | Optional | Rich result card below the header, after the call returns | `packages/builtin-tools/src/renders.ts` |
|
||||
| Placeholder | Optional | Skeleton between "args streaming complete" and "result arrives" | `packages/builtin-tools/src/placeholders.ts` |
|
||||
| Streaming | Optional | Live output during execution (e.g. command stdout) | `packages/builtin-tools/src/streamings.ts` |
|
||||
| Intervention | Optional | Approval / edit-before-run dialog (when `humanIntervention` triggers) | `packages/builtin-tools/src/interventions.ts` |
|
||||
| Portal | Optional | Full-screen detail view (right-side or modal) | `packages/builtin-tools/src/portals.ts` |
|
||||
|
||||
The two reference tools to read end-to-end:
|
||||
|
||||
- **`builtin-tool-web-browsing/src/client/`** — Inspector + Render + Placeholder + Portal (no Intervention/Streaming).
|
||||
- **`builtin-tool-local-system/src/client/`** — all six surfaces, including `components/` for shared building blocks.
|
||||
|
||||
---
|
||||
|
||||
## 0. Shared Style Rules
|
||||
|
||||
These apply across every surface.
|
||||
|
||||
### 0.1 Use `'use client'` at the top of every component file
|
||||
|
||||
Tool surfaces are leaves in the chat tree and must not block server rendering.
|
||||
|
||||
### 0.2 Prefer `createStaticStyles + cssVar.*`
|
||||
|
||||
Zero-runtime CSS-in-JS — the styles compile once and read CSS variables at runtime.
|
||||
|
||||
```tsx
|
||||
import { createStaticStyles, cssVar } from 'antd-style';
|
||||
|
||||
const styles = createStaticStyles(({ css, cssVar }) => ({
|
||||
chip: css`
|
||||
padding-block: 2px;
|
||||
padding-inline: 8px;
|
||||
border-radius: 999px;
|
||||
color: ${cssVar.colorText};
|
||||
background: ${cssVar.colorFillTertiary};
|
||||
`,
|
||||
}));
|
||||
```
|
||||
|
||||
Fall back to `createStyles + token` only when you need runtime token computation (rare). Inline `style={{ color: cssVar.colorTextSecondary }}` is fine for one-off dynamic values.
|
||||
|
||||
### 0.3 Use `@lobehub/ui`, not raw `antd`
|
||||
|
||||
`Block`, `Text`, `Flexbox`, `Highlighter`, `Alert`, `Tooltip`, `Skeleton` all come from `@lobehub/ui`. Modals come from `@lobehub/ui/base-ui` (`createModal`, `useModalContext`, `confirmModal`) — see the **modal** skill.
|
||||
|
||||
Memory note: `@lobehub/ui`'s `<Text type='secondary'>` is a lighter shade than `colorTextSecondary`. If you need that exact token color, write `<Text style={{ color: cssVar.colorTextSecondary }}>`.
|
||||
|
||||
### 0.4 Always `memo` and set `displayName`
|
||||
|
||||
```tsx
|
||||
export const SearchInspector = memo<BuiltinInspectorProps<SearchQuery, UniformSearchResponse>>(
|
||||
({ args /* … */ }) => {
|
||||
/* … */
|
||||
},
|
||||
);
|
||||
SearchInspector.displayName = 'SearchInspector';
|
||||
export default SearchInspector;
|
||||
```
|
||||
|
||||
### 0.5 Always type with `BuiltinXProps<Args, State>` generics
|
||||
|
||||
Don't widen to `any`. The Args generic is the JSON Schema params, the State generic is the executor's `state` field. The two should match `<Name>Params` and `<Name>State` from `types.ts`.
|
||||
|
||||
### 0.6 Pull strings from `t('plugin')`
|
||||
|
||||
```tsx
|
||||
const { t } = useTranslation('plugin');
|
||||
t('builtins.<identifier>.apiName.<api>');
|
||||
```
|
||||
|
||||
Every Inspector should default to `t('builtins.<identifier>.apiName.<api>')` so it shows something while args stream in.
|
||||
|
||||
### 0.7 Read store state from `@/store/chat`, not props
|
||||
|
||||
Tool surfaces sometimes need cross-cutting state (loading, streaming buffer). Read it inside the component via Zustand selectors, not from props — props only carry args/state/messageId.
|
||||
|
||||
---
|
||||
|
||||
## 1. Inspector — Header Chip (required)
|
||||
|
||||
**Lifecycle:** Inspector renders for **every phase** of a tool call: while args are streaming in, while the executor is running, and after results come back. It's the only surface that's always visible.
|
||||
|
||||
**Goal:** keep it to a single line. Show what's happening with as much context as is currently available.
|
||||
|
||||
### Props (`BuiltinInspectorProps<Args, State>`)
|
||||
|
||||
```ts
|
||||
interface BuiltinInspectorProps<Arguments = any, State = any> {
|
||||
apiName: string;
|
||||
args: Arguments; // final args (only after the assistant stops streaming)
|
||||
identifier: string;
|
||||
isArgumentsStreaming?: boolean; // args still arriving
|
||||
isLoading?: boolean; // args complete, executor running
|
||||
partialArgs?: Arguments; // partial JSON during streaming
|
||||
pluginState?: State; // executor's `state` after success
|
||||
result?: { content: string | null; error?: any };
|
||||
}
|
||||
```
|
||||
|
||||
### State machine
|
||||
|
||||
| Phase | What's available | What to show |
|
||||
| ----------------------------------- | ---------------------------------------------------------- | ---------------------------------------------------------- |
|
||||
| Args streaming, no useful field yet | `isArgumentsStreaming === true`, `partialArgs.X` undefined | Just the API title with `shinyTextStyles.shinyText` |
|
||||
| Args streaming, key field arrived | `partialArgs.X` populated | Title + key field chip, still pulse-animated |
|
||||
| Args complete, executor running | `args` populated, `isLoading === true` | Same as above, still pulse-animated |
|
||||
| Result arrived | `pluginState` populated, `isLoading === false` | Title + chips + result summary (count, identifier, status) |
|
||||
|
||||
### Canonical example — Search
|
||||
|
||||
`packages/builtin-tool-web-browsing/src/client/Inspector/Search/index.tsx`:
|
||||
|
||||
```tsx
|
||||
'use client';
|
||||
|
||||
import type { BuiltinInspectorProps, SearchQuery, UniformSearchResponse } from '@lobechat/types';
|
||||
import { Text } from '@lobehub/ui';
|
||||
import { cssVar, cx } from 'antd-style';
|
||||
import { memo } from 'react';
|
||||
import { useTranslation } from 'react-i18next';
|
||||
|
||||
import { highlightTextStyles, inspectorTextStyles, shinyTextStyles } from '@/styles';
|
||||
|
||||
export const SearchInspector = memo<BuiltinInspectorProps<SearchQuery, UniformSearchResponse>>(
|
||||
({ args, partialArgs, isArgumentsStreaming, isLoading, pluginState }) => {
|
||||
const { t } = useTranslation('plugin');
|
||||
|
||||
const query = args?.query || partialArgs?.query || '';
|
||||
const resultCount = pluginState?.results?.length ?? 0;
|
||||
const hasResults = resultCount > 0;
|
||||
|
||||
if (isArgumentsStreaming && !query) {
|
||||
return (
|
||||
<div className={cx(inspectorTextStyles.root, shinyTextStyles.shinyText)}>
|
||||
<span>{t('builtins.lobe-web-browsing.apiName.search')}</span>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
return (
|
||||
<div
|
||||
className={cx(
|
||||
inspectorTextStyles.root,
|
||||
(isArgumentsStreaming || isLoading) && shinyTextStyles.shinyText,
|
||||
)}
|
||||
>
|
||||
<span>{t('builtins.lobe-web-browsing.apiName.search')}: </span>
|
||||
{query && <span className={highlightTextStyles.primary}>{query}</span>}
|
||||
{!isLoading &&
|
||||
!isArgumentsStreaming &&
|
||||
pluginState?.results &&
|
||||
(hasResults ? (
|
||||
<span style={{ marginInlineStart: 4 }}>({resultCount})</span>
|
||||
) : (
|
||||
<Text as="span" color={cssVar.colorTextDescription} fontSize={12}>
|
||||
({t('builtins.lobe-web-browsing.inspector.noResults')})
|
||||
</Text>
|
||||
))}
|
||||
</div>
|
||||
);
|
||||
},
|
||||
);
|
||||
SearchInspector.displayName = 'SearchInspector';
|
||||
export default SearchInspector;
|
||||
```
|
||||
|
||||
### Inspector rules
|
||||
|
||||
- Wrap the whole row with `inspectorTextStyles.root` (provides correct flex / line-height baseline).
|
||||
- Pulse with `shinyTextStyles.shinyText` whenever `isArgumentsStreaming || isLoading`.
|
||||
- Show the i18n title first so the row is non-empty during the earliest streaming phase.
|
||||
- Read both `args?.X` and `partialArgs?.X` together — `args` is final, `partialArgs` is in-stream.
|
||||
- Use chips/tags for distinct facets (identifier, name, parent, status, count). Each chip should clip with `text-overflow: ellipsis` and have a `max-width` so long values don't blow out the chat bubble.
|
||||
- Append `pluginState`-derived suffixes only **after** loading finishes — count or "(no results)" should not appear while still searching.
|
||||
|
||||
### Inspector registry — `client/Inspector/index.ts`
|
||||
|
||||
```ts
|
||||
import type { BuiltinInspector } from '@lobechat/types';
|
||||
|
||||
import { TaskApiName } from '../../types';
|
||||
import { CreateTaskInspector } from './CreateTask';
|
||||
import { ListTasksInspector } from './ListTasks';
|
||||
/* … */
|
||||
|
||||
export const TaskInspectors: Record<string, BuiltinInspector> = {
|
||||
[TaskApiName.createTask]: CreateTaskInspector as BuiltinInspector,
|
||||
[TaskApiName.listTasks]: ListTasksInspector as BuiltinInspector,
|
||||
/* one entry per ApiName */
|
||||
};
|
||||
|
||||
export { CreateTaskInspector } from './CreateTask';
|
||||
export { ListTasksInspector } from './ListTasks';
|
||||
/* re-export each */
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Render — Rich Result Card (optional)
|
||||
|
||||
**Lifecycle:** rendered **once the result arrives** (after Placeholder/Streaming hand off). Sits below the Inspector header.
|
||||
|
||||
**Skip if** the API is read-only or the result is just text — the framework already shows the executor's `content` string. Add a Render only when there's a structured artifact worth seeing: a card, a chart, a diff, a list of files.
|
||||
|
||||
### Props (`BuiltinRenderProps<Args, State, Content>`)
|
||||
|
||||
```ts
|
||||
interface BuiltinRenderProps<Arguments = any, State = any, Content = any> {
|
||||
apiName?: string;
|
||||
args: Arguments; // final params from the LLM
|
||||
content: Content; // executor's content string (or parsed)
|
||||
identifier?: string;
|
||||
messageId: string; // for store lookups
|
||||
pluginError?: any; // from BuiltinToolResult.error
|
||||
pluginState?: State; // executor's state
|
||||
toolCallId?: string;
|
||||
}
|
||||
```
|
||||
|
||||
### Two patterns
|
||||
|
||||
**Pattern A — Single-file Render** (web-browsing CrawlSinglePage):
|
||||
|
||||
```tsx
|
||||
// client/Render/CrawlSinglePage.tsx
|
||||
import type { BuiltinRenderProps, CrawlPluginState, CrawlSinglePageQuery } from '@lobechat/types';
|
||||
import { memo } from 'react';
|
||||
|
||||
import PageContent from './PageContent';
|
||||
|
||||
const CrawlSinglePage = memo<BuiltinRenderProps<CrawlSinglePageQuery, CrawlPluginState>>(
|
||||
({ messageId, pluginState, args }) => (
|
||||
<PageContent messageId={messageId} results={pluginState?.results} urls={[args?.url]} />
|
||||
),
|
||||
);
|
||||
export default CrawlSinglePage;
|
||||
```
|
||||
|
||||
**Pattern B — Folder with subcomponents** (web-browsing Search):
|
||||
|
||||
```
|
||||
client/Render/Search/
|
||||
├── index.tsx # composes the subcomponents, handles error states
|
||||
├── ConfigForm.tsx # appears when pluginError.type === 'PluginSettingsInvalid'
|
||||
├── SearchQuery.tsx # editable query header
|
||||
└── SearchResult.tsx # result list
|
||||
```
|
||||
|
||||
Use Pattern B when the Render has internal state (editing mode, expanded items), error variants, or is large enough to benefit from splitting.
|
||||
|
||||
### Error handling in Render
|
||||
|
||||
Renders are the canonical place to surface `pluginError` because the chat doesn't auto-render typed errors:
|
||||
|
||||
```tsx
|
||||
if (pluginError) {
|
||||
if (pluginError?.type === 'PluginSettingsInvalid') {
|
||||
return <ConfigForm id={messageId} provider={pluginError.body?.provider} />;
|
||||
}
|
||||
return (
|
||||
<Alert
|
||||
title={pluginError?.message}
|
||||
type="error"
|
||||
extra={<Highlighter language="json">{JSON.stringify(pluginError.body, null, 2)}</Highlighter>}
|
||||
/>
|
||||
);
|
||||
}
|
||||
```
|
||||
|
||||
### Render rules
|
||||
|
||||
- **Return `null`** if there's nothing useful to draw yet (avoids empty cards during stream).
|
||||
- Use `pluginState` for server-truth (ids, counts, server-assigned status) and `args` for what the LLM asked. **Combine — neither alone is enough.**
|
||||
- For lists, summarize with a header line and show top N items with a "+N more" tail rather than rendering everything.
|
||||
- For modals from a Render, use `@lobehub/ui/base-ui` (`createModal`, `useModalContext`, `confirmModal`) — see the **modal** skill.
|
||||
|
||||
### Render registry — `client/Render/index.ts`
|
||||
|
||||
```ts
|
||||
import type { BuiltinRender } from '@lobechat/types';
|
||||
|
||||
import { TaskApiName } from '../../types';
|
||||
import CreateTaskRender from './CreateTask';
|
||||
import RunTasksRender from './RunTasks';
|
||||
|
||||
export const TaskRenders: Record<string, BuiltinRender> = {
|
||||
[TaskApiName.createTask]: CreateTaskRender as BuiltinRender,
|
||||
[TaskApiName.runTasks]: RunTasksRender as BuiltinRender,
|
||||
/* only the APIs with rich result UI — others fall back to text content */
|
||||
};
|
||||
|
||||
export { default as CreateTaskRender } from './CreateTask';
|
||||
export { default as RunTasksRender } from './RunTasks';
|
||||
```
|
||||
|
||||
### Render display control (rare)
|
||||
|
||||
If the Render should hide for certain results (e.g. ClaudeCode's TodoWrite hides when the agent is mid-stream), add a `RenderDisplayControl` to `packages/builtin-tools/src/displayControls.ts`. See `ClaudeCodeRenderDisplayControls` for the pattern.
|
||||
|
||||
---
|
||||
|
||||
## 3. Placeholder — Skeleton Between Args and Result (optional)
|
||||
|
||||
**Lifecycle:** rendered when the args have finished streaming but the executor hasn't returned yet. Disappears when `pluginState` arrives. Bridges the moment of perceived lag.
|
||||
|
||||
**Add for** APIs with noticeable execution time: web search, network crawl, file list, large grep. **Skip for** instant ops (status flips, calculator).
|
||||
|
||||
### Props (`BuiltinPlaceholderProps<Args>`)
|
||||
|
||||
```ts
|
||||
interface BuiltinPlaceholderProps<T extends Record<string, any> = any> {
|
||||
apiName: string;
|
||||
args?: T;
|
||||
identifier: string;
|
||||
}
|
||||
```
|
||||
|
||||
No `pluginState` — Placeholder lives entirely in the "executing" gap.
|
||||
|
||||
### Canonical example — Search Placeholder
|
||||
|
||||
`packages/builtin-tool-web-browsing/src/client/Placeholder/Search.tsx`:
|
||||
|
||||
```tsx
|
||||
import type { BuiltinPlaceholderProps, SearchQuery } from '@lobechat/types';
|
||||
import { Flexbox, Icon, Skeleton } from '@lobehub/ui';
|
||||
import { createStaticStyles, cx } from 'antd-style';
|
||||
import { SearchIcon } from 'lucide-react';
|
||||
import { memo } from 'react';
|
||||
|
||||
import { useIsMobile } from '@/hooks/useIsMobile';
|
||||
import { shinyTextStyles } from '@/styles';
|
||||
|
||||
const styles = createStaticStyles(({ css, cssVar }) => ({
|
||||
query: cx(
|
||||
css`
|
||||
padding: 4px 8px;
|
||||
border-radius: 8px;
|
||||
font-size: 12px;
|
||||
color: ${cssVar.colorTextSecondary};
|
||||
&:hover {
|
||||
background: ${cssVar.colorFillTertiary};
|
||||
}
|
||||
`,
|
||||
shinyTextStyles.shinyText,
|
||||
),
|
||||
}));
|
||||
|
||||
export const Search = memo<BuiltinPlaceholderProps<SearchQuery>>(({ args }) => {
|
||||
const { query } = args || {};
|
||||
const isMobile = useIsMobile();
|
||||
|
||||
return (
|
||||
<Flexbox gap={8}>
|
||||
<Flexbox horizontal={!isMobile} gap={isMobile ? 8 : 40}>
|
||||
<Flexbox horizontal align="center" className={styles.query} gap={8}>
|
||||
<Icon icon={SearchIcon} />
|
||||
{query ? query : <Skeleton.Block active style={{ height: 20, width: 40 }} />}
|
||||
</Flexbox>
|
||||
<Skeleton.Block active style={{ height: 20, width: 40 }} />
|
||||
</Flexbox>
|
||||
<Flexbox horizontal gap={12}>
|
||||
{[1, 2, 3, 4, 5].map((id) => (
|
||||
<Skeleton.Button active key={id} style={{ borderRadius: 8, height: 80, width: 160 }} />
|
||||
))}
|
||||
</Flexbox>
|
||||
</Flexbox>
|
||||
);
|
||||
});
|
||||
```
|
||||
|
||||
### Placeholder rules
|
||||
|
||||
- **Mirror the eventual Render's layout.** When the result arrives the Placeholder unmounts and the Render mounts; if they share dimensions, the chat doesn't jump.
|
||||
- Use `Skeleton.Block` / `Skeleton.Button` from `@lobehub/ui` for placeholder shapes.
|
||||
- Embed any args you have (e.g. the query text) — context helps the user know what's loading.
|
||||
- Pulse with `shinyTextStyles.shinyText` if the Placeholder includes literal text.
|
||||
|
||||
### Placeholder registry — `client/Placeholder/index.ts`
|
||||
|
||||
```ts
|
||||
import { WebBrowsingApiName } from '../../types';
|
||||
import CrawlMultiPages from './CrawlMultiPages';
|
||||
import CrawlSinglePage from './CrawlSinglePage';
|
||||
import { Search } from './Search';
|
||||
|
||||
export const WebBrowsingPlaceholders = {
|
||||
[WebBrowsingApiName.crawlMultiPages]: CrawlMultiPages,
|
||||
[WebBrowsingApiName.crawlSinglePage]: CrawlSinglePage,
|
||||
[WebBrowsingApiName.search]: Search,
|
||||
};
|
||||
|
||||
export { CrawlMultiPages, CrawlSinglePage, Search };
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 4. Streaming — Live Output During Execution (optional)
|
||||
|
||||
**Lifecycle:** rendered **while the executor is still running** for APIs that emit incremental output. The component is responsible for fetching the in-flight stream from the chat store and rendering it.
|
||||
|
||||
**Add for** long-running ops with continuous output: shell command execution (stdout/stderr), file write progress, code interpreter cells.
|
||||
|
||||
### Props (`BuiltinStreamingProps<Args>`)
|
||||
|
||||
```ts
|
||||
interface BuiltinStreamingProps<Arguments = any> {
|
||||
apiName: string;
|
||||
args: Arguments;
|
||||
identifier: string;
|
||||
messageId: string; // use to fetch the streaming buffer from store
|
||||
toolCallId: string;
|
||||
}
|
||||
```
|
||||
|
||||
Note there's **no `state` or `result` prop** — the Streaming component is for the in-flight phase. It pulls the live buffer from the store itself (typically via `chatToolSelectors.streamingContent(messageId)` or similar).
|
||||
|
||||
### Canonical example — RunCommandStreaming
|
||||
|
||||
`packages/builtin-tool-local-system/src/client/Streaming/RunCommand/index.tsx`:
|
||||
|
||||
```tsx
|
||||
'use client';
|
||||
|
||||
import type { BuiltinStreamingProps } from '@lobechat/types';
|
||||
import { Highlighter } from '@lobehub/ui';
|
||||
import { memo } from 'react';
|
||||
|
||||
interface RunCommandParams {
|
||||
command?: string;
|
||||
description?: string;
|
||||
timeout?: number;
|
||||
}
|
||||
|
||||
export const RunCommandStreaming = memo<BuiltinStreamingProps<RunCommandParams>>(({ args }) => {
|
||||
const { command } = args || {};
|
||||
if (!command) return null;
|
||||
|
||||
return (
|
||||
<Highlighter
|
||||
animated
|
||||
wrap
|
||||
language="sh"
|
||||
showLanguage={false}
|
||||
style={{ padding: '4px 8px' }}
|
||||
variant="outlined"
|
||||
>
|
||||
{command}
|
||||
</Highlighter>
|
||||
);
|
||||
});
|
||||
RunCommandStreaming.displayName = 'RunCommandStreaming';
|
||||
```
|
||||
|
||||
For real-time output beyond just the command (stderr/stdout streaming), pull from the chat store:
|
||||
|
||||
```tsx
|
||||
const buffer = useChatStore((state) =>
|
||||
chatToolSelectors.streamingBuffer(messageId, toolCallId)(state),
|
||||
);
|
||||
```
|
||||
|
||||
### Streaming rules
|
||||
|
||||
- Render `null` until you have something to display (avoids flash).
|
||||
- For terminal-style output, use `Highlighter` with `animated` to show typing-like effect.
|
||||
- The Streaming component must **unmount cleanly** when execution ends — typically the framework swaps it out for the Render automatically.
|
||||
|
||||
### Streaming registry — `client/Streaming/index.ts`
|
||||
|
||||
```ts
|
||||
import { LocalSystemApiName } from '../..';
|
||||
import { RunCommandStreaming } from './RunCommand';
|
||||
import { WriteFileStreaming } from './WriteFile';
|
||||
|
||||
export const LocalSystemStreamings = {
|
||||
[LocalSystemApiName.runCommand]: RunCommandStreaming,
|
||||
[LocalSystemApiName.writeLocalFile]: WriteFileStreaming,
|
||||
};
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Intervention — Approval / Edit-Before-Run (optional)
|
||||
|
||||
**Lifecycle:** rendered **before the executor runs** for APIs whose manifest sets `humanIntervention`. The user sees a preview of the args, can edit them, then approves or skips/cancels.
|
||||
|
||||
**Add for** destructive or sensitive ops: shell commands, file writes, file moves, payments, message broadcasts.
|
||||
|
||||
### Props (`BuiltinInterventionProps<Args>`)
|
||||
|
||||
```ts
|
||||
interface BuiltinInterventionProps<Arguments = any> {
|
||||
apiName?: string;
|
||||
args: Arguments;
|
||||
identifier?: string;
|
||||
interactionMode?: 'approval' | 'custom';
|
||||
messageId: string;
|
||||
|
||||
/** Called when the user edits the args; the approve action awaits this. */
|
||||
onArgsChange?: (args: Arguments) => void | Promise<void>;
|
||||
|
||||
/** Called on approve / skip / cancel. */
|
||||
onInteractionAction?: (
|
||||
action:
|
||||
| { type: 'submit'; payload: Record<string, unknown> }
|
||||
| { type: 'skip'; payload?: Record<string, unknown>; reason?: string }
|
||||
| { type: 'cancel'; payload?: Record<string, unknown> },
|
||||
) => Promise<void>;
|
||||
|
||||
/** Register a callback to flush pending saves before approval. Returns cleanup. */
|
||||
registerBeforeApprove?: (id: string, callback: () => void | Promise<void>) => () => void;
|
||||
}
|
||||
```
|
||||
|
||||
### Canonical example — RunCommand Intervention
|
||||
|
||||
`packages/builtin-tool-local-system/src/client/Intervention/RunCommand/index.tsx`:
|
||||
|
||||
```tsx
|
||||
import type { RunCommandParams } from '@lobechat/electron-client-ipc';
|
||||
import type { BuiltinInterventionProps } from '@lobechat/types';
|
||||
import { Flexbox, Highlighter, Text } from '@lobehub/ui';
|
||||
import { memo } from 'react';
|
||||
|
||||
const RunCommand = memo<BuiltinInterventionProps<RunCommandParams>>(({ args }) => {
|
||||
const { description, command, timeout } = args;
|
||||
return (
|
||||
<Flexbox gap={8}>
|
||||
<Flexbox horizontal justify="space-between">
|
||||
{description && <Text>{description}</Text>}
|
||||
{timeout && (
|
||||
<Text style={{ fontSize: 12 }} type="secondary">
|
||||
timeout: {formatTimeout(timeout)}
|
||||
</Text>
|
||||
)}
|
||||
</Flexbox>
|
||||
{command && (
|
||||
<Highlighter wrap language="sh" showLanguage={false} variant="outlined">
|
||||
{command}
|
||||
</Highlighter>
|
||||
)}
|
||||
</Flexbox>
|
||||
);
|
||||
});
|
||||
export default RunCommand;
|
||||
```
|
||||
|
||||
### Intervention rules
|
||||
|
||||
- **Show a preview, not a form by default.** Editing UI is opt-in via `onArgsChange` and is usually inline (click to edit a code block, etc.).
|
||||
- For args with debounced edit state (text fields), use `registerBeforeApprove(id, flushFn)` so the approve action waits for the debounce to flush. Always return the cleanup function.
|
||||
- Call `onInteractionAction({ type: 'submit', payload })` when the user approves; `'skip'` if they skip with a reason; `'cancel'` if they cancel the whole turn.
|
||||
- Add a corresponding `interventionAudit.ts` in the package root if the tool needs scope/path validation before approval (see `local-system/src/interventionAudit.ts`).
|
||||
|
||||
### Intervention registry — `client/Intervention/index.ts`
|
||||
|
||||
```ts
|
||||
import { LocalSystemApiName } from '../..';
|
||||
import EditLocalFile from './EditLocalFile';
|
||||
import RunCommand from './RunCommand';
|
||||
import WriteFile from './WriteFile';
|
||||
/* … */
|
||||
|
||||
export const LocalSystemInterventions = {
|
||||
[LocalSystemApiName.editLocalFile]: EditLocalFile,
|
||||
[LocalSystemApiName.runCommand]: RunCommand,
|
||||
[LocalSystemApiName.writeLocalFile]: WriteFile,
|
||||
/* one entry per API that needs approval */
|
||||
};
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Portal — Full-Screen Detail View (optional)
|
||||
|
||||
**Lifecycle:** rendered when the user opens the tool message in a side panel or full-screen modal. One Portal per **tool**, not per API — the Portal switches on `apiName` internally.
|
||||
|
||||
**Add for** tools whose results deserve a deep-dive view: search results with editable filters, page content with reader mode, code interpreter sessions.
|
||||
|
||||
### Props (`BuiltinPortalProps<Args, State>`)
|
||||
|
||||
```ts
|
||||
interface BuiltinPortalProps<Arguments = Record<string, any>, State = any> {
|
||||
apiName?: string;
|
||||
arguments: Arguments;
|
||||
identifier: string;
|
||||
messageId: string;
|
||||
state: State;
|
||||
}
|
||||
```
|
||||
|
||||
### Canonical example — Web-Browsing Portal
|
||||
|
||||
`packages/builtin-tool-web-browsing/src/client/Portal/index.tsx`:
|
||||
|
||||
```tsx
|
||||
import type { BuiltinPortalProps, CrawlPluginState, SearchQuery } from '@lobechat/types';
|
||||
import { memo } from 'react';
|
||||
|
||||
import { WebBrowsingApiName } from '../../types';
|
||||
import PageContent from './PageContent';
|
||||
import PageContents from './PageContents';
|
||||
import Search from './Search';
|
||||
|
||||
const Portal = memo<BuiltinPortalProps>(({ arguments: args, messageId, state, apiName }) => {
|
||||
switch (apiName) {
|
||||
case WebBrowsingApiName.search:
|
||||
return <Search messageId={messageId} query={args as SearchQuery} response={state} />;
|
||||
|
||||
case WebBrowsingApiName.crawlSinglePage: {
|
||||
const result = (state as CrawlPluginState).results.find((r) => r.originalUrl === args.url);
|
||||
return <PageContent messageId={messageId} result={result} />;
|
||||
}
|
||||
|
||||
case WebBrowsingApiName.crawlMultiPages:
|
||||
return (
|
||||
<PageContents
|
||||
messageId={messageId}
|
||||
results={(state as CrawlPluginState).results}
|
||||
urls={args.urls}
|
||||
/>
|
||||
);
|
||||
}
|
||||
return null;
|
||||
});
|
||||
export default Portal;
|
||||
```
|
||||
|
||||
### Portal rules
|
||||
|
||||
- One Portal per tool — the file is the routing layer, subcomponents implement each API's view.
|
||||
- Portals can read the chat store directly to detect "still streaming" and render a Skeleton internally (see `Search/index.tsx:20-46`).
|
||||
- Layout assumes more space than the Render — use `Flexbox` with `height={'100%'}` and structure for a side panel viewport.
|
||||
|
||||
### Portal registry — `packages/builtin-tools/src/portals.ts`
|
||||
|
||||
```ts
|
||||
import { WebBrowsingManifest, WebBrowsingPortal } from '@lobechat/builtin-tool-web-browsing/client';
|
||||
import { type BuiltinPortal } from '@lobechat/types';
|
||||
|
||||
export const BuiltinToolsPortals: Record<string, BuiltinPortal> = {
|
||||
[WebBrowsingManifest.identifier]: WebBrowsingPortal as BuiltinPortal,
|
||||
};
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. `client/components/` — Shared Subcomponents
|
||||
|
||||
Cross-cutting building blocks used by multiple surfaces live here, not duplicated in each surface folder.
|
||||
|
||||
Examples from `web-browsing/src/client/components/`:
|
||||
|
||||
- `CategoryAvatar.tsx` — search category icon
|
||||
- `EngineAvatar.tsx` — search engine logo (used in Inspector chip + Render list + Portal header)
|
||||
- `SearchBar.tsx` — editable query bar (used in Render and Portal)
|
||||
|
||||
Examples from `local-system/src/client/components/`:
|
||||
|
||||
- `FileItem.tsx` — single file row (used in ListFiles Render, SearchFiles Render, MoveLocalFiles Render)
|
||||
- `FilePathDisplay.tsx` — path with truncation (used everywhere)
|
||||
|
||||
### Rules
|
||||
|
||||
- Live under `client/components/`, exported via `client/components/index.ts`.
|
||||
- Re-export from `client/index.ts` only if other packages need them; otherwise keep internal.
|
||||
- Keep them dumb — props in, JSX out, no store reads. The store reads belong in the surface that composes them.
|
||||
|
||||
---
|
||||
|
||||
## 8. `client/index.ts` — Package Public API
|
||||
|
||||
Re-exports everything the registries need plus useful types/manifest:
|
||||
|
||||
```ts
|
||||
// Inspector — required
|
||||
export { TaskInspectors } from './Inspector';
|
||||
|
||||
// Render — only if any API has one
|
||||
export { TaskRenders, CreateTaskRender, RunTasksRender } from './Render';
|
||||
|
||||
// Placeholder / Streaming / Intervention — only if used
|
||||
export { LocalSystemListFilesPlaceholder, LocalSystemSearchFilesPlaceholder } from './Placeholder';
|
||||
export { LocalSystemStreamings } from './Streaming';
|
||||
export { LocalSystemInterventions } from './Intervention';
|
||||
|
||||
// Portal — single export per tool
|
||||
export { default as WebBrowsingPortal } from './Portal';
|
||||
|
||||
// Reusable components if other packages need them
|
||||
export { CategoryAvatar, EngineAvatar, SearchBar } from './components';
|
||||
|
||||
// Re-export manifest, identifier, types for convenience
|
||||
export { TaskManifest, TaskIdentifier } from '../manifest';
|
||||
export * from '../types';
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 9. Diagnostic Quick-Lookup
|
||||
|
||||
| Symptom | Surface to check | | |
|
||||
| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- | --- | ------------------------- |
|
||||
| No header at all on the tool call | Inspector missing from `client/Inspector/index.ts` registry | | |
|
||||
| Header shows the API name but no chips | Inspector missing \`args?.X | | partialArgs?.X\` fallback |
|
||||
| Header doesn't pulse during loading | Missing `shinyTextStyles.shinyText` on `isArgumentsStreaming \|\| isLoading` | | |
|
||||
| Empty result card under header | Render returned `<div />` instead of `null` when no data | | |
|
||||
| Layout jump when result arrives | Placeholder dimensions don't match Render dimensions | | |
|
||||
| Approval dialog never appears | Manifest missing `humanIntervention`, or Intervention not in registry | | |
|
||||
| Approval click doesn't wait for inline edit | Missing `registerBeforeApprove(id, flushFn)` | | |
|
||||
| Portal opens but blank | Switch in `Portal/index.tsx` doesn't cover the apiName | | |
|
||||
| Strings show as `builtins.lobe-foo.apiName.bar` | Missing i18n key in `src/locales/default/plugin.ts` (or not seeded in dev locale files) | | |
|
||||
| Wrong color shade on `<Text type="secondary">` | `type='secondary'` is lighter than `colorTextSecondary` — pass via `style={{ color: cssVar.colorTextSecondary }}` | | |
|
||||
@@ -8,7 +8,6 @@ description: >
|
||||
(4) Send interactive cards or stream AI responses to chat platforms.
|
||||
Triggers on "chat sdk", "chat bot", "slack bot", "teams bot", "discord bot", "@chat-adapter",
|
||||
building bots that work across multiple chat platforms.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# Chat SDK
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,244 +0,0 @@
|
||||
# Walkthrough: Adding a New Feature End-to-End
|
||||
|
||||
This is a worked example of the canonical 6-step recipe applied to a new entity (`Dataset`), showing a variant of the main skill's pattern: **a list keyed by a parent id** (`datasetMap[benchmarkId]`), useful when the same shape appears under different parents.
|
||||
|
||||
If you only need the canonical (single-array) pattern, the main `SKILL.md` already shows it for `Benchmark`. Read this file when you need the parent-keyed Map variant, or when you want a checklist-style walkthrough.
|
||||
|
||||
## Step 1: Add Service methods
|
||||
|
||||
```typescript
|
||||
class AgentEvalService {
|
||||
async listDatasets(benchmarkId: string) {
|
||||
return lambdaClient.agentEval.listDatasets.query({ benchmarkId });
|
||||
}
|
||||
async getDataset(id: string) {
|
||||
return lambdaClient.agentEval.getDataset.query({ id });
|
||||
}
|
||||
async createDataset(params: CreateDatasetParams) {
|
||||
return lambdaClient.agentEval.createDataset.mutate(params);
|
||||
}
|
||||
// updateDataset / deleteDataset follow the same shape
|
||||
}
|
||||
```
|
||||
|
||||
## Step 2: Reducer (optimistic updates)
|
||||
|
||||
```typescript
|
||||
// src/store/eval/slices/dataset/reducer.ts
|
||||
export type DatasetDispatch =
|
||||
| { type: 'addDataset'; value: Dataset }
|
||||
| { type: 'updateDataset'; id: string; value: Partial<Dataset> }
|
||||
| { type: 'deleteDataset'; id: string };
|
||||
|
||||
export const datasetReducer = (state: Dataset[] = [], payload: DatasetDispatch): Dataset[] =>
|
||||
produce(state, (draft) => {
|
||||
switch (payload.type) {
|
||||
case 'addDataset':
|
||||
draft.unshift(payload.value);
|
||||
break;
|
||||
case 'updateDataset': {
|
||||
const i = draft.findIndex((item) => item.id === payload.id);
|
||||
if (i !== -1) draft[i] = { ...draft[i], ...payload.value };
|
||||
break;
|
||||
}
|
||||
case 'deleteDataset': {
|
||||
const i = draft.findIndex((item) => item.id === payload.id);
|
||||
if (i !== -1) draft.splice(i, 1);
|
||||
break;
|
||||
}
|
||||
}
|
||||
});
|
||||
```
|
||||
|
||||
## Step 3: Store slice
|
||||
|
||||
```typescript
|
||||
// src/store/eval/slices/dataset/initialState.ts
|
||||
export interface DatasetData {
|
||||
currentPage: number;
|
||||
hasMore: boolean;
|
||||
isLoading: boolean;
|
||||
items: Dataset[];
|
||||
pageSize: number;
|
||||
total: number;
|
||||
}
|
||||
|
||||
export interface DatasetSliceState {
|
||||
// Map keyed by benchmarkId — multiple parent contexts share the slice
|
||||
datasetMap: Record<string, DatasetData>;
|
||||
// Single item for modal display
|
||||
datasetDetail: Dataset | null;
|
||||
isLoadingDatasetDetail: boolean;
|
||||
loadingDatasetIds: string[];
|
||||
}
|
||||
|
||||
export const datasetInitialState: DatasetSliceState = {
|
||||
datasetMap: {},
|
||||
datasetDetail: null,
|
||||
isLoadingDatasetDetail: false,
|
||||
loadingDatasetIds: [],
|
||||
};
|
||||
```
|
||||
|
||||
```typescript
|
||||
// src/store/eval/slices/dataset/action.ts
|
||||
const FETCH_DATASETS_KEY = 'FETCH_DATASETS';
|
||||
const FETCH_DATASET_DETAIL_KEY = 'FETCH_DATASET_DETAIL';
|
||||
|
||||
export const createDatasetSlice: StateCreator<EvalStore, any, [], DatasetAction> = (set, get) => ({
|
||||
// Cache key includes benchmarkId so each parent has its own SWR entry
|
||||
useFetchDatasets: (benchmarkId) =>
|
||||
useClientDataSWR(
|
||||
benchmarkId ? [FETCH_DATASETS_KEY, benchmarkId] : null,
|
||||
() => agentEvalService.listDatasets(benchmarkId!),
|
||||
{
|
||||
onSuccess: (data) => {
|
||||
set({
|
||||
datasetMap: {
|
||||
...get().datasetMap,
|
||||
[benchmarkId!]: {
|
||||
currentPage: 1,
|
||||
hasMore: false,
|
||||
isLoading: false,
|
||||
items: data,
|
||||
pageSize: data.length,
|
||||
total: data.length,
|
||||
},
|
||||
},
|
||||
});
|
||||
},
|
||||
},
|
||||
),
|
||||
|
||||
useFetchDatasetDetail: (id) =>
|
||||
useClientDataSWR(
|
||||
id ? [FETCH_DATASET_DETAIL_KEY, id] : null,
|
||||
() => agentEvalService.getDataset(id!),
|
||||
{
|
||||
onSuccess: (data) => set({ datasetDetail: data, isLoadingDatasetDetail: false }),
|
||||
},
|
||||
),
|
||||
|
||||
refreshDatasets: (benchmarkId) => mutate([FETCH_DATASETS_KEY, benchmarkId]),
|
||||
refreshDatasetDetail: (id) => mutate([FETCH_DATASET_DETAIL_KEY, id]),
|
||||
|
||||
// CREATE with optimistic update — note the temp id pattern
|
||||
createDataset: async (params) => {
|
||||
const tmpId = Date.now().toString();
|
||||
const { benchmarkId } = params;
|
||||
|
||||
get().internal_dispatchDataset(
|
||||
{ type: 'addDataset', value: { ...params, id: tmpId, createdAt: Date.now() } as any },
|
||||
benchmarkId,
|
||||
);
|
||||
get().internal_updateDatasetLoading(tmpId, true);
|
||||
|
||||
try {
|
||||
const result = await agentEvalService.createDataset(params);
|
||||
await get().refreshDatasets(benchmarkId);
|
||||
return result;
|
||||
} finally {
|
||||
get().internal_updateDatasetLoading(tmpId, false);
|
||||
}
|
||||
},
|
||||
|
||||
// UPDATE / DELETE follow the same optimistic + refresh pattern as BenchmarkSlice
|
||||
// (see the main SKILL.md)
|
||||
|
||||
// Internal — dispatch reducer scoped to a parent
|
||||
internal_dispatchDataset: (payload, benchmarkId) => {
|
||||
const currentData = get().datasetMap[benchmarkId];
|
||||
const nextItems = datasetReducer(currentData?.items, payload);
|
||||
|
||||
// Skip set when nothing changed — avoids unnecessary re-renders
|
||||
if (isEqual(nextItems, currentData?.items)) return;
|
||||
|
||||
set({
|
||||
datasetMap: {
|
||||
...get().datasetMap,
|
||||
[benchmarkId]: {
|
||||
...currentData,
|
||||
currentPage: currentData?.currentPage ?? 1,
|
||||
hasMore: currentData?.hasMore ?? false,
|
||||
isLoading: false,
|
||||
items: nextItems,
|
||||
pageSize: currentData?.pageSize ?? nextItems.length,
|
||||
total: currentData?.total ?? nextItems.length,
|
||||
},
|
||||
},
|
||||
});
|
||||
},
|
||||
|
||||
internal_updateDatasetLoading: (id, loading) => {
|
||||
set((state) => ({
|
||||
loadingDatasetIds: loading
|
||||
? [...state.loadingDatasetIds, id]
|
||||
: state.loadingDatasetIds.filter((i) => i !== id),
|
||||
}));
|
||||
},
|
||||
});
|
||||
```
|
||||
|
||||
## Step 4: Wire into the store
|
||||
|
||||
```typescript
|
||||
// src/store/eval/store.ts
|
||||
export type EvalStore = EvalStoreState & BenchmarkAction & DatasetAction & RunAction;
|
||||
|
||||
const createStore: StateCreator<EvalStore, [['zustand/devtools', never]]> = (set, get, store) => ({
|
||||
...initialState,
|
||||
...createBenchmarkSlice(set, get, store),
|
||||
...createDatasetSlice(set, get, store),
|
||||
...createRunSlice(set, get, store),
|
||||
});
|
||||
|
||||
// src/store/eval/initialState.ts
|
||||
export const initialState: EvalStoreState = {
|
||||
...benchmarkInitialState,
|
||||
...datasetInitialState,
|
||||
...runInitialState,
|
||||
};
|
||||
```
|
||||
|
||||
## Step 5: Selectors (optional but recommended)
|
||||
|
||||
```typescript
|
||||
export const datasetSelectors = {
|
||||
getDatasetData: (benchmarkId: string) => (s: EvalStore) => s.datasetMap[benchmarkId],
|
||||
getDatasets: (benchmarkId: string) => (s: EvalStore) => s.datasetMap[benchmarkId]?.items ?? [],
|
||||
isLoadingDataset: (id: string) => (s: EvalStore) => s.loadingDatasetIds.includes(id),
|
||||
};
|
||||
```
|
||||
|
||||
## Step 6: Use in component
|
||||
|
||||
```tsx
|
||||
// List scoped to a parent
|
||||
const DatasetList = ({ benchmarkId }: { benchmarkId: string }) => {
|
||||
const useFetchDatasets = useEvalStore((s) => s.useFetchDatasets);
|
||||
const datasets = useEvalStore(datasetSelectors.getDatasets(benchmarkId));
|
||||
const datasetData = useEvalStore(datasetSelectors.getDatasetData(benchmarkId));
|
||||
|
||||
useFetchDatasets(benchmarkId);
|
||||
|
||||
if (datasetData?.isLoading) return <Loading />;
|
||||
return (
|
||||
<div>
|
||||
<h2>Total: {datasetData?.total ?? 0}</h2>
|
||||
<List data={datasets} />
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
// Single item for modal — conditional fetching pattern
|
||||
const DatasetImportModal = ({ open, datasetId }: Props) => {
|
||||
const useFetchDatasetDetail = useEvalStore((s) => s.useFetchDatasetDetail);
|
||||
const dataset = useEvalStore((s) => s.datasetDetail);
|
||||
const isLoading = useEvalStore((s) => s.isLoadingDatasetDetail);
|
||||
|
||||
// Only fetch when modal is open AND id present
|
||||
useFetchDatasetDetail(open && datasetId ? datasetId : undefined);
|
||||
|
||||
return <Modal open={open}>{isLoading ? <Loading /> : <div>{dataset?.name}</div>}</Modal>;
|
||||
};
|
||||
```
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: db-migrations
|
||||
description: 'Use when generating or regenerating Drizzle migration files, changing database schema tables or columns, resolving migration sequence conflicts after rebase, reviewing migration SQL for idempotent patterns, or renaming migration files.'
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# Database Migrations Guide
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: debug-package
|
||||
description: "Guide for the `debug` npm package and LobeHub log namespaces (lobe-server:*, lobe-desktop:*, lobe-client:*, lobe-*-router:*). Use whenever adding a `debug(...)` logger, picking a namespace for new server/desktop/client/router code, troubleshooting why DEBUG=lobe-* logs don't show up, or when the user asks to 'add logging', 'add a logger', 'instrument this', 'trace this call', 'why isn't my log printing', or mentions `debug(`, `DEBUG=`, `localStorage.debug`, or log format specifiers like %O / %o / %s / %d in a LobeHub codebase."
|
||||
name: debug
|
||||
description: Debug package usage guide. Use when adding debug logging, understanding log namespaces, or implementing debugging features. Triggers on debug logging requests or logging implementation.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: drizzle
|
||||
description: "Drizzle ORM schema authoring and query style for LobeHub (postgres, strict mode). Use when editing anything under `src/database/schemas/`, defining `pgTable` columns/indexes/junction tables, spreading `...timestamps`, generating `createInsertSchema`/`$inferSelect`/`$inferInsert` types, writing `db.select().from(...).leftJoin(...)` queries, or deciding when to split a relational `with:` into two queries. Triggers on `pgTable`, `db.select`, `db.query`, `eq()`/`and()`/`inArray()`, `uniqueIndex`, `primaryKey`, `references({ onDelete })`, 'add a column', 'new table', 'foreign key', 'junction table', 'schema field'. For migration files specifically, see the `db-migrations` skill."
|
||||
user-invocable: false
|
||||
description: Drizzle ORM schema and database guide. Use when working with database schemas (src/database/schemas/*), defining tables, creating migrations, or database model code. Triggers on Drizzle schema definition, database migrations, or ORM usage questions.
|
||||
---
|
||||
|
||||
# Drizzle ORM Schema Style Guide
|
||||
@@ -126,7 +125,11 @@ The relational API generates complex lateral joins with `json_build_array` that
|
||||
|
||||
```typescript
|
||||
// ✅ Good
|
||||
const [result] = await this.db.select().from(agents).where(eq(agents.id, id)).limit(1);
|
||||
const [result] = await this.db
|
||||
.select()
|
||||
.from(agents)
|
||||
.where(eq(agents.id, id))
|
||||
.limit(1);
|
||||
return result;
|
||||
|
||||
// ❌ Bad: relational API
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: hotkey
|
||||
description: "Adding or editing keyboard shortcuts in LobeHub. Use when registering a new hotkey, changing a key combo, scoping a shortcut to chat vs global, or wiring a hotkey hook + tooltip. Covers the 5-step flow: add to `HotkeyEnum` in `src/types/hotkey.ts`, register in `HOTKEYS_REGISTRATION` (`src/const/hotkeys.ts`) with `combineKeys([Key.Mod, …])`, add i18n in `src/locales/default/hotkey.ts`, expose via `useHotkeyById` in `src/hooks/useHotkeys/`, and render `<Tooltip hotkey={…}>`. Triggers on `HotkeyEnum`, `HOTKEYS_REGISTRATION`, `useHotkeyById`, `combineKeys`, `Key.Mod`/`Key.Shift`, 'add a hotkey', 'add a shortcut', '加快捷键', '快捷键', 'Cmd+K', 'keyboard shortcut', 'hotkey scope', 'hotkey conflict'."
|
||||
user-invocable: false
|
||||
description: Guide for adding keyboard shortcuts. Use when implementing new hotkeys, registering shortcuts, or working with keyboard interactions. Triggers on hotkey implementation or keyboard shortcut tasks.
|
||||
---
|
||||
|
||||
# Adding Keyboard Shortcuts Guide
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: i18n
|
||||
description: "LobeHub internationalization with react-i18next. Use when adding any user-facing string in `.tsx`/`.ts` files, creating or renaming a key under `src/locales/default/{namespace}.ts`, deciding the `{feature}.{context}.{action}` flat-key pattern, wiring a new namespace into `src/locales/default/index.ts`, or translating zh-CN/en-US JSON for dev preview. Triggers on `useTranslation`, `t('foo.bar')`, `i18next.t`, `{{variable}}` interpolation, hardcoded UI strings (zh or en) that should be extracted, 'add i18n', '加 i18n key', '翻译', 'locale key', 'namespace', 'pnpm i18n'."
|
||||
user-invocable: false
|
||||
description: Internationalization guide using react-i18next. Use when adding translations, creating i18n keys, or working with localized text in React components (.tsx files). Triggers on translation tasks, locale management, or i18n implementation.
|
||||
---
|
||||
|
||||
# LobeHub Internationalization Guide
|
||||
|
||||
@@ -1,55 +1,55 @@
|
||||
---
|
||||
name: linear
|
||||
description: "Linear issue management. Use when the user mentions LOBE-xxx issue IDs (e.g. LOBE-4540), says 'linear' / 'linear issue' / 'link linear', or when creating PRs that reference Linear issues. Covers retrieving issues, updating status, adding completion comments, and creating sub-issue trees."
|
||||
user-invocable: false
|
||||
description: "Linear issue management. MUST USE when: (1) user mentions LOBE-xxx issue IDs (e.g. LOBE-4540), (2) user says 'linear', 'linear issue', 'link linear', (3) creating PRs that reference Linear issues. Provides workflows for retrieving issues, updating status, and adding comments."
|
||||
---
|
||||
|
||||
# Linear Issue Management
|
||||
|
||||
Before using Linear workflows, search for `linear` MCP tools. If not found, treat as not installed.
|
||||
|
||||
## PR Creation with Linear Issues
|
||||
## ⚠️ CRITICAL: PR Creation with Linear Issues
|
||||
|
||||
A PR that fixes a Linear issue has **two separate jobs to do**, and both matter:
|
||||
**When creating a PR that references Linear issues (LOBE-xxx), you MUST:**
|
||||
|
||||
1. **`Fixes LOBE-xxx` in the PR body** — Linear watches GitHub for these magic keywords and auto-links the PR and auto-closes the issue on merge. This is the machine-readable side.
|
||||
2. **A completion comment on the Linear issue** — gives the reviewer/PM/teammate landing in Linear a human-readable summary of what changed and why, without forcing them to click through to GitHub and read a diff.
|
||||
1. Create the PR with magic keywords (`Fixes LOBE-xxx`)
|
||||
2. **IMMEDIATELY after PR creation**, add completion comments to ALL referenced Linear issues
|
||||
3. Do NOT consider the task complete until Linear comments are added
|
||||
|
||||
If you only do step 1, Linear watchers (often non-engineers) hit the issue and see no context. So pair PR creation with the Linear comment as part of the same task — finish both before considering the work done.
|
||||
This is NON-NEGOTIABLE. Skipping Linear comments is a workflow violation.
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **Retrieve issue details** before starting: `mcp__linear-server__get_issue`
|
||||
2. **Read images** — issue descriptions often contain screenshots with critical context (mockups, error states, before/after). Use `mcp__linear-server__extract_images` so you actually see them; reading raw markdown alone misses what the reporter was looking at.
|
||||
3. **Check for sub-issues**: `mcp__linear-server__list_issues` with `parentId` filter
|
||||
4. **Mark as In Progress** at the moment you start planning or implementing — this signals to teammates the issue is owned, so they don't double-pick it up.
|
||||
2. **Read images**: If the issue description contains images, MUST use `mcp__linear-server__extract_images` to read image content for full context
|
||||
3. **Check for sub-issues**: Use `mcp__linear-server__list_issues` with `parentId` filter
|
||||
4. **Mark as In Progress**: When starting to plan or implement an issue, immediately update status to **"In Progress"** via `mcp__linear-server__update_issue`
|
||||
5. **Update issue status** when completing: `mcp__linear-server__update_issue`
|
||||
6. **Add completion comment** (see [format below](#completion-comment-format))
|
||||
6. **Add completion comment** (REQUIRED): `mcp__linear-server__create_comment`
|
||||
|
||||
## Creating Issues
|
||||
|
||||
When creating issues with `mcp__linear-server__create_issue`, add the `claude code` label. Reason: the label is how the team filters/audits AI-generated issues; without it those issues vanish into the general backlog and the team loses visibility into AI contribution patterns.
|
||||
When creating issues with `mcp__linear-server__create_issue`, **MUST add the `claude code` label**.
|
||||
|
||||
## Language
|
||||
|
||||
Match the issue language to the conversation that produced it — if you're discussing in 中文，write the issue in 中文；if discussing in English, write it in English. Reason: the issue is a continuation of the conversation, and forcing a language switch creates translation friction for the collaborator who started the thread.
|
||||
Issue titles, descriptions, and comments **MUST follow the language of the current conversation**, not default to English.
|
||||
|
||||
Specifics:
|
||||
|
||||
- 中文 conversation → 中文 body; technical terms (file paths, identifiers, library names, commands, error messages) stay in English.
|
||||
- English conversation → English body.
|
||||
- Conversation in 中文 → issue body in 中文；technical terms (file paths, identifiers, library names, commands, error messages) stay in English.
|
||||
- Conversation in English → issue body in English.
|
||||
- Code blocks, file paths, and quoted strings always stay in their original form regardless of surrounding language.
|
||||
- This applies equally to **updates** — when editing an existing issue (description **and titles**), preserve the language of the conversation that triggered the edit; don't switch the issue language mid-refactor.
|
||||
- This applies equally to **updates** — when editing an existing issue (description **and titles**), preserve the language of the conversation that triggered the edit; do not switch the issue language during a refactor (Chinese → English or vice versa).
|
||||
|
||||
Rationale: the issue is a continuation of the conversation. Forcing English when the discussion is in Chinese creates translation friction for the collaborator who came from that thread.
|
||||
|
||||
## Creating Sub-issue Trees
|
||||
|
||||
When breaking a parent issue into a tree of sub-issues (e.g., task decomposition for LOBE-xxx), follow these rules — they work around real limitations of the Linear MCP tools.
|
||||
|
||||
### 1. Prefix titles with an ordering index
|
||||
### 1. ALWAYS prefix titles with an ordering index
|
||||
|
||||
The Linear Sub-issues panel orders children by `sortOrder`, which **defaults to newest-first** (most recently created appears on top). Neither parallel nor serial creation produces the intended top-to-bottom reading order, and the MCP `save_issue` tool does **not expose a `sortOrder` parameter** — you can't set order at create time.
|
||||
The Linear Sub-issues panel displays children by `sortOrder`, which **defaults to newest-first** (most recently created appears on top). Neither parallel nor serial creation will produce the intended top-to-bottom reading order, and the MCP `save_issue` tool does **not expose a `sortOrder` parameter** — you cannot set order at create time.
|
||||
|
||||
Workaround: encode execution order in the title itself:
|
||||
**Workaround**: encode execution order in the title itself:
|
||||
|
||||
```plaintext
|
||||
[1] [db] add schema fields
|
||||
@@ -100,7 +100,7 @@ The implementer may open only the sub-issue, not the parent — don't rely on co
|
||||
|
||||
## Completion Comment Format
|
||||
|
||||
Each completed issue gets a comment summarizing the work, so reviewers and future readers don't have to reconstruct it from the PR diff:
|
||||
Every completed issue MUST have a comment summarizing work done:
|
||||
|
||||
```markdown
|
||||
## Changes Summary
|
||||
@@ -116,28 +116,34 @@ Each completed issue gets a comment summarizing the work, so reviewers and futur
|
||||
- ...
|
||||
```
|
||||
|
||||
This gives team visibility, code-review context, and a paper trail for future reference.
|
||||
This is critical for:
|
||||
|
||||
## PR Association
|
||||
- Team visibility
|
||||
- Code review context
|
||||
- Future reference
|
||||
|
||||
When creating PRs for Linear issues, include magic keywords in the PR body:
|
||||
## PR Association (REQUIRED)
|
||||
|
||||
When creating PRs for Linear issues, include magic keywords in PR body:
|
||||
|
||||
- `Fixes LOBE-123`
|
||||
- `Closes LOBE-123`
|
||||
- `Resolves LOBE-123`
|
||||
|
||||
These trigger Linear's auto-link + auto-close on merge.
|
||||
|
||||
## Per-Issue Completion Rule
|
||||
|
||||
When working on multiple issues, close out **each one before starting the next** — don't batch all the Linear updates to the end. Batching is where comments get forgotten and issues stay stuck in "In Progress" days after the PR shipped.
|
||||
|
||||
For each issue:
|
||||
When working on multiple issues, update EACH issue IMMEDIATELY after completing it:
|
||||
|
||||
1. Complete implementation
|
||||
2. Run `bun run type-check`
|
||||
3. Run related tests
|
||||
4. Create PR if needed
|
||||
5. Update status to **"In Review"** (not "Done" — "Done" is for after the PR merges)
|
||||
6. Add the completion comment
|
||||
7. Move to the next issue
|
||||
5. Update status to **"In Review"** (NOT "Done")
|
||||
6. **Add completion comment immediately**
|
||||
7. Move to next issue
|
||||
|
||||
**Note:** Status → "In Review" when PR created. "Done" only after PR merged.
|
||||
|
||||
**❌ Wrong:** Complete all → Create PR → Forget Linear comments
|
||||
|
||||
**✅ Correct:** Complete → Create PR → Add Linear comments → Task done
|
||||
|
||||
@@ -11,169 +11,86 @@
|
||||
# Environment variables:
|
||||
# CDP_PORT — Chrome DevTools Protocol port (default: 9222)
|
||||
# ELECTRON_LOG — Log file path (default: /tmp/electron-dev.log)
|
||||
# ELECTRON_WAIT_S — Max seconds to wait for CDP to become reachable (default: 90)
|
||||
# RENDERER_WAIT_S — Max seconds to wait for SPA after CDP is up (default: 60)
|
||||
# FORCE_KILL_USER — When set to 1, silently kill the user's `bun run dev`
|
||||
# Electron without confirmation (default: always confirm-by-action)
|
||||
# ELECTRON_WAIT_S — Max seconds to wait for Electron process (default: 60)
|
||||
# RENDERER_WAIT_S — Max seconds to wait for renderer/SPA (default: 60)
|
||||
#
|
||||
set -euo pipefail
|
||||
|
||||
CDP_PORT="${CDP_PORT:-9222}"
|
||||
ELECTRON_LOG="${ELECTRON_LOG:-/tmp/electron-dev.log}"
|
||||
ELECTRON_WAIT_S="${ELECTRON_WAIT_S:-90}"
|
||||
ELECTRON_WAIT_S="${ELECTRON_WAIT_S:-60}"
|
||||
RENDERER_WAIT_S="${RENDERER_WAIT_S:-60}"
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
||||
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
|
||||
PIDFILE="/tmp/electron-dev-cdp-${CDP_PORT}.pid"
|
||||
|
||||
# Project-scoped electron path prefix used for pgrep matching. Any Electron
|
||||
# binary from this project (main + helpers, with or without --remote-debugging-port)
|
||||
# starts with this string in its argv[0], so a single substring match catches all.
|
||||
PROJECT_ELECTRON_PATH="${PROJECT_ROOT}/apps/desktop/node_modules/.pnpm/electron@"
|
||||
|
||||
# ── Helpers ──────────────────────────────────────────────────────────
|
||||
|
||||
# Print pid + every descendant pid (DFS via pgrep -P).
|
||||
expand_descendants() {
|
||||
local pid="$1"
|
||||
echo "$pid"
|
||||
local children
|
||||
children=$(pgrep -P "$pid" 2>/dev/null || true)
|
||||
for c in $children; do
|
||||
expand_descendants "$c"
|
||||
done
|
||||
# Get the Electron binary path used by this project
|
||||
electron_bin_pattern() {
|
||||
echo "${PROJECT_ROOT}/apps/desktop/node_modules/.pnpm/electron@*/node_modules/electron/dist/Electron.app"
|
||||
}
|
||||
|
||||
# Find seed PIDs related to this project's Electron dev session.
|
||||
# Matches REGARDLESS of whether --remote-debugging-port was passed, so it also
|
||||
# catches a plain `bun run dev` session the user started outside this script.
|
||||
find_project_pids() {
|
||||
# Find all PIDs related to the project's Electron dev session
|
||||
find_electron_pids() {
|
||||
local pids=""
|
||||
|
||||
# 1. Any process whose command line mentions this project's electron path
|
||||
# (covers the main Electron binary AND every Helper subprocess)
|
||||
local electron_pids
|
||||
electron_pids=$(pgrep -f "$PROJECT_ELECTRON_PATH" 2>/dev/null || true)
|
||||
pids="$pids $electron_pids"
|
||||
# 1. Main Electron process (launched with --remote-debugging-port)
|
||||
local main_pids
|
||||
main_pids=$(pgrep -f "Electron\.app.*--remote-debugging-port=${CDP_PORT}" 2>/dev/null || true)
|
||||
[ -n "$main_pids" ] && pids="$pids $main_pids"
|
||||
|
||||
# 2. electron-vite dev server (narrow match to avoid catching unrelated Vite invocations)
|
||||
# 2. Electron Helper processes (gpu, renderer, utility) spawned from the project's electron binary
|
||||
local helper_pids
|
||||
helper_pids=$(pgrep -f "${PROJECT_ROOT}/apps/desktop/node_modules/.*Electron Helper" 2>/dev/null || true)
|
||||
[ -n "$helper_pids" ] && pids="$pids $helper_pids"
|
||||
|
||||
# 3. electron-vite dev server
|
||||
local vite_pids
|
||||
vite_pids=$(pgrep -f "electron-vite[/.].*\\bdev\\b" 2>/dev/null || true)
|
||||
pids="$pids $vite_pids"
|
||||
vite_pids=$(pgrep -f "electron-vite.*dev" 2>/dev/null || true)
|
||||
[ -n "$vite_pids" ] && pids="$pids $vite_pids"
|
||||
|
||||
# 3. The launcher subshell from a previous `start` (saved to pidfile)
|
||||
# 4. PID from pidfile (fallback)
|
||||
if [ -f "$PIDFILE" ]; then
|
||||
local saved_pid
|
||||
saved_pid=$(cat "$PIDFILE" 2>/dev/null || true)
|
||||
if [ -n "$saved_pid" ] && kill -0 "$saved_pid" 2>/dev/null; then
|
||||
saved_pid=$(cat "$PIDFILE")
|
||||
if kill -0 "$saved_pid" 2>/dev/null; then
|
||||
pids="$pids $saved_pid"
|
||||
fi
|
||||
fi
|
||||
|
||||
# 4. Whatever is currently bound to the CDP port — catches strays whose
|
||||
# binary path doesn't match (e.g. orphaned from a crashed restart)
|
||||
local port_pid
|
||||
port_pid=$(lsof -ti tcp:"$CDP_PORT" -sTCP:LISTEN 2>/dev/null || true)
|
||||
pids="$pids $port_pid"
|
||||
|
||||
# `|| true` because `grep -v '^$'` exits 1 when input has no non-empty
|
||||
# lines, which (with pipefail + set -e) silently kills the caller.
|
||||
# Deduplicate
|
||||
echo "$pids" | tr ' ' '\n' | sort -u | grep -v '^$' | tr '\n' ' ' || true
|
||||
}
|
||||
|
||||
# Wait for the CDP HTTP endpoint to respond, with a deadline + early bail-out
|
||||
# if the launcher process died (no point waiting if Electron crashed).
|
||||
wait_for_cdp() {
|
||||
local deadline=$(( $(date +%s) + ELECTRON_WAIT_S ))
|
||||
echo "[electron-dev] Waiting for CDP on port ${CDP_PORT} (up to ${ELECTRON_WAIT_S}s)..."
|
||||
|
||||
while [ "$(date +%s)" -lt "$deadline" ]; do
|
||||
if curl -sf --max-time 2 "http://localhost:${CDP_PORT}/json/version" >/dev/null 2>&1; then
|
||||
echo "[electron-dev] CDP is reachable."
|
||||
return 0
|
||||
fi
|
||||
|
||||
# If our launcher subshell died, abort early so we don't hang the full timeout
|
||||
if [ -f "$PIDFILE" ]; then
|
||||
local saved_pid
|
||||
saved_pid=$(cat "$PIDFILE" 2>/dev/null || true)
|
||||
if [ -n "$saved_pid" ] && ! kill -0 "$saved_pid" 2>/dev/null; then
|
||||
echo "[electron-dev] Launcher PID $saved_pid is gone before CDP came up."
|
||||
echo "[electron-dev] Last 30 lines of $ELECTRON_LOG:"
|
||||
tail -30 "$ELECTRON_LOG" 2>/dev/null || true
|
||||
return 1
|
||||
fi
|
||||
fi
|
||||
|
||||
sleep 2
|
||||
done
|
||||
|
||||
echo "[electron-dev] ERROR: CDP did not respond within ${ELECTRON_WAIT_S}s"
|
||||
echo "[electron-dev] Last 30 lines of $ELECTRON_LOG:"
|
||||
tail -30 "$ELECTRON_LOG" 2>/dev/null || true
|
||||
return 1
|
||||
}
|
||||
|
||||
# After CDP is up, wait until the SPA renders interactive elements.
|
||||
wait_for_renderer() {
|
||||
local deadline=$(( $(date +%s) + RENDERER_WAIT_S ))
|
||||
echo "[electron-dev] Waiting for SPA to load (up to ${RENDERER_WAIT_S}s)..."
|
||||
|
||||
while [ "$(date +%s)" -lt "$deadline" ]; do
|
||||
local snap
|
||||
snap=$(agent-browser --cdp "$CDP_PORT" snapshot -i 2>&1 || true)
|
||||
if echo "$snap" | grep -qE '\b(link|button)\b'; then
|
||||
echo "[electron-dev] Renderer ready."
|
||||
return 0
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
|
||||
echo "[electron-dev] WARNING: Renderer not interactive within ${RENDERER_WAIT_S}s — proceeding anyway."
|
||||
return 0
|
||||
}
|
||||
|
||||
# ── Commands ─────────────────────────────────────────────────────────
|
||||
|
||||
do_stop() {
|
||||
echo "[electron-dev] Stopping Electron dev environment..."
|
||||
|
||||
local seed_pids
|
||||
seed_pids=$(find_project_pids)
|
||||
local pids
|
||||
pids=$(find_electron_pids)
|
||||
|
||||
# Expand to include all descendants — catches helpers spawned by the main
|
||||
# process AFTER our pgrep snapshot, and the launcher's child node/electron-vite
|
||||
# process tree.
|
||||
local all_pids=""
|
||||
for pid in $seed_pids; do
|
||||
all_pids="$all_pids $(expand_descendants "$pid")"
|
||||
done
|
||||
all_pids=$(echo "$all_pids" | tr ' ' '\n' | sort -u | grep -v '^$' | tr '\n' ' ' || true)
|
||||
|
||||
if [ -z "$all_pids" ]; then
|
||||
echo "[electron-dev] No project Electron/vite processes found."
|
||||
if [ -z "$pids" ]; then
|
||||
echo "[electron-dev] No Electron processes found."
|
||||
else
|
||||
local count
|
||||
count=$(echo "$all_pids" | tr ' ' '\n' | grep -c .)
|
||||
echo "[electron-dev] Sending SIGTERM to $count process(es): $all_pids"
|
||||
for pid in $all_pids; do
|
||||
echo "[electron-dev] Killing PIDs: $pids"
|
||||
for pid in $pids; do
|
||||
kill "$pid" 2>/dev/null || true
|
||||
done
|
||||
|
||||
# Wait up to 5s for graceful exit
|
||||
# Wait up to 5s for graceful exit, then force-kill survivors
|
||||
local waited=0
|
||||
while [ $waited -lt 5 ]; do
|
||||
local any_alive=0
|
||||
for pid in $all_pids; do
|
||||
if kill -0 "$pid" 2>/dev/null; then any_alive=1; break; fi
|
||||
local alive=""
|
||||
for pid in $pids; do
|
||||
kill -0 "$pid" 2>/dev/null && alive="$alive $pid"
|
||||
done
|
||||
[ "$any_alive" = "0" ] && break
|
||||
[ -z "$alive" ] && break
|
||||
sleep 1
|
||||
waited=$((waited + 1))
|
||||
done
|
||||
|
||||
# SIGKILL anyone still alive
|
||||
for pid in $all_pids; do
|
||||
# Force-kill any remaining
|
||||
for pid in $pids; do
|
||||
if kill -0 "$pid" 2>/dev/null; then
|
||||
echo "[electron-dev] Force-killing PID $pid"
|
||||
kill -9 "$pid" 2>/dev/null || true
|
||||
@@ -181,27 +98,7 @@ do_stop() {
|
||||
done
|
||||
fi
|
||||
|
||||
# Belt-and-suspenders: anything still bound to the CDP port goes away
|
||||
local port_pid
|
||||
port_pid=$(lsof -ti tcp:"$CDP_PORT" -sTCP:LISTEN 2>/dev/null || true)
|
||||
if [ -n "$port_pid" ]; then
|
||||
echo "[electron-dev] Port $CDP_PORT still bound by PID $port_pid; force-killing"
|
||||
# shellcheck disable=SC2086
|
||||
kill -9 $port_pid 2>/dev/null || true
|
||||
fi
|
||||
|
||||
# Also re-sweep the project's electron processes — sometimes the OS spawns
|
||||
# new helpers during shutdown that didn't exist when we first enumerated.
|
||||
local stragglers
|
||||
stragglers=$(pgrep -f "$PROJECT_ELECTRON_PATH" 2>/dev/null || true)
|
||||
if [ -n "$stragglers" ]; then
|
||||
echo "[electron-dev] Cleaning up stragglers: $stragglers"
|
||||
for pid in $stragglers; do
|
||||
kill -9 "$pid" 2>/dev/null || true
|
||||
done
|
||||
fi
|
||||
|
||||
# Close any agent-browser sessions connected to this port
|
||||
# Also close any agent-browser sessions connected to this port
|
||||
agent-browser --cdp "$CDP_PORT" close --all 2>/dev/null || true
|
||||
|
||||
rm -f "$PIDFILE"
|
||||
@@ -210,91 +107,113 @@ do_stop() {
|
||||
|
||||
do_status() {
|
||||
local pids
|
||||
pids=$(find_project_pids)
|
||||
pids=$(find_electron_pids)
|
||||
|
||||
if [ -z "$pids" ]; then
|
||||
echo "[electron-dev] No project Electron processes found."
|
||||
echo "[electron-dev] Electron is NOT running."
|
||||
return 1
|
||||
fi
|
||||
|
||||
echo "[electron-dev] Project processes: $pids"
|
||||
echo "[electron-dev] Electron is running (PIDs: $pids)"
|
||||
|
||||
if curl -sf --max-time 2 "http://localhost:${CDP_PORT}/json/version" >/dev/null 2>&1; then
|
||||
# Check CDP connectivity
|
||||
if agent-browser --cdp "$CDP_PORT" get url >/dev/null 2>&1; then
|
||||
local url
|
||||
url=$(agent-browser --cdp "$CDP_PORT" get url 2>&1 | tail -1 || echo "?")
|
||||
url=$(agent-browser --cdp "$CDP_PORT" get url 2>&1 | tail -1)
|
||||
echo "[electron-dev] CDP port ${CDP_PORT} is reachable. URL: $url"
|
||||
return 0
|
||||
else
|
||||
echo "[electron-dev] CDP port ${CDP_PORT} is NOT reachable (no --remote-debugging-port, or still loading)."
|
||||
echo "[electron-dev] CDP port ${CDP_PORT} is NOT reachable (Electron may still be loading)."
|
||||
return 2
|
||||
fi
|
||||
}
|
||||
|
||||
wait_for_electron() {
|
||||
echo "[electron-dev] Waiting for Electron process (up to ${ELECTRON_WAIT_S}s)..."
|
||||
local elapsed=0
|
||||
local interval=3
|
||||
while [ $elapsed -lt "$ELECTRON_WAIT_S" ]; do
|
||||
if strings "$ELECTRON_LOG" 2>/dev/null | grep -q "starting electron"; then
|
||||
echo "[electron-dev] Electron process started."
|
||||
return 0
|
||||
fi
|
||||
sleep "$interval"
|
||||
elapsed=$((elapsed + interval))
|
||||
echo "[electron-dev] Still waiting... (${elapsed}/${ELECTRON_WAIT_S}s)"
|
||||
done
|
||||
echo "[electron-dev] ERROR: Electron did not start within ${ELECTRON_WAIT_S}s"
|
||||
echo "[electron-dev] Last 20 lines of log:"
|
||||
tail -20 "$ELECTRON_LOG" 2>/dev/null || true
|
||||
return 1
|
||||
}
|
||||
|
||||
wait_for_renderer() {
|
||||
echo "[electron-dev] Waiting for renderer/SPA to load (up to ${RENDERER_WAIT_S}s)..."
|
||||
|
||||
# Initial delay — renderer needs time to bootstrap
|
||||
sleep 10
|
||||
|
||||
local elapsed=10
|
||||
local interval=5
|
||||
while [ $elapsed -lt "$RENDERER_WAIT_S" ]; do
|
||||
if agent-browser --cdp "$CDP_PORT" wait 2000 >/dev/null 2>&1; then
|
||||
# Check if interactive elements are present (SPA loaded)
|
||||
local snap
|
||||
snap=$(agent-browser --cdp "$CDP_PORT" snapshot -i 2>&1 || true)
|
||||
if echo "$snap" | grep -qE 'link |button '; then
|
||||
echo "[electron-dev] Renderer ready (interactive elements found)."
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
sleep "$interval"
|
||||
elapsed=$((elapsed + interval))
|
||||
echo "[electron-dev] SPA still loading... (${elapsed}/${RENDERER_WAIT_S}s)"
|
||||
done
|
||||
|
||||
echo "[electron-dev] WARNING: Timed out waiting for renderer, proceeding anyway."
|
||||
return 0
|
||||
}
|
||||
|
||||
do_start() {
|
||||
# Already up and CDP is reachable → nothing to do
|
||||
if curl -sf --max-time 2 "http://localhost:${CDP_PORT}/json/version" >/dev/null 2>&1; then
|
||||
echo "[electron-dev] CDP already reachable on port $CDP_PORT. Skipping start."
|
||||
echo "[electron-dev] Use 'restart' to force a fresh session."
|
||||
# If already running and healthy, skip
|
||||
local status_ok=0
|
||||
do_status >/dev/null 2>&1 || status_ok=$?
|
||||
if [ "$status_ok" -eq 0 ]; then
|
||||
echo "[electron-dev] Electron is already running and CDP is reachable. Skipping start."
|
||||
echo "[electron-dev] Use 'restart' to force a fresh session, or 'stop' to tear down."
|
||||
return 0
|
||||
fi
|
||||
|
||||
# Detect the user's existing dev session (or stale processes) BEFORE killing
|
||||
local existing
|
||||
existing=$(find_project_pids)
|
||||
if [ -n "$existing" ]; then
|
||||
echo "[electron-dev] Existing project Electron/vite processes detected:"
|
||||
echo "$existing" | tr ' ' '\n' | sed 's/^/[electron-dev] PID /'
|
||||
echo "[electron-dev] Tearing them down so we can start a CDP-enabled session..."
|
||||
fi
|
||||
|
||||
# Clean up any stale processes
|
||||
do_stop
|
||||
|
||||
# Wait for port + user-data-dir locks to release. Without this, the new
|
||||
# Electron may fail with "user data directory in use" or fail to bind CDP.
|
||||
local waited=0
|
||||
while [ $waited -lt 10 ]; do
|
||||
if ! lsof -i tcp:"$CDP_PORT" >/dev/null 2>&1 \
|
||||
&& ! pgrep -f "$PROJECT_ELECTRON_PATH" >/dev/null 2>&1; then
|
||||
break
|
||||
fi
|
||||
[ $waited -eq 0 ] && echo "[electron-dev] Waiting for port + Electron locks to release..."
|
||||
sleep 1
|
||||
waited=$((waited + 1))
|
||||
done
|
||||
|
||||
# Start fresh
|
||||
echo "[electron-dev] Starting Electron dev server..."
|
||||
echo "[electron-dev] Project: $PROJECT_ROOT"
|
||||
echo "[electron-dev] Project: $PROJECT_ROOT"
|
||||
echo "[electron-dev] CDP port: $CDP_PORT"
|
||||
echo "[electron-dev] Log: $ELECTRON_LOG"
|
||||
echo "[electron-dev] Log: $ELECTRON_LOG"
|
||||
|
||||
: > "$ELECTRON_LOG" # Truncate log
|
||||
|
||||
# Launch in a new session (setsid) so the whole process tree shares a PGID
|
||||
# we can later signal in one shot. `setsid bash -c '... exec ...' &` keeps
|
||||
# the bash shell as the session leader; its PID is what we save.
|
||||
# macOS doesn't ship setsid by default — fall back to plain bash; cleanup
|
||||
# still works via `expand_descendants` walking the process tree.
|
||||
local launch_cmd="
|
||||
cd '$PROJECT_ROOT/apps/desktop'
|
||||
exec npx electron-vite dev -- --remote-debugging-port=$CDP_PORT
|
||||
"
|
||||
if command -v setsid >/dev/null 2>&1; then
|
||||
setsid bash -c "$launch_cmd" >> "$ELECTRON_LOG" 2>&1 < /dev/null &
|
||||
else
|
||||
bash -c "$launch_cmd" >> "$ELECTRON_LOG" 2>&1 < /dev/null &
|
||||
fi
|
||||
local launcher_pid=$!
|
||||
echo "$launcher_pid" > "$PIDFILE"
|
||||
echo "[electron-dev] Launcher PID (session leader): $launcher_pid"
|
||||
(
|
||||
cd "$PROJECT_ROOT/apps/desktop" && \
|
||||
ELECTRON_ENABLE_LOGGING=1 npx electron-vite dev -- --remote-debugging-port="$CDP_PORT" \
|
||||
>> "$ELECTRON_LOG" 2>&1
|
||||
) &
|
||||
local bg_pid=$!
|
||||
echo "$bg_pid" > "$PIDFILE"
|
||||
echo "[electron-dev] Background PID: $bg_pid"
|
||||
|
||||
if ! wait_for_cdp; then
|
||||
echo "[electron-dev] Failed to bring up CDP. Cleaning up..."
|
||||
# Wait for Electron process to start
|
||||
if ! wait_for_electron; then
|
||||
echo "[electron-dev] Failed to start. Cleaning up..."
|
||||
do_stop
|
||||
return 1
|
||||
fi
|
||||
|
||||
# Wait for renderer to be interactive
|
||||
if ! wait_for_renderer; then
|
||||
echo "[electron-dev] Renderer not interactive — you may need to wait more."
|
||||
echo "[electron-dev] Renderer not ready, but Electron is running. You may need to wait more."
|
||||
fi
|
||||
|
||||
echo "[electron-dev] Ready! Use: agent-browser --cdp $CDP_PORT snapshot -i"
|
||||
@@ -302,7 +221,7 @@ do_start() {
|
||||
|
||||
do_restart() {
|
||||
do_stop
|
||||
sleep 1
|
||||
sleep 2
|
||||
do_start
|
||||
}
|
||||
|
||||
@@ -316,12 +235,10 @@ case "${1:-help}" in
|
||||
*)
|
||||
echo "Usage: $0 {start|stop|status|restart}"
|
||||
echo ""
|
||||
echo " start — Start Electron dev with CDP. Detects + tears down any"
|
||||
echo " existing project Electron (e.g. \`bun run dev\`) first."
|
||||
echo " stop — Kill all project Electron/vite processes (main + helpers"
|
||||
echo " + descendants), with SIGTERM → 5s wait → SIGKILL fallback."
|
||||
echo " status — Check if Electron is running and CDP is reachable."
|
||||
echo " restart — Stop then start."
|
||||
echo " start — Start Electron dev with CDP (idempotent, skips if already running)"
|
||||
echo " stop — Kill all Electron dev processes (main + helpers + vite)"
|
||||
echo " status — Check if Electron is running and CDP is reachable"
|
||||
echo " restart — Stop then start"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
@@ -1,16 +1,10 @@
|
||||
---
|
||||
name: microcopy
|
||||
description: UI copy and microcopy guidelines. Use when writing UI text, buttons, error messages, empty states, onboarding, or any user-facing copy. Triggers on i18n translation, UI text writing, or copy improvement tasks. Supports both Chinese and English.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# LobeHub UI Microcopy Guidelines
|
||||
|
||||
This file is the quick-reference summary. For full prompt-style guidelines with extensive examples (anti-patterns, tone matrices, scenario walk-throughs), load the language-specific reference:
|
||||
|
||||
- **中文文案** — [`references/zh.md`](./references/zh.md)
|
||||
- **English copy** — [`references/en.md`](./references/en.md)
|
||||
|
||||
Brand: **Where Agents Collaborate** - Focus on collaborative agent system, not just "generation".
|
||||
|
||||
## Fixed Terminology
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: modal
|
||||
description: "LobeHub imperative-modal conventions. Use whenever creating, editing, opening, or migrating a modal/dialog/popup — prefer `createModal` / `confirmModal` / `useModalContext` from `@lobehub/ui/base-ui` (headless) over the legacy root `@lobehub/ui` `createModal` (antd Modal props) and over any declarative `open` state + `<Modal />` pattern. Covers required `ModalHost` mounting, the `Content` + `index.tsx` file layout, `content` vs `children` slot, i18n inside `createModal()` (`import { t } from 'i18next'`), and migration notes. Triggers on `createModal`, `confirmModal`, `useModalContext`, `ModalHost`, `antd Modal`, `<Modal open>`, 'open a modal', 'popup', 'dialog', 'confirm dialog', '弹框', '弹窗', '确认框', 'migrate to base-ui'."
|
||||
description: MUST use when creating, editing, or writing modal dialogs or imperative modals. Prefer createModal / useModalContext / confirmModal from @lobehub/ui/base-ui; root @lobehub/ui is legacy (antd Modal). Covers patterns, ModalHost, and migration notes.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: project-overview
|
||||
description: Complete project architecture and structure guide. Use when exploring the codebase, understanding project organization, finding files, or needing comprehensive architectural context. Triggers on architecture questions, directory navigation, or project overview needs.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# LobeHub Project Overview
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: react
|
||||
description: "LobeHub React/SPA component conventions: antd-style with `createStaticStyles` + `cssVar.*` (prefer zero-runtime over `createStyles` + `token`), `@lobehub/ui/base-ui` primitives before `@lobehub/ui` before antd, `Flexbox`/`Center` for layouts, react-router-dom navigation, and the `.desktop.tsx` sync rule. Use when writing or editing any `.tsx` under `src/**`, picking a styling helper, choosing a component (Select/Modal/Drawer/Button/Tooltip), wiring routes in `desktopRouter.config.tsx`/`.desktop.tsx`, or adding a `Link`/`useNavigate` call in the SPA. Triggers on `createStyles`/`createStaticStyles`, `cssVar`, `@lobehub/ui`, `antd-style`, `Flexbox`, `useNavigate`, `react-router-dom`, `Link`, 'new component', 'add a page', 'edit a layout', 'desktopRouter', 'componentMap.desktop'."
|
||||
user-invocable: false
|
||||
description: React component development guide. Use when working with React components (.tsx files), creating UI, using @lobehub/ui components, implementing routing, or building frontend features. Triggers on React component creation, modification, layout implementation, or navigation tasks.
|
||||
---
|
||||
|
||||
# React Component Writing Guide
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: review-checklist
|
||||
description: 'Common recurring mistakes in LobeHub code review — console leftovers, missing return await, hardcoded secrets, hardcoded i18n strings, desktop router pair drift, antd vs @lobehub/ui, non-idempotent migrations, cloud impact red flags. Use as a quick checklist when reviewing PRs, diffs, or branch changes.'
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# Review Checklist
|
||||
|
||||
@@ -1,44 +0,0 @@
|
||||
---
|
||||
name: 'source-command-dedupe'
|
||||
description: 'Find duplicate GitHub issues'
|
||||
---
|
||||
|
||||
# source-command-dedupe
|
||||
|
||||
Use this skill when the user asks to run the migrated source command `dedupe`.
|
||||
|
||||
## Command Template
|
||||
|
||||
Find up to 3 likely duplicate issues for a given GitHub issue.
|
||||
|
||||
To do this, follow these steps precisely:
|
||||
|
||||
1. Use an agent to check if the Github issue (a) is closed, (b) does not need to be deduped (eg. because it is broad product feedback without a specific solution, or positive feedback), or (c) already has a duplicates comment that you made earlier. If so, do not proceed.
|
||||
2. Use an agent to view a Github issue, and ask the agent to return a summary of the issue
|
||||
3. Then, launch 5 parallel agents to search Github for duplicates of this issue, using diverse keywords and search approaches, using the summary from #1
|
||||
4. Next, feed the results from #1 and #2 into another agent, so that it can filter out false positives, that are likely not actually duplicates of the original issue. If there are no duplicates remaining, do not proceed.
|
||||
5. Finally, comment back on the issue with a list of up to three duplicate issues (or zero, if there are no likely duplicates)
|
||||
|
||||
Notes (be sure to tell this to your agents, too):
|
||||
|
||||
- Use `gh` to interact with Github, rather than web fetch
|
||||
- Do not use other tools, beyond `gh` (eg. don't use other MCP servers, file edit, etc.)
|
||||
- Make a todo list first
|
||||
- For your comment, follow the following format precisely (assuming for this example that you found 3 suspected duplicates):
|
||||
|
||||
---
|
||||
|
||||
Found 3 possible duplicate issues:
|
||||
|
||||
1. <link to issue>
|
||||
2. <link to issue>
|
||||
3. <link to issue>
|
||||
|
||||
This issue will be automatically closed as a duplicate in 3 days.
|
||||
|
||||
- If your issue is a duplicate, please close it and 👍 the existing issue instead
|
||||
- To prevent auto-closure, add a comment or 👎 this comment
|
||||
|
||||
> 🤖 Generated with Codex
|
||||
|
||||
---
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: spa-routes
|
||||
description: MUST use when editing src/routes/ segments, src/spa/router/desktopRouter.config.tsx or desktopRouter.config.desktop.tsx (always change both together), mobileRouter.config.tsx, or when moving UI/logic between routes and src/features/.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# SPA Routes and Features Guide
|
||||
@@ -85,10 +84,10 @@ Each feature should:
|
||||
|
||||
## 3a. Desktop router pair (`desktopRouter.config` × 2)
|
||||
|
||||
| File | Role |
|
||||
| ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `desktopRouter.config.tsx` | Dynamic imports via `dynamicElement` / `dynamicLayout` — code-splitting; used by `entry.web.tsx` and `entry.desktop.tsx`. |
|
||||
| `desktopRouter.config.desktop.tsx` | Same route tree with **synchronous** imports — kept for Electron / local parity and predictable bundling. |
|
||||
| File | Role |
|
||||
|------|------|
|
||||
| `desktopRouter.config.tsx` | Dynamic imports via `dynamicElement` / `dynamicLayout` — code-splitting; used by `entry.web.tsx` and `entry.desktop.tsx`. |
|
||||
| `desktopRouter.config.desktop.tsx` | Same route tree with **synchronous** imports — kept for Electron / local parity and predictable bundling. |
|
||||
|
||||
Anything that changes the tree (new segment, renamed `path`, moved layout, new child route) must be reflected in **both** files in one PR or commit. Remove routes from both when deleting.
|
||||
|
||||
|
||||
@@ -1,91 +1,257 @@
|
||||
---
|
||||
name: store-data-structures
|
||||
description: Zustand store data structure patterns for LobeHub. Covers List vs Detail data structures, Map + Reducer patterns, type definitions, and when to use each pattern. Use when designing store state, choosing data structures, or implementing list/detail pages.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# LobeHub Store Data Structures
|
||||
|
||||
How to structure data in Zustand stores for fast list rendering, multi-detail caching, and ergonomic optimistic updates.
|
||||
This guide covers how to structure data in Zustand stores for optimal performance and user experience.
|
||||
|
||||
## Core Principles
|
||||
|
||||
### ✅ DO
|
||||
|
||||
1. **Separate List and Detail** — different structures for list pages and detail pages
|
||||
2. **Use Map for Details** — cache multiple detail pages with `Record<string, Detail>`
|
||||
3. **Use Array for Lists** — simple arrays for list display
|
||||
4. **Types from `@lobechat/types`** — never use `@lobechat/database` types in stores
|
||||
5. **Distinguish List and Detail types** — List types may have computed UI fields
|
||||
1. **Separate List and Detail** - Use different structures for list pages and detail pages
|
||||
2. **Use Map for Details** - Cache multiple detail pages with `Record<string, Detail>`
|
||||
3. **Use Array for Lists** - Simple arrays for list display
|
||||
4. **Types from @lobechat/types** - Never use `@lobechat/database` types in stores
|
||||
5. **Distinguish List and Detail types** - List types may have computed UI fields
|
||||
|
||||
### ❌ DON'T
|
||||
|
||||
1. **Don't use a single detail object** — can't cache multiple pages
|
||||
2. **Don't mix List and Detail types** — they have different purposes
|
||||
3. **Don't use database types** — use types from `@lobechat/types`
|
||||
4. **Don't use Map for lists** — simple arrays are sufficient
|
||||
1. **Don't use single detail object** - Can't cache multiple pages
|
||||
2. **Don't mix List and Detail types** - They have different purposes
|
||||
3. **Don't use database types** - Use types from `@lobechat/types`
|
||||
4. **Don't use Map for lists** - Simple arrays are sufficient
|
||||
|
||||
---
|
||||
|
||||
## Type Definitions
|
||||
|
||||
Each entity gets its own file under `@lobechat/types/`. Each file exports two types:
|
||||
Types should be organized by entity in separate files:
|
||||
|
||||
- **Detail type** — full entity, including heavy fields (rubrics, content, editor state, …)
|
||||
- **List item type** — a **subset** that excludes heavy fields, may add computed UI fields (counts, timestamps formatted for display)
|
||||
```
|
||||
@lobechat/types/src/eval/
|
||||
├── benchmark.ts # Benchmark types
|
||||
├── agentEvalDataset.ts # Dataset types
|
||||
├── agentEvalRun.ts # Run types
|
||||
└── index.ts # Re-exports
|
||||
```
|
||||
|
||||
**Important:** the List type is a **subset**, not an `extends` of Detail. Extending pulls the heavy fields right back in.
|
||||
### Example: Benchmark Types
|
||||
|
||||
> See [`references/types.md`](./references/types.md) for full worked examples (Benchmark, Document) and the heavy-field exclusion checklist.
|
||||
```typescript
|
||||
// packages/types/src/eval/benchmark.ts
|
||||
import type { EvalBenchmarkRubric } from './rubric';
|
||||
|
||||
// ============================================
|
||||
// Detail Type - Full entity (for detail pages)
|
||||
// ============================================
|
||||
|
||||
/**
|
||||
* Full benchmark entity with all fields including heavy data
|
||||
*/
|
||||
export interface AgentEvalBenchmark {
|
||||
createdAt: Date;
|
||||
description?: string | null;
|
||||
id: string;
|
||||
identifier: string;
|
||||
isSystem: boolean;
|
||||
metadata?: Record<string, unknown> | null;
|
||||
name: string;
|
||||
referenceUrl?: string | null;
|
||||
rubrics: EvalBenchmarkRubric[]; // Heavy field
|
||||
updatedAt: Date;
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// List Type - Lightweight (for list display)
|
||||
// ============================================
|
||||
|
||||
/**
|
||||
* Lightweight benchmark item - excludes heavy fields
|
||||
* May include computed statistics for UI
|
||||
*/
|
||||
export interface AgentEvalBenchmarkListItem {
|
||||
createdAt: Date;
|
||||
description?: string | null;
|
||||
id: string;
|
||||
identifier: string;
|
||||
isSystem: boolean;
|
||||
name: string;
|
||||
// Note: rubrics NOT included (heavy field)
|
||||
|
||||
// Computed statistics for UI display
|
||||
datasetCount?: number;
|
||||
runCount?: number;
|
||||
testCaseCount?: number;
|
||||
}
|
||||
```
|
||||
|
||||
### Example: Document Types (with heavy content)
|
||||
|
||||
```typescript
|
||||
// packages/types/src/document.ts
|
||||
|
||||
/**
|
||||
* Full document entity - includes heavy content fields
|
||||
*/
|
||||
export interface Document {
|
||||
id: string;
|
||||
title: string;
|
||||
description?: string;
|
||||
content: string; // Heavy field - full markdown content
|
||||
editorData: any; // Heavy field - editor state
|
||||
metadata?: Record<string, unknown>;
|
||||
createdAt: Date;
|
||||
updatedAt: Date;
|
||||
}
|
||||
|
||||
/**
|
||||
* Lightweight document item - excludes heavy content
|
||||
*/
|
||||
export interface DocumentListItem {
|
||||
id: string;
|
||||
title: string;
|
||||
description?: string;
|
||||
// Note: content and editorData NOT included
|
||||
createdAt: Date;
|
||||
updatedAt: Date;
|
||||
|
||||
// Computed statistics
|
||||
wordCount?: number;
|
||||
lastEditedBy?: string;
|
||||
}
|
||||
```
|
||||
|
||||
**Key Points:**
|
||||
|
||||
- **Detail types** include ALL fields from database (full entity)
|
||||
- **List types** are **subsets** that exclude heavy/large fields
|
||||
- List types may add computed statistics for UI (e.g., `testCaseCount`)
|
||||
- **Each entity gets its own file** (not mixed together)
|
||||
- **All types** exported from `@lobechat/types`, NOT `@lobechat/database`
|
||||
|
||||
**Heavy fields to exclude from List:**
|
||||
|
||||
- Large text content (`content`, `editorData`, `fullDescription`)
|
||||
- Complex objects (`rubrics`, `config`, `metrics`)
|
||||
- Binary data (`image`, `file`)
|
||||
- Large arrays (`messages`, `items`)
|
||||
|
||||
---
|
||||
|
||||
## When to Use Map vs Array
|
||||
|
||||
### Use Map + Reducer — for Detail Data
|
||||
### Use Map + Reducer (for Detail Data)
|
||||
|
||||
✅ Detail page data caching — multiple detail pages cached simultaneously
|
||||
✅ Optimistic updates — update UI before API responds
|
||||
✅ Per-item loading states — track which items are being updated
|
||||
✅ Multi-page navigation — user can switch between details without refetching
|
||||
✅ **Detail page data caching** - Cache multiple detail pages simultaneously
|
||||
✅ **Optimistic updates** - Update UI before API responds
|
||||
✅ **Per-item loading states** - Track which items are being updated
|
||||
✅ **Multiple pages open** - User can navigate between details without refetching
|
||||
|
||||
**Structure:**
|
||||
|
||||
```typescript
|
||||
benchmarkDetailMap: Record<string, AgentEvalBenchmark>;
|
||||
```
|
||||
|
||||
Examples: benchmark detail pages, dataset detail pages, user profiles.
|
||||
**Example:** Benchmark detail pages, Dataset detail pages, User profiles
|
||||
|
||||
### Use Simple Array — for List Data
|
||||
### Use Simple Array (for List Data)
|
||||
|
||||
✅ List display — lists, tables, cards
|
||||
✅ Refresh as a whole — entire list refreshes together
|
||||
✅ No per-item updates — no need to mutate individual rows in place
|
||||
✅ Simple data flow — fewer moving parts
|
||||
✅ **List display** - Lists, tables, cards
|
||||
✅ **Read-only or refresh-as-whole** - Entire list refreshes together
|
||||
✅ **No per-item updates** - No need to update individual items
|
||||
✅ **Simple data flow** - Easier to understand and maintain
|
||||
|
||||
**Structure:**
|
||||
|
||||
```typescript
|
||||
benchmarkList: AgentEvalBenchmarkListItem[];
|
||||
benchmarkList: AgentEvalBenchmarkListItem[]
|
||||
```
|
||||
|
||||
Examples: benchmark list, dataset list, user list.
|
||||
**Example:** Benchmark list, Dataset list, User list
|
||||
|
||||
---
|
||||
|
||||
## State Structure Pattern
|
||||
|
||||
### Complete Example
|
||||
|
||||
```typescript
|
||||
// packages/types/src/eval/benchmark.ts
|
||||
import type { EvalBenchmarkRubric } from './rubric';
|
||||
|
||||
/**
|
||||
* Full benchmark entity (for detail pages)
|
||||
*/
|
||||
export interface AgentEvalBenchmark {
|
||||
id: string;
|
||||
name: string;
|
||||
description?: string | null;
|
||||
identifier: string;
|
||||
rubrics: EvalBenchmarkRubric[]; // Heavy field
|
||||
metadata?: Record<string, unknown> | null;
|
||||
isSystem: boolean;
|
||||
createdAt: Date;
|
||||
updatedAt: Date;
|
||||
}
|
||||
|
||||
/**
|
||||
* Lightweight benchmark (for list display)
|
||||
* Excludes heavy fields like rubrics
|
||||
*/
|
||||
export interface AgentEvalBenchmarkListItem {
|
||||
id: string;
|
||||
name: string;
|
||||
description?: string | null;
|
||||
identifier: string;
|
||||
isSystem: boolean;
|
||||
createdAt: Date;
|
||||
// Note: rubrics excluded
|
||||
|
||||
// Computed statistics
|
||||
testCaseCount?: number;
|
||||
datasetCount?: number;
|
||||
runCount?: number;
|
||||
}
|
||||
```
|
||||
|
||||
```typescript
|
||||
// src/store/eval/slices/benchmark/initialState.ts
|
||||
import type { AgentEvalBenchmark, AgentEvalBenchmarkListItem } from '@lobechat/types';
|
||||
|
||||
export interface BenchmarkSliceState {
|
||||
// List — simple array
|
||||
// ============================================
|
||||
// List Data - Simple Array
|
||||
// ============================================
|
||||
/**
|
||||
* List of benchmarks for list page display
|
||||
* May include computed fields like testCaseCount
|
||||
*/
|
||||
benchmarkList: AgentEvalBenchmarkListItem[];
|
||||
benchmarkListInit: boolean;
|
||||
|
||||
// Detail — map for multi-entity caching
|
||||
// ============================================
|
||||
// Detail Data - Map for Caching
|
||||
// ============================================
|
||||
/**
|
||||
* Map of benchmark details keyed by ID
|
||||
* Caches detail page data for multiple benchmarks
|
||||
* Enables optimistic updates and per-item loading
|
||||
*/
|
||||
benchmarkDetailMap: Record<string, AgentEvalBenchmark>;
|
||||
loadingBenchmarkDetailIds: string[]; // per-item loading
|
||||
|
||||
// Mutation states (drive form-level UI)
|
||||
/**
|
||||
* Track which benchmark details are being loaded/updated
|
||||
* For showing spinners on specific items
|
||||
*/
|
||||
loadingBenchmarkDetailIds: string[];
|
||||
|
||||
// ============================================
|
||||
// Mutation States
|
||||
// ============================================
|
||||
isCreatingBenchmark: boolean;
|
||||
isUpdatingBenchmark: boolean;
|
||||
isDeletingBenchmark: boolean;
|
||||
@@ -106,51 +272,180 @@ export const benchmarkInitialState: BenchmarkSliceState = {
|
||||
|
||||
## Reducer Pattern (for Detail Map)
|
||||
|
||||
When the Detail Map needs optimistic updates (i.e. the user edits a row and the UI should reflect it before the server confirms), wire a typed reducer instead of inlining `set` calls. This keeps mutations testable and the dispatch surface small.
|
||||
### Why Use Reducer?
|
||||
|
||||
> See [`references/reducer.md`](./references/reducer.md) for the full discriminated-union action types, the `produce`-based reducer, and the `internal_dispatch*` slice methods that connect them to Zustand.
|
||||
- **Immutable updates** - Immer ensures immutability
|
||||
- **Type-safe actions** - TypeScript discriminated unions
|
||||
- **Testable** - Pure functions easy to test
|
||||
- **Reusable** - Same reducer for optimistic updates and server data
|
||||
|
||||
### Reducer Structure
|
||||
|
||||
```typescript
|
||||
// src/store/eval/slices/benchmark/reducer.ts
|
||||
import { produce } from 'immer';
|
||||
import type { AgentEvalBenchmark } from '@lobechat/types';
|
||||
|
||||
// ============================================
|
||||
// Action Types
|
||||
// ============================================
|
||||
|
||||
type SetBenchmarkDetailAction = {
|
||||
id: string;
|
||||
type: 'setBenchmarkDetail';
|
||||
value: AgentEvalBenchmark;
|
||||
};
|
||||
|
||||
type UpdateBenchmarkDetailAction = {
|
||||
id: string;
|
||||
type: 'updateBenchmarkDetail';
|
||||
value: Partial<AgentEvalBenchmark>;
|
||||
};
|
||||
|
||||
type DeleteBenchmarkDetailAction = {
|
||||
id: string;
|
||||
type: 'deleteBenchmarkDetail';
|
||||
};
|
||||
|
||||
export type BenchmarkDetailDispatch =
|
||||
| SetBenchmarkDetailAction
|
||||
| UpdateBenchmarkDetailAction
|
||||
| DeleteBenchmarkDetailAction;
|
||||
|
||||
// ============================================
|
||||
// Reducer Function
|
||||
// ============================================
|
||||
|
||||
export const benchmarkDetailReducer = (
|
||||
state: Record<string, AgentEvalBenchmark> = {},
|
||||
payload: BenchmarkDetailDispatch,
|
||||
): Record<string, AgentEvalBenchmark> => {
|
||||
switch (payload.type) {
|
||||
case 'setBenchmarkDetail': {
|
||||
return produce(state, (draft) => {
|
||||
draft[payload.id] = payload.value;
|
||||
});
|
||||
}
|
||||
|
||||
case 'updateBenchmarkDetail': {
|
||||
return produce(state, (draft) => {
|
||||
if (draft[payload.id]) {
|
||||
draft[payload.id] = { ...draft[payload.id], ...payload.value };
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
case 'deleteBenchmarkDetail': {
|
||||
return produce(state, (draft) => {
|
||||
delete draft[payload.id];
|
||||
});
|
||||
}
|
||||
|
||||
default:
|
||||
return state;
|
||||
}
|
||||
};
|
||||
```
|
||||
|
||||
### Internal Dispatch Methods
|
||||
|
||||
```typescript
|
||||
// In action.ts
|
||||
export interface BenchmarkAction {
|
||||
// ... other methods ...
|
||||
|
||||
// Internal methods - not for direct UI use
|
||||
internal_dispatchBenchmarkDetail: (payload: BenchmarkDetailDispatch) => void;
|
||||
internal_updateBenchmarkDetailLoading: (id: string, loading: boolean) => void;
|
||||
}
|
||||
|
||||
export const createBenchmarkSlice: StateCreator<...> = (set, get) => ({
|
||||
// ... other methods ...
|
||||
|
||||
// Internal - Dispatch to reducer
|
||||
internal_dispatchBenchmarkDetail: (payload) => {
|
||||
const currentMap = get().benchmarkDetailMap;
|
||||
const nextMap = benchmarkDetailReducer(currentMap, payload);
|
||||
|
||||
// Only update if changed
|
||||
if (isEqual(nextMap, currentMap)) return;
|
||||
|
||||
set(
|
||||
{ benchmarkDetailMap: nextMap },
|
||||
false,
|
||||
`dispatchBenchmarkDetail/${payload.type}`,
|
||||
);
|
||||
},
|
||||
|
||||
// Internal - Update loading state
|
||||
internal_updateBenchmarkDetailLoading: (id, loading) => {
|
||||
set(
|
||||
(state) => {
|
||||
if (loading) {
|
||||
return { loadingBenchmarkDetailIds: [...state.loadingBenchmarkDetailIds, id] };
|
||||
}
|
||||
return {
|
||||
loadingBenchmarkDetailIds: state.loadingBenchmarkDetailIds.filter((i) => i !== id),
|
||||
};
|
||||
},
|
||||
false,
|
||||
'updateBenchmarkDetailLoading',
|
||||
);
|
||||
},
|
||||
});
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Data Structure Comparison
|
||||
|
||||
### ❌ WRONG — Single Detail Object
|
||||
### ❌ WRONG - Single Detail Object
|
||||
|
||||
```typescript
|
||||
interface BenchmarkSliceState {
|
||||
// ❌ Can only cache one detail
|
||||
benchmarkDetail: AgentEvalBenchmark | null;
|
||||
|
||||
// ❌ Global loading state
|
||||
isLoadingBenchmarkDetail: boolean;
|
||||
}
|
||||
```
|
||||
|
||||
Problems:
|
||||
**Problems:**
|
||||
|
||||
- Can only cache one detail page at a time
|
||||
- Switching between details forces refetch
|
||||
- Switching between details causes unnecessary refetches
|
||||
- No optimistic updates
|
||||
- No per-item loading states
|
||||
|
||||
### ✅ CORRECT — Separate List and Detail
|
||||
### ✅ CORRECT - Separate List and Detail
|
||||
|
||||
```typescript
|
||||
import type { AgentEvalBenchmark, AgentEvalBenchmarkListItem } from '@lobechat/types';
|
||||
|
||||
interface BenchmarkSliceState {
|
||||
// ✅ List data - simple array
|
||||
benchmarkList: AgentEvalBenchmarkListItem[];
|
||||
benchmarkListInit: boolean;
|
||||
|
||||
// ✅ Detail data - map for caching
|
||||
benchmarkDetailMap: Record<string, AgentEvalBenchmark>;
|
||||
|
||||
// ✅ Per-item loading
|
||||
loadingBenchmarkDetailIds: string[];
|
||||
|
||||
// ✅ Mutation states
|
||||
isCreatingBenchmark: boolean;
|
||||
isUpdatingBenchmark: boolean;
|
||||
isDeletingBenchmark: boolean;
|
||||
}
|
||||
```
|
||||
|
||||
Benefits:
|
||||
**Benefits:**
|
||||
|
||||
- Cache multiple detail pages
|
||||
- Fast navigation between cached details
|
||||
- Optimistic updates via reducer
|
||||
- Optimistic updates with reducer
|
||||
- Per-item loading states
|
||||
- Clear separation of concerns
|
||||
|
||||
@@ -160,16 +455,22 @@ Benefits:
|
||||
|
||||
### Accessing List Data
|
||||
|
||||
```tsx
|
||||
```typescript
|
||||
const BenchmarkList = () => {
|
||||
// Simple array access
|
||||
const benchmarks = useEvalStore((s) => s.benchmarkList);
|
||||
const isInit = useEvalStore((s) => s.benchmarkListInit);
|
||||
|
||||
if (!isInit) return <Loading />;
|
||||
|
||||
return (
|
||||
<div>
|
||||
{benchmarks.map((b) => (
|
||||
<BenchmarkCard key={b.id} name={b.name} testCaseCount={b.testCaseCount} />
|
||||
{benchmarks.map(b => (
|
||||
<BenchmarkCard
|
||||
key={b.id}
|
||||
name={b.name}
|
||||
testCaseCount={b.testCaseCount} // Computed field
|
||||
/>
|
||||
))}
|
||||
</div>
|
||||
);
|
||||
@@ -178,18 +479,22 @@ const BenchmarkList = () => {
|
||||
|
||||
### Accessing Detail Data
|
||||
|
||||
```tsx
|
||||
```typescript
|
||||
const BenchmarkDetail = () => {
|
||||
const { benchmarkId } = useParams<{ benchmarkId: string }>();
|
||||
|
||||
// Get from map
|
||||
const benchmark = useEvalStore((s) =>
|
||||
benchmarkId ? s.benchmarkDetailMap[benchmarkId] : undefined,
|
||||
);
|
||||
|
||||
// Check loading
|
||||
const isLoading = useEvalStore((s) =>
|
||||
benchmarkId ? s.loadingBenchmarkDetailIds.includes(benchmarkId) : false,
|
||||
);
|
||||
|
||||
if (!benchmark) return <Loading />;
|
||||
|
||||
return (
|
||||
<div>
|
||||
<h1>{benchmark.name}</h1>
|
||||
@@ -205,6 +510,7 @@ const BenchmarkDetail = () => {
|
||||
// src/store/eval/slices/benchmark/selectors.ts
|
||||
export const benchmarkSelectors = {
|
||||
getBenchmarkDetail: (id: string) => (s: EvalStore) => s.benchmarkDetailMap[id],
|
||||
|
||||
isLoadingBenchmarkDetail: (id: string) => (s: EvalStore) =>
|
||||
s.loadingBenchmarkDetailIds.includes(id),
|
||||
};
|
||||
@@ -218,7 +524,7 @@ const isLoading = useEvalStore(benchmarkSelectors.isLoadingBenchmarkDetail(bench
|
||||
|
||||
## Decision Tree
|
||||
|
||||
```text
|
||||
```
|
||||
Need to store data?
|
||||
│
|
||||
├─ Is it a LIST for display?
|
||||
@@ -241,40 +547,43 @@ Need to store data?
|
||||
|
||||
When designing store state structure:
|
||||
|
||||
- [ ] **Organize types by entity** in separate files (e.g. `benchmark.ts`, `agentEvalDataset.ts`)
|
||||
- [ ] **Organize types by entity** in separate files (e.g., `benchmark.ts`, `agentEvalDataset.ts`)
|
||||
- [ ] Create **Detail** type (full entity with all fields including heavy ones)
|
||||
- [ ] Create **ListItem** type:
|
||||
- [ ] Subset of Detail (exclude heavy fields)
|
||||
- [ ] Subset of Detail type (exclude heavy fields)
|
||||
- [ ] May include computed statistics for UI
|
||||
- [ ] **NOT** `extends` Detail
|
||||
- [ ] **NOT** extending Detail type (it's a subset, not extension)
|
||||
- [ ] Use **array** for list data: `xxxList: XxxListItem[]`
|
||||
- [ ] Use **Map** for detail data: `xxxDetailMap: Record<string, Xxx>`
|
||||
- [ ] Per-item loading: `loadingXxxDetailIds: string[]`
|
||||
- [ ] **Reducer** for detail map if optimistic updates needed (see [`references/reducer.md`](./references/reducer.md))
|
||||
- [ ] **Internal dispatch** and **loading** methods
|
||||
- [ ] **Selectors** for clean access (optional but recommended)
|
||||
- [ ] Document in comments which fields are excluded from List and why
|
||||
- [ ] Add per-item loading: `loadingXxxDetailIds: string[]`
|
||||
- [ ] Create **reducer** for detail map if optimistic updates needed
|
||||
- [ ] Add **internal dispatch** and **loading** methods
|
||||
- [ ] Create **selectors** for clean access (optional but recommended)
|
||||
- [ ] Document in comments:
|
||||
- [ ] What fields are excluded from List and why
|
||||
- [ ] What computed fields mean
|
||||
- [ ] What each Map is for
|
||||
|
||||
---
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **File organization** — one entity per file, not mixed
|
||||
2. **List is a subset** — ListItem excludes heavy fields, does not `extends` Detail
|
||||
3. **Clear naming** — `xxxList` for arrays, `xxxDetailMap` for maps
|
||||
4. **Consistent patterns** — all detail maps follow the same shape
|
||||
5. **Type safety** — never use `any`, always use proper types
|
||||
6. **Document exclusions** — comment which fields are excluded and why
|
||||
7. **Selectors** — encapsulate access patterns
|
||||
8. **Loading states** — per-item for details, global for mutations
|
||||
9. **Immutability** — use Immer in reducers
|
||||
1. **File organization** - One entity per file, not mixed together
|
||||
2. **List is subset** - ListItem excludes heavy fields, not extends Detail
|
||||
3. **Clear naming** - `xxxList` for arrays, `xxxDetailMap` for maps
|
||||
4. **Consistent patterns** - All detail maps follow same structure
|
||||
5. **Type safety** - Never use `any`, always use proper types
|
||||
6. **Document exclusions** - Comment which fields are excluded from List and why
|
||||
7. **Selectors** - Encapsulate access patterns
|
||||
8. **Loading states** - Per-item for details, global for lists
|
||||
9. **Immutability** - Use Immer in reducers
|
||||
|
||||
### Common Mistakes to Avoid
|
||||
|
||||
❌ **DON'T extend Detail in List:**
|
||||
|
||||
```typescript
|
||||
// Wrong — pulls heavy fields back in
|
||||
// Wrong - List should not extend Detail
|
||||
export interface BenchmarkListItem extends Benchmark {
|
||||
testCaseCount?: number;
|
||||
}
|
||||
@@ -283,6 +592,7 @@ export interface BenchmarkListItem extends Benchmark {
|
||||
✅ **DO create separate subset:**
|
||||
|
||||
```typescript
|
||||
// Correct - List is a subset with computed fields
|
||||
export interface BenchmarkListItem {
|
||||
id: string;
|
||||
name: string;
|
||||
@@ -293,14 +603,14 @@ export interface BenchmarkListItem {
|
||||
|
||||
❌ **DON'T mix entities in one file:**
|
||||
|
||||
```text
|
||||
// Wrong — all entities in agentEvalEntities.ts
|
||||
```typescript
|
||||
// Wrong - all entities in agentEvalEntities.ts
|
||||
```
|
||||
|
||||
✅ **DO separate by entity:**
|
||||
|
||||
```text
|
||||
// Correct — separate files
|
||||
```typescript
|
||||
// Correct - separate files
|
||||
// benchmark.ts
|
||||
// agentEvalDataset.ts
|
||||
// agentEvalRun.ts
|
||||
@@ -310,5 +620,5 @@ export interface BenchmarkListItem {
|
||||
|
||||
## Related Skills
|
||||
|
||||
- `data-fetching` — how to fetch and update this data
|
||||
- `zustand` — general Zustand patterns
|
||||
- `data-fetching` - How to fetch and update this data
|
||||
- `zustand` - General Zustand patterns
|
||||
|
||||
@@ -1,118 +0,0 @@
|
||||
# Reducer Pattern (for Detail Map)
|
||||
|
||||
## Why Use a Reducer?
|
||||
|
||||
- **Immutable updates** — Immer makes immutability easy
|
||||
- **Type-safe actions** — discriminated union of action types prevents typos
|
||||
- **Testable** — pure function, easy to unit test
|
||||
- **Reusable** — same reducer powers optimistic updates and server-data writes
|
||||
|
||||
## Reducer Structure
|
||||
|
||||
```typescript
|
||||
// src/store/eval/slices/benchmark/reducer.ts
|
||||
import { produce } from 'immer';
|
||||
import type { AgentEvalBenchmark } from '@lobechat/types';
|
||||
|
||||
// Action types — discriminated union
|
||||
type SetBenchmarkDetailAction = {
|
||||
id: string;
|
||||
type: 'setBenchmarkDetail';
|
||||
value: AgentEvalBenchmark;
|
||||
};
|
||||
|
||||
type UpdateBenchmarkDetailAction = {
|
||||
id: string;
|
||||
type: 'updateBenchmarkDetail';
|
||||
value: Partial<AgentEvalBenchmark>;
|
||||
};
|
||||
|
||||
type DeleteBenchmarkDetailAction = {
|
||||
id: string;
|
||||
type: 'deleteBenchmarkDetail';
|
||||
};
|
||||
|
||||
export type BenchmarkDetailDispatch =
|
||||
| SetBenchmarkDetailAction
|
||||
| UpdateBenchmarkDetailAction
|
||||
| DeleteBenchmarkDetailAction;
|
||||
|
||||
export const benchmarkDetailReducer = (
|
||||
state: Record<string, AgentEvalBenchmark> = {},
|
||||
payload: BenchmarkDetailDispatch,
|
||||
): Record<string, AgentEvalBenchmark> => {
|
||||
switch (payload.type) {
|
||||
case 'setBenchmarkDetail': {
|
||||
return produce(state, (draft) => {
|
||||
draft[payload.id] = payload.value;
|
||||
});
|
||||
}
|
||||
|
||||
case 'updateBenchmarkDetail': {
|
||||
return produce(state, (draft) => {
|
||||
if (draft[payload.id]) {
|
||||
draft[payload.id] = { ...draft[payload.id], ...payload.value };
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
case 'deleteBenchmarkDetail': {
|
||||
return produce(state, (draft) => {
|
||||
delete draft[payload.id];
|
||||
});
|
||||
}
|
||||
|
||||
default:
|
||||
return state;
|
||||
}
|
||||
};
|
||||
```
|
||||
|
||||
## Internal Dispatch Methods
|
||||
|
||||
The slice exposes two `internal_*` methods so the reducer and the loading state stay encapsulated behind a stable contract:
|
||||
|
||||
```typescript
|
||||
// In action.ts
|
||||
export interface BenchmarkAction {
|
||||
// ... other methods ...
|
||||
|
||||
// Internal — not for direct UI use
|
||||
internal_dispatchBenchmarkDetail: (payload: BenchmarkDetailDispatch) => void;
|
||||
internal_updateBenchmarkDetailLoading: (id: string, loading: boolean) => void;
|
||||
}
|
||||
|
||||
export const createBenchmarkSlice: StateCreator<...> = (set, get) => ({
|
||||
// ... other methods ...
|
||||
|
||||
// Dispatch to reducer
|
||||
internal_dispatchBenchmarkDetail: (payload) => {
|
||||
const currentMap = get().benchmarkDetailMap;
|
||||
const nextMap = benchmarkDetailReducer(currentMap, payload);
|
||||
|
||||
// Skip set when nothing changed — avoids unnecessary re-renders
|
||||
if (isEqual(nextMap, currentMap)) return;
|
||||
|
||||
set(
|
||||
{ benchmarkDetailMap: nextMap },
|
||||
false,
|
||||
`dispatchBenchmarkDetail/${payload.type}`,
|
||||
);
|
||||
},
|
||||
|
||||
// Update loading state for a specific id
|
||||
internal_updateBenchmarkDetailLoading: (id, loading) => {
|
||||
set(
|
||||
(state) => ({
|
||||
loadingBenchmarkDetailIds: loading
|
||||
? [...state.loadingBenchmarkDetailIds, id]
|
||||
: state.loadingBenchmarkDetailIds.filter((i) => i !== id),
|
||||
}),
|
||||
false,
|
||||
'updateBenchmarkDetailLoading',
|
||||
);
|
||||
},
|
||||
});
|
||||
```
|
||||
|
||||
The `internal_` prefix is a convention — UI components should call the public mutation methods (e.g. `updateBenchmark`), which in turn call `internal_dispatch*`. This keeps reducer dispatch shapes out of the component layer.
|
||||
@@ -1,101 +0,0 @@
|
||||
# Type Definitions in Detail
|
||||
|
||||
The skill body's Type Definitions section covers the rules; this file holds the full worked examples to keep SKILL.md lean.
|
||||
|
||||
## Organization
|
||||
|
||||
Types should be organized by entity in separate files (not mixed):
|
||||
|
||||
```text
|
||||
@lobechat/types/src/eval/
|
||||
├── benchmark.ts # Benchmark types
|
||||
├── agentEvalDataset.ts # Dataset types
|
||||
├── agentEvalRun.ts # Run types
|
||||
└── index.ts # Re-exports
|
||||
```
|
||||
|
||||
## Example: Benchmark Types
|
||||
|
||||
```typescript
|
||||
// packages/types/src/eval/benchmark.ts
|
||||
import type { EvalBenchmarkRubric } from './rubric';
|
||||
|
||||
/**
|
||||
* Full benchmark entity with all fields including heavy data.
|
||||
*/
|
||||
export interface AgentEvalBenchmark {
|
||||
createdAt: Date;
|
||||
description?: string | null;
|
||||
id: string;
|
||||
identifier: string;
|
||||
isSystem: boolean;
|
||||
metadata?: Record<string, unknown> | null;
|
||||
name: string;
|
||||
referenceUrl?: string | null;
|
||||
rubrics: EvalBenchmarkRubric[]; // Heavy field
|
||||
updatedAt: Date;
|
||||
}
|
||||
|
||||
/**
|
||||
* Lightweight benchmark item — excludes heavy fields, may add computed stats.
|
||||
*/
|
||||
export interface AgentEvalBenchmarkListItem {
|
||||
createdAt: Date;
|
||||
description?: string | null;
|
||||
id: string;
|
||||
identifier: string;
|
||||
isSystem: boolean;
|
||||
name: string;
|
||||
// Note: rubrics NOT included (heavy field)
|
||||
|
||||
// Computed statistics for UI display
|
||||
datasetCount?: number;
|
||||
runCount?: number;
|
||||
testCaseCount?: number;
|
||||
}
|
||||
```
|
||||
|
||||
## Example: Document Types (with heavy content)
|
||||
|
||||
```typescript
|
||||
// packages/types/src/document.ts
|
||||
|
||||
/**
|
||||
* Full document entity — includes heavy content fields.
|
||||
*/
|
||||
export interface Document {
|
||||
id: string;
|
||||
title: string;
|
||||
description?: string;
|
||||
content: string; // Heavy field — full markdown content
|
||||
editorData: any; // Heavy field — editor state
|
||||
metadata?: Record<string, unknown>;
|
||||
createdAt: Date;
|
||||
updatedAt: Date;
|
||||
}
|
||||
|
||||
/**
|
||||
* Lightweight document item — excludes heavy content.
|
||||
*/
|
||||
export interface DocumentListItem {
|
||||
id: string;
|
||||
title: string;
|
||||
description?: string;
|
||||
// Note: content and editorData NOT included
|
||||
createdAt: Date;
|
||||
updatedAt: Date;
|
||||
|
||||
// Computed statistics
|
||||
wordCount?: number;
|
||||
lastEditedBy?: string;
|
||||
}
|
||||
```
|
||||
|
||||
## Heavy Fields to Exclude from List
|
||||
|
||||
- Large text content (`content`, `editorData`, `fullDescription`)
|
||||
- Complex objects (`rubrics`, `config`, `metrics`)
|
||||
- Binary data (`image`, `file`)
|
||||
- Large arrays (`messages`, `items`)
|
||||
|
||||
The reason these belong only on Detail: list pages render many rows, so pulling heavy fields blows up payload size and slows render. Detail pages render one entity, so the full payload is fine.
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: testing
|
||||
description: Testing guide using Vitest. Use when writing tests (.test.ts, .test.tsx), fixing failing tests, improving test coverage, or debugging test issues. Triggers on test creation, test debugging, mock setup, or test-related questions.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# LobeHub Testing Guide
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: trpc-router
|
||||
description: TRPC router development guide. Use when creating or modifying TRPC routers (src/server/routers/**), adding procedures, or working with server-side API endpoints. Triggers on TRPC router creation, procedure implementation, or API endpoint tasks.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
# TRPC Router Guide
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: typescript
|
||||
description: "TypeScript code style and type-safety guide for LobeHub. Read before writing or editing any `.ts` / `.tsx` / `.mts` — covers `interface` vs `type`, `Record<PropertyKey, unknown>` over `any`/`object`, `as const satisfies`, `@ts-expect-error` over `@ts-ignore`, `import type` (`separate-type-imports`), `async`/`await` + `Promise.all`, `for…of` over indexed `for`, and the no-silent-`.catch(() => fallback)` rule. Also use when reviewing type quality, deciding module augmentation (`declare module`) over `namespace`, or designing extensible types (e.g. `PipelineContext.metadata`). Triggers on any TypeScript file edit, 'fix the type', 'why is this `any`', 'should this be interface or type', 'eslint type-import', 'ts-expect-error'."
|
||||
user-invocable: false
|
||||
description: TypeScript code style and optimization guidelines. MUST READ before writing or modifying any TypeScript code (.ts, .tsx, .mts files). Also use when reviewing code quality or implementing type-safe patterns. Triggers on any TypeScript file edit, code style discussions, or type safety questions.
|
||||
---
|
||||
|
||||
# TypeScript Code Style Guide
|
||||
@@ -29,16 +28,12 @@ user-invocable: false
|
||||
## Imports
|
||||
|
||||
- This project uses `simple-import-sort/imports` and `consistent-type-imports` (`fixStyle: 'separate-type-imports'`)
|
||||
|
||||
- **Separate type imports**: always use `import type { ... }` for type-only imports, NOT `import { type ... }` inline syntax
|
||||
|
||||
- When a file already has `import type { ... }` from a package and you need to add a value import, keep them as **two separate statements**:
|
||||
|
||||
```ts
|
||||
import type { ChatTopicBotContext } from '@lobechat/types';
|
||||
import { RequestTrigger } from '@lobechat/types';
|
||||
```
|
||||
|
||||
- Within each import statement, specifiers are sorted **alphabetically by name**
|
||||
|
||||
## Code Structure
|
||||
@@ -47,7 +42,6 @@ user-invocable: false
|
||||
- Use consistent, descriptive naming; avoid obscure abbreviations
|
||||
- Replace magic numbers/strings with well-named constants
|
||||
- Defer formatting to tooling
|
||||
- Prefer **named exports** over `export default` — keeps refactor renames and IDE auto-import in sync, and avoids the `default` re-naming drift you get with `import Foo from './foo'`. Reserve `export default` for files where the framework requires it (Next.js page/route/layout, React.lazy targets, config files like `vitest.config.ts`)
|
||||
|
||||
## UI and Theming
|
||||
|
||||
@@ -57,6 +51,7 @@ user-invocable: false
|
||||
|
||||
## Performance
|
||||
|
||||
- Prefer `for…of` loops over index-based `for` loops
|
||||
- Reuse existing utils in `packages/utils` or installed npm packages
|
||||
- Query only required columns from database
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
+8
-22
@@ -1,20 +1,6 @@
|
||||
# Cloud Project Workflow Configuration
|
||||
|
||||
Cloud-specific workflow configurations and patterns for the lobehub-cloud project.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Overview](#overview)
|
||||
2. [Directory Structure](#directory-structure) — submodule + cloud layout
|
||||
3. [Cloud-Specific Patterns](#cloud-specific-patterns) — cloud-only workflows + re-export pattern
|
||||
4. [TypeScript Path Mappings](#typescript-path-mappings)
|
||||
5. [Workflow Class Location](#workflow-class-location) — cloud-only vs shared
|
||||
6. [Environment Variables](#environment-variables)
|
||||
7. [Best Practices](#best-practices) — decide cloud vs OSS, re-export rules, naming
|
||||
8. [Migration Guide](#migration-guide) — moving workflows from cloud to lobehub
|
||||
9. [Examples](#examples) — `welcome-placeholder`, `agent-eval-run`
|
||||
10. [Troubleshooting](#troubleshooting) — circular imports, 404s, type errors
|
||||
11. [Related Documentation](#related-documentation)
|
||||
This document covers cloud-specific workflow configurations and patterns for the lobehub-cloud project.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -29,7 +15,7 @@ The lobehub-cloud project extends the open-source lobehub codebase with cloud-sp
|
||||
|
||||
### Lobehub Submodule (Open-source)
|
||||
|
||||
```text
|
||||
```
|
||||
lobehub/
|
||||
└── src/
|
||||
├── app/(backend)/api/workflows/
|
||||
@@ -42,7 +28,7 @@ lobehub/
|
||||
|
||||
### Lobehub-cloud (Proprietary)
|
||||
|
||||
```text
|
||||
```
|
||||
lobehub-cloud/
|
||||
└── src/
|
||||
├── app/(backend)/api/workflows/
|
||||
@@ -74,7 +60,7 @@ lobehub-cloud/
|
||||
|
||||
**Structure**:
|
||||
|
||||
```text
|
||||
```
|
||||
lobehub-cloud/src/
|
||||
├── app/(backend)/api/workflows/
|
||||
│ └── feature-name/
|
||||
@@ -176,7 +162,7 @@ This allows cloud to override specific modules while using lobehub defaults.
|
||||
|
||||
Place workflow class in cloud:
|
||||
|
||||
```text
|
||||
```
|
||||
lobehub-cloud/src/server/workflows/featureName/index.ts
|
||||
```
|
||||
|
||||
@@ -184,7 +170,7 @@ lobehub-cloud/src/server/workflows/featureName/index.ts
|
||||
|
||||
Place workflow class in lobehub, re-export in cloud if needed:
|
||||
|
||||
```text
|
||||
```
|
||||
lobehub/src/server/workflows/featureName/index.ts
|
||||
```
|
||||
|
||||
@@ -259,7 +245,7 @@ For shared features:
|
||||
|
||||
Follow consistent naming across lobehub and cloud:
|
||||
|
||||
```text
|
||||
```
|
||||
# Both should use same structure
|
||||
lobehub/src/app/(backend)/api/workflows/feature-name/
|
||||
lobehub-cloud/src/app/(backend)/api/workflows/feature-name/
|
||||
@@ -320,7 +306,7 @@ import { Workflow } from 'lobehub/src/server/workflows/feature';
|
||||
|
||||
**Structure**:
|
||||
|
||||
```text
|
||||
```
|
||||
lobehub-cloud/
|
||||
├── src/app/(backend)/api/workflows/welcome-placeholder/
|
||||
│ ├── process-users/route.ts
|
||||
@@ -1,226 +0,0 @@
|
||||
# Best Practices & Common Pitfalls
|
||||
|
||||
Apply these once your scaffold from `implementation.md` is in place.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Error Handling](#1-error-handling)
|
||||
2. [Logging](#2-logging)
|
||||
3. [Return Values](#3-return-values)
|
||||
4. [flowControl Configuration](#4-flowcontrol-configuration)
|
||||
5. [context.run() Best Practices](#5-contextrun-best-practices)
|
||||
6. [Payload Validation](#6-payload-validation)
|
||||
7. [Database Connection](#7-database-connection)
|
||||
8. [Testing](#8-testing)
|
||||
9. [Common Pitfalls](#common-pitfalls)
|
||||
|
||||
---
|
||||
|
||||
## 1. Error Handling
|
||||
|
||||
```typescript
|
||||
export const { POST } = serve<Payload>(
|
||||
async (context) => {
|
||||
const { itemId } = context.requestPayload ?? {};
|
||||
|
||||
if (!itemId) {
|
||||
return { success: false, error: 'Missing itemId in payload' };
|
||||
}
|
||||
|
||||
try {
|
||||
const result = await context.run('step-name', () => doWork(itemId));
|
||||
return { success: true, itemId, result };
|
||||
} catch (error) {
|
||||
console.error('[workflow:error]', error);
|
||||
return {
|
||||
success: false,
|
||||
error: error instanceof Error ? error.message : 'Unknown error',
|
||||
};
|
||||
}
|
||||
},
|
||||
{ flowControl: { ... } },
|
||||
);
|
||||
```
|
||||
|
||||
## 2. Logging
|
||||
|
||||
Consistent prefixes make debugging much easier across QStash dashboards and grep:
|
||||
|
||||
```typescript
|
||||
console.log('[{workflow}:{layer}] Starting with payload:', payload);
|
||||
console.log('[{workflow}:{layer}] Processing items:', { count: items.length });
|
||||
console.log('[{workflow}:{layer}] Completed:', result);
|
||||
console.error('[{workflow}:{layer}:error]', error);
|
||||
```
|
||||
|
||||
## 3. Return Values
|
||||
|
||||
Pick the shape that matches the layer's purpose — entry points return statistics, execution layers return per-item results.
|
||||
|
||||
```typescript
|
||||
// Success
|
||||
return { success: true, itemId, result, message: 'Optional success message' };
|
||||
|
||||
// Error
|
||||
return { success: false, error: 'Error description', itemId };
|
||||
|
||||
// Statistics (entry point)
|
||||
return {
|
||||
success: true,
|
||||
totalEligible: 100,
|
||||
toProcess: 80,
|
||||
alreadyProcessed: 20,
|
||||
dryRun: true, // if applicable
|
||||
message: 'Summary message',
|
||||
};
|
||||
```
|
||||
|
||||
## 4. flowControl Configuration
|
||||
|
||||
Tune concurrency by layer — entry points are singletons, execution layers fan out.
|
||||
|
||||
```typescript
|
||||
// Layer 1: Entry — single instance to avoid duplicate processing
|
||||
flowControl: { key: '{workflow}.process', parallelism: 1, ratePerSecond: 1 }
|
||||
|
||||
// Layer 2: Pagination — moderate concurrency
|
||||
flowControl: { key: '{workflow}.paginate', parallelism: 20, ratePerSecond: 5 }
|
||||
|
||||
// Layer 3: Execution — higher concurrency for parallel item work
|
||||
flowControl: { key: '{workflow}.execute', parallelism: 10, ratePerSecond: 5 }
|
||||
```
|
||||
|
||||
**Why these defaults:**
|
||||
|
||||
- **Layer 1** always uses `parallelism: 1` so concurrent triggers don't both start the same batch.
|
||||
- **Layer 2** can fan out widely (10-20) since pagination is cheap.
|
||||
- **Layer 3** caps at 5-10 by default; raise/lower based on external API rate limits.
|
||||
|
||||
## 5. context.run() Best Practices
|
||||
|
||||
- Use descriptive step names with prefixes: `{workflow}:step-name`
|
||||
- Each step should be idempotent (safe to retry)
|
||||
- Don't nest `context.run()` calls — keep them flat
|
||||
- Use unique step names when processing multiple items:
|
||||
|
||||
```typescript
|
||||
// ✅ Unique step names
|
||||
await Promise.all(
|
||||
items.map((item) => context.run(`{workflow}:execute:${item.id}`, () => processItem(item))),
|
||||
);
|
||||
|
||||
// ❌ Same step name — Upstash de-dupes by step name and you'll lose data
|
||||
await Promise.all(items.map((item) => context.run(`{workflow}:execute`, () => processItem(item))));
|
||||
```
|
||||
|
||||
## 6. Payload Validation
|
||||
|
||||
Validate at the top so failures are explicit, not silent `undefined` cascades:
|
||||
|
||||
```typescript
|
||||
export const { POST } = serve<Payload>(
|
||||
async (context) => {
|
||||
const { itemId, configId } = context.requestPayload ?? {};
|
||||
|
||||
if (!itemId) return { success: false, error: 'Missing itemId in payload' };
|
||||
if (!configId) return { success: false, error: 'Missing configId in payload' };
|
||||
|
||||
// Proceed with work...
|
||||
},
|
||||
{ flowControl: { ... } },
|
||||
);
|
||||
```
|
||||
|
||||
## 7. Database Connection
|
||||
|
||||
Get the connection once per workflow — `getServerDB()` is async, repeating it inside each step adds latency:
|
||||
|
||||
```typescript
|
||||
export const { POST } = serve<Payload>(
|
||||
async (context) => {
|
||||
const db = await getServerDB();
|
||||
|
||||
const item = await context.run('get-item', () => itemModel.findById(db, itemId));
|
||||
const result = await context.run('save-result', () => resultModel.create(db, result));
|
||||
},
|
||||
{ flowControl: { ... } },
|
||||
);
|
||||
```
|
||||
|
||||
## 8. Testing
|
||||
|
||||
Integration tests should exercise both the dry-run statistics path and the full execution path:
|
||||
|
||||
```typescript
|
||||
describe('WorkflowName', () => {
|
||||
it('should process items successfully', async () => {
|
||||
const items = await createTestItems();
|
||||
await WorkflowClass.triggerProcessItems({ dryRun: false });
|
||||
await waitForCompletion();
|
||||
const results = await getResults();
|
||||
expect(results).toHaveLength(items.length);
|
||||
});
|
||||
|
||||
it('should support dryRun mode', async () => {
|
||||
const result = await WorkflowClass.triggerProcessItems({ dryRun: true });
|
||||
expect(result).toMatchObject({
|
||||
success: true,
|
||||
dryRun: true,
|
||||
totalEligible: expect.any(Number),
|
||||
toProcess: expect.any(Number),
|
||||
});
|
||||
});
|
||||
});
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Common Pitfalls
|
||||
|
||||
### ❌ Reusing `context.run()` step names
|
||||
|
||||
```typescript
|
||||
// Bad — Upstash dedupes by step name
|
||||
await Promise.all(items.map((item) => context.run('process', () => process(item))));
|
||||
|
||||
// Good
|
||||
await Promise.all(items.map((item) => context.run(`process:${item.id}`, () => process(item))));
|
||||
```
|
||||
|
||||
### ❌ Skipping payload validation
|
||||
|
||||
```typescript
|
||||
// Bad — undefined cascades into a confusing failure later
|
||||
const { itemId } = context.requestPayload ?? {};
|
||||
const result = await process(itemId);
|
||||
|
||||
// Good — fail fast with a clear error
|
||||
if (!itemId) return { success: false, error: 'Missing itemId' };
|
||||
```
|
||||
|
||||
### ❌ Skipping the filter step
|
||||
|
||||
```typescript
|
||||
// Bad — duplicates work for items that were already processed
|
||||
const allItems = await getAllItems();
|
||||
await Promise.all(allItems.map((item) => triggerExecute(item)));
|
||||
|
||||
// Good — keeps the pipeline idempotent
|
||||
const allItems = await getAllItems();
|
||||
const itemsNeedingProcessing = await filterExisting(allItems);
|
||||
await Promise.all(itemsNeedingProcessing.map((item) => triggerExecute(item)));
|
||||
```
|
||||
|
||||
### ❌ Inconsistent logging
|
||||
|
||||
```typescript
|
||||
// Bad — different prefixes, mixed formats
|
||||
console.log('Starting workflow');
|
||||
log.info('Processing item:', itemId);
|
||||
console.log(`Done with ${itemId}`);
|
||||
|
||||
// Good — uniform prefix lets you grep by workflow+layer
|
||||
console.log('[workflow:layer] Starting with payload:', payload);
|
||||
console.log('[workflow:layer] Processing item:', { itemId });
|
||||
console.log('[workflow:layer] Completed:', { itemId, result });
|
||||
```
|
||||
@@ -1,91 +0,0 @@
|
||||
# Worked Examples
|
||||
|
||||
Two real workflows already in the codebase that follow this skill's pattern verbatim. Skim them when you want to see the pattern applied to concrete entities.
|
||||
|
||||
## Example 1: Welcome Placeholder
|
||||
|
||||
**Use case:** Generate AI-powered welcome placeholders for users.
|
||||
|
||||
**Structure:**
|
||||
|
||||
- Layer 1: `process-users` — entry point, checks eligible users
|
||||
- Layer 2: `paginate-users` — paginates through active users
|
||||
- Layer 3: `generate-user` — generates placeholders for ONE user
|
||||
|
||||
**Key features:**
|
||||
|
||||
- Filters users who already have cached placeholders in Redis
|
||||
- `paidOnly` flag to scope to subscribed users
|
||||
- `dryRun` mode for statistics
|
||||
- Fan-out for large user batches (`CHUNK_SIZE=20`)
|
||||
|
||||
**Layer 3 shape:**
|
||||
|
||||
```typescript
|
||||
export const { POST } = serve<GenerateUserPlaceholderPayload>(async (context) => {
|
||||
const { userId } = context.requestPayload ?? {};
|
||||
|
||||
const workflow = new WelcomePlaceholderWorkflow(db, userId);
|
||||
const placeholders = await context.run('generate', () => workflow.generate());
|
||||
|
||||
return { success: true, userId, placeholdersCount: placeholders.length };
|
||||
});
|
||||
```
|
||||
|
||||
**Files:**
|
||||
|
||||
- `/api/workflows/welcome-placeholder/process-users/route.ts`
|
||||
- `/api/workflows/welcome-placeholder/paginate-users/route.ts`
|
||||
- `/api/workflows/welcome-placeholder/generate-user/route.ts`
|
||||
- `/server/workflows/welcomePlaceholder/index.ts`
|
||||
|
||||
---
|
||||
|
||||
## Example 2: Agent Welcome
|
||||
|
||||
**Use case:** Generate welcome messages and open questions for AI agents.
|
||||
|
||||
**Structure:**
|
||||
|
||||
- Layer 1: `process-agents` — entry point, checks eligible agents
|
||||
- Layer 2: `paginate-agents` — paginates through active agents
|
||||
- Layer 3: `generate-agent` — generates welcome data for ONE agent
|
||||
|
||||
**Key features:**
|
||||
|
||||
- Filters agents who already have cached data in Redis
|
||||
- `paidOnly` flag for subscribed users' agents only
|
||||
- `dryRun` mode for statistics
|
||||
- Fan-out for large agent batches (`CHUNK_SIZE=20`)
|
||||
|
||||
**Layer 3 shape:**
|
||||
|
||||
```typescript
|
||||
export const { POST } = serve<GenerateAgentWelcomePayload>(async (context) => {
|
||||
const { agentId } = context.requestPayload ?? {};
|
||||
|
||||
const workflow = new AgentWelcomeWorkflow(db, agentId);
|
||||
const data = await context.run('generate', () => workflow.generate());
|
||||
|
||||
return { success: true, agentId, data };
|
||||
});
|
||||
```
|
||||
|
||||
**Files:**
|
||||
|
||||
- `/api/workflows/agent-welcome/process-agents/route.ts`
|
||||
- `/api/workflows/agent-welcome/paginate-agents/route.ts`
|
||||
- `/api/workflows/agent-welcome/generate-agent/route.ts`
|
||||
- `/server/workflows/agentWelcome/index.ts`
|
||||
|
||||
---
|
||||
|
||||
## What's identical, what differs
|
||||
|
||||
Both workflows are the **same pattern** — they only differ in:
|
||||
|
||||
- Entity type (users vs agents)
|
||||
- Business logic (placeholder generation vs welcome generation)
|
||||
- Data source (different database queries)
|
||||
|
||||
Everything else — the 3-layer split, dry-run handling, fan-out, filter-existing, flowControl tuning — is identical. That's the whole point: once you internalize the pattern, adding a new workflow is mostly entity-substitution.
|
||||
@@ -1,333 +0,0 @@
|
||||
# Implementation Patterns
|
||||
|
||||
Full code templates for the 3-layer architecture. Read this when actually writing workflow files.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Workflow Class](#workflow-class) — `src/server/workflows/{workflowName}/index.ts`
|
||||
2. [Layer 1: Entry Point](#layer-1-entry-point-process-) — `process-*` route
|
||||
3. [Layer 2: Pagination](#layer-2-pagination-paginate-) — `paginate-*` route
|
||||
4. [Layer 3: Execution](#layer-3-execution-execute--generate-) — `execute-*` / `generate-*` route
|
||||
|
||||
---
|
||||
|
||||
## Workflow Class
|
||||
|
||||
**Location:** `src/server/workflows/{workflowName}/index.ts`
|
||||
|
||||
```typescript
|
||||
import { Client } from '@upstash/workflow';
|
||||
import debug from 'debug';
|
||||
|
||||
const log = debug('lobe-server:workflows:{workflow-name}');
|
||||
|
||||
// Workflow paths
|
||||
const WORKFLOW_PATHS = {
|
||||
processItems: '/api/workflows/{workflow-name}/process-items',
|
||||
paginateItems: '/api/workflows/{workflow-name}/paginate-items',
|
||||
executeItem: '/api/workflows/{workflow-name}/execute-item',
|
||||
} as const;
|
||||
|
||||
// Payload types
|
||||
export interface ProcessItemsPayload {
|
||||
dryRun?: boolean;
|
||||
force?: boolean;
|
||||
}
|
||||
|
||||
export interface PaginateItemsPayload {
|
||||
cursor?: string;
|
||||
itemIds?: string[]; // For fanout chunks
|
||||
}
|
||||
|
||||
export interface ExecuteItemPayload {
|
||||
itemId: string;
|
||||
}
|
||||
|
||||
const getWorkflowUrl = (path: string): string => {
|
||||
const baseUrl = process.env.APP_URL;
|
||||
if (!baseUrl) throw new Error('APP_URL is required to trigger workflows');
|
||||
return new URL(path, baseUrl).toString();
|
||||
};
|
||||
|
||||
const getWorkflowClient = (): Client => {
|
||||
const token = process.env.QSTASH_TOKEN;
|
||||
if (!token) throw new Error('QSTASH_TOKEN is required to trigger workflows');
|
||||
|
||||
const config: ConstructorParameters<typeof Client>[0] = { token };
|
||||
if (process.env.QSTASH_URL) {
|
||||
(config as Record<string, unknown>).url = process.env.QSTASH_URL;
|
||||
}
|
||||
return new Client(config);
|
||||
};
|
||||
|
||||
export class {WorkflowName}Workflow {
|
||||
private static client: Client;
|
||||
|
||||
private static getClient(): Client {
|
||||
if (!this.client) this.client = getWorkflowClient();
|
||||
return this.client;
|
||||
}
|
||||
|
||||
static triggerProcessItems(payload: ProcessItemsPayload) {
|
||||
const url = getWorkflowUrl(WORKFLOW_PATHS.processItems);
|
||||
log('Triggering process-items workflow');
|
||||
return this.getClient().trigger({ body: payload, url });
|
||||
}
|
||||
|
||||
static triggerPaginateItems(payload: PaginateItemsPayload) {
|
||||
const url = getWorkflowUrl(WORKFLOW_PATHS.paginateItems);
|
||||
log('Triggering paginate-items workflow');
|
||||
return this.getClient().trigger({ body: payload, url });
|
||||
}
|
||||
|
||||
static triggerExecuteItem(payload: ExecuteItemPayload) {
|
||||
const url = getWorkflowUrl(WORKFLOW_PATHS.executeItem);
|
||||
log('Triggering execute-item workflow: %s', payload.itemId);
|
||||
return this.getClient().trigger({ body: payload, url });
|
||||
}
|
||||
|
||||
/**
|
||||
* Filter items that need processing (e.g. check Redis cache, database state).
|
||||
* Return only the ones that actually need work — keeps the pipeline idempotent.
|
||||
*/
|
||||
static async filterItemsNeedingProcessing(itemIds: string[]): Promise<string[]> {
|
||||
if (itemIds.length === 0) return [];
|
||||
// Check existing state and return items that need processing
|
||||
return itemIds;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Layer 1: Entry Point (process-\*)
|
||||
|
||||
**Purpose:** Validates prerequisites, calculates statistics, supports dry-run mode.
|
||||
|
||||
```typescript
|
||||
import { serve } from '@upstash/workflow/nextjs';
|
||||
import { getServerDB } from '@/database/server';
|
||||
import { WorkflowClass, type ProcessPayload } from '@/server/workflows/{workflowName}';
|
||||
|
||||
export const { POST } = serve<ProcessPayload>(
|
||||
async (context) => {
|
||||
const { dryRun, force } = context.requestPayload ?? {};
|
||||
|
||||
console.log('[{workflow}:process] Starting with payload:', { dryRun, force });
|
||||
|
||||
const allItemIds = await context.run('{workflow}:get-all-items', async () => {
|
||||
const db = await getServerDB();
|
||||
// Query database for eligible items
|
||||
return items.map((item) => item.id);
|
||||
});
|
||||
|
||||
console.log('[{workflow}:process] Total eligible items:', allItemIds.length);
|
||||
|
||||
if (allItemIds.length === 0) {
|
||||
return { success: true, totalEligible: 0, message: 'No eligible items found' };
|
||||
}
|
||||
|
||||
const itemsNeedingProcessing = await context.run('{workflow}:filter-existing', () =>
|
||||
WorkflowClass.filterItemsNeedingProcessing(allItemIds),
|
||||
);
|
||||
|
||||
const result = {
|
||||
success: true,
|
||||
totalEligible: allItemIds.length,
|
||||
toProcess: itemsNeedingProcessing.length,
|
||||
alreadyProcessed: allItemIds.length - itemsNeedingProcessing.length,
|
||||
};
|
||||
|
||||
// Dry-run short-circuits before any side effects
|
||||
if (dryRun) {
|
||||
console.log('[{workflow}:process] Dry run mode, returning statistics only');
|
||||
return {
|
||||
...result,
|
||||
dryRun: true,
|
||||
message: `[DryRun] Would process ${itemsNeedingProcessing.length} items`,
|
||||
};
|
||||
}
|
||||
|
||||
if (itemsNeedingProcessing.length === 0) {
|
||||
return { ...result, message: 'All items already processed' };
|
||||
}
|
||||
|
||||
await context.run('{workflow}:trigger-paginate', () => WorkflowClass.triggerPaginateItems({}));
|
||||
|
||||
return {
|
||||
...result,
|
||||
message: `Triggered pagination for ${itemsNeedingProcessing.length} items`,
|
||||
};
|
||||
},
|
||||
{
|
||||
flowControl: {
|
||||
key: '{workflow}.process',
|
||||
parallelism: 1, // single instance — avoids duplicate processing
|
||||
ratePerSecond: 1,
|
||||
},
|
||||
},
|
||||
);
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Layer 2: Pagination (paginate-\*)
|
||||
|
||||
**Purpose:** Handles cursor-based pagination, implements fan-out for large batches.
|
||||
|
||||
```typescript
|
||||
import { serve } from '@upstash/workflow/nextjs';
|
||||
import { chunk } from 'es-toolkit/compat';
|
||||
import { getServerDB } from '@/database/server';
|
||||
import { WorkflowClass, type PaginatePayload } from '@/server/workflows/{workflowName}';
|
||||
|
||||
const PAGE_SIZE = 50;
|
||||
const CHUNK_SIZE = 20;
|
||||
|
||||
export const { POST } = serve<PaginatePayload>(
|
||||
async (context) => {
|
||||
const { cursor, itemIds: payloadItemIds } = context.requestPayload ?? {};
|
||||
|
||||
console.log('[{workflow}:paginate] Starting:', {
|
||||
cursor,
|
||||
itemIdsCount: payloadItemIds?.length ?? 0,
|
||||
});
|
||||
|
||||
// If specific itemIds were passed in (from a fanout chunk), process them directly
|
||||
if (payloadItemIds && payloadItemIds.length > 0) {
|
||||
await Promise.all(
|
||||
payloadItemIds.map((itemId) =>
|
||||
context.run(`{workflow}:execute:${itemId}`, () =>
|
||||
WorkflowClass.triggerExecuteItem({ itemId }),
|
||||
),
|
||||
),
|
||||
);
|
||||
return { success: true, processedItems: payloadItemIds.length };
|
||||
}
|
||||
|
||||
// Paginate through all items
|
||||
const itemBatch = await context.run('{workflow}:get-batch', async () => {
|
||||
const db = await getServerDB();
|
||||
const items = await db.query(...);
|
||||
if (!items.length) return { ids: [] };
|
||||
const last = items.at(-1);
|
||||
return {
|
||||
ids: items.map((item) => item.id),
|
||||
cursor: last ? last.id : undefined,
|
||||
};
|
||||
});
|
||||
|
||||
const batchItemIds = itemBatch.ids;
|
||||
const nextCursor = 'cursor' in itemBatch ? itemBatch.cursor : undefined;
|
||||
|
||||
if (batchItemIds.length === 0) {
|
||||
return { success: true, message: 'Pagination complete' };
|
||||
}
|
||||
|
||||
const itemIds = await context.run('{workflow}:filter-existing', () =>
|
||||
WorkflowClass.filterItemsNeedingProcessing(batchItemIds),
|
||||
);
|
||||
|
||||
if (itemIds.length > 0) {
|
||||
if (itemIds.length > CHUNK_SIZE) {
|
||||
// Fan out — recursively re-enter pagination with each chunk
|
||||
const chunks = chunk(itemIds, CHUNK_SIZE);
|
||||
console.log('[{workflow}:paginate] Fanout mode:', {
|
||||
chunks: chunks.length,
|
||||
chunkSize: CHUNK_SIZE,
|
||||
});
|
||||
|
||||
await Promise.all(
|
||||
chunks.map((ids, idx) =>
|
||||
context.run(`{workflow}:fanout:${idx + 1}/${chunks.length}`, () =>
|
||||
WorkflowClass.triggerPaginateItems({ itemIds: ids }),
|
||||
),
|
||||
),
|
||||
);
|
||||
} else {
|
||||
// Process this page directly
|
||||
await Promise.all(
|
||||
itemIds.map((itemId) =>
|
||||
context.run(`{workflow}:execute:${itemId}`, () =>
|
||||
WorkflowClass.triggerExecuteItem({ itemId }),
|
||||
),
|
||||
),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Tail-call into the next page
|
||||
if (nextCursor) {
|
||||
await context.run('{workflow}:next-page', () =>
|
||||
WorkflowClass.triggerPaginateItems({ cursor: nextCursor }),
|
||||
);
|
||||
}
|
||||
|
||||
return {
|
||||
success: true,
|
||||
processedItems: itemIds.length,
|
||||
skippedItems: batchItemIds.length - itemIds.length,
|
||||
nextCursor: nextCursor ?? null,
|
||||
};
|
||||
},
|
||||
{
|
||||
flowControl: {
|
||||
key: '{workflow}.paginate',
|
||||
parallelism: 20,
|
||||
ratePerSecond: 5,
|
||||
},
|
||||
},
|
||||
);
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Layer 3: Execution (execute-\* / generate-\*)
|
||||
|
||||
**Purpose:** Performs the actual business logic for exactly ONE item.
|
||||
|
||||
```typescript
|
||||
import { serve } from '@upstash/workflow/nextjs';
|
||||
import { getServerDB } from '@/database/server';
|
||||
import { WorkflowClass, type ExecutePayload } from '@/server/workflows/{workflowName}';
|
||||
|
||||
export const { POST } = serve<ExecutePayload>(
|
||||
async (context) => {
|
||||
const { itemId } = context.requestPayload ?? {};
|
||||
|
||||
if (!itemId) {
|
||||
return { success: false, error: 'Missing itemId' };
|
||||
}
|
||||
|
||||
const db = await getServerDB();
|
||||
|
||||
const item = await context.run('{workflow}:get-item', async () => {
|
||||
// Query database for item
|
||||
return item;
|
||||
});
|
||||
|
||||
if (!item) {
|
||||
return { success: false, error: 'Item not found' };
|
||||
}
|
||||
|
||||
const result = await context.run('{workflow}:process-item', async () => {
|
||||
const workflow = new WorkflowClass(db, itemId);
|
||||
return workflow.generate(); // or process(), execute(), etc.
|
||||
});
|
||||
|
||||
await context.run('{workflow}:save-result', async () => {
|
||||
const workflow = new WorkflowClass(db, itemId);
|
||||
return workflow.saveToRedis(result); // or saveToDatabase(), etc.
|
||||
});
|
||||
|
||||
return { success: true, itemId, result };
|
||||
},
|
||||
{
|
||||
flowControl: {
|
||||
key: '{workflow}.execute',
|
||||
parallelism: 10,
|
||||
ratePerSecond: 5,
|
||||
},
|
||||
},
|
||||
);
|
||||
```
|
||||
@@ -1,14 +1,10 @@
|
||||
---
|
||||
name: version-release
|
||||
description: "Version release workflow. Use when the user mentions 'release', 'hotfix', 'version upgrade', 'weekly release', or '发版'/'发布'/'小班车'. This skill is for release process and GitHub Release notes (not docs/changelog page writing)."
|
||||
disable-model-invocation: true
|
||||
argument-hint: '[minor|patch] [version?]'
|
||||
---
|
||||
|
||||
# Version Release Workflow
|
||||
|
||||
This skill is a router. The detailed steps live in `references/`.
|
||||
|
||||
## Scope Boundary (Important)
|
||||
|
||||
This skill is only for:
|
||||
@@ -32,12 +28,68 @@ The primary development branch is **canary**. All day-to-day development happens
|
||||
|
||||
Only two release types are used in practice (major releases are extremely rare and can be ignored):
|
||||
|
||||
| Type | Use Case | Frequency | Source Branch | PR Title Format | Version | Reference |
|
||||
| ----- | ---------------------------------------------- | --------------------- | -------------- | ------------------------------------ | ------------- | --------------------------------------- |
|
||||
| Minor | Feature iteration release | \~Every 4 weeks | canary | `🚀 release: v{x.y.0}` | Manually set | `references/minor-release.md` |
|
||||
| Patch | Weekly release / hotfix / model / DB migration | \~Weekly or as needed | canary or main | Custom (e.g. `🚀 release: 20260222`) | Auto patch +1 | `references/patch-release-scenarios.md` |
|
||||
| Type | Use Case | Frequency | Source Branch | PR Title Format | Version |
|
||||
| ----- | ---------------------------------------------- | --------------------- | -------------- | ------------------------------------ | ------------- |
|
||||
| Minor | Feature iteration release | \~Every 4 weeks | canary | `🚀 release: v{x.y.0}` | Manually set |
|
||||
| Patch | Weekly release / hotfix / model / DB migration | \~Weekly or as needed | canary or main | Custom (e.g. `🚀 release: 20260222`) | Auto patch +1 |
|
||||
|
||||
For writing the release-note body (any release type), see `references/release-notes-style.md`.
|
||||
## Minor Release Workflow
|
||||
|
||||
Used to publish a new minor version (e.g. `v2.2.0`), roughly every 4 weeks.
|
||||
|
||||
### Steps
|
||||
|
||||
1. **Create a release branch from canary**
|
||||
|
||||
```bash
|
||||
git checkout canary
|
||||
git pull origin canary
|
||||
git checkout -b release/v{version}
|
||||
git push -u origin release/v{version}
|
||||
```
|
||||
|
||||
2. **Determine the version number** — Read the current version from `package.json` and compute the next minor version (e.g. 2.1.x -> 2.2.0)
|
||||
|
||||
3. **Create a PR to main**
|
||||
|
||||
```bash
|
||||
gh pr create \
|
||||
--title "🚀 release: v{version}" \
|
||||
--base main \
|
||||
--head release/v{version} \
|
||||
--body "## 📦 Release v{version} ..."
|
||||
```
|
||||
|
||||
> \[!IMPORTANT]
|
||||
> The PR title must strictly match the `🚀 release: v{x.y.z}` format. CI uses a regex on this title to determine the exact version number.
|
||||
|
||||
4. **Automatic trigger after merge**: `auto-tag-release` detects the title format and uses the version number from the title to complete the release.
|
||||
|
||||
### Scripts
|
||||
|
||||
```bash
|
||||
bun run release:branch # Interactive
|
||||
bun run release:branch --minor # Directly specify minor
|
||||
```
|
||||
|
||||
## Patch Release Workflow
|
||||
|
||||
Version number is automatically bumped by patch +1. There are 4 common scenarios:
|
||||
|
||||
| Scenario | Source Branch | Branch Naming | Description |
|
||||
| ------------------- | ------------- | ----------------------------- | ------------------------------------------------ |
|
||||
| Weekly Release | canary | `release/weekly-{YYYYMMDD}` | Weekly release train, canary -> main |
|
||||
| Bug Hotfix | main | `hotfix/v{version}-{hash}` | Emergency bug fix |
|
||||
| New Model Launch | canary | Community PR merged directly | New model launch, triggered by PR title prefix |
|
||||
| DB Schema Migration | main | `release/db-migration-{name}` | Database migration, requires dedicated changelog |
|
||||
|
||||
All scenarios auto-bump patch +1. Patch PR titles do not need a version number. See `reference/patch-release-scenarios.md` for detailed steps per scenario.
|
||||
|
||||
### Scripts
|
||||
|
||||
```bash
|
||||
bun run hotfix:branch # Hotfix scenario
|
||||
```
|
||||
|
||||
## Auto-Release Trigger Rules (`auto-tag-release.yml`)
|
||||
|
||||
@@ -75,7 +127,7 @@ PRs that don't match any conditions above (e.g. `docs`, `chore`, `ci`, `test`) w
|
||||
|
||||
When the user requests a release:
|
||||
|
||||
### Precheck (applies to all release types)
|
||||
### Precheck
|
||||
|
||||
Before creating the release branch, verify the source branch:
|
||||
|
||||
@@ -83,18 +135,204 @@ Before creating the release branch, verify the source branch:
|
||||
- **All other release/hotfix branches**: must branch from `main`; run `git merge-base --is-ancestor main <branch> && echo OK`
|
||||
- If the branch is based on the wrong source, recreate from the correct base
|
||||
|
||||
### Routing
|
||||
### Minor Release
|
||||
|
||||
Pick the right reference and follow it end-to-end:
|
||||
1. Read `package.json` to get the current version and compute the next minor version
|
||||
2. Create a `release/v{version}` branch from canary
|
||||
3. Push and create PR — **title must be `🚀 release: v{version}`**
|
||||
4. Inform the user that merge will auto-trigger release
|
||||
|
||||
- **Minor release** → `references/minor-release.md`
|
||||
- **Patch release** (weekly / hotfix / model launch / DB migration) → `references/patch-release-scenarios.md`
|
||||
- **Writing the PR body / release notes** (any release type) → `references/release-notes-style.md`
|
||||
### Patch Release
|
||||
|
||||
### Hard Rules (apply to every release type)
|
||||
Choose workflow by scenario (see `reference/patch-release-scenarios.md`):
|
||||
|
||||
- **Do NOT** manually modify `package.json` version — CI handles it.
|
||||
- **Do NOT** manually create tags — CI handles them.
|
||||
- Minor PR title format is strict (`🚀 release: v{x.y.z}`).
|
||||
- Patch PRs do not need an explicit version number.
|
||||
- Keep release facts accurate; do not invent metrics or availability statements. Release-note inputs (compare base, PR refs, contributor list) **must be derived from `git`** per `references/release-notes-style.md` § Computing Inputs — never from memory or descriptions.
|
||||
- **Weekly Release**: create `release/weekly-{YYYYMMDD}` from canary; use `git log main..canary` for release note inputs; title like `🚀 release: 20260222`
|
||||
- **Bug Hotfix**: create `hotfix/` from main; use gitmoji prefix title (e.g. `🐛 fix: ...`)
|
||||
- **New Model Launch**: community PRs trigger automatically via title prefix (`feat` / `style`)
|
||||
- **DB Migration**: create `release/db-migration-{name}` from main; cherry-pick migration commits; include dedicated migration notes
|
||||
|
||||
### Hard Rules
|
||||
|
||||
- **Do NOT** manually modify `package.json` version
|
||||
- **Do NOT** manually create tags
|
||||
- Minor PR title format is strict
|
||||
- Patch PRs do not need explicit version number
|
||||
- Keep release facts accurate; do not invent metrics or availability statements
|
||||
|
||||
## GitHub Release Changelog Standard (Long-Form Style)
|
||||
|
||||
Use this section for writing **GitHub Release notes** (or release PR body when the PR body is intended to become release notes).\
|
||||
Do not use this as `docs/changelog` page guidance.
|
||||
|
||||
### Positioning
|
||||
|
||||
This release-note style is:
|
||||
|
||||
1. **Data-backed at the top** (date, range, key metrics)
|
||||
2. **Narrative first, then structured detail**
|
||||
3. **Deep but scannable** (clear sectioning + compact bullets)
|
||||
4. **Contributor-forward** (credits are part of the release story)
|
||||
|
||||
### Required Inputs Before Writing
|
||||
|
||||
Collect these inputs first:
|
||||
|
||||
1. Compare range (`<prev_tag>...<current_tag>`)
|
||||
2. Release metrics (commits, merged PRs, resolved issues, contributors, optional files/insertions/deletions)
|
||||
3. High-impact changes by domain (core loop, platform/gateway, UX, tooling, security, reliability)
|
||||
4. Contributor list (with standout contributions if known)
|
||||
5. Known risks / migrations / rollout notes (if any)
|
||||
|
||||
If metrics cannot be reliably computed, omit unknown numbers instead of guessing.
|
||||
|
||||
### Canonical Structure
|
||||
|
||||
Follow this section order unless the user asks otherwise:
|
||||
|
||||
1. `# 🚀 LobeHub v<x.y.z> (<YYYYMMDD>)`
|
||||
2. Metadata lines:
|
||||
- `Release Date`
|
||||
- `Since <Previous Version>` metrics
|
||||
3. One quoted release thesis (single paragraph, 1-2 lines)
|
||||
4. `## ✨ Highlights` (6-12 bullets for major releases; 3-8 for weekly)
|
||||
5. Domain blocks with optional `###` subsections:
|
||||
- `## 🏗️ Core Agent & Architecture` (or equivalent product core)
|
||||
- `## 📱 Platforms / Integrations`
|
||||
- `## 🖥️ CLI & User Experience`
|
||||
- `## 🔧 Tooling`
|
||||
- `## 🔒 Security & Reliability`
|
||||
- `## 📚 Documentation` (optional if meaningful)
|
||||
6. `## 👥 Contributors`
|
||||
7. `**Full Changelog**: <prev>...<current>`
|
||||
|
||||
Use `---` separators between major blocks for long releases.
|
||||
|
||||
### Writing Rules (Hard)
|
||||
|
||||
1. **No fabricated metrics**: all numbers must be traceable.
|
||||
2. **No vague headline bullets**: each bullet must include capability + impact.
|
||||
3. **No internal-only framing**: phrase from user/operator perspective.
|
||||
4. **Security must be explicit** when security-sensitive fixes are present.
|
||||
5. **PR/issue linkage**: use `(#1234)` when IDs are available.
|
||||
6. **Terminology consistency**: same feature/provider name across sections.
|
||||
7. **Do not bury migration or breaking changes**: elevate to dedicated section or callout.
|
||||
|
||||
### Style Rules (Long-Form)
|
||||
|
||||
1. Start with an "everyday use" framing, not implementation internals.
|
||||
2. Mix narrative sentence + evidence bullets.
|
||||
3. Keep bullets compact but informative:
|
||||
- Good: `**Fast Mode (`/fast`)** — Priority routing for OpenAI and Anthropic, reducing latency on supported models. (#6875, #6960)`
|
||||
4. Use bold only for capability names, not for whole sentences.
|
||||
5. Keep heading depth <= 3 levels.
|
||||
|
||||
### Release Size Heuristics
|
||||
|
||||
- **Minor / major milestone release**
|
||||
- Include full structure with multiple domain blocks.
|
||||
- `Highlights` usually 8-12 bullets.
|
||||
- **Weekly patch release**
|
||||
- Keep full skeleton but reduce subsection count.
|
||||
- `Highlights` usually 4-8 bullets.
|
||||
- **DB migration release**
|
||||
- Keep concise.
|
||||
- Must include `Migration overview`, operator impact, and rollback/backup note.
|
||||
|
||||
### Contributor Ordering
|
||||
|
||||
Render contributors as a **single flat list** (no separate "Community" / "Core Team" subsections). Order: **community contributors first, team members after**. Within each group, sort by PR count desc. Bots (`@lobehubbot`, `renovate[bot]`) go on a separate "maintenance" line.
|
||||
|
||||
**LobeHub team roster** — anyone in this list is a team member; anyone not in this list is a community contributor:
|
||||
|
||||
- @arvinxx
|
||||
- @Innei
|
||||
- @tjx666 (commit author name: YuTengjing)
|
||||
- @LiJian
|
||||
- @Neko
|
||||
- @Rdmclin2
|
||||
- @AmAzing129
|
||||
- @sudongyuer
|
||||
- @rivertwilight
|
||||
- @CanisMinor
|
||||
|
||||
> **Resolving handles** — git author names (e.g. `YuTengjing`) are not always the GitHub handle. Verify via `gh pr view <PR> --json author` or `gh api search/users -f q='<email>'` before listing.
|
||||
|
||||
If a new contributor appears who is not on this list, treat them as community by default and ask the user whether to add them to the roster.
|
||||
|
||||
### GitHub Release Changelog Template
|
||||
|
||||
```md
|
||||
# 🚀 LobeHub v<x.y.z> (<YYYYMMDD>)
|
||||
|
||||
**Release Date:** <Month DD, YYYY>
|
||||
**Since <Previous Version>:** <N merged PRs> · <N resolved issues> · <N contributors>
|
||||
|
||||
> <One release thesis sentence: what this release unlocks in practice.>
|
||||
|
||||
---
|
||||
|
||||
## ✨ Highlights
|
||||
|
||||
- **<Capability A>** — <What changed and why it matters>. (#1234)
|
||||
- **<Capability B>** — <What changed and why it matters>. (#2345)
|
||||
- **<Capability C>** — <What changed and why it matters>. (#3456)
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Core Product & Architecture
|
||||
|
||||
### <Subdomain>
|
||||
|
||||
- <Concrete change + impact>. (#...)
|
||||
- <Concrete change + impact>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 📱 Platforms / Integrations
|
||||
|
||||
- <Platform update + impact>. (#...)
|
||||
- <Compatibility/reliability fix + impact>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 🖥️ CLI & User Experience
|
||||
|
||||
- <User-facing workflow improvement>. (#...)
|
||||
- <Quality-of-life fix>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Tooling
|
||||
|
||||
- <Tool/runtime improvement>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 🔒 Security & Reliability
|
||||
|
||||
- **Security:** <hardening or vulnerability fix>. (#...)
|
||||
- **Reliability:** <stability/performance behavior improvement>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 👥 Contributors
|
||||
|
||||
Huge thanks to **<N contributors>** who shipped **<N merged PRs>** this cycle.
|
||||
|
||||
@<community-handle> · @<community-handle> · @<team-handle> · @<team-handle>
|
||||
|
||||
Plus @lobehubbot and renovate[bot] for maintenance.
|
||||
|
||||
---
|
||||
|
||||
**Full Changelog**: <previous_tag>...<current_tag>
|
||||
```
|
||||
|
||||
### Quick Checklist
|
||||
|
||||
- [ ] Uses top metadata and a clear release thesis
|
||||
- [ ] Includes `Highlights` plus domain-grouped sections
|
||||
- [ ] Every major bullet states both change and user/operator impact
|
||||
- [ ] Security and reliability updates are explicitly surfaced (when present)
|
||||
- [ ] Contributor credits and compare range are included
|
||||
- [ ] All numbers and claims are verifiable
|
||||
|
||||
+9
-1
@@ -1,4 +1,4 @@
|
||||
# 🚀 LobeHub Release (20260416)
|
||||
# 🚀 LobeHub v2.1.50 (20260416)
|
||||
|
||||
**Release Date:** April 20, 2026\
|
||||
**Migration Scope:** Agent benchmark data model bootstrap (5 new tables, 2 new indexes)
|
||||
@@ -7,6 +7,14 @@
|
||||
|
||||
---
|
||||
|
||||
## ✨ Highlights
|
||||
|
||||
- **Benchmark Lifecycle Schema** — Added a relational model that tracks benchmark setup, runs, per-topic execution, and record outputs end-to-end.
|
||||
- **Queryability Upgrade** — Added indexes for run status and benchmark-topic joins, improving operational queries in dashboard and debugging workflows.
|
||||
- **Safer Operator Rollout** — Migration is startup-driven and backward-compatible with existing non-benchmark chat workflows.
|
||||
|
||||
---
|
||||
|
||||
## 🗄️ Migration Overview
|
||||
|
||||
Added tables:
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
# 🚀 LobeHub Release (20260427)
|
||||
# 🚀 LobeHub v2.1.54 (20260427)
|
||||
|
||||
**Hotfix Scope:** Agent topic-switching regression — stale chat state on agent change
|
||||
|
||||
+3
-3
@@ -1,7 +1,7 @@
|
||||
# 🚀 LobeHub Release (20260420)
|
||||
# 🚀 LobeHub v2.1.50 (20260420)
|
||||
|
||||
**Release Date:** April 20, 2026\
|
||||
**Since previous release:** 96 commits · 58 merged PRs · 31 resolved issues · 17 contributors
|
||||
**Since v2026.04.13:** 96 commits · 58 merged PRs · 31 resolved issues · 17 contributors
|
||||
|
||||
> This weekly release focuses on reducing friction in everyday agent work: faster model routing, smoother gateway behavior, stronger task continuity, and clearer operator diagnostics when something goes wrong.
|
||||
|
||||
@@ -77,4 +77,4 @@
|
||||
|
||||
---
|
||||
|
||||
**Full Changelog**: <previous-tag>...<current-tag>
|
||||
**Full Changelog**: v2026.04.13...v2026.04.20
|
||||
+3
-7
@@ -21,16 +21,12 @@ git push -u origin release/weekly-{YYYYMMDD}
|
||||
|
||||
2. **Scan changes and write changelog**
|
||||
|
||||
Compute the previous tag from main first — never reuse the last weekly's tag, since hotfixes published in between will be missed:
|
||||
|
||||
```bash
|
||||
git fetch origin main canary --tags
|
||||
PREV_TAG=$(git describe --tags --abbrev=0 origin/main --match 'v*.*.*' --exclude '*-canary*' --exclude '*-nightly*')
|
||||
git log "$PREV_TAG..origin/release/weekly-{YYYYMMDD}" --oneline --no-merges
|
||||
git diff "$PREV_TAG...origin/release/weekly-{YYYYMMDD}" --stat
|
||||
git log main..canary --oneline
|
||||
git diff main...canary --stat
|
||||
```
|
||||
|
||||
Then follow `./release-notes-style.md` § **Computing Inputs (Hard Rules)** to derive PR refs, metrics, and contributors. Every `(#XXXX)` in the body must come from actual commit subjects in this range — never inferred from descriptions.
|
||||
Write a user-facing changelog following the format in `patch-release-changelog-example.md`.
|
||||
|
||||
3. **Create PR to main** with the changelog as the PR body
|
||||
|
||||
@@ -1,47 +0,0 @@
|
||||
# Minor Release Workflow
|
||||
|
||||
Used to publish a new minor version (e.g. `v2.2.0`), roughly every 4 weeks. The PR title carries the exact version number; CI parses it to drive the rest of the release.
|
||||
|
||||
## Steps
|
||||
|
||||
1. **Create a release branch from canary**
|
||||
|
||||
```bash
|
||||
git checkout canary
|
||||
git pull origin canary
|
||||
git checkout -b release/v{version}
|
||||
git push -u origin release/v{version}
|
||||
```
|
||||
|
||||
2. **Determine the version number** — Read the current version from `package.json` and compute the next minor version (e.g. `2.1.x` → `2.2.0`).
|
||||
|
||||
3. **Create a PR to main**
|
||||
|
||||
```bash
|
||||
gh pr create \
|
||||
--title "🚀 release: v{version}" \
|
||||
--base main \
|
||||
--head release/v{version} \
|
||||
--body-file release_body.md
|
||||
```
|
||||
|
||||
> \[!IMPORTANT]
|
||||
> The PR title must strictly match the `🚀 release: v{x.y.z}` format. CI uses a regex on this title to determine the exact version number.
|
||||
|
||||
4. **Write the PR body as release notes** — Follow `release-notes-style.md`. Compare base is the latest semver tag on main (`git describe --tags --abbrev=0 origin/main`).
|
||||
|
||||
5. **Automatic trigger after merge** — `auto-tag-release` detects the title format, uses the version number from the title, bumps `package.json`, tags `v{x.y.z}`, creates the GitHub Release, and dispatches `sync-main-to-canary`.
|
||||
|
||||
## Scripts
|
||||
|
||||
```bash
|
||||
bun run release:branch # Interactive
|
||||
bun run release:branch --minor # Directly specify minor
|
||||
```
|
||||
|
||||
## Hard Rules (specific to Minor)
|
||||
|
||||
- PR title format is **strict**: `🚀 release: v{x.y.z}`. Any deviation falls through to patch detection.
|
||||
- Do **NOT** manually modify `package.json` version — CI will bump it.
|
||||
- Do **NOT** manually create the tag — CI will tag.
|
||||
- Highlights bullet count is usually 8–12 (see `release-notes-style.md` size heuristics).
|
||||
@@ -1,330 +0,0 @@
|
||||
# GitHub Release Changelog Standard (Long-Form Style)
|
||||
|
||||
Use this guide for **GitHub Release notes** — the body of a release PR that becomes the GitHub Release after merge. Do **not** use it for `docs/changelog/*.mdx` website pages (load `../../docs-changelog/SKILL.md` instead).
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Positioning](#positioning) — what this style optimizes for
|
||||
2. [Required Inputs Before Writing](#required-inputs-before-writing)
|
||||
3. [Computing Inputs (Hard Rules — Verify, Never Guess)](#computing-inputs-hard-rules--verify-never-guess) — base ref, PR refs, metrics, authors, pre-publish verification
|
||||
4. [Canonical Structure (Long-Form: Minor / Weekly)](#canonical-structure-long-form-minor--weekly)
|
||||
5. [Variants for Shorter Releases](#variants-for-shorter-releases) — hotfix, DB migration
|
||||
6. [Writing Rules (Hard)](#writing-rules-hard)
|
||||
7. [Style Rules (Long-Form)](#style-rules-long-form)
|
||||
8. [Release Size Heuristics](#release-size-heuristics) — when to use which variant
|
||||
9. [Contributor Ordering](#contributor-ordering)
|
||||
10. [Template](#template) — copy-paste skeleton
|
||||
11. [Quick Checklist](#quick-checklist) — long-form + hotfix
|
||||
|
||||
## Positioning
|
||||
|
||||
This release-note style is:
|
||||
|
||||
1. **Data-backed at the top** (date, range, key metrics)
|
||||
2. **Narrative first, then structured detail**
|
||||
3. **Deep but scannable** (clear sectioning + compact bullets)
|
||||
4. **Contributor-forward** (credits are part of the release story)
|
||||
|
||||
## Required Inputs Before Writing
|
||||
|
||||
Collect these inputs first:
|
||||
|
||||
1. Compare range (`<prev_tag>...<current_tag>`)
|
||||
2. Release metrics (commits, merged PRs, resolved issues, contributors, optional files/insertions/deletions)
|
||||
3. High-impact changes by domain (core loop, platform/gateway, UX, tooling, security, reliability)
|
||||
4. Contributor list (with standout contributions if known)
|
||||
5. Known risks / migrations / rollout notes (if any)
|
||||
|
||||
If metrics cannot be reliably computed, omit unknown numbers instead of guessing.
|
||||
|
||||
## Computing Inputs (Hard Rules — Verify, Never Guess)
|
||||
|
||||
> Hallucinated PR numbers and wrong "Since v..." bases are the #1 failure mode of this skill. Every number and every `(#XXXX)` must come from `git`, never from memory or inference.
|
||||
|
||||
### 1. Compare base = latest semver tag on `main`
|
||||
|
||||
Do **not** eyeball the tag list or pick the "last weekly" PR. Compute it:
|
||||
|
||||
```bash
|
||||
git fetch origin main canary --tags
|
||||
PREV_TAG=$(git describe --tags --abbrev=0 origin/main --match 'v*.*.*' --exclude '*-canary*' --exclude '*-nightly*')
|
||||
echo "$PREV_TAG"
|
||||
```
|
||||
|
||||
Sanity check that the tag is reachable from the release branch:
|
||||
|
||||
```bash
|
||||
git merge-base --is-ancestor "$PREV_TAG" origin/release/weekly-{YYYYMMDD} && echo OK
|
||||
```
|
||||
|
||||
If the check fails, stop and ask the user — the release branch is based on the wrong source.
|
||||
|
||||
> **Why not "the last weekly release PR"?** Hotfixes (`v2.1.54`, `v2.1.55`, …) merge directly into main between weeklies. They get back-merged via `sync-main-to-canary`, so the latest semver tag on main _is_ the correct previous release for both weekly and minor flows. Picking the previous weekly's tag will silently undercount and put a stale version in "Since v…".
|
||||
|
||||
### 2. PR refs must come from commit subjects — never from descriptions
|
||||
|
||||
Compute the canonical set:
|
||||
|
||||
```bash
|
||||
git log "$PREV_TAG..origin/release/weekly-{YYYYMMDD}" \
|
||||
--pretty=format:'%s' --no-merges \
|
||||
| grep -oE '\(#[0-9]+\)$' \
|
||||
| sort -u > /tmp/release_prs.txt
|
||||
```
|
||||
|
||||
Hard rules:
|
||||
|
||||
- Every `(#XXXX)` you write in the body **must** appear in `/tmp/release_prs.txt`. No exceptions.
|
||||
- Never infer a PR number from a feature description. If you remember "the KB BM25 PR was around #14501", that memory is wrong about half the time. Look up the commit hash by feature keyword and read its actual subject.
|
||||
- If your terminal truncates long subjects (any wrapper that compresses output, e.g. `rtk`), bypass it. With `rtk` use `rtk proxy git log …`. Verify with `wc -l /tmp/release_prs.txt` — the count must match `git log $PREV_TAG..HEAD --no-merges --pretty=format:'%h' | wc -l` minus the few commits without a PR ref. A mismatch of >5% means subjects are being silently truncated.
|
||||
|
||||
### 3. Metrics must come from git counts
|
||||
|
||||
```bash
|
||||
PR_COUNT=$(wc -l < /tmp/release_prs.txt | tr -d ' ')
|
||||
|
||||
COMMIT_COUNT=$(git log "$PREV_TAG..origin/release/weekly-{YYYYMMDD}" --no-merges --pretty=format:'%h' | wc -l | tr -d ' ')
|
||||
|
||||
CONTRIBUTOR_COUNT=$(git log "$PREV_TAG..origin/release/weekly-{YYYYMMDD}" --no-merges --pretty=format:'%an' \
|
||||
| sort -u \
|
||||
| grep -viE '^(lobehubbot|LobeHub Bot|renovate\[bot\])$' \
|
||||
| wc -l | tr -d ' ')
|
||||
```
|
||||
|
||||
If a number cannot be confidently derived, omit it — never guess.
|
||||
|
||||
### 4. Author-to-handle resolution
|
||||
|
||||
Git `%an` is the commit author display name, not the GitHub handle. For each author you mention, confirm the handle:
|
||||
|
||||
```bash
|
||||
gh pr view "$PR_NUMBER" --repo lobehub/lobe-chat --json author --jq '.author.login'
|
||||
```
|
||||
|
||||
Use the result for `@handle`. Then classify each author per the `LobeHub team roster` below; community first, team after.
|
||||
|
||||
### 5. Pre-publish verification (mandatory)
|
||||
|
||||
Before `gh pr create` / `gh pr edit --body-file`, diff body PR refs against the canonical set:
|
||||
|
||||
```bash
|
||||
grep -oE '#[0-9]+' release_body.md | sort -u > /tmp/body_prs.txt
|
||||
sed 's/[()]//g' /tmp/release_prs.txt > /tmp/release_prs_clean.txt
|
||||
|
||||
echo "=== In body but NOT in actual range (must be EMPTY) ==="
|
||||
comm -23 /tmp/body_prs.txt /tmp/release_prs_clean.txt
|
||||
```
|
||||
|
||||
Empty diff = OK. Any output = the body cites a PR that wasn't merged in this range. Stop and fix before publishing.
|
||||
|
||||
Also verify the metrics line in the body matches the computed values (`PR_COUNT`, `CONTRIBUTOR_COUNT`) and that `**Full Changelog**` uses `$PREV_TAG`, not some older tag.
|
||||
|
||||
## Canonical Structure (Long-Form: Minor / Weekly)
|
||||
|
||||
Follow this section order for **Minor** and **Weekly** releases unless the user asks otherwise. For **Hotfix** and **DB Migration**, see § Variants for Shorter Releases below — the canonical structure does not apply.
|
||||
|
||||
1. `# 🚀 LobeHub Release (<YYYYMMDD>)`
|
||||
2. Metadata lines:
|
||||
- `Release Date`
|
||||
- `Since <Previous Version>` metrics
|
||||
3. One quoted release thesis (single paragraph, 1-2 lines)
|
||||
4. `## ✨ Highlights` (6-12 bullets for major releases; 3-8 for weekly)
|
||||
5. Domain blocks with optional `###` subsections:
|
||||
- `## 🏗️ Core Agent & Architecture` (or equivalent product core)
|
||||
- `## 📱 Platforms / Integrations`
|
||||
- `## 🖥️ CLI & User Experience`
|
||||
- `## 🔧 Tooling`
|
||||
- `## 🔒 Security & Reliability`
|
||||
- `## 📚 Documentation` (optional if meaningful)
|
||||
6. `## 👥 Contributors`
|
||||
7. `**Full Changelog**: <prev>...<current>`
|
||||
|
||||
Use `---` separators between major blocks for long releases.
|
||||
|
||||
## Variants for Shorter Releases
|
||||
|
||||
The Canonical Structure above is for **long-form** (Minor / Weekly). Two short-form variants override it.
|
||||
|
||||
### Hotfix Variant
|
||||
|
||||
A hotfix targets one regression and ships fast. The body is short and operator-focused — no Highlights, no domain blocks, no Contributors line.
|
||||
|
||||
Required sections, in order:
|
||||
|
||||
1. `# 🚀 LobeHub Release (<YYYYMMDD>)`
|
||||
2. `**Hotfix Scope:**` — one line summarizing the regression scope (e.g. `Agent topic-switching regression — stale chat state on agent change`). Replaces the long-form `Release Date` / `Since vX.Y.Z` metrics.
|
||||
3. One quoted thesis (single paragraph, 1-2 lines) describing what is now restored.
|
||||
4. `## 🐛 What's Fixed` — 1-3 bullets, each `**<symptom>** — <fix in one sentence>. (#PR)`. No root-cause prose; that lives in the commit message.
|
||||
5. `## ⚙️ Upgrade` — short notes for self-hosted (pull image / restart, schema or env changes) and cloud (usually "applied automatically").
|
||||
6. `## 👥 Owner` — single `@handle` for the PR author, resolved via `gh pr view "$PR" --json author --jq '.author.login'`. Never hardcoded.
|
||||
|
||||
Hard rules specific to hotfix:
|
||||
|
||||
- **No Highlights / domain blocks / Contributors / Full Changelog** — these add noise to a one-shot fix.
|
||||
- **No metric line** — `Since vX.Y.Z` doesn't apply; the body cites the single PR (or 1-3 PRs) directly.
|
||||
- **Owner ≠ Contributors** — one author, listed under § Owner. Not a flat handle list.
|
||||
- See `changelog-example/hotfix.md` for the canonical template.
|
||||
|
||||
### DB Migration Variant
|
||||
|
||||
Database schema changes that need to be released independently. Operator impact is the headline.
|
||||
|
||||
Required sections, in order:
|
||||
|
||||
1. `# 🚀 LobeHub Release (<YYYYMMDD>)` + scope line
|
||||
2. **Migration overview** — what tables / columns are added, modified, or removed
|
||||
3. **Operator impact** — backwards-compatible? required actions for self-hosted?
|
||||
4. **Rollback / backup note** — how to recover
|
||||
5. `## 👥 Owner` — single PR author, resolved via `gh pr view`
|
||||
|
||||
See `changelog-example/db-migration.md` for the canonical template.
|
||||
|
||||
## Writing Rules (Hard)
|
||||
|
||||
1. **No fabricated metrics**: all numbers must be traceable.
|
||||
2. **No vague headline bullets**: each bullet must include capability + impact.
|
||||
3. **No internal-only framing**: phrase from user/operator perspective.
|
||||
4. **Security must be explicit** when security-sensitive fixes are present.
|
||||
5. **PR/issue linkage**: use `(#1234)` when IDs are available.
|
||||
6. **Terminology consistency**: same feature/provider name across sections.
|
||||
7. **Do not bury migration or breaking changes**: elevate to dedicated section or callout.
|
||||
|
||||
## Style Rules (Long-Form)
|
||||
|
||||
1. Start with an "everyday use" framing, not implementation internals.
|
||||
2. Mix narrative sentence + evidence bullets.
|
||||
3. Keep bullets compact but informative:
|
||||
- Good: `**Fast Mode (`/fast`)** — Priority routing for OpenAI and Anthropic, reducing latency on supported models. (#6875, #6960)`
|
||||
4. Use bold only for capability names, not for whole sentences.
|
||||
5. Keep heading depth ≤ 3 levels.
|
||||
|
||||
## Release Size Heuristics
|
||||
|
||||
- **Minor / major milestone release**
|
||||
- Long-form structure with multiple domain blocks.
|
||||
- `Highlights` usually 8-12 bullets.
|
||||
- **Weekly patch release**
|
||||
- Long-form skeleton with reduced subsection count.
|
||||
- `Highlights` usually 4-8 bullets.
|
||||
- **Hotfix release**
|
||||
- Short-form (see § Variants → Hotfix). No Highlights, no domain blocks, no Contributors.
|
||||
- 1-3 fix bullets. Body should fit on one screen.
|
||||
- **DB migration release**
|
||||
- Short-form (see § Variants → DB Migration).
|
||||
- Must include `Migration overview`, operator impact, and rollback/backup note.
|
||||
|
||||
## Contributor Ordering
|
||||
|
||||
Render contributors as a **single flat list** (no separate "Community" / "Core Team" subsections). Order: **community contributors first, team members after**. Within each group, sort by PR count desc. Bots (`@lobehubbot`, `renovate[bot]`) go on a separate "maintenance" line.
|
||||
|
||||
**LobeHub team roster** — anyone in this list is a team member; anyone not in this list is a community contributor:
|
||||
|
||||
- @arvinxx
|
||||
- @Innei
|
||||
- @tjx666 (commit author name: YuTengjing)
|
||||
- @LiJian
|
||||
- @Neko
|
||||
- @Rdmclin2
|
||||
- @AmAzing129
|
||||
- @sudongyuer (commit author name: Tsuki)
|
||||
- @rivertwilight (commit author name: René Wang)
|
||||
- @CanisMinor
|
||||
- @cy948 (commit author name: Rylan Cai)
|
||||
|
||||
> **Resolving handles** — git author names (e.g. `YuTengjing`) are not always the GitHub handle. Verify via `gh pr view "$PR" --json author` or `gh api search/users -f q='<email>'` before listing.
|
||||
|
||||
If a new contributor appears who is not on this list, treat them as community by default and ask the user whether to add them to the roster.
|
||||
|
||||
## Template
|
||||
|
||||
```md
|
||||
# 🚀 LobeHub Release (<YYYYMMDD>)
|
||||
|
||||
**Release Date:** <Month DD, YYYY>
|
||||
**Since <Previous Version>:** <N merged PRs> · <N resolved issues> · <N contributors>
|
||||
|
||||
> <One release thesis sentence: what this release unlocks in practice.>
|
||||
|
||||
---
|
||||
|
||||
## ✨ Highlights
|
||||
|
||||
- **<Capability A>** — <What changed and why it matters>. (#1234)
|
||||
- **<Capability B>** — <What changed and why it matters>. (#2345)
|
||||
- **<Capability C>** — <What changed and why it matters>. (#3456)
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Core Product & Architecture
|
||||
|
||||
### <Subdomain>
|
||||
|
||||
- <Concrete change + impact>. (#...)
|
||||
- <Concrete change + impact>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 📱 Platforms / Integrations
|
||||
|
||||
- <Platform update + impact>. (#...)
|
||||
- <Compatibility/reliability fix + impact>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 🖥️ CLI & User Experience
|
||||
|
||||
- <User-facing workflow improvement>. (#...)
|
||||
- <Quality-of-life fix>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Tooling
|
||||
|
||||
- <Tool/runtime improvement>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 🔒 Security & Reliability
|
||||
|
||||
- **Security:** <hardening or vulnerability fix>. (#...)
|
||||
- **Reliability:** <stability/performance behavior improvement>. (#...)
|
||||
|
||||
---
|
||||
|
||||
## 👥 Contributors
|
||||
|
||||
Huge thanks to **<N contributors>** who shipped **<N merged PRs>** this cycle.
|
||||
|
||||
@<community-handle> · @<community-handle> · @<team-handle> · @<team-handle>
|
||||
|
||||
Plus @lobehubbot and renovate[bot] for maintenance.
|
||||
|
||||
---
|
||||
|
||||
**Full Changelog**: <previous_tag>...<current_tag>
|
||||
```
|
||||
|
||||
## Quick Checklist
|
||||
|
||||
### Long-Form (Minor / Weekly)
|
||||
|
||||
- [ ] `PREV_TAG` is `git describe --tags --abbrev=0 origin/main` (latest semver), not the last weekly's tag
|
||||
- [ ] Every `(#XXXX)` in the body appears in `/tmp/release_prs.txt` (verified via `comm -23`)
|
||||
- [ ] `Since v…` line uses `$PREV_TAG`; PR / contributor counts match `wc -l` on the computed sets
|
||||
- [ ] `**Full Changelog**` uses `$PREV_TAG...release/weekly-<YYYYMMDD>` (or `…v{x.y.z}` for minor)
|
||||
- [ ] Author handles resolved via `gh pr view --json author`, not assumed from `%an`
|
||||
- [ ] Uses top metadata and a clear release thesis
|
||||
- [ ] Includes `Highlights` plus domain-grouped sections
|
||||
- [ ] Every major bullet states both change and user/operator impact
|
||||
- [ ] Security and reliability updates are explicitly surfaced (when present)
|
||||
- [ ] Contributor credits and compare range are included
|
||||
- [ ] All numbers and claims are verifiable
|
||||
|
||||
### Hotfix
|
||||
|
||||
- [ ] `**Hotfix Scope:**` line replaces metrics line
|
||||
- [ ] Single quoted thesis describes what is restored (operator-facing, not internal)
|
||||
- [ ] `## 🐛 What's Fixed` has 1-3 bullets, each `**<symptom>** — <fix>. (#PR)` with PR ref verified to exist and be merged
|
||||
- [ ] `## ⚙️ Upgrade` notes self-hosted action and cloud auto-apply
|
||||
- [ ] `## 👥 Owner` is a single `@handle` resolved via `gh pr view "$PR" --json author`
|
||||
- [ ] No Highlights / domain blocks / Contributors / Full Changelog included
|
||||
@@ -1,7 +1,6 @@
|
||||
---
|
||||
name: zustand
|
||||
description: "LobeHub Zustand store conventions: public/internal/dispatch action layers, optimistic update pattern, slice composition via `flattenActions`, and class-based action migration. Use whenever working under `src/store/**`, adding a `createXxxSlice`, writing `internal_*` or `internal_dispatch*` actions, designing `messagesMap`/`topicsMap` reducers, refactoring a `StateCreator` object slice into a `XxxActionImpl` class, or debugging stale store reads. Triggers on `useChatStore`/`useUserStore`/`useGlobalStore`, `createStore`, `flattenActions`, `StoreSetter`, `internal_dispatch`, 'add an action', 'zustand selector', 'store slice', 'class action', 'optimistic update'."
|
||||
user-invocable: false
|
||||
description: Zustand state management guide. Use when working with store code (src/store/**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management questions, or action implementation.
|
||||
---
|
||||
|
||||
# LobeHub Zustand State Management
|
||||
@@ -175,64 +174,9 @@ export const chatGroupAction: StateCreator<
|
||||
- `ChatGroupStoreWithRefresh` for member refresh
|
||||
- `ChatGroupStoreWithInternal` for curd `internal_dispatchChatGroup`
|
||||
|
||||
### Slices That Don't Currently Need `set`
|
||||
|
||||
When a slice doesn't write local state at the moment — e.g. it reads context
|
||||
from `#get()` and forwards calls to another store, or just runs hooks — drop
|
||||
the `#set` field. Otherwise ESLint's `no-unused-vars` flags the unused private
|
||||
field.
|
||||
|
||||
Mark the constructor's `set` param as `_set` and `void _set` it to keep the
|
||||
`(set, get, api)` shape aligned with `StateCreator`. This is **a snapshot of
|
||||
the current need, not a permanent contract** — if a later change needs `set`,
|
||||
restore the `#set` field and use it; do not invent a workaround to keep the
|
||||
"unused" form.
|
||||
|
||||
```ts
|
||||
type Setter = StoreSetter<ConversationStore>;
|
||||
|
||||
export const toolSlice = (set: Setter, get: () => ConversationStore, _api?: unknown) =>
|
||||
new ToolActionImpl(set, get, _api);
|
||||
|
||||
export class ToolActionImpl {
|
||||
readonly #get: () => ConversationStore;
|
||||
|
||||
// Mark unused params with `_` prefix and `void _x` so the constructor still
|
||||
// matches StateCreator's `(set, get, api)` shape without triggering unused
|
||||
// diagnostics.
|
||||
constructor(_set: Setter, get: () => ConversationStore, _api?: unknown) {
|
||||
void _set;
|
||||
void _api;
|
||||
this.#get = get;
|
||||
}
|
||||
|
||||
approveToolCall = async (id: string) => {
|
||||
const { context, hooks } = this.#get();
|
||||
await useChatStore.getState().approveToolCalling(id, '', context);
|
||||
hooks.onToolCallComplete?.(id, undefined);
|
||||
};
|
||||
}
|
||||
|
||||
export type ToolAction = Pick<ToolActionImpl, keyof ToolActionImpl>;
|
||||
```
|
||||
|
||||
Rules of thumb:
|
||||
|
||||
- If a slice doesn't currently call `set`, drop `#set` (use `_set` + `void _set`
|
||||
in the constructor). When a later edit needs `set`, restore `#set` and use it.
|
||||
- Don't add `setNamespace` for slices that don't write state. Add it when the
|
||||
slice starts writing state.
|
||||
- Never leave `#set` declared but unused "for future use" — lint will fail and
|
||||
re-adding it later costs nothing.
|
||||
|
||||
### Do / Don't
|
||||
|
||||
- **Do**: keep constructor signature aligned with `StateCreator` params `(set, get, api)`.
|
||||
- **Do**: use `#private` to avoid `set/get` being exposed.
|
||||
- **Do**: use `flattenActions` instead of spreading class instances.
|
||||
- **Do**: drop `#set` (and use `_set` + `void _set` in the constructor) for
|
||||
delegate-only slices that never write state — keeps lint green without
|
||||
breaking the `(set, get, api)` shape.
|
||||
- **Don't**: keep both old slice objects and class actions active at the same time.
|
||||
- **Don't**: keep an unused `#set` field "for future use" — it fails ESLint and
|
||||
re-adding it later costs nothing.
|
||||
|
||||
+11
-20
@@ -56,6 +56,7 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
# add your custom model name, multi model separate by comma. for example gpt-3.5-1106,gpt-4-1106
|
||||
# OPENAI_MODEL_LIST=gpt-3.5-turbo
|
||||
|
||||
|
||||
# ## Azure OpenAI ###
|
||||
|
||||
# you can learn azure OpenAI Service on https://learn.microsoft.com/en-us/azure/ai-services/openai/overview
|
||||
@@ -70,6 +71,7 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
# Azure's API version, follows the YYYY-MM-DD format
|
||||
# AZURE_API_VERSION=2024-10-21
|
||||
|
||||
|
||||
# ## Anthropic Service ####
|
||||
|
||||
# ANTHROPIC_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
@@ -77,16 +79,19 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
# use a proxy to connect to the Anthropic API
|
||||
# ANTHROPIC_PROXY_URL=https://api.anthropic.com
|
||||
|
||||
|
||||
# ## Google AI ####
|
||||
|
||||
# GOOGLE_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
|
||||
|
||||
# ## AWS Bedrock ###
|
||||
|
||||
# AWS_REGION=us-east-1
|
||||
# AWS_ACCESS_KEY_ID=xxxxxxxxxxxxxxxxxxx
|
||||
# AWS_SECRET_ACCESS_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
|
||||
|
||||
# ## Ollama AI ####
|
||||
|
||||
# You can use ollama to get and run LLM locally, learn more about it via https://github.com/ollama/ollama
|
||||
@@ -96,11 +101,13 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
|
||||
# OLLAMA_MODEL_LIST=your_ollama_model_names
|
||||
|
||||
|
||||
# ## OpenRouter Service ###
|
||||
|
||||
# OPENROUTER_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
# OPENROUTER_MODEL_LIST=model1,model2,model3
|
||||
|
||||
|
||||
# ## Mistral AI ###
|
||||
|
||||
# MISTRAL_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
@@ -161,6 +168,7 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
|
||||
# SILICONCLOUD_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
|
||||
|
||||
# ## TencentCloud AI ####
|
||||
|
||||
# TENCENT_CLOUD_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
@@ -173,6 +181,7 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
|
||||
# INFINIAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
|
||||
|
||||
# ## 302.AI ###
|
||||
|
||||
# AI302_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
||||
@@ -213,6 +222,7 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
|
||||
# VERCELAIGATEWAY_API_KEY=your_vercel_ai_gateway_api_key
|
||||
|
||||
|
||||
# #######################################
|
||||
# ########### Market Service ############
|
||||
# #######################################
|
||||
@@ -273,6 +283,7 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
# but some service providers may require configuration
|
||||
# S3_REGION=us-west-1
|
||||
|
||||
|
||||
# #######################################
|
||||
# ########### Auth Service ##############
|
||||
# #######################################
|
||||
@@ -413,23 +424,3 @@ OPENAI_API_KEY=sk-xxxxxxxxx
|
||||
# MESSAGE_GATEWAY_ENABLED=1
|
||||
# MESSAGE_GATEWAY_URL=https://message-gateway.lobehub.com
|
||||
# MESSAGE_GATEWAY_SERVICE_TOKEN=your_service_token_here
|
||||
|
||||
# #######################################
|
||||
# ########### Messenger Bot #############
|
||||
# #######################################
|
||||
|
||||
# LobeHub-operated bots that users link their account to once and then chat
|
||||
# with any of their agents from. Credentials (Telegram / Slack / Discord) are
|
||||
# now managed in dc-center → Agent → System Bots and stored in the
|
||||
# `system_bot_providers` table. See docs/development/messenger/managed-by-dc-center.md.
|
||||
#
|
||||
# Webhook URLs are registered against APP_URL:
|
||||
# Telegram: <APP_URL>/api/agent/messenger/webhooks/telegram
|
||||
# Slack: <APP_URL>/api/agent/messenger/webhooks/slack
|
||||
# Discord: <APP_URL>/api/agent/messenger/webhooks/discord
|
||||
#
|
||||
# For local dev with bot platforms, point APP_URL at your tunnel
|
||||
# (ngrok / cloudflared) so platforms can reach your machine.
|
||||
|
||||
# Verify-im link token TTL in seconds (default 1800 = 30 min)
|
||||
# LOBE_LINK_TOKEN_TTL_SECONDS=1800
|
||||
|
||||
@@ -32,7 +32,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
name: Test Packages
|
||||
env:
|
||||
PACKAGES: '@lobechat/file-loaders @lobechat/prompts @lobechat/model-runtime @lobechat/web-crawler @lobechat/electron-server-ipc @lobechat/utils @lobechat/python-interpreter @lobechat/context-engine @lobechat/agent-runtime @lobechat/conversation-flow @lobechat/ssrf-safe-fetch @lobechat/memory-user-memory @lobechat/types @lobechat/builtin-tool-lobe-agent model-bank'
|
||||
PACKAGES: '@lobechat/file-loaders @lobechat/prompts @lobechat/model-runtime @lobechat/web-crawler @lobechat/electron-server-ipc @lobechat/utils @lobechat/python-interpreter @lobechat/context-engine @lobechat/agent-runtime @lobechat/conversation-flow @lobechat/ssrf-safe-fetch @lobechat/memory-user-memory model-bank'
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
@@ -148,6 +148,3 @@ apps/desktop/resources/cli-package.json
|
||||
.superpowers/
|
||||
docs/superpowers/
|
||||
.heerogeneous-tracing
|
||||
|
||||
# Kagura agent runtime
|
||||
.kagura/
|
||||
|
||||
@@ -2,68 +2,6 @@
|
||||
|
||||
# Changelog
|
||||
|
||||
## [Version 2.1.57](https://github.com/lobehub/lobe-chat/compare/v2.1.57-canary.33...v2.1.57)
|
||||
|
||||
<sup>Released on **2026-05-09**</sup>
|
||||
|
||||
#### 🐛 Bug Fixes
|
||||
|
||||
- **docker**: replace pnpm init with static package.json in /deps.
|
||||
- **onboarding**: guard skip/mode-switch footer with feature flag, desktop & init checks.
|
||||
- **misc**: hide runtime-only model aliases.
|
||||
|
||||
#### ✨ Features
|
||||
|
||||
- **misc**: set OSS default model to DeepSeek V4 Pro.
|
||||
|
||||
<br/>
|
||||
|
||||
<details>
|
||||
<summary><kbd>Improvements and Fixes</kbd></summary>
|
||||
|
||||
#### What's fixed
|
||||
|
||||
- **docker**: replace pnpm init with static package.json in /deps, closes [#14576](https://github.com/lobehub/lobe-chat/issues/14576) ([8ed31df](https://github.com/lobehub/lobe-chat/commit/8ed31df))
|
||||
- **onboarding**: guard skip/mode-switch footer with feature flag, desktop & init checks, closes [#14560](https://github.com/lobehub/lobe-chat/issues/14560) ([9756dab](https://github.com/lobehub/lobe-chat/commit/9756dab))
|
||||
- **misc**: hide runtime-only model aliases, closes [#14552](https://github.com/lobehub/lobe-chat/issues/14552) ([2d33322](https://github.com/lobehub/lobe-chat/commit/2d33322))
|
||||
|
||||
#### What's improved
|
||||
|
||||
- **misc**: set OSS default model to DeepSeek V4 Pro, closes [#14555](https://github.com/lobehub/lobe-chat/issues/14555) ([8105fc0](https://github.com/lobehub/lobe-chat/commit/8105fc0))
|
||||
|
||||
</details>
|
||||
|
||||
<div align="right">
|
||||
|
||||
[](#readme-top)
|
||||
|
||||
</div>
|
||||
|
||||
### [Version 2.1.56](https://github.com/lobehub/lobe-chat/compare/v2.1.55...v2.1.56)
|
||||
|
||||
<sup>Released on **2026-05-01**</sup>
|
||||
|
||||
#### 👷 Build System
|
||||
|
||||
- **database**: add `metadata` and `trigger` to `briefs` table.
|
||||
|
||||
<br/>
|
||||
|
||||
<details>
|
||||
<summary><kbd>Improvements and Fixes</kbd></summary>
|
||||
|
||||
#### Build System
|
||||
|
||||
- **database**: add `metadata` and `trigger` to `briefs` table, closes [#14354](https://github.com/lobehub/lobe-chat/issues/14354) ([86a23b5](https://github.com/lobehub/lobe-chat/commit/86a23b5))
|
||||
|
||||
</details>
|
||||
|
||||
<div align="right">
|
||||
|
||||
[](#readme-top)
|
||||
|
||||
</div>
|
||||
|
||||
### [Version 2.1.55](https://github.com/lobehub/lobe-chat/compare/v2.1.54...v2.1.55)
|
||||
|
||||
<sup>Released on **2026-04-29**</sup>
|
||||
|
||||
+1
-1
@@ -89,7 +89,7 @@ RUN set -e && \
|
||||
pnpm i && \
|
||||
mkdir -p /deps && \
|
||||
cd /deps && \
|
||||
echo '{"name":"deps","private":true}' > package.json && \
|
||||
pnpm init && \
|
||||
pnpm add pg drizzle-orm
|
||||
|
||||
COPY . .
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
.\" Code generated by `npm run man:generate`; DO NOT EDIT.
|
||||
.\" Manual command details come from the Commander command tree.
|
||||
.TH LH 1 "" "@lobehub/cli 0.0.15" "User Commands"
|
||||
.TH LH 1 "" "@lobehub/cli 0.0.8" "User Commands"
|
||||
.SH NAME
|
||||
lh \- LobeHub CLI \- manage and connect to LobeHub services
|
||||
.SH SYNOPSIS
|
||||
@@ -68,15 +68,15 @@ Manage agent groups
|
||||
.B bot
|
||||
Manage bot integrations
|
||||
.TP
|
||||
.B cron
|
||||
Manage agent cron jobs
|
||||
.TP
|
||||
.B generate
|
||||
Generate content (text, image, video, speech) Alias: gen.
|
||||
.TP
|
||||
.B file
|
||||
Manage files
|
||||
.TP
|
||||
.B hetero
|
||||
Run heterogeneous agent CLIs (Claude Code / Codex) and stream their output
|
||||
.TP
|
||||
.B skill
|
||||
Manage agent skills
|
||||
.TP
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lobehub/cli",
|
||||
"version": "0.0.15",
|
||||
"version": "0.0.8",
|
||||
"type": "module",
|
||||
"bin": {
|
||||
"lh": "./dist/index.js",
|
||||
@@ -30,7 +30,6 @@
|
||||
"devDependencies": {
|
||||
"@lobechat/agent-gateway-client": "workspace:*",
|
||||
"@lobechat/device-gateway-client": "workspace:*",
|
||||
"@lobechat/heterogeneous-agents": "workspace:*",
|
||||
"@lobechat/local-file-shell": "workspace:*",
|
||||
"@trpc/client": "^11.8.1",
|
||||
"@types/node": "^22.13.5",
|
||||
|
||||
@@ -1,10 +1,6 @@
|
||||
packages:
|
||||
- '../../packages/agent-gateway-client'
|
||||
- '../../packages/device-gateway-client'
|
||||
- '../../packages/heterogeneous-agents'
|
||||
- '../../packages/local-file-shell'
|
||||
- '../../packages/types'
|
||||
- '../../packages/model-bank'
|
||||
- '../../packages/business/const'
|
||||
- '../../packages/file-loaders'
|
||||
- '.'
|
||||
|
||||
@@ -318,7 +318,7 @@ export function registerAgentCommand(program: Command) {
|
||||
}
|
||||
|
||||
// 1. Exec agent to get operationId
|
||||
const input: Record<string, any> = { prompt: options.prompt, trigger: 'cli' };
|
||||
const input: Record<string, any> = { prompt: options.prompt };
|
||||
if (options.agentId) input.agentId = options.agentId;
|
||||
if (deviceId) input.deviceId = deviceId;
|
||||
if (options.slug) input.slug = options.slug;
|
||||
|
||||
@@ -55,7 +55,7 @@ export function registerBriefCommand(program: Command) {
|
||||
typeBadge(b.type, b.priority),
|
||||
truncate(b.title, 40),
|
||||
truncate(b.summary, 50),
|
||||
b.taskId ? pc.dim(b.taskId) : '-',
|
||||
b.taskId ? pc.dim(b.taskId) : b.cronJobId ? pc.dim(b.cronJobId) : '-',
|
||||
b.resolvedAt ? pc.green('resolved') : b.readAt ? pc.dim('read') : 'new',
|
||||
timeAgo(b.createdAt),
|
||||
]);
|
||||
@@ -102,6 +102,7 @@ export function registerBriefCommand(program: Command) {
|
||||
console.log(`${pc.dim('Type:')} ${b.type} ${pc.dim('Created:')} ${timeAgo(b.createdAt)}`);
|
||||
if (b.agentId) console.log(`${pc.dim('Agent:')} ${b.agentId}`);
|
||||
if (b.taskId) console.log(`${pc.dim('Task:')} ${b.taskId}`);
|
||||
if (b.cronJobId) console.log(`${pc.dim('CronJob:')} ${b.cronJobId}`);
|
||||
if (b.topicId) console.log(`${pc.dim('Topic:')} ${b.topicId}`);
|
||||
console.log(`\n${b.summary}`);
|
||||
|
||||
@@ -120,14 +121,14 @@ export function registerBriefCommand(program: Command) {
|
||||
for (const a of actions) {
|
||||
const cmd =
|
||||
a.type === 'comment'
|
||||
? `lh brief resolve ${b.id} --action ${a.key} -m "message"`
|
||||
? `lh brief resolve ${b.id} --action ${a.key} -m "内容"`
|
||||
: `lh brief resolve ${b.id} --action ${a.key}`;
|
||||
console.log(` ${a.label} ${pc.dim(cmd)}`);
|
||||
}
|
||||
} else {
|
||||
console.log(pc.dim('Actions:'));
|
||||
console.log(pc.dim(` lh brief resolve ${b.id} # Approve`));
|
||||
console.log(pc.dim(` lh brief resolve ${b.id} --reply "revision notes" # Request revision`));
|
||||
console.log(pc.dim(` lh brief resolve ${b.id} # 确认通过`));
|
||||
console.log(pc.dim(` lh brief resolve ${b.id} --reply "修改意见" # 反馈修改`));
|
||||
}
|
||||
} else if ((b as any).resolvedComment) {
|
||||
console.log(`${pc.dim('Comment:')} ${(b as any).resolvedComment}`);
|
||||
|
||||
@@ -0,0 +1,172 @@
|
||||
import { Command } from 'commander';
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import { registerCronCommand } from './cron';
|
||||
|
||||
const { mockTrpcClient } = vi.hoisted(() => ({
|
||||
mockTrpcClient: {
|
||||
agentCronJob: {
|
||||
batchUpdateStatus: { mutate: vi.fn() },
|
||||
create: { mutate: vi.fn() },
|
||||
delete: { mutate: vi.fn() },
|
||||
findById: { query: vi.fn() },
|
||||
getStats: { query: vi.fn() },
|
||||
list: { query: vi.fn() },
|
||||
resetExecutions: { mutate: vi.fn() },
|
||||
update: { mutate: vi.fn() },
|
||||
},
|
||||
},
|
||||
}));
|
||||
|
||||
const { getTrpcClient: mockGetTrpcClient } = vi.hoisted(() => ({
|
||||
getTrpcClient: vi.fn(),
|
||||
}));
|
||||
|
||||
vi.mock('../api/client', () => ({ getTrpcClient: mockGetTrpcClient }));
|
||||
vi.mock('../utils/logger', () => ({
|
||||
log: { debug: vi.fn(), error: vi.fn(), info: vi.fn(), warn: vi.fn() },
|
||||
setVerbose: vi.fn(),
|
||||
}));
|
||||
|
||||
describe('cron command', () => {
|
||||
let exitSpy: ReturnType<typeof vi.spyOn>;
|
||||
let consoleSpy: ReturnType<typeof vi.spyOn>;
|
||||
|
||||
beforeEach(() => {
|
||||
exitSpy = vi.spyOn(process, 'exit').mockImplementation((() => {}) as any);
|
||||
consoleSpy = vi.spyOn(console, 'log').mockImplementation(() => {});
|
||||
mockGetTrpcClient.mockResolvedValue(mockTrpcClient);
|
||||
for (const method of Object.values(mockTrpcClient.agentCronJob)) {
|
||||
for (const fn of Object.values(method)) {
|
||||
(fn as ReturnType<typeof vi.fn>).mockReset();
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
exitSpy.mockRestore();
|
||||
consoleSpy.mockRestore();
|
||||
});
|
||||
|
||||
function createProgram() {
|
||||
const program = new Command();
|
||||
program.exitOverride();
|
||||
registerCronCommand(program);
|
||||
return program;
|
||||
}
|
||||
|
||||
describe('list', () => {
|
||||
it('should list cron jobs', async () => {
|
||||
mockTrpcClient.agentCronJob.list.query.mockResolvedValue({
|
||||
data: [{ enabled: true, id: 'c1', name: 'Test Job', schedule: '* * * * *' }],
|
||||
});
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'list']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.list.query).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('should filter by agent-id', async () => {
|
||||
mockTrpcClient.agentCronJob.list.query.mockResolvedValue({ data: [] });
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'list', '--agent-id', 'a1']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.list.query).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ agentId: 'a1' }),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('view', () => {
|
||||
it('should view cron job details', async () => {
|
||||
mockTrpcClient.agentCronJob.findById.query.mockResolvedValue({
|
||||
data: { enabled: true, id: 'c1', name: 'Test', schedule: '* * * * *' },
|
||||
});
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'view', 'c1']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.findById.query).toHaveBeenCalledWith({ id: 'c1' });
|
||||
});
|
||||
});
|
||||
|
||||
describe('create', () => {
|
||||
it('should create a cron job', async () => {
|
||||
mockTrpcClient.agentCronJob.create.mutate.mockResolvedValue({ data: { id: 'c1' } });
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync([
|
||||
'node',
|
||||
'test',
|
||||
'cron',
|
||||
'create',
|
||||
'--agent-id',
|
||||
'a1',
|
||||
'-s',
|
||||
'* * * * *',
|
||||
'-n',
|
||||
'My Job',
|
||||
]);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.create.mutate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ agentId: 'a1', cronPattern: '* * * * *', name: 'My Job' }),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('delete', () => {
|
||||
it('should delete a cron job', async () => {
|
||||
mockTrpcClient.agentCronJob.delete.mutate.mockResolvedValue({});
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'delete', 'c1', '--yes']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.delete.mutate).toHaveBeenCalledWith({ id: 'c1' });
|
||||
});
|
||||
});
|
||||
|
||||
describe('toggle', () => {
|
||||
it('should batch enable cron jobs', async () => {
|
||||
mockTrpcClient.agentCronJob.batchUpdateStatus.mutate.mockResolvedValue({
|
||||
data: { updatedCount: 2 },
|
||||
});
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'toggle', 'c1', 'c2', '--enable']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.batchUpdateStatus.mutate).toHaveBeenCalledWith({
|
||||
enabled: true,
|
||||
ids: ['c1', 'c2'],
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('reset', () => {
|
||||
it('should reset execution count', async () => {
|
||||
mockTrpcClient.agentCronJob.resetExecutions.mutate.mockResolvedValue({});
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'reset', 'c1', '--max', '100']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.resetExecutions.mutate).toHaveBeenCalledWith({
|
||||
id: 'c1',
|
||||
newMaxExecutions: 100,
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('stats', () => {
|
||||
it('should get stats', async () => {
|
||||
mockTrpcClient.agentCronJob.getStats.query.mockResolvedValue({
|
||||
data: { totalJobs: 5, totalExecutions: 100 },
|
||||
});
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'cron', 'stats']);
|
||||
|
||||
expect(mockTrpcClient.agentCronJob.getStats.query).toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,271 @@
|
||||
import type { Command } from 'commander';
|
||||
import pc from 'picocolors';
|
||||
|
||||
import { getTrpcClient } from '../api/client';
|
||||
import { confirm, outputJson, printTable, timeAgo, truncate } from '../utils/format';
|
||||
import { log } from '../utils/logger';
|
||||
|
||||
export function registerCronCommand(program: Command) {
|
||||
const cron = program.command('cron').description('Manage agent cron jobs');
|
||||
|
||||
// ── list ──────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('list')
|
||||
.description('List cron jobs')
|
||||
.option('--agent-id <id>', 'Filter by agent ID')
|
||||
.option('--enabled', 'Only show enabled jobs')
|
||||
.option('--disabled', 'Only show disabled jobs')
|
||||
.option('-L, --limit <n>', 'Page size', '20')
|
||||
.option('--offset <n>', 'Offset', '0')
|
||||
.option('--json [fields]', 'Output JSON, optionally specify fields (comma-separated)')
|
||||
.action(
|
||||
async (options: {
|
||||
agentId?: string;
|
||||
disabled?: boolean;
|
||||
enabled?: boolean;
|
||||
json?: string | boolean;
|
||||
limit?: string;
|
||||
offset?: string;
|
||||
}) => {
|
||||
const client = await getTrpcClient();
|
||||
|
||||
const input: Record<string, any> = {};
|
||||
if (options.agentId) input.agentId = options.agentId;
|
||||
if (options.enabled) input.enabled = true;
|
||||
if (options.disabled) input.enabled = false;
|
||||
if (options.limit) input.limit = Number.parseInt(options.limit, 10);
|
||||
if (options.offset) input.offset = Number.parseInt(options.offset, 10);
|
||||
|
||||
const result = await client.agentCronJob.list.query(input as any);
|
||||
const items = (result as any).data ?? [];
|
||||
|
||||
if (options.json !== undefined) {
|
||||
const fields = typeof options.json === 'string' ? options.json : undefined;
|
||||
outputJson(items, fields);
|
||||
return;
|
||||
}
|
||||
|
||||
if (items.length === 0) {
|
||||
console.log('No cron jobs found.');
|
||||
return;
|
||||
}
|
||||
|
||||
const rows = items.map((j: any) => [
|
||||
j.id || '',
|
||||
truncate(j.name || '', 30),
|
||||
j.schedule || '',
|
||||
j.enabled ? pc.green('enabled') : pc.dim('disabled'),
|
||||
`${j.executionCount ?? 0}/${j.maxExecutions ?? '∞'}`,
|
||||
j.updatedAt ? timeAgo(j.updatedAt) : '',
|
||||
]);
|
||||
|
||||
printTable(rows, ['ID', 'NAME', 'SCHEDULE', 'STATUS', 'EXECUTIONS', 'UPDATED']);
|
||||
},
|
||||
);
|
||||
|
||||
// ── view ──────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('view <id>')
|
||||
.description('View cron job details')
|
||||
.option('--json [fields]', 'Output JSON')
|
||||
.action(async (id: string, options: { json?: string | boolean }) => {
|
||||
const client = await getTrpcClient();
|
||||
const result = await client.agentCronJob.findById.query({ id });
|
||||
const job = (result as any).data;
|
||||
|
||||
if (options.json !== undefined) {
|
||||
const fields = typeof options.json === 'string' ? options.json : undefined;
|
||||
outputJson(job, fields);
|
||||
return;
|
||||
}
|
||||
|
||||
if (!job) {
|
||||
log.error('Cron job not found.');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
console.log(`${pc.bold('ID:')} ${job.id}`);
|
||||
console.log(`${pc.bold('Name:')} ${job.name || ''}`);
|
||||
console.log(`${pc.bold('Agent ID:')} ${job.agentId || ''}`);
|
||||
console.log(`${pc.bold('Schedule:')} ${job.schedule || ''}`);
|
||||
console.log(
|
||||
`${pc.bold('Status:')} ${job.enabled ? pc.green('enabled') : pc.dim('disabled')}`,
|
||||
);
|
||||
console.log(
|
||||
`${pc.bold('Executions:')} ${job.executionCount ?? 0}/${job.maxExecutions ?? '∞'}`,
|
||||
);
|
||||
if (job.prompt) console.log(`${pc.bold('Prompt:')} ${truncate(job.prompt, 80)}`);
|
||||
if (job.createdAt) console.log(`${pc.bold('Created:')} ${timeAgo(job.createdAt)}`);
|
||||
if (job.updatedAt) console.log(`${pc.bold('Updated:')} ${timeAgo(job.updatedAt)}`);
|
||||
});
|
||||
|
||||
// ── create ────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('create')
|
||||
.description('Create a cron job')
|
||||
.requiredOption('--agent-id <id>', 'Agent ID')
|
||||
.requiredOption('-s, --schedule <cron>', 'Cron schedule expression')
|
||||
.option('-n, --name <name>', 'Job name')
|
||||
.option('-p, --prompt <prompt>', 'Prompt text')
|
||||
.option('--max-executions <n>', 'Maximum number of executions')
|
||||
.option('--json', 'Output JSON')
|
||||
.action(
|
||||
async (options: {
|
||||
agentId: string;
|
||||
json?: boolean;
|
||||
maxExecutions?: string;
|
||||
name?: string;
|
||||
prompt?: string;
|
||||
schedule: string;
|
||||
}) => {
|
||||
const client = await getTrpcClient();
|
||||
|
||||
const input: Record<string, any> = {
|
||||
agentId: options.agentId,
|
||||
cronPattern: options.schedule,
|
||||
};
|
||||
if (options.name) input.name = options.name;
|
||||
if (options.prompt) input.content = options.prompt;
|
||||
if (options.maxExecutions) input.maxExecutions = Number.parseInt(options.maxExecutions, 10);
|
||||
|
||||
const result = await client.agentCronJob.create.mutate(input as any);
|
||||
|
||||
if (options.json) {
|
||||
console.log(JSON.stringify(result, null, 2));
|
||||
return;
|
||||
}
|
||||
|
||||
const data = (result as any).data;
|
||||
console.log(`${pc.green('✓')} Created cron job ${pc.bold(data?.id || '')}`);
|
||||
},
|
||||
);
|
||||
|
||||
// ── edit ───────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('edit <id>')
|
||||
.description('Update a cron job')
|
||||
.option('-n, --name <name>', 'Job name')
|
||||
.option('-s, --schedule <cron>', 'Cron schedule expression')
|
||||
.option('-p, --prompt <prompt>', 'Prompt text')
|
||||
.option('--max-executions <n>', 'Maximum number of executions')
|
||||
.option('--enable', 'Enable the job')
|
||||
.option('--disable', 'Disable the job')
|
||||
.action(
|
||||
async (
|
||||
id: string,
|
||||
options: {
|
||||
disable?: boolean;
|
||||
enable?: boolean;
|
||||
maxExecutions?: string;
|
||||
name?: string;
|
||||
prompt?: string;
|
||||
schedule?: string;
|
||||
},
|
||||
) => {
|
||||
const data: Record<string, any> = {};
|
||||
if (options.name) data.name = options.name;
|
||||
if (options.schedule) data.cronPattern = options.schedule;
|
||||
if (options.prompt) data.content = options.prompt;
|
||||
if (options.maxExecutions) data.maxExecutions = Number.parseInt(options.maxExecutions, 10);
|
||||
if (options.enable) data.enabled = true;
|
||||
if (options.disable) data.enabled = false;
|
||||
|
||||
if (Object.keys(data).length === 0) {
|
||||
log.error(
|
||||
'No changes specified. Use --name, --schedule, --prompt, --enable, or --disable.',
|
||||
);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
const client = await getTrpcClient();
|
||||
await client.agentCronJob.update.mutate({ data, id } as any);
|
||||
console.log(`${pc.green('✓')} Updated cron job ${pc.bold(id)}`);
|
||||
},
|
||||
);
|
||||
|
||||
// ── delete ────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('delete <id>')
|
||||
.description('Delete a cron job')
|
||||
.option('--yes', 'Skip confirmation prompt')
|
||||
.action(async (id: string, options: { yes?: boolean }) => {
|
||||
if (!options.yes) {
|
||||
const confirmed = await confirm('Are you sure you want to delete this cron job?');
|
||||
if (!confirmed) {
|
||||
console.log('Cancelled.');
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
const client = await getTrpcClient();
|
||||
await client.agentCronJob.delete.mutate({ id });
|
||||
console.log(`${pc.green('✓')} Deleted cron job ${pc.bold(id)}`);
|
||||
});
|
||||
|
||||
// ── toggle ────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('toggle <ids...>')
|
||||
.description('Batch enable or disable cron jobs')
|
||||
.option('--enable', 'Enable the jobs')
|
||||
.option('--disable', 'Disable the jobs')
|
||||
.action(async (ids: string[], options: { disable?: boolean; enable?: boolean }) => {
|
||||
if (!options.enable && !options.disable) {
|
||||
log.error('Specify --enable or --disable.');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
const enabled = !!options.enable;
|
||||
const client = await getTrpcClient();
|
||||
const result = await client.agentCronJob.batchUpdateStatus.mutate({ enabled, ids });
|
||||
const count = (result as any).data?.updatedCount ?? ids.length;
|
||||
console.log(`${pc.green('✓')} ${enabled ? 'Enabled' : 'Disabled'} ${count} cron job(s)`);
|
||||
});
|
||||
|
||||
// ── reset ─────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('reset <id>')
|
||||
.description('Reset execution count for a cron job')
|
||||
.option('--max <n>', 'Set new max executions')
|
||||
.action(async (id: string, options: { max?: string }) => {
|
||||
const client = await getTrpcClient();
|
||||
|
||||
const input: Record<string, any> = { id };
|
||||
if (options.max) input.newMaxExecutions = Number.parseInt(options.max, 10);
|
||||
|
||||
await client.agentCronJob.resetExecutions.mutate(input as any);
|
||||
console.log(`${pc.green('✓')} Reset execution count for ${pc.bold(id)}`);
|
||||
});
|
||||
|
||||
// ── stats ─────────────────────────────────────────────
|
||||
|
||||
cron
|
||||
.command('stats')
|
||||
.description('Get cron job execution statistics')
|
||||
.option('--json', 'Output JSON')
|
||||
.action(async (options: { json?: boolean }) => {
|
||||
const client = await getTrpcClient();
|
||||
const result = await client.agentCronJob.getStats.query();
|
||||
const stats = (result as any).data;
|
||||
|
||||
if (options.json) {
|
||||
console.log(JSON.stringify(stats, null, 2));
|
||||
return;
|
||||
}
|
||||
|
||||
if (!stats) {
|
||||
console.log('No statistics available.');
|
||||
return;
|
||||
}
|
||||
|
||||
for (const [key, value] of Object.entries(stats as Record<string, any>)) {
|
||||
console.log(`${pc.bold(key + ':')} ${value}`);
|
||||
}
|
||||
});
|
||||
}
|
||||
@@ -1,344 +0,0 @@
|
||||
import { PassThrough } from 'node:stream';
|
||||
|
||||
import { Command } from 'commander';
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import { registerHeteroCommand } from './hetero';
|
||||
|
||||
const { mockSpawnAgent } = vi.hoisted(() => ({
|
||||
mockSpawnAgent: vi.fn(),
|
||||
}));
|
||||
|
||||
vi.mock('@lobechat/heterogeneous-agents/spawn', () => ({
|
||||
spawnAgent: mockSpawnAgent,
|
||||
}));
|
||||
|
||||
vi.mock('../utils/logger', () => ({
|
||||
log: { debug: vi.fn(), error: vi.fn(), info: vi.fn(), warn: vi.fn() },
|
||||
setVerbose: vi.fn(),
|
||||
}));
|
||||
|
||||
/**
|
||||
* Build a Promise resolving to a fake `SpawnAgentHandle`. `spawnAgent` itself
|
||||
* is async, so test mocks return the handle wrapped — same iterable contract,
|
||||
* just behind one microtask. The async iterable yields `events` synchronously
|
||||
* and ends, so the command's `for await (const event of ...)` loop terminates
|
||||
* without hanging the test.
|
||||
*/
|
||||
const createFakeHandle = ({
|
||||
events = [] as any[],
|
||||
exitCode = 0,
|
||||
signal = null as NodeJS.Signals | null,
|
||||
stderrChunks = [] as string[],
|
||||
}: {
|
||||
events?: any[];
|
||||
exitCode?: number | null;
|
||||
signal?: NodeJS.Signals | null;
|
||||
stderrChunks?: string[];
|
||||
} = {}) => {
|
||||
const stderr = new PassThrough();
|
||||
setImmediate(() => {
|
||||
for (const c of stderrChunks) stderr.write(c);
|
||||
stderr.end();
|
||||
});
|
||||
|
||||
const eventsIter: AsyncIterable<any> = {
|
||||
[Symbol.asyncIterator]() {
|
||||
let i = 0;
|
||||
return {
|
||||
async next() {
|
||||
if (i < events.length) return { done: false, value: events[i++] };
|
||||
return { done: true, value: undefined };
|
||||
},
|
||||
};
|
||||
},
|
||||
};
|
||||
|
||||
return Promise.resolve({
|
||||
events: eventsIter,
|
||||
exit: Promise.resolve({ code: exitCode, signal }),
|
||||
kill: vi.fn(),
|
||||
pid: 12_345,
|
||||
stderr,
|
||||
});
|
||||
};
|
||||
|
||||
describe('hetero exec command', () => {
|
||||
let exitSpy: ReturnType<typeof vi.spyOn>;
|
||||
let stdoutSpy: ReturnType<typeof vi.spyOn>;
|
||||
|
||||
beforeEach(() => {
|
||||
// Stub `process.exit` so the test runner doesn't tear down — but THROW a
|
||||
// sentinel rather than return, mirroring `process.exit`'s `never` return
|
||||
// type in production. Without throwing, the command's code after an
|
||||
// `exit(2)` keeps running and crashes on `handle.stderr` (no spawn mock).
|
||||
exitSpy = vi.spyOn(process, 'exit').mockImplementation(((code?: number) => {
|
||||
throw new Error(`__exit__${code}`);
|
||||
}) as any);
|
||||
stdoutSpy = vi.spyOn(process.stdout, 'write').mockImplementation(() => true);
|
||||
mockSpawnAgent.mockReset();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
exitSpy.mockRestore();
|
||||
stdoutSpy.mockRestore();
|
||||
vi.restoreAllMocks();
|
||||
});
|
||||
|
||||
/** Build a fresh program with the hetero command registered. */
|
||||
const buildProgram = () => {
|
||||
const program = new Command();
|
||||
program.exitOverride();
|
||||
registerHeteroCommand(program);
|
||||
return program;
|
||||
};
|
||||
|
||||
/**
|
||||
* Run the parsed command. Swallows our `__exit__<code>` sentinel so tests
|
||||
* can inspect `exitSpy.mock.calls` afterwards instead of having to wrap
|
||||
* every `parseAsync` in `expect(...).rejects`. Real production exits stay
|
||||
* `process.exit` so this only affects the test path.
|
||||
*/
|
||||
const runCmd = async (argv: string[]) => {
|
||||
try {
|
||||
await buildProgram().parseAsync(argv, { from: 'user' });
|
||||
} catch (err) {
|
||||
if (err instanceof Error && err.message.startsWith('__exit__')) return;
|
||||
throw err;
|
||||
}
|
||||
};
|
||||
|
||||
it('rejects unsupported agent types via process.exit(2)', async () => {
|
||||
await runCmd(['hetero', 'exec', '--type', 'kimi-cli', '--prompt', 'hi']);
|
||||
expect(exitSpy).toHaveBeenCalledWith(2);
|
||||
expect(mockSpawnAgent).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('rejects empty prompts via process.exit(2)', async () => {
|
||||
await runCmd(['hetero', 'exec', '--type', 'claude-code', '--prompt', ' ']);
|
||||
expect(exitSpy).toHaveBeenCalledWith(2);
|
||||
expect(mockSpawnAgent).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('passes --type / --prompt / --resume / --cwd / --command through to spawnAgent', async () => {
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle());
|
||||
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'codex',
|
||||
'--prompt',
|
||||
'do thing',
|
||||
'--resume',
|
||||
'thread_abc',
|
||||
'--cwd',
|
||||
'/tmp/work',
|
||||
'--command',
|
||||
'/usr/local/bin/codex',
|
||||
]);
|
||||
|
||||
expect(mockSpawnAgent).toHaveBeenCalledTimes(1);
|
||||
const call = mockSpawnAgent.mock.calls[0][0];
|
||||
expect(call).toMatchObject({
|
||||
agentType: 'codex',
|
||||
command: '/usr/local/bin/codex',
|
||||
cwd: '/tmp/work',
|
||||
prompt: 'do thing',
|
||||
resumeSessionId: 'thread_abc',
|
||||
});
|
||||
// operationId auto-generated when omitted (uuid v4 shape)
|
||||
expect(call.operationId).toMatch(/^[0-9a-f-]{36}$/i);
|
||||
});
|
||||
|
||||
it('uses the provided --operation-id verbatim', async () => {
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle());
|
||||
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'claude-code',
|
||||
'--prompt',
|
||||
'hi',
|
||||
'--operation-id',
|
||||
'op-server-allocated',
|
||||
]);
|
||||
|
||||
const call = mockSpawnAgent.mock.calls[0][0];
|
||||
expect(call.operationId).toBe('op-server-allocated');
|
||||
});
|
||||
|
||||
it('streams events to stdout as JSONL, one line per event', async () => {
|
||||
const events = [
|
||||
{ data: { foo: 1 }, operationId: 'op-1', stepIndex: 0, timestamp: 1, type: 'stream_start' },
|
||||
{
|
||||
data: { chunkType: 'text', content: 'hi' },
|
||||
operationId: 'op-1',
|
||||
stepIndex: 0,
|
||||
timestamp: 2,
|
||||
type: 'stream_chunk',
|
||||
},
|
||||
];
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle({ events }));
|
||||
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'claude-code',
|
||||
'--prompt',
|
||||
'hi',
|
||||
'--operation-id',
|
||||
'op-1',
|
||||
]);
|
||||
|
||||
// Each event is one JSON line with a trailing \n.
|
||||
const lines = stdoutSpy.mock.calls.map((c) => c[0]).filter((s) => typeof s === 'string');
|
||||
expect(lines).toHaveLength(2);
|
||||
for (const line of lines as string[]) {
|
||||
expect(line.endsWith('\n')).toBe(true);
|
||||
const parsed = JSON.parse(line);
|
||||
expect(parsed.operationId).toBe('op-1');
|
||||
}
|
||||
});
|
||||
|
||||
it('passes the child exit code straight through', async () => {
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle({ exitCode: 7 }));
|
||||
|
||||
await runCmd(['hetero', 'exec', '--type', 'claude-code', '--prompt', 'hi']);
|
||||
expect(exitSpy).toHaveBeenCalledWith(7);
|
||||
});
|
||||
|
||||
it('maps SIGINT (code === null) to POSIX exit code 130', async () => {
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle({ exitCode: null, signal: 'SIGINT' }));
|
||||
|
||||
await runCmd(['hetero', 'exec', '--type', 'claude-code', '--prompt', 'hi']);
|
||||
expect(exitSpy).toHaveBeenCalledWith(130);
|
||||
});
|
||||
|
||||
it('combines --prompt + --image into mixed content blocks', async () => {
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle());
|
||||
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'claude-code',
|
||||
'--prompt',
|
||||
'describe',
|
||||
'--image',
|
||||
'./fixture-a.png',
|
||||
'--image',
|
||||
'https://cdn.example/fixture-b.png',
|
||||
]);
|
||||
|
||||
const call = mockSpawnAgent.mock.calls[0][0];
|
||||
expect(Array.isArray(call.prompt)).toBe(true);
|
||||
expect(call.prompt).toEqual([
|
||||
{ text: 'describe', type: 'text' },
|
||||
// Path is resolved against process.cwd() — match by suffix to be CI-portable.
|
||||
{
|
||||
source: expect.objectContaining({ type: 'path' }),
|
||||
type: 'image',
|
||||
},
|
||||
{
|
||||
source: { type: 'url', url: 'https://cdn.example/fixture-b.png' },
|
||||
type: 'image',
|
||||
},
|
||||
]);
|
||||
expect(call.prompt[1].source.path).toMatch(/fixture-a\.png$/);
|
||||
});
|
||||
|
||||
it('parses a data: URL --image into a base64 source', async () => {
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle());
|
||||
|
||||
const dataUrl = `data:image/png;base64,${Buffer.from([0x89, 0x50, 0x4e, 0x47]).toString('base64')}`;
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'claude-code',
|
||||
'--prompt',
|
||||
'see',
|
||||
'--image',
|
||||
dataUrl,
|
||||
]);
|
||||
|
||||
const call = mockSpawnAgent.mock.calls[0][0];
|
||||
expect(call.prompt[1]).toEqual({
|
||||
source: {
|
||||
data: Buffer.from([0x89, 0x50, 0x4e, 0x47]).toString('base64'),
|
||||
mediaType: 'image/png',
|
||||
type: 'base64',
|
||||
},
|
||||
type: 'image',
|
||||
});
|
||||
});
|
||||
|
||||
it('reads multimodal content from --input-json <file>', async () => {
|
||||
const { mkdtemp, writeFile, rm } = await import('node:fs/promises');
|
||||
const { tmpdir } = await import('node:os');
|
||||
const path = await import('node:path');
|
||||
const dir = await mkdtemp(`${tmpdir()}/hetero-input-json-`);
|
||||
const file = path.join(dir, 'input.json');
|
||||
await writeFile(
|
||||
file,
|
||||
JSON.stringify([
|
||||
{ text: 'analyze', type: 'text' },
|
||||
{ source: { type: 'url', url: 'https://x/y.png' }, type: 'image' },
|
||||
]),
|
||||
);
|
||||
|
||||
mockSpawnAgent.mockReturnValue(createFakeHandle());
|
||||
try {
|
||||
await runCmd(['hetero', 'exec', '--type', 'claude-code', '--input-json', file]);
|
||||
} finally {
|
||||
await rm(dir, { force: true, recursive: true });
|
||||
}
|
||||
|
||||
const call = mockSpawnAgent.mock.calls[0][0];
|
||||
expect(call.prompt).toEqual([
|
||||
{ text: 'analyze', type: 'text' },
|
||||
{ source: { type: 'url', url: 'https://x/y.png' }, type: 'image' },
|
||||
]);
|
||||
});
|
||||
|
||||
it('reports spawnAgent rejections (e.g. missing --image path) as a clean error + exit(1)', async () => {
|
||||
// spawnAgent is now async and can reject during image normalization —
|
||||
// missing local --image paths, fetch failures, etc. The CLI must catch
|
||||
// these and exit with a friendly message instead of crashing on an
|
||||
// unhandled rejection.
|
||||
mockSpawnAgent.mockReturnValue(
|
||||
Promise.reject(new Error('ENOENT: no such file or directory, open /missing.png')),
|
||||
);
|
||||
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'claude-code',
|
||||
'--prompt',
|
||||
'see',
|
||||
'--image',
|
||||
'/missing.png',
|
||||
]);
|
||||
|
||||
expect(exitSpy).toHaveBeenCalledWith(1);
|
||||
});
|
||||
|
||||
it('rejects --prompt + --input-json (mutually exclusive)', async () => {
|
||||
await runCmd([
|
||||
'hetero',
|
||||
'exec',
|
||||
'--type',
|
||||
'claude-code',
|
||||
'--prompt',
|
||||
'hi',
|
||||
'--input-json',
|
||||
'/tmp/bogus.json',
|
||||
]);
|
||||
expect(exitSpy).toHaveBeenCalledWith(2);
|
||||
expect(mockSpawnAgent).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
@@ -1,380 +0,0 @@
|
||||
import { randomUUID } from 'node:crypto';
|
||||
import { readFile } from 'node:fs/promises';
|
||||
import path from 'node:path';
|
||||
|
||||
import type {
|
||||
AgentContentBlock,
|
||||
AgentImageSource,
|
||||
AgentPromptInput,
|
||||
} from '@lobechat/heterogeneous-agents/spawn';
|
||||
import { spawnAgent } from '@lobechat/heterogeneous-agents/spawn';
|
||||
import type { Command } from 'commander';
|
||||
|
||||
import { getTrpcClient } from '../api/client';
|
||||
import { BatchIngester, NoopIngestSink } from '../utils/BatchIngester';
|
||||
import { log } from '../utils/logger';
|
||||
import { TrpcIngestSink } from '../utils/TrpcIngestSink';
|
||||
|
||||
const SUPPORTED_AGENT_TYPES = new Set(['claude-code', 'codex']);
|
||||
|
||||
interface ExecOptions {
|
||||
command?: string;
|
||||
cwd?: string;
|
||||
image?: string[];
|
||||
inputJson?: string;
|
||||
operationId?: string;
|
||||
prompt?: string;
|
||||
/**
|
||||
* Output rendering mode.
|
||||
* jsonl — emit each `AgentStreamEvent` as a JSONL line on stdout (default
|
||||
* when no --topic is set, or when explicitly requested).
|
||||
* none — suppress JSONL stdout; only server-ingest mode is active.
|
||||
* Default when --topic is set and running non-interactively.
|
||||
*/
|
||||
render?: 'jsonl' | 'none';
|
||||
resume?: string;
|
||||
/**
|
||||
* Server topic id. When set, enables server-ingest mode: events are
|
||||
* batch-POSTed to `aiAgent.heteroIngest` in addition to (or instead of)
|
||||
* being written to stdout. Requires `--operation-id` to be a valid
|
||||
* server-allocated operation id.
|
||||
*/
|
||||
topic?: string;
|
||||
type: string;
|
||||
}
|
||||
|
||||
const collectImage = (value: string, previous: string[] = []): string[] => [...previous, value];
|
||||
|
||||
const readStdin = async (): Promise<string> => {
|
||||
const chunks: Buffer[] = [];
|
||||
for await (const chunk of process.stdin) {
|
||||
chunks.push(typeof chunk === 'string' ? Buffer.from(chunk) : (chunk as Buffer));
|
||||
}
|
||||
return Buffer.concat(chunks).toString('utf8');
|
||||
};
|
||||
|
||||
/**
|
||||
* Resolve a raw `--input-json` argument: `'-'` (or empty) reads stdin, anything
|
||||
* else is treated as a filesystem path.
|
||||
*/
|
||||
const readInputJson = async (location: string): Promise<string> => {
|
||||
if (location === '-' || location === '') return readStdin();
|
||||
return readFile(location, 'utf8');
|
||||
};
|
||||
|
||||
const looksLikeJsonInput = (value: string): boolean => {
|
||||
const trimmed = value.trimStart();
|
||||
return trimmed.startsWith('{') || trimmed.startsWith('[');
|
||||
};
|
||||
|
||||
/**
|
||||
* Convert an `--image <value>` argument into an image source. Recognized
|
||||
* shapes: `https?://...` URL, `data:` URL, otherwise a filesystem path
|
||||
* resolved relative to the CLI's cwd.
|
||||
*/
|
||||
const parseImageArg = (value: string): AgentImageSource => {
|
||||
if (/^https?:\/\//i.test(value)) return { type: 'url', url: value };
|
||||
if (value.startsWith('data:')) {
|
||||
const match = value.match(/^data:([^;,]+);base64,(.+)$/);
|
||||
if (!match) {
|
||||
throw new Error(`Invalid data URL for --image: ${value.slice(0, 40)}…`);
|
||||
}
|
||||
return { data: match[2]!, mediaType: match[1]!, type: 'base64' };
|
||||
}
|
||||
return { path: path.resolve(process.cwd(), value), type: 'path' };
|
||||
};
|
||||
|
||||
/**
|
||||
* Best-effort coercion of a JSON-decoded value into an `AgentPromptInput`.
|
||||
* Accepts:
|
||||
* - `'plain text'` → single text block
|
||||
* - `[{ type: 'text', text }, { type: 'image', source }]` → content blocks
|
||||
* - `{ content: [...] }` (Anthropic message shape) → unwraps `content`
|
||||
* - `{ type: 'text', ... } | { type: 'image', ... }` → single block
|
||||
*/
|
||||
const coerceJsonPrompt = (parsed: unknown): AgentPromptInput => {
|
||||
if (typeof parsed === 'string') return parsed;
|
||||
if (Array.isArray(parsed)) return parsed as AgentContentBlock[];
|
||||
if (parsed && typeof parsed === 'object') {
|
||||
const obj = parsed as Record<string, unknown>;
|
||||
if (Array.isArray(obj.content)) return obj.content as AgentContentBlock[];
|
||||
if (obj.type === 'text' || obj.type === 'image') return [obj as AgentContentBlock];
|
||||
}
|
||||
throw new Error(
|
||||
'Invalid --input-json shape: expected a string, array of content blocks, ' +
|
||||
'or `{ content: [...] }` envelope.',
|
||||
);
|
||||
};
|
||||
|
||||
interface ResolvedPrompt {
|
||||
/** Human-readable description for the empty-input check. */
|
||||
describe: () => string;
|
||||
prompt: AgentPromptInput;
|
||||
}
|
||||
|
||||
const buildPromptFromText = (text: string, images: string[]): ResolvedPrompt => {
|
||||
if (images.length === 0) {
|
||||
return { describe: () => text.trim(), prompt: text };
|
||||
}
|
||||
const blocks: AgentContentBlock[] = [];
|
||||
if (text.length > 0) blocks.push({ text, type: 'text' });
|
||||
for (const image of images) {
|
||||
blocks.push({ source: parseImageArg(image), type: 'image' });
|
||||
}
|
||||
return {
|
||||
describe: () =>
|
||||
blocks
|
||||
.map((b) => (b.type === 'text' ? b.text.trim() : '[image]'))
|
||||
.filter(Boolean)
|
||||
.join(' ')
|
||||
.trim(),
|
||||
prompt: blocks,
|
||||
};
|
||||
};
|
||||
|
||||
/**
|
||||
* Decide which input mode the user requested and produce a unified prompt.
|
||||
*
|
||||
* Mode resolution (mutually exclusive):
|
||||
* 1. `--input-json` → read JSON file or stdin, parse to content blocks
|
||||
* 2. `--prompt` (with optional `--image` flags) → text + images
|
||||
* 3. (default) read stdin: auto-detect JSON vs plain text by first char
|
||||
*/
|
||||
const resolvePrompt = async (options: ExecOptions): Promise<ResolvedPrompt> => {
|
||||
const images = options.image ?? [];
|
||||
|
||||
if (options.inputJson !== undefined) {
|
||||
if (options.prompt !== undefined) {
|
||||
throw new Error('--prompt and --input-json are mutually exclusive.');
|
||||
}
|
||||
if (images.length > 0) {
|
||||
throw new Error('--image cannot be combined with --input-json (put images in the JSON).');
|
||||
}
|
||||
const raw = await readInputJson(options.inputJson);
|
||||
return { describe: () => raw.trim(), prompt: coerceJsonPrompt(JSON.parse(raw)) };
|
||||
}
|
||||
|
||||
if (options.prompt !== undefined && options.prompt !== '-') {
|
||||
return buildPromptFromText(options.prompt, images);
|
||||
}
|
||||
|
||||
// No --prompt or --prompt -: read stdin and auto-detect.
|
||||
const raw = await readStdin();
|
||||
if (looksLikeJsonInput(raw)) {
|
||||
return { describe: () => raw.trim(), prompt: coerceJsonPrompt(JSON.parse(raw)) };
|
||||
}
|
||||
return buildPromptFromText(raw, images);
|
||||
};
|
||||
|
||||
const exec = async (options: ExecOptions): Promise<void> => {
|
||||
if (!SUPPORTED_AGENT_TYPES.has(options.type)) {
|
||||
log.error(
|
||||
`Unsupported --type "${options.type}". Supported: ${[...SUPPORTED_AGENT_TYPES].join(', ')}`,
|
||||
);
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
let resolved: ResolvedPrompt;
|
||||
try {
|
||||
resolved = await resolvePrompt(options);
|
||||
} catch (err) {
|
||||
log.error(err instanceof Error ? err.message : String(err));
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
if (!resolved.describe()) {
|
||||
log.error(
|
||||
'Empty prompt. Pass --prompt <text>, --image <path>, --input-json <file|->, or pipe content via stdin.',
|
||||
);
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
// Server-ingest mode is active when --topic is provided.
|
||||
// --operation-id must be a server-allocated id in this mode (the server
|
||||
// generates it before spawning the process and passes it via CLI args).
|
||||
const serverIngest = !!options.topic;
|
||||
if (serverIngest && !options.operationId) {
|
||||
log.error('--operation-id is required when --topic is set (server-ingest mode).');
|
||||
process.exit(2);
|
||||
}
|
||||
|
||||
const operationId = options.operationId || randomUUID();
|
||||
|
||||
// Determine JSONL output mode.
|
||||
// Explicit --render flag always wins. Otherwise: emit JSONL in standalone
|
||||
// mode; suppress in server-ingest mode (sink handles the data path).
|
||||
const emitJsonl = options.render === 'jsonl' || (options.render === undefined && !serverIngest);
|
||||
|
||||
// Build the ingest sink — no-op for standalone mode, real tRPC sink for
|
||||
// server-ingest mode. The tRPC client reads LOBEHUB_JWT (operation-scoped
|
||||
// JWT injected by the server) for authentication.
|
||||
const agentType = options.type as 'claude-code' | 'codex';
|
||||
let sink: InstanceType<typeof TrpcIngestSink> | InstanceType<typeof NoopIngestSink>;
|
||||
if (serverIngest) {
|
||||
const client = await getTrpcClient();
|
||||
sink = new TrpcIngestSink(client, agentType, operationId, options.topic!);
|
||||
} else {
|
||||
sink = new NoopIngestSink();
|
||||
}
|
||||
const ingester = new BatchIngester(sink);
|
||||
|
||||
// `spawnAgent` is async and can reject DURING image normalization — fetch
|
||||
// failures, missing local --image paths, decode errors. Surface those as a
|
||||
// clean error + exit code instead of an unhandled promise rejection / stack
|
||||
// trace, mirroring the validation try/catch above.
|
||||
let handle: Awaited<ReturnType<typeof spawnAgent>>;
|
||||
try {
|
||||
handle = await spawnAgent({
|
||||
agentType: options.type,
|
||||
command: options.command,
|
||||
cwd: options.cwd || process.cwd(),
|
||||
operationId,
|
||||
prompt: resolved.prompt,
|
||||
resumeSessionId: options.resume,
|
||||
});
|
||||
} catch (err) {
|
||||
log.error('Failed to start agent:', err instanceof Error ? err.message : String(err));
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// Forward the child's stderr to ours so users see CLI errors / warnings
|
||||
// (auth prompts, missing-binary errors, etc.) in the terminal.
|
||||
handle.stderr.pipe(process.stderr);
|
||||
|
||||
// Ctrl-C → SIGINT to the child's process group so the spawned CLI gets a
|
||||
// chance to clean up. Repeated Ctrl-C escalates to SIGKILL via the
|
||||
// standard "double-tap" pattern most CLIs implement themselves.
|
||||
// In server-ingest mode, drain the ingester and call heteroFinish before
|
||||
// exiting so the server knows the operation was cancelled.
|
||||
let interrupted = false;
|
||||
const onSigint = async () => {
|
||||
if (interrupted) {
|
||||
handle.kill('SIGKILL');
|
||||
return;
|
||||
}
|
||||
interrupted = true;
|
||||
handle.kill('SIGINT');
|
||||
if (serverIngest) {
|
||||
try {
|
||||
await ingester.drain();
|
||||
await sink.finish({ result: 'cancelled' });
|
||||
} catch {
|
||||
// best-effort; process is exiting anyway
|
||||
}
|
||||
}
|
||||
};
|
||||
process.on('SIGINT', onSigint);
|
||||
process.on('SIGTERM', async () => {
|
||||
handle.kill('SIGTERM');
|
||||
if (serverIngest) {
|
||||
try {
|
||||
await ingester.drain();
|
||||
await sink.finish({ result: 'cancelled' });
|
||||
} catch {
|
||||
// best-effort
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Stream events. Each event is optionally written as JSONL and always
|
||||
// pushed into the ingester (which batches and sends to the server).
|
||||
let ingestError = false;
|
||||
try {
|
||||
for await (const event of handle.events) {
|
||||
if (emitJsonl) {
|
||||
process.stdout.write(`${JSON.stringify(event)}\n`);
|
||||
}
|
||||
ingester.push(event);
|
||||
}
|
||||
} catch (err) {
|
||||
log.error('Stream error from agent process:', err instanceof Error ? err.message : String(err));
|
||||
if (serverIngest) {
|
||||
try {
|
||||
await ingester.drain();
|
||||
await sink.finish({
|
||||
result: 'error',
|
||||
error: { message: String(err), type: 'stream_error' },
|
||||
});
|
||||
} catch {
|
||||
// best-effort
|
||||
}
|
||||
}
|
||||
process.exit(1);
|
||||
} finally {
|
||||
process.off('SIGINT', onSigint);
|
||||
}
|
||||
|
||||
// Pass the child's exit code through. In server-ingest mode, drain the
|
||||
// ingester and call heteroFinish before exiting.
|
||||
const { code, signal } = await handle.exit;
|
||||
|
||||
if (serverIngest) {
|
||||
try {
|
||||
await ingester.drain();
|
||||
} catch (err) {
|
||||
log.error(
|
||||
'Failed to flush events to server:',
|
||||
err instanceof Error ? err.message : String(err),
|
||||
);
|
||||
ingestError = true;
|
||||
}
|
||||
|
||||
const exitedClean = !ingestError && (code === 0 || signal === 'SIGTERM');
|
||||
try {
|
||||
await sink.finish({
|
||||
result: exitedClean ? 'success' : 'error',
|
||||
sessionId: handle.sessionId,
|
||||
});
|
||||
} catch (err) {
|
||||
log.error('Failed to send heteroFinish:', err instanceof Error ? err.message : String(err));
|
||||
}
|
||||
}
|
||||
|
||||
if (code !== null) process.exit(ingestError ? 1 : code);
|
||||
if (signal === 'SIGINT') process.exit(130);
|
||||
if (signal === 'SIGTERM') process.exit(143);
|
||||
if (signal === 'SIGKILL') process.exit(137);
|
||||
process.exit(1);
|
||||
};
|
||||
|
||||
export function registerHeteroCommand(program: Command) {
|
||||
const hetero = program
|
||||
.command('hetero')
|
||||
.description('Run heterogeneous agent CLIs (Claude Code / Codex) and stream their output');
|
||||
|
||||
hetero
|
||||
.command('exec')
|
||||
.description(
|
||||
'Spawn a heterogeneous agent CLI and stream its events as JSONL on stdout. Standalone mode (no server ingest).',
|
||||
)
|
||||
.requiredOption('-t, --type <type>', `Agent type: ${[...SUPPORTED_AGENT_TYPES].join(' | ')}`)
|
||||
.option('-p, --prompt [text]', 'Prompt text. Pass `-` (or omit the value) to read from stdin.')
|
||||
.option(
|
||||
'-i, --image <path|url>',
|
||||
'Attach an image (repeatable). Accepts a local path, http(s) URL, or data: URL.',
|
||||
collectImage,
|
||||
)
|
||||
.option(
|
||||
'--input-json <path>',
|
||||
'Read full multimodal prompt as JSON content blocks from a file. Use `-` for stdin.',
|
||||
)
|
||||
.option('-r, --resume <sessionId>', 'Resume an existing agent session by its native id')
|
||||
.option('-d, --cwd <path>', 'Working directory for the spawned agent (default: process.cwd())')
|
||||
.option(
|
||||
'-c, --command <bin>',
|
||||
'Override the agent CLI binary name (default: `claude` or `codex`)',
|
||||
)
|
||||
.option(
|
||||
'--operation-id <id>',
|
||||
'Operation id stamped onto every emitted event. Required in server-ingest mode (--topic). Generated as a UUID if omitted (standalone).',
|
||||
)
|
||||
.option(
|
||||
'--topic <topicId>',
|
||||
'Server topic id. Enables server-ingest mode: events are batch-POSTed to aiAgent.heteroIngest. Requires --operation-id.',
|
||||
)
|
||||
.option(
|
||||
'--render <mode>',
|
||||
'Output mode: jsonl (emit events as JSONL on stdout) | none (suppress stdout). Defaults to jsonl in standalone, none in server-ingest mode.',
|
||||
)
|
||||
.action(exec);
|
||||
}
|
||||
@@ -208,7 +208,7 @@ function readAgentProfile(workspacePath: string): AgentProfile {
|
||||
// Try to extract **Emoji:** value (single emoji)
|
||||
const emojiMatch = content.match(/\*{0,2}Emoji:?\*{0,2}\s*(.+)/i);
|
||||
const rawAvatar = emojiMatch ? emojiMatch[1].trim() : undefined;
|
||||
// Filter out placeholder text like (TBD), _(TBD)_, N/A, and Chinese-language equivalents.
|
||||
// Filter out placeholder text like （待定）(Chinese TBD), _(待定)_, (TBD), N/A, etc.
|
||||
const isPlaceholder =
|
||||
rawAvatar && /^[_*（(].*[)）_*]$|^(?:tbd|todo|n\/?a|none|待定|未定)$/i.test(rawAvatar);
|
||||
const avatar = rawAvatar && !isPlaceholder ? rawAvatar : undefined;
|
||||
|
||||
@@ -83,23 +83,6 @@ describe('model command', () => {
|
||||
|
||||
expect(consoleSpy).toHaveBeenCalledWith(JSON.stringify(models, null, 2));
|
||||
});
|
||||
|
||||
it('should filter hidden runtime-only models from JSON output', async () => {
|
||||
const visibleModels = [{ displayName: 'DeepSeek V4 Pro', id: 'deepseek-v4-pro' }];
|
||||
mockTrpcClient.aiModel.getAiProviderModelList.query.mockResolvedValue([
|
||||
...visibleModels,
|
||||
{
|
||||
displayName: 'LobeHub Onboarding',
|
||||
id: 'lobehub-onboarding-v1',
|
||||
visible: false,
|
||||
},
|
||||
]);
|
||||
|
||||
const program = createProgram();
|
||||
await program.parseAsync(['node', 'test', 'model', 'list', 'lobehub', '--json']);
|
||||
|
||||
expect(consoleSpy).toHaveBeenCalledWith(JSON.stringify(visibleModels, null, 2));
|
||||
});
|
||||
});
|
||||
|
||||
describe('view', () => {
|
||||
|
||||
@@ -5,8 +5,6 @@ import { getTrpcClient } from '../api/client';
|
||||
import { confirm, outputJson, printTable, truncate } from '../utils/format';
|
||||
import { log } from '../utils/logger';
|
||||
|
||||
const isVisibleModel = (model: { visible?: boolean }) => model.visible !== false;
|
||||
|
||||
export function registerModelCommand(program: Command) {
|
||||
const model = program.command('model').description('Manage AI models');
|
||||
|
||||
@@ -35,9 +33,7 @@ export function registerModelCommand(program: Command) {
|
||||
if (options.type) input.type = options.type;
|
||||
|
||||
const result = await client.aiModel.getAiProviderModelList.query(input as any);
|
||||
let items = (Array.isArray(result) ? result : ((result as any).items ?? [])).filter(
|
||||
isVisibleModel,
|
||||
);
|
||||
let items = Array.isArray(result) ? result : ((result as any).items ?? []);
|
||||
|
||||
if (options.type) {
|
||||
items = items.filter((m: any) => m.type === options.type);
|
||||
|
||||
@@ -145,7 +145,7 @@ export function registerReviewCommands(task: Command) {
|
||||
|
||||
rc.command('add <id>')
|
||||
.description('Add a review rubric')
|
||||
.requiredOption('-n, --name <name>', 'Rubric name (e.g. "Content Accuracy")')
|
||||
.requiredOption('-n, --name <name>', 'Rubric name (e.g. "内容准确性")')
|
||||
.option('--type <type>', 'Rubric type (default: llm-rubric)', 'llm-rubric')
|
||||
.option('-t, --threshold <n>', 'Pass threshold 0-100 (converted to 0-1)')
|
||||
.option('-d, --description <text>', 'Criteria description (for llm-rubric type)')
|
||||
|
||||
@@ -8,12 +8,12 @@ import { registerBotCommand } from './commands/bot';
|
||||
import { registerCompletionCommand } from './commands/completion';
|
||||
import { registerConfigCommand } from './commands/config';
|
||||
import { registerConnectCommand } from './commands/connect';
|
||||
import { registerCronCommand } from './commands/cron';
|
||||
import { registerDeviceCommand } from './commands/device';
|
||||
import { registerDocCommand } from './commands/doc';
|
||||
import { registerEvalCommand } from './commands/eval';
|
||||
import { registerFileCommand } from './commands/file';
|
||||
import { registerGenerateCommand } from './commands/generate';
|
||||
import { registerHeteroCommand } from './commands/hetero';
|
||||
import { registerKbCommand } from './commands/kb';
|
||||
import { registerLoginCommand } from './commands/login';
|
||||
import { registerLogoutCommand } from './commands/logout';
|
||||
@@ -59,9 +59,9 @@ export function createProgram() {
|
||||
registerAgentCommand(program);
|
||||
registerAgentGroupCommand(program);
|
||||
registerBotCommand(program);
|
||||
registerCronCommand(program);
|
||||
registerGenerateCommand(program);
|
||||
registerFileCommand(program);
|
||||
registerHeteroCommand(program);
|
||||
registerSkillCommand(program);
|
||||
registerSessionGroupCommand(program);
|
||||
registerTaskCommand(program);
|
||||
|
||||
@@ -27,22 +27,22 @@ describe('executeToolCall', () => {
|
||||
fs.rmSync(tmpDir, { force: true, recursive: true });
|
||||
});
|
||||
|
||||
it('should dispatch readFile', async () => {
|
||||
it('should dispatch readLocalFile', async () => {
|
||||
const filePath = path.join(tmpDir, 'test.txt');
|
||||
await writeFile(filePath, 'hello world');
|
||||
|
||||
const result = await executeToolCall('readFile', JSON.stringify({ path: filePath }));
|
||||
const result = await executeToolCall('readLocalFile', JSON.stringify({ path: filePath }));
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
const parsed = JSON.parse(result.content);
|
||||
expect(parsed.content).toContain('hello world');
|
||||
});
|
||||
|
||||
it('should dispatch writeFile', async () => {
|
||||
it('should dispatch writeLocalFile', async () => {
|
||||
const filePath = path.join(tmpDir, 'new.txt');
|
||||
|
||||
const result = await executeToolCall(
|
||||
'writeFile',
|
||||
'writeLocalFile',
|
||||
JSON.stringify({ content: 'written', path: filePath }),
|
||||
);
|
||||
|
||||
@@ -50,17 +50,6 @@ describe('executeToolCall', () => {
|
||||
expect(fs.readFileSync(filePath, 'utf8')).toBe('written');
|
||||
});
|
||||
|
||||
it('should dispatch legacy alias readLocalFile', async () => {
|
||||
const filePath = path.join(tmpDir, 'legacy.txt');
|
||||
await writeFile(filePath, 'legacy hello');
|
||||
|
||||
const result = await executeToolCall('readLocalFile', JSON.stringify({ path: filePath }));
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
const parsed = JSON.parse(result.content);
|
||||
expect(parsed.content).toContain('legacy hello');
|
||||
});
|
||||
|
||||
it('should dispatch runCommand', async () => {
|
||||
const result = await executeToolCall(
|
||||
'runCommand',
|
||||
@@ -72,21 +61,21 @@ describe('executeToolCall', () => {
|
||||
expect(parsed.stdout).toContain('dispatched');
|
||||
});
|
||||
|
||||
it('should dispatch listFiles', async () => {
|
||||
it('should dispatch listLocalFiles', async () => {
|
||||
await writeFile(path.join(tmpDir, 'a.txt'), 'a');
|
||||
|
||||
const result = await executeToolCall('listFiles', JSON.stringify({ path: tmpDir }));
|
||||
const result = await executeToolCall('listLocalFiles', JSON.stringify({ path: tmpDir }));
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
const parsed = JSON.parse(result.content);
|
||||
expect(parsed.totalCount).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
it('should dispatch globFiles', async () => {
|
||||
it('should dispatch globLocalFiles', async () => {
|
||||
await writeFile(path.join(tmpDir, 'test.ts'), 'code');
|
||||
|
||||
const result = await executeToolCall(
|
||||
'globFiles',
|
||||
'globLocalFiles',
|
||||
JSON.stringify({ cwd: tmpDir, pattern: '*.ts' }),
|
||||
);
|
||||
|
||||
@@ -95,12 +84,12 @@ describe('executeToolCall', () => {
|
||||
expect(parsed.files).toContain('test.ts');
|
||||
});
|
||||
|
||||
it('should dispatch editFile', async () => {
|
||||
it('should dispatch editLocalFile', async () => {
|
||||
const filePath = path.join(tmpDir, 'edit.txt');
|
||||
await writeFile(filePath, 'old content');
|
||||
|
||||
const result = await executeToolCall(
|
||||
'editFile',
|
||||
'editLocalFile',
|
||||
JSON.stringify({
|
||||
file_path: filePath,
|
||||
new_string: 'new content',
|
||||
@@ -127,7 +116,7 @@ describe('executeToolCall', () => {
|
||||
const filePath = path.join(tmpDir, 'str.txt');
|
||||
await writeFile(filePath, 'content');
|
||||
|
||||
const result = await executeToolCall('readFile', JSON.stringify({ path: filePath }));
|
||||
const result = await executeToolCall('readLocalFile', JSON.stringify({ path: filePath }));
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
// Result should be valid JSON
|
||||
@@ -135,7 +124,7 @@ describe('executeToolCall', () => {
|
||||
});
|
||||
|
||||
it('should return error for invalid JSON arguments', async () => {
|
||||
const result = await executeToolCall('readFile', 'not-json');
|
||||
const result = await executeToolCall('readLocalFile', 'not-json');
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.error).toBeDefined();
|
||||
@@ -152,11 +141,11 @@ describe('executeToolCall', () => {
|
||||
expect(result.success).toBe(true);
|
||||
});
|
||||
|
||||
it('should dispatch searchFiles', async () => {
|
||||
it('should dispatch searchLocalFiles', async () => {
|
||||
await writeFile(path.join(tmpDir, 'search_target.txt'), 'found');
|
||||
|
||||
const result = await executeToolCall(
|
||||
'searchFiles',
|
||||
'searchLocalFiles',
|
||||
JSON.stringify({ directory: tmpDir, keywords: 'search_target' }),
|
||||
);
|
||||
|
||||
|
||||
@@ -11,22 +11,14 @@ import {
|
||||
import { getCommandOutput, killCommand, runCommand } from './shell';
|
||||
|
||||
const methodMap: Record<string, (args: any) => Promise<unknown>> = {
|
||||
editFile: editLocalFile,
|
||||
editLocalFile,
|
||||
getCommandOutput,
|
||||
globFiles: globLocalFiles,
|
||||
globLocalFiles,
|
||||
grepContent,
|
||||
killCommand,
|
||||
listFiles: listLocalFiles,
|
||||
readFile: readLocalFile,
|
||||
runCommand,
|
||||
searchFiles: searchLocalFiles,
|
||||
writeFile: writeLocalFile,
|
||||
|
||||
// Legacy aliases — older Gateway versions may still send the long form
|
||||
editLocalFile,
|
||||
globLocalFiles,
|
||||
listLocalFiles,
|
||||
readLocalFile,
|
||||
runCommand,
|
||||
searchLocalFiles,
|
||||
writeLocalFile,
|
||||
};
|
||||
|
||||
@@ -1,99 +0,0 @@
|
||||
import type { AgentStreamEvent } from '@lobechat/heterogeneous-agents/spawn';
|
||||
|
||||
export interface IngestSink {
|
||||
finish: (params: {
|
||||
error?: { message: string; type: string };
|
||||
result: 'cancelled' | 'error' | 'success';
|
||||
sessionId?: string;
|
||||
}) => Promise<void>;
|
||||
ingest: (events: AgentStreamEvent[]) => Promise<void>;
|
||||
}
|
||||
|
||||
export class NoopIngestSink implements IngestSink {
|
||||
async finish(_params: Parameters<IngestSink['finish']>[0]): Promise<void> {}
|
||||
async ingest(_events: AgentStreamEvent[]): Promise<void> {}
|
||||
}
|
||||
|
||||
const MAX_BATCH = 50;
|
||||
const FLUSH_INTERVAL_MS = 250;
|
||||
const MAX_RETRIES = 5;
|
||||
|
||||
const sleep = (ms: number) => new Promise<void>((r) => setTimeout(r, ms));
|
||||
|
||||
/**
|
||||
* Buffers `AgentStreamEvent`s and flushes them in batches to an `IngestSink`.
|
||||
*
|
||||
* Flush triggers:
|
||||
* - Buffer reaches MAX_BATCH (50) → immediate flush
|
||||
* - FLUSH_INTERVAL_MS (250ms) timer fires → flush whatever is buffered
|
||||
*
|
||||
* Each batch is retried up to MAX_RETRIES (5) times with exponential back-off
|
||||
* starting at 500ms, doubling up to 8s. After the final retry the error is
|
||||
* stored and re-thrown by `drain()`, allowing the caller to call
|
||||
* `sink.finish({ result: 'error' })` and exit(1).
|
||||
*
|
||||
* Call order: push() repeatedly → drain() once (before finish()).
|
||||
*/
|
||||
export class BatchIngester {
|
||||
private buffer: AgentStreamEvent[] = [];
|
||||
private fatalError: Error | null = null;
|
||||
private inflightFlush: Promise<void> = Promise.resolve();
|
||||
private timer: ReturnType<typeof setTimeout> | null = null;
|
||||
|
||||
constructor(private readonly sink: IngestSink) {}
|
||||
|
||||
push(event: AgentStreamEvent): void {
|
||||
if (this.fatalError) return;
|
||||
this.buffer.push(event);
|
||||
if (this.buffer.length >= MAX_BATCH) {
|
||||
if (this.timer) {
|
||||
clearTimeout(this.timer);
|
||||
this.timer = null;
|
||||
}
|
||||
this.triggerFlush();
|
||||
} else if (!this.timer) {
|
||||
this.timer = setTimeout(() => {
|
||||
this.timer = null;
|
||||
this.triggerFlush();
|
||||
}, FLUSH_INTERVAL_MS);
|
||||
}
|
||||
}
|
||||
|
||||
/** Flush remaining buffer and wait for all in-flight sends to settle. */
|
||||
async drain(): Promise<void> {
|
||||
if (this.timer) {
|
||||
clearTimeout(this.timer);
|
||||
this.timer = null;
|
||||
}
|
||||
this.triggerFlush();
|
||||
await this.inflightFlush;
|
||||
if (this.fatalError) throw this.fatalError;
|
||||
}
|
||||
|
||||
private async sendWithRetry(batch: AgentStreamEvent[]): Promise<void> {
|
||||
let delay = 500;
|
||||
for (let attempt = 0; attempt <= MAX_RETRIES; attempt++) {
|
||||
try {
|
||||
await this.sink.ingest(batch);
|
||||
return;
|
||||
} catch (err) {
|
||||
if (attempt === MAX_RETRIES) {
|
||||
this.fatalError = err instanceof Error ? err : new Error(String(err));
|
||||
throw this.fatalError;
|
||||
}
|
||||
await sleep(delay);
|
||||
delay = Math.min(delay * 2, 8_000);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private triggerFlush(): void {
|
||||
if (this.fatalError || this.buffer.length === 0) return;
|
||||
const batch = this.buffer.splice(0);
|
||||
this.inflightFlush = this.inflightFlush
|
||||
.then(() => this.sendWithRetry(batch))
|
||||
.catch(() => {
|
||||
// fatalError is already set; drain() re-throws it
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -1,38 +0,0 @@
|
||||
import type { AgentStreamEvent } from '@lobechat/heterogeneous-agents/spawn';
|
||||
|
||||
import type { TrpcClient } from '../api/client';
|
||||
import type { IngestSink } from './BatchIngester';
|
||||
|
||||
/**
|
||||
* `IngestSink` implementation that forwards batches to the server via tRPC
|
||||
* (`aiAgent.heteroIngest` / `aiAgent.heteroFinish`).
|
||||
*
|
||||
* The CLI authenticates using the `LOBEHUB_JWT` env var (operation-scoped JWT
|
||||
* injected by the server before spawning the sandbox / desktop process).
|
||||
*/
|
||||
export class TrpcIngestSink implements IngestSink {
|
||||
constructor(
|
||||
private readonly client: TrpcClient,
|
||||
private readonly agentType: 'claude-code' | 'codex',
|
||||
private readonly operationId: string,
|
||||
private readonly topicId: string,
|
||||
) {}
|
||||
|
||||
async finish(params: Parameters<IngestSink['finish']>[0]): Promise<void> {
|
||||
await this.client.aiAgent.heteroFinish.mutate({
|
||||
agentType: this.agentType,
|
||||
operationId: this.operationId,
|
||||
topicId: this.topicId,
|
||||
...params,
|
||||
});
|
||||
}
|
||||
|
||||
async ingest(events: AgentStreamEvent[]): Promise<void> {
|
||||
await this.client.aiAgent.heteroIngest.mutate({
|
||||
agentType: this.agentType,
|
||||
events: events as any,
|
||||
operationId: this.operationId,
|
||||
topicId: this.topicId,
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -58,7 +58,6 @@
|
||||
"@lobechat/electron-client-ipc": "workspace:*",
|
||||
"@lobechat/electron-server-ipc": "workspace:*",
|
||||
"@lobechat/file-loaders": "workspace:*",
|
||||
"@lobechat/heterogeneous-agents": "workspace:*",
|
||||
"@lobechat/local-file-shell": "workspace:*",
|
||||
"@lobehub/i18n-cli": "^1.25.1",
|
||||
"@modelcontextprotocol/sdk": "^1.24.3",
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
packages:
|
||||
- '../cli'
|
||||
- '../../packages/agent-gateway-client'
|
||||
- '../../packages/heterogeneous-agents'
|
||||
- '../../packages/const'
|
||||
- '../../packages/electron-server-ipc'
|
||||
- '../../packages/electron-client-ipc'
|
||||
|
||||
@@ -7,18 +7,18 @@ import { entryLocaleJsonFilepath, i18nConfig, localeDir, srcDefaultLocales } fro
|
||||
import { tagWhite, writeJSON } from './utils';
|
||||
|
||||
export const genDefaultLocale = () => {
|
||||
consola.info(`Default locale: ${i18nConfig.entryLocale}...`);
|
||||
consola.info(`默认语言为 ${i18nConfig.entryLocale}...`);
|
||||
|
||||
// Ensure entry locale directory exists
|
||||
const entryLocaleDir = localeDir(i18nConfig.entryLocale);
|
||||
if (!existsSync(entryLocaleDir)) {
|
||||
mkdirSync(entryLocaleDir, { recursive: true });
|
||||
consola.info(`Creating directory: ${entryLocaleDir}`);
|
||||
consola.info(`创建目录：${entryLocaleDir}`);
|
||||
}
|
||||
|
||||
const resources = require(srcDefaultLocales);
|
||||
const data = Object.entries(resources.default);
|
||||
consola.start(`Generating default locale JSON files, found ${data.length} namespaces...`);
|
||||
consola.start(`生成默认语言 JSON 文件，发现 ${data.length} 个命名空间...`);
|
||||
|
||||
for (const [ns, value] of data) {
|
||||
const filepath = entryLocaleJsonFilepath(`${ns}.json`);
|
||||
|
||||
@@ -13,7 +13,7 @@ import {
|
||||
import { readJSON, tagWhite, writeJSON } from './utils';
|
||||
|
||||
export const genDiff = () => {
|
||||
consola.start(`Comparing localization files between dev and prod environments...`);
|
||||
consola.start(`对比开发与生产环境中的本地化文件...`);
|
||||
|
||||
const resources = require(srcDefaultLocales);
|
||||
const data = Object.entries(resources.default);
|
||||
@@ -21,7 +21,7 @@ export const genDiff = () => {
|
||||
for (const [ns, devJSON] of data) {
|
||||
const filepath = entryLocaleJsonFilepath(`${ns}.json`);
|
||||
if (!existsSync(filepath)) {
|
||||
consola.info(`File does not exist, skipping: ${filepath}`);
|
||||
consola.info(`文件不存在，跳过：${filepath}`);
|
||||
continue;
|
||||
}
|
||||
|
||||
@@ -50,7 +50,7 @@ export const genDiff = () => {
|
||||
}
|
||||
|
||||
if (clearLocals.length > 0) {
|
||||
consola.info('Cleaned up stale entries for the following locales:', clearLocals.join(', '));
|
||||
consola.info('清理了以下语言的过期项目：', clearLocals.join(', '));
|
||||
}
|
||||
consola.success(tagWhite(ns), colors.gray(filepath));
|
||||
}
|
||||
|
||||
@@ -21,15 +21,15 @@ const run = async () => {
|
||||
ensureLocalesDirs();
|
||||
|
||||
// Diff analysis
|
||||
split('Diff Analysis');
|
||||
split('差异分析');
|
||||
genDiff();
|
||||
|
||||
// Generate default locale files
|
||||
split('Generate Default Locale Files');
|
||||
split('生成默认语言文件');
|
||||
genDefaultLocale();
|
||||
|
||||
// Generate i18n files
|
||||
split('Generate i18n Files');
|
||||
split('生成国际化文件');
|
||||
};
|
||||
|
||||
run();
|
||||
|
||||
@@ -26,7 +26,6 @@ export const defaultProxySettings: NetworkProxySettings = {
|
||||
* Storage default values
|
||||
*/
|
||||
export const STORE_DEFAULTS: ElectronMainStore = {
|
||||
appTrayVisible: true,
|
||||
dataSyncConfig: { storageMode: 'cloud' },
|
||||
encryptedTokens: {},
|
||||
gatewayDeviceDescription: '',
|
||||
|
||||
@@ -1,9 +1,7 @@
|
||||
import type { AgentRunRequestMessage } from '@lobechat/device-gateway-client';
|
||||
import type { GatewayConnectionStatus } from '@lobechat/electron-client-ipc';
|
||||
|
||||
import GatewayConnectionService from '@/services/gatewayConnectionSrv';
|
||||
|
||||
import HeterogeneousAgentCtr from './HeterogeneousAgentCtr';
|
||||
import { ControllerModule, IpcMethod } from './index';
|
||||
import LocalFileCtr from './LocalFileCtr';
|
||||
import RemoteServerConfigCtr from './RemoteServerConfigCtr';
|
||||
@@ -35,10 +33,6 @@ export default class GatewayConnectionCtr extends ControllerModule {
|
||||
return this.app.getController(ShellCommandCtr);
|
||||
}
|
||||
|
||||
private get heterogeneousAgentCtr() {
|
||||
return this.app.getController(HeterogeneousAgentCtr);
|
||||
}
|
||||
|
||||
// ─── Lifecycle ───
|
||||
|
||||
afterAppReady() {
|
||||
@@ -53,9 +47,6 @@ export default class GatewayConnectionCtr extends ControllerModule {
|
||||
// Wire up tool call handler
|
||||
srv.setToolCallHandler((apiName, args) => this.executeToolCall(apiName, args));
|
||||
|
||||
// Wire up agent run handler
|
||||
srv.setAgentRunHandler((request) => this.executeAgentRun(request));
|
||||
|
||||
// Auto-connect if already logged in
|
||||
this.tryAutoConnect();
|
||||
}
|
||||
@@ -117,81 +108,23 @@ export default class GatewayConnectionCtr extends ControllerModule {
|
||||
await this.service.connect();
|
||||
}
|
||||
|
||||
// ─── Agent Run Routing ───
|
||||
|
||||
private async executeAgentRun(
|
||||
request: AgentRunRequestMessage,
|
||||
): Promise<{ reason?: string; status: 'accepted' | 'rejected' }> {
|
||||
try {
|
||||
const ctr = this.heterogeneousAgentCtr;
|
||||
|
||||
// Create a session for the hetero agent.
|
||||
const { sessionId } = await ctr.startSession({
|
||||
agentType: request.agentType,
|
||||
args: [],
|
||||
command: request.agentType === 'codex' ? 'codex' : 'claude',
|
||||
cwd: request.cwd,
|
||||
// Inject LOBEHUB_JWT so the CLI authenticates against heteroIngest.
|
||||
env: { LOBEHUB_JWT: request.jwt },
|
||||
resumeSessionId: request.resumeSessionId,
|
||||
});
|
||||
|
||||
// Fire-and-forget: sendPrompt runs the CLI until completion.
|
||||
ctr
|
||||
.sendPrompt({
|
||||
operationId: request.operationId,
|
||||
prompt: request.prompt,
|
||||
sessionId,
|
||||
})
|
||||
.catch((err: Error) => {
|
||||
// Errors are surfaced via heteroFinish on the server side.
|
||||
// Log locally for desktop debugging only.
|
||||
console.error('[GatewayConnectionCtr] agent run failed:', err.message);
|
||||
});
|
||||
|
||||
return { status: 'accepted' };
|
||||
} catch (err) {
|
||||
const reason = err instanceof Error ? err.message : String(err);
|
||||
return { reason, status: 'rejected' };
|
||||
}
|
||||
}
|
||||
|
||||
// ─── Tool Call Routing ───
|
||||
|
||||
private async executeToolCall(apiName: string, args: any): Promise<unknown> {
|
||||
const editFile = () => this.localFileCtr.handleEditFile(args);
|
||||
const globFiles = () => this.localFileCtr.handleGlobFiles(args);
|
||||
const listFiles = () => this.localFileCtr.listLocalFiles(args);
|
||||
const moveFiles = () => this.localFileCtr.handleMoveFiles(args);
|
||||
const readFile = () => this.localFileCtr.readFile(args);
|
||||
const searchFiles = () => this.localFileCtr.handleLocalFilesSearch(args);
|
||||
const writeFile = () => this.localFileCtr.handleWriteFile(args);
|
||||
|
||||
const methodMap: Record<string, () => Promise<unknown>> = {
|
||||
editFile,
|
||||
globFiles,
|
||||
editLocalFile: () => this.localFileCtr.handleEditFile(args),
|
||||
globLocalFiles: () => this.localFileCtr.handleGlobFiles(args),
|
||||
grepContent: () => this.localFileCtr.handleGrepContent(args),
|
||||
listFiles,
|
||||
moveFiles,
|
||||
readFile,
|
||||
searchFiles,
|
||||
writeFile,
|
||||
listLocalFiles: () => this.localFileCtr.listLocalFiles(args),
|
||||
moveLocalFiles: () => this.localFileCtr.handleMoveFiles(args),
|
||||
readLocalFile: () => this.localFileCtr.readFile(args),
|
||||
renameLocalFile: () => this.localFileCtr.handleRenameFile(args),
|
||||
searchLocalFiles: () => this.localFileCtr.handleLocalFilesSearch(args),
|
||||
writeLocalFile: () => this.localFileCtr.handleWriteFile(args),
|
||||
|
||||
getCommandOutput: () => this.shellCommandCtr.handleGetCommandOutput(args),
|
||||
killCommand: () => this.shellCommandCtr.handleKillCommand(args),
|
||||
runCommand: () => this.shellCommandCtr.handleRunCommand(args),
|
||||
|
||||
// Legacy aliases — keep these so older Gateway versions sending the long
|
||||
// names continue to route correctly. `renameLocalFile` is also kept even
|
||||
// though the new surface drops rename (it's now handled by `moveFiles`).
|
||||
editLocalFile: editFile,
|
||||
globLocalFiles: globFiles,
|
||||
listLocalFiles: listFiles,
|
||||
moveLocalFiles: moveFiles,
|
||||
readLocalFile: readFile,
|
||||
renameLocalFile: () => this.localFileCtr.handleRenameFile(args),
|
||||
searchLocalFiles: searchFiles,
|
||||
writeLocalFile: writeFile,
|
||||
};
|
||||
|
||||
const handler = methodMap[apiName];
|
||||
|
||||
@@ -1,21 +1,17 @@
|
||||
import { execFile, spawn } from 'node:child_process';
|
||||
import { readFile, rm, stat } from 'node:fs/promises';
|
||||
import { execFile } from 'node:child_process';
|
||||
import { readFile } from 'node:fs/promises';
|
||||
import path from 'node:path';
|
||||
import { promisify } from 'node:util';
|
||||
|
||||
import type {
|
||||
GetGitBranchDiffPayload,
|
||||
GitAheadBehind,
|
||||
GitBranchDiffPatches,
|
||||
GitBranchInfo,
|
||||
GitBranchListItem,
|
||||
GitCheckoutResult,
|
||||
GitFileDiffStatus,
|
||||
GitFileRevertResult,
|
||||
GitLinkedPullRequestResult,
|
||||
GitPullResult,
|
||||
GitPushResult,
|
||||
GitRemoteBranchListItem,
|
||||
GitWorkingTreeFiles,
|
||||
GitWorkingTreePatch,
|
||||
GitWorkingTreePatches,
|
||||
@@ -29,412 +25,6 @@ import { ControllerModule, IpcMethod } from './index';
|
||||
|
||||
const logger = createLogger('controllers:GitCtr');
|
||||
|
||||
interface DirtyEntry {
|
||||
filePath: string;
|
||||
status: GitFileDiffStatus;
|
||||
}
|
||||
|
||||
interface DiffBlock {
|
||||
isBinary: boolean;
|
||||
patch: string;
|
||||
/** Destination path (or source path for deleted files). */
|
||||
path: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Split the output of `git diff HEAD --` into one block per file. Each block
|
||||
* starts at a `^diff --git ` line and runs to just before the next one (or
|
||||
* EOF). Path comes from the `+++ b/<path>` line, falling back to `--- a/<path>`
|
||||
* when the destination is `/dev/null` (deletion). Quoted paths (spaces /
|
||||
* non-ASCII when `core.quotepath` is on) are minimally de-escaped.
|
||||
*/
|
||||
const splitBulkDiff = (diffText: string): DiffBlock[] => {
|
||||
if (!diffText) return [];
|
||||
const blocks: DiffBlock[] = [];
|
||||
const headerRe = /^diff --git /gm;
|
||||
const starts: number[] = [];
|
||||
let m: RegExpExecArray | null;
|
||||
while ((m = headerRe.exec(diffText)) !== null) starts.push(m.index);
|
||||
for (let i = 0; i < starts.length; i++) {
|
||||
const start = starts[i];
|
||||
const end = i + 1 < starts.length ? starts[i + 1] : diffText.length;
|
||||
const block = diffText.slice(start, end);
|
||||
const filePath = extractPathFromDiffBlock(block);
|
||||
if (!filePath) continue;
|
||||
blocks.push({
|
||||
isBinary: /^Binary files .* differ$/m.test(block),
|
||||
path: filePath,
|
||||
patch: block,
|
||||
});
|
||||
}
|
||||
return blocks;
|
||||
};
|
||||
|
||||
/**
|
||||
* Pull the file path out of a per-file diff block. Looks at the `+++ b/<path>`
|
||||
* line first (covers add/modify); falls back to `--- a/<path>` for deletes
|
||||
* where `+++` is `/dev/null`; final fallback is the `diff --git a/x b/y`
|
||||
* header line.
|
||||
*/
|
||||
const extractPathFromDiffBlock = (block: string): string | null => {
|
||||
let plusPath: string | null = null;
|
||||
let minusPath: string | null = null;
|
||||
for (const line of block.split('\n')) {
|
||||
if (line.startsWith('+++ ')) {
|
||||
plusPath = parseDiffPathLine(line.slice(4), 'b/');
|
||||
} else if (line.startsWith('--- ')) {
|
||||
minusPath = parseDiffPathLine(line.slice(4), 'a/');
|
||||
}
|
||||
// The file headers always come before the first hunk / binary marker;
|
||||
// bail once we hit either to avoid scanning huge diff bodies.
|
||||
if (line.startsWith('@@') || line.startsWith('Binary files ')) break;
|
||||
}
|
||||
if (plusPath) return plusPath;
|
||||
if (minusPath) return minusPath;
|
||||
// Last-resort: parse the `diff --git a/x b/y` header itself.
|
||||
const header = block.split('\n', 1)[0];
|
||||
const match = /^diff --git a\/.+? b\/(.+)$/.exec(header);
|
||||
return match ? match[1] : null;
|
||||
};
|
||||
|
||||
/**
|
||||
* Strip the `a/` or `b/` prefix off a `+++` / `---` line, drop the optional
|
||||
* trailing tab+timestamp, and de-quote git's C-style escaping. Returns null
|
||||
* for `/dev/null` (which means the other side of the diff is the real path).
|
||||
*/
|
||||
const parseDiffPathLine = (raw: string, prefix: 'a/' | 'b/'): string | null => {
|
||||
const tabIdx = raw.indexOf('\t');
|
||||
let p = tabIdx >= 0 ? raw.slice(0, tabIdx) : raw;
|
||||
if (p === '/dev/null') return null;
|
||||
// Quoted form: "b/path with spaces"
|
||||
if (p.startsWith('"') && p.endsWith('"')) {
|
||||
p = dequoteGitPath(p.slice(1, -1));
|
||||
}
|
||||
return p.startsWith(prefix) ? p.slice(prefix.length) : p;
|
||||
};
|
||||
|
||||
export const dequoteGitPath = (s: string): string =>
|
||||
s.replaceAll(/\\(["\\trn]|[0-7]{3})/g, (_, esc: string) => {
|
||||
if (esc === '"') return '"';
|
||||
if (esc === '\\') return '\\';
|
||||
if (esc === 't') return '\t';
|
||||
if (esc === 'r') return '\r';
|
||||
if (esc === 'n') return '\n';
|
||||
return String.fromCodePoint(Number.parseInt(esc, 8));
|
||||
});
|
||||
|
||||
/**
|
||||
* Inverse of {@link dequoteGitPath} — returns either `<prefix><path>` (when
|
||||
* no escaping is needed) or git's C-style quoted form `"<prefix><escaped>"`
|
||||
* (when the path contains TAB / LF / CR / quote / backslash / control bytes).
|
||||
* The prefix lives *inside* the quotes so the output matches what real `git
|
||||
* diff` would emit, e.g. `"a/file\twith tab.txt"` rather than `a/"file\twith
|
||||
* tab.txt"`. Plain spaces are not quoted (git tolerates them; the trailing
|
||||
* ` b/<path>` marker on the diff header is enough to delimit the source).
|
||||
*/
|
||||
// eslint-disable-next-line no-control-regex
|
||||
const NEEDS_QUOTING = /["\\\x00-\x1F\x7F]/;
|
||||
export const quoteGitPath = (prefix: 'a/' | 'b/', filePath: string): string => {
|
||||
const combined = prefix + filePath;
|
||||
if (!NEEDS_QUOTING.test(combined)) return combined;
|
||||
let out = '"';
|
||||
for (const ch of combined) {
|
||||
if (ch === '\\') out += '\\\\';
|
||||
else if (ch === '"') out += '\\"';
|
||||
else if (ch === '\t') out += '\\t';
|
||||
else if (ch === '\n') out += '\\n';
|
||||
else if (ch === '\r') out += '\\r';
|
||||
else {
|
||||
const code = ch.codePointAt(0)!;
|
||||
if (code < 0x20 || code === 0x7f) {
|
||||
out += '\\' + code.toString(8).padStart(3, '0');
|
||||
} else {
|
||||
out += ch;
|
||||
}
|
||||
}
|
||||
}
|
||||
return out + '"';
|
||||
};
|
||||
|
||||
/**
|
||||
* Status from a single diff block's preamble: `new file mode` → added,
|
||||
* `deleted file mode` → deleted, otherwise modified. Used by branch-diff mode
|
||||
* where there's no `git status` to consult — the diff itself is the source.
|
||||
*/
|
||||
const detectDiffBlockStatus = (block: string): GitFileDiffStatus => {
|
||||
// Only scan up to the first hunk / binary marker so huge bodies aren't walked.
|
||||
for (const line of block.split('\n')) {
|
||||
if (line.startsWith('new file mode ')) return 'added';
|
||||
if (line.startsWith('deleted file mode ')) return 'deleted';
|
||||
if (line.startsWith('@@') || line.startsWith('Binary files ')) break;
|
||||
}
|
||||
return 'modified';
|
||||
};
|
||||
|
||||
/** Walk a patch counting `+`/`-` lines while skipping `+++`/`---` headers. */
|
||||
const countAddDel = (patch: string): { additions: number; deletions: number } => {
|
||||
let additions = 0;
|
||||
let deletions = 0;
|
||||
for (const line of patch.split('\n')) {
|
||||
if (line.startsWith('+++') || line.startsWith('---')) continue;
|
||||
if (line.startsWith('+')) additions++;
|
||||
else if (line.startsWith('-')) deletions++;
|
||||
}
|
||||
return { additions, deletions };
|
||||
};
|
||||
|
||||
const emptyPatch = (entry: DirtyEntry): GitWorkingTreePatch => ({
|
||||
additions: 0,
|
||||
deletions: 0,
|
||||
filePath: entry.filePath,
|
||||
isBinary: false,
|
||||
patch: '',
|
||||
status: entry.status,
|
||||
truncated: false,
|
||||
});
|
||||
|
||||
const buildTrackedPatch = (
|
||||
entry: DirtyEntry,
|
||||
block: DiffBlock,
|
||||
maxBytes: number,
|
||||
): GitWorkingTreePatch => {
|
||||
if (block.isBinary) {
|
||||
return { ...emptyPatch(entry), isBinary: true };
|
||||
}
|
||||
if (block.patch.length > maxBytes) {
|
||||
return { ...emptyPatch(entry), truncated: true };
|
||||
}
|
||||
const { additions, deletions } = countAddDel(block.patch);
|
||||
return {
|
||||
additions,
|
||||
deletions,
|
||||
filePath: entry.filePath,
|
||||
isBinary: false,
|
||||
patch: block.patch,
|
||||
status: entry.status,
|
||||
truncated: false,
|
||||
};
|
||||
};
|
||||
|
||||
/**
|
||||
* Build a synthetic add-only patch for an untracked file by reading it from
|
||||
* disk — replaces the per-file `git diff --no-index /dev/null <file>` fork.
|
||||
* Binary detection uses a NUL-byte sniff over the first 8 KB (matches what
|
||||
* git itself does internally).
|
||||
*/
|
||||
const readUntrackedAsPatch = async (
|
||||
cwd: string,
|
||||
entry: DirtyEntry,
|
||||
maxBytes: number,
|
||||
): Promise<GitWorkingTreePatch> => {
|
||||
const absolute = path.resolve(cwd, entry.filePath);
|
||||
let size: number;
|
||||
try {
|
||||
const s = await stat(absolute);
|
||||
if (!s.isFile()) return emptyPatch(entry);
|
||||
size = s.size;
|
||||
} catch (error: any) {
|
||||
logger.debug('[readUntrackedAsPatch] stat failed', {
|
||||
filePath: entry.filePath,
|
||||
message: error?.message,
|
||||
});
|
||||
return emptyPatch(entry);
|
||||
}
|
||||
// Pre-quote so the path is C-style escaped wherever it lands in the synthetic
|
||||
// patch — raw `entry.filePath` interpolation would emit malformed `diff --git`
|
||||
// / `+++` lines for filenames containing TAB / LF / quote / backslash.
|
||||
const aPath = quoteGitPath('a/', entry.filePath);
|
||||
const bPath = quoteGitPath('b/', entry.filePath);
|
||||
if (size === 0) {
|
||||
return {
|
||||
...emptyPatch(entry),
|
||||
patch:
|
||||
[
|
||||
`diff --git ${aPath} ${bPath}`,
|
||||
'new file mode 100644',
|
||||
'--- /dev/null',
|
||||
`+++ ${bPath}`,
|
||||
].join('\n') + '\n',
|
||||
};
|
||||
}
|
||||
// Cap the synthesized patch by *file* size, not patch size — a 200 KB file
|
||||
// produces a ~200 KB patch (one `+` per line). Close enough.
|
||||
if (size > maxBytes) {
|
||||
return { ...emptyPatch(entry), truncated: true };
|
||||
}
|
||||
let buf: Buffer;
|
||||
try {
|
||||
buf = await readFile(absolute);
|
||||
} catch (error: any) {
|
||||
logger.debug('[readUntrackedAsPatch] read failed', {
|
||||
filePath: entry.filePath,
|
||||
message: error?.message,
|
||||
});
|
||||
return emptyPatch(entry);
|
||||
}
|
||||
const sniffEnd = Math.min(buf.length, 8192);
|
||||
for (let i = 0; i < sniffEnd; i++) {
|
||||
if (buf[i] === 0) return { ...emptyPatch(entry), isBinary: true };
|
||||
}
|
||||
const text = buf.toString('utf8');
|
||||
// text.split('\n') leaves a trailing '' when the file ends with '\n';
|
||||
// exclude it so the hunk header line count matches git's own output.
|
||||
const rawLines = text.split('\n');
|
||||
const trailingEmpty = rawLines.length > 0 && rawLines.at(-1) === '';
|
||||
const lineCount = trailingEmpty ? rawLines.length - 1 : rawLines.length;
|
||||
if (lineCount === 0) {
|
||||
return { ...emptyPatch(entry), patch: '' };
|
||||
}
|
||||
const body = rawLines
|
||||
.slice(0, lineCount)
|
||||
.map((line) => '+' + line)
|
||||
.join('\n');
|
||||
// Mirror `git diff --no-index`'s "no newline at end of file" footer when the
|
||||
// source had no trailing newline — keeps PatchDiff's hunk parser happy.
|
||||
const noNewlineFooter = trailingEmpty ? '' : '\n\\ No newline at end of file';
|
||||
const patch =
|
||||
[
|
||||
`diff --git ${aPath} ${bPath}`,
|
||||
'new file mode 100644',
|
||||
'--- /dev/null',
|
||||
`+++ ${bPath}`,
|
||||
`@@ -0,0 +1,${lineCount} @@`,
|
||||
body,
|
||||
].join('\n') +
|
||||
noNewlineFooter +
|
||||
'\n';
|
||||
return {
|
||||
additions: lineCount,
|
||||
deletions: 0,
|
||||
filePath: entry.filePath,
|
||||
isBinary: false,
|
||||
patch,
|
||||
status: entry.status,
|
||||
truncated: false,
|
||||
};
|
||||
};
|
||||
|
||||
/**
|
||||
* Stream a git invocation's stdout via `spawn` instead of `execFile`'s
|
||||
* fixed-size buffer. Replaces the bulk-diff caller's old 64 MB `maxBuffer`
|
||||
* cap — pipe-buffer-sized chunks accumulate in memory until the process
|
||||
* exits, with no hard ceiling. SIGTERM on timeout. Resolves with the full
|
||||
* stdout string; rejects with an Error carrying `stderr` and `partialStdout`
|
||||
* fields so callers can salvage partial output (or fall back) on failure.
|
||||
*/
|
||||
const runGitCaptureStream = (cwd: string, args: string[], timeoutMs: number): Promise<string> =>
|
||||
new Promise((resolve, reject) => {
|
||||
const child = spawn('git', args, { cwd });
|
||||
const stdoutChunks: Buffer[] = [];
|
||||
let stderrBuf = '';
|
||||
let timedOut = false;
|
||||
const timer = setTimeout(() => {
|
||||
timedOut = true;
|
||||
child.kill('SIGTERM');
|
||||
}, timeoutMs);
|
||||
child.stdout.on('data', (chunk: Buffer) => stdoutChunks.push(chunk));
|
||||
child.stderr.on('data', (chunk: Buffer) => {
|
||||
stderrBuf += chunk.toString('utf8');
|
||||
});
|
||||
child.on('error', (err) => {
|
||||
clearTimeout(timer);
|
||||
reject(Object.assign(err, { stderr: stderrBuf }));
|
||||
});
|
||||
child.on('close', (code) => {
|
||||
clearTimeout(timer);
|
||||
const stdout = Buffer.concat(stdoutChunks).toString('utf8');
|
||||
if (timedOut) {
|
||||
const err: any = new Error('git command timed out');
|
||||
err.stderr = stderrBuf;
|
||||
err.partialStdout = stdout;
|
||||
return reject(err);
|
||||
}
|
||||
// `git diff HEAD` (without --exit-code) exits 0 even when there are
|
||||
// diffs; non-zero is therefore a real error.
|
||||
if (code !== 0) {
|
||||
const err: any = new Error(`git exited with code ${code}`);
|
||||
err.code = code;
|
||||
err.stderr = stderrBuf;
|
||||
err.partialStdout = stdout;
|
||||
return reject(err);
|
||||
}
|
||||
resolve(stdout);
|
||||
});
|
||||
});
|
||||
|
||||
/**
|
||||
* Last-resort per-file diff for tracked entries the bulk diff didn't cover —
|
||||
* either because the bulk command failed entirely or because git emitted no
|
||||
* patch for a path the status step listed (rare race with concurrent writes).
|
||||
* Mirrors the original per-file behavior so individual files keep their
|
||||
* patches even when the bulk fast-path is unavailable.
|
||||
*/
|
||||
const fetchTrackedPatchPerFile = async (
|
||||
cwd: string,
|
||||
entry: DirtyEntry,
|
||||
maxBytes: number,
|
||||
): Promise<GitWorkingTreePatch> => {
|
||||
const execFileAsync = promisify(execFile);
|
||||
let text: string;
|
||||
try {
|
||||
const { stdout } = await execFileAsync(
|
||||
'git',
|
||||
['-c', 'core.quotepath=off', 'diff', '--no-color', 'HEAD', '--', entry.filePath],
|
||||
{
|
||||
cwd,
|
||||
encoding: 'utf8',
|
||||
maxBuffer: maxBytes * 4,
|
||||
timeout: 10_000,
|
||||
},
|
||||
);
|
||||
text = stdout as string;
|
||||
} catch (error: any) {
|
||||
logger.debug('[fetchTrackedPatchPerFile] diff failed', {
|
||||
filePath: entry.filePath,
|
||||
stderr: error?.stderr?.toString?.() ?? error?.stderr,
|
||||
});
|
||||
return emptyPatch(entry);
|
||||
}
|
||||
if (text.length > maxBytes) return { ...emptyPatch(entry), truncated: true };
|
||||
if (/^Binary files .* differ$/m.test(text)) return { ...emptyPatch(entry), isBinary: true };
|
||||
if (!text) return emptyPatch(entry);
|
||||
const { additions, deletions } = countAddDel(text);
|
||||
return {
|
||||
additions,
|
||||
deletions,
|
||||
filePath: entry.filePath,
|
||||
isBinary: false,
|
||||
patch: text,
|
||||
status: entry.status,
|
||||
truncated: false,
|
||||
};
|
||||
};
|
||||
|
||||
/**
|
||||
* Bounded `Promise.all` — runs at most `limit` async tasks at a time. Used
|
||||
* for the per-file fallback so we cap fork pressure at a small constant
|
||||
* instead of replaying the original 200-parallel `git diff` storm.
|
||||
*/
|
||||
const mapWithConcurrency = async <T, R>(
|
||||
items: T[],
|
||||
limit: number,
|
||||
fn: (item: T) => Promise<R>,
|
||||
): Promise<R[]> => {
|
||||
const results: R[] = Array.from({ length: items.length });
|
||||
let cursor = 0;
|
||||
const workerCount = Math.min(limit, items.length);
|
||||
await Promise.all(
|
||||
Array.from({ length: workerCount }, async () => {
|
||||
while (true) {
|
||||
const idx = cursor++;
|
||||
if (idx >= items.length) return;
|
||||
results[idx] = await fn(items[idx]);
|
||||
}
|
||||
}),
|
||||
);
|
||||
return results;
|
||||
};
|
||||
|
||||
export default class GitController extends ControllerModule {
|
||||
static override readonly groupName = 'git';
|
||||
|
||||
@@ -575,54 +165,6 @@ export default class GitController extends ControllerModule {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* List remote branches under `refs/remotes/origin/*`, ordered by most
|
||||
* recent commit. The `HEAD` symref is filtered out and the resolved
|
||||
* default branch is flagged via `isDefault` so the UI can render it
|
||||
* with a marker. Used by the Review panel's branch-compare picker.
|
||||
*/
|
||||
@IpcMethod()
|
||||
async listGitRemoteBranches(dirPath: string): Promise<GitRemoteBranchListItem[]> {
|
||||
const execFileAsync = promisify(execFile);
|
||||
let defaultRef: string | undefined;
|
||||
try {
|
||||
const { stdout } = await execFileAsync(
|
||||
'git',
|
||||
['symbolic-ref', '--short', 'refs/remotes/origin/HEAD'],
|
||||
{ cwd: dirPath, timeout: 5000 },
|
||||
);
|
||||
defaultRef = stdout.trim() || undefined;
|
||||
} catch {
|
||||
defaultRef = undefined;
|
||||
}
|
||||
try {
|
||||
const { stdout } = await execFileAsync(
|
||||
'git',
|
||||
[
|
||||
'for-each-ref',
|
||||
'--sort=-committerdate',
|
||||
'--format=%(refname:short)',
|
||||
'refs/remotes/origin',
|
||||
],
|
||||
{ cwd: dirPath, timeout: 5000 },
|
||||
);
|
||||
return stdout
|
||||
.replaceAll('\r', '')
|
||||
.split('\n')
|
||||
.map((line) => line.trim())
|
||||
.filter((name) => name.length > 0 && name !== 'origin/HEAD' && !name.endsWith('/HEAD'))
|
||||
.map((name) => ({ isDefault: name === defaultRef, name }));
|
||||
} catch (error: any) {
|
||||
logger.warn('[listGitRemoteBranches] git command failed', {
|
||||
code: error?.code,
|
||||
cwd: dirPath,
|
||||
message: error?.message,
|
||||
stderr: error?.stderr?.toString?.() ?? error?.stderr,
|
||||
});
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Bucket dirty files into added / modified / deleted via `git status --porcelain -z`.
|
||||
* Each file is counted once: untracked (`??`) and staged-add (`A`) → added,
|
||||
@@ -724,18 +266,14 @@ export default class GitController extends ControllerModule {
|
||||
|
||||
/**
|
||||
* Pull every dirty file's unified diff in one shot — one IPC call returns
|
||||
* the patches the renderer needs to render `<PatchDiff />` per file.
|
||||
* the patches the renderer needs to render `<PatchDiff />` per file. We do
|
||||
* the per-file `git diff` invocations in parallel inside this method so
|
||||
* the renderer doesn't have to fan out N IPC round trips.
|
||||
*
|
||||
* Tracked changes (modified / deleted / staged-A) all come from a *single*
|
||||
* `git diff HEAD --` invocation that we split per-file in JS — fork-bombing
|
||||
* the main process with N parallel `git diff` subprocesses was costing us
|
||||
* ~5–10ms × N in fork overhead plus `.git/index` lock contention, and the
|
||||
* libuv worker pool stayed busy while other IPC handlers queued. One
|
||||
* subprocess instead of N keeps the freeze invisible.
|
||||
*
|
||||
* Untracked files are read directly with `fs.readFile` and a synthetic
|
||||
* `--- /dev/null / +++ b/<path>` patch is built in Node — no `git diff`
|
||||
* subprocess at all.
|
||||
* Tracked changes (modified / deleted / staged-A) come from
|
||||
* `git diff HEAD -- <file>`; pure untracked files come from
|
||||
* `git diff --no-index /dev/null <file>` (which exits with code 1 when
|
||||
* there are differences — that's success, not failure).
|
||||
*
|
||||
* Per-file patches are capped at 256 KB; oversized or binary entries get an
|
||||
* empty `patch` string and a flag the renderer can use for a placeholder.
|
||||
@@ -753,7 +291,7 @@ export default class GitController extends ControllerModule {
|
||||
|
||||
// Step 1 — classify every dirty path. Mirrors getGitWorkingTreeFiles but
|
||||
// also distinguishes untracked (`??`) from staged-add (`A`) so we can pick
|
||||
// the right path (git diff vs raw read) per entry.
|
||||
// the right diff command per entry.
|
||||
const entries: Entry[] = [];
|
||||
try {
|
||||
const { stdout } = await execFileAsync('git', ['status', '--porcelain', '-z'], {
|
||||
@@ -792,163 +330,100 @@ export default class GitController extends ControllerModule {
|
||||
return { patches: [] };
|
||||
}
|
||||
|
||||
// Step 2a — single bulk `git diff HEAD` for every tracked dirty path,
|
||||
// then split per-file in JS. We pass paths explicitly (not all) so a
|
||||
// huge unrelated working tree doesn't pull extra patches into the
|
||||
// stream. Output is streamed via spawn so there's no maxBuffer ceiling
|
||||
// — even a multi-hundred-MB combined diff lands intact, and any partial
|
||||
// output recovered from a failed run still feeds the per-file fallback.
|
||||
const trackedEntries = entries.filter((e) => !e.isUntracked);
|
||||
const trackedByPath = new Map(trackedEntries.map((e) => [e.filePath, e]));
|
||||
const trackedPatches = new Map<string, GitWorkingTreePatch>();
|
||||
if (trackedEntries.length > 0) {
|
||||
let bulkDiff = '';
|
||||
try {
|
||||
bulkDiff = await runGitCaptureStream(
|
||||
dirPath,
|
||||
[
|
||||
'-c',
|
||||
'core.quotepath=off',
|
||||
'diff',
|
||||
'--no-color',
|
||||
'HEAD',
|
||||
'--',
|
||||
...trackedEntries.map((e) => e.filePath),
|
||||
],
|
||||
30_000,
|
||||
);
|
||||
} catch (error: any) {
|
||||
logger.warn('[getGitWorkingTreePatches] bulk diff failed; per-file fallback', {
|
||||
cwd: dirPath,
|
||||
stderr: error?.stderr?.toString?.() ?? error?.stderr,
|
||||
});
|
||||
// Salvage any patches that did stream through before the failure —
|
||||
// the per-file fallback below only retries the stragglers.
|
||||
if (typeof error?.partialStdout === 'string') bulkDiff = error.partialStdout;
|
||||
// Walk the patch line-by-line counting `+`/`-` payload lines while
|
||||
// skipping the `+++ b/...` / `--- a/...` headers (they look like
|
||||
// additions/deletions but aren't). Cheap enough to do inline per file —
|
||||
// each patch is capped at MAX_PATCH_BYTES.
|
||||
const countAddDel = (patch: string): { additions: number; deletions: number } => {
|
||||
let additions = 0;
|
||||
let deletions = 0;
|
||||
for (const line of patch.split('\n')) {
|
||||
if (line.startsWith('+++') || line.startsWith('---')) continue;
|
||||
if (line.startsWith('+')) additions++;
|
||||
else if (line.startsWith('-')) deletions++;
|
||||
}
|
||||
for (const block of splitBulkDiff(bulkDiff)) {
|
||||
const entry = trackedByPath.get(block.path);
|
||||
if (!entry) continue;
|
||||
trackedPatches.set(entry.filePath, buildTrackedPatch(entry, block, MAX_PATCH_BYTES));
|
||||
}
|
||||
// Anything the bulk diff didn't cover (bulk crashed, race-with-write,
|
||||
// or git emitted no patch for a path status flagged dirty) gets a
|
||||
// per-file retry. Concurrency-capped to avoid the original fork storm.
|
||||
const stragglers = trackedEntries.filter((e) => !trackedPatches.has(e.filePath));
|
||||
if (stragglers.length > 0) {
|
||||
const recovered = await mapWithConcurrency(stragglers, 8, (entry) =>
|
||||
fetchTrackedPatchPerFile(dirPath, entry, MAX_PATCH_BYTES),
|
||||
);
|
||||
for (const patch of recovered) trackedPatches.set(patch.filePath, patch);
|
||||
}
|
||||
}
|
||||
return { additions, deletions };
|
||||
};
|
||||
|
||||
// Step 2b — read untracked files directly in Node. fs.readFile is bounded
|
||||
// by libuv's thread pool (4 by default) so unbounded Promise.all is fine.
|
||||
const untrackedEntries = entries.filter((e) => e.isUntracked);
|
||||
const untrackedPatches = await Promise.all(
|
||||
untrackedEntries.map((entry) => readUntrackedAsPatch(dirPath, entry, MAX_PATCH_BYTES)),
|
||||
// Step 2 — per-file diff in parallel. `--no-index` exits 1 when there's a
|
||||
// diff (which is the expected outcome for untracked files), so we have to
|
||||
// pull stdout off the rejected error rather than letting it throw.
|
||||
const patches = await Promise.all(
|
||||
entries.map(async ({ filePath, isUntracked, status }): Promise<GitWorkingTreePatch> => {
|
||||
const args = isUntracked
|
||||
? ['diff', '--no-color', '--no-index', '/dev/null', filePath]
|
||||
: ['diff', '--no-color', 'HEAD', '--', filePath];
|
||||
|
||||
let text: string;
|
||||
try {
|
||||
const { stdout } = await execFileAsync('git', args, {
|
||||
cwd: dirPath,
|
||||
encoding: 'utf8',
|
||||
maxBuffer: MAX_PATCH_BYTES * 4,
|
||||
timeout: 10_000,
|
||||
});
|
||||
text = stdout as string;
|
||||
} catch (error: any) {
|
||||
if (error?.stdout == null) {
|
||||
logger.debug('[getGitWorkingTreePatches] diff failed', {
|
||||
filePath,
|
||||
status,
|
||||
stderr: error?.stderr?.toString?.() ?? error?.stderr,
|
||||
});
|
||||
return {
|
||||
additions: 0,
|
||||
deletions: 0,
|
||||
filePath,
|
||||
isBinary: false,
|
||||
patch: '',
|
||||
status,
|
||||
truncated: false,
|
||||
};
|
||||
}
|
||||
text = error.stdout.toString();
|
||||
}
|
||||
|
||||
if (text.length > MAX_PATCH_BYTES) {
|
||||
return {
|
||||
additions: 0,
|
||||
deletions: 0,
|
||||
filePath,
|
||||
isBinary: false,
|
||||
patch: '',
|
||||
status,
|
||||
truncated: true,
|
||||
};
|
||||
}
|
||||
if (/^Binary files .* differ$/m.test(text)) {
|
||||
return {
|
||||
additions: 0,
|
||||
deletions: 0,
|
||||
filePath,
|
||||
isBinary: true,
|
||||
patch: '',
|
||||
status,
|
||||
truncated: false,
|
||||
};
|
||||
}
|
||||
const { additions, deletions } = countAddDel(text);
|
||||
return {
|
||||
additions,
|
||||
deletions,
|
||||
filePath,
|
||||
isBinary: false,
|
||||
patch: text,
|
||||
status,
|
||||
truncated: false,
|
||||
};
|
||||
}),
|
||||
);
|
||||
|
||||
// Step 3 — combine + sort to match the working-tree popover order.
|
||||
const order: Record<GitFileDiffStatus, number> = { added: 0, modified: 1, deleted: 2 };
|
||||
const allPatches: GitWorkingTreePatch[] = [...trackedPatches.values(), ...untrackedPatches];
|
||||
allPatches.sort((a, b) => order[a.status] - order[b.status]);
|
||||
|
||||
return { patches: allPatches };
|
||||
}
|
||||
|
||||
/**
|
||||
* Diff every changed file between the current HEAD and the remote default
|
||||
* branch (resolved via `refs/remotes/origin/HEAD` — typically `origin/main`
|
||||
* or `origin/canary`). Uses `<base>...HEAD` so the result is "what this
|
||||
* branch added since it forked", ignoring upstream-only commits.
|
||||
*
|
||||
* Best-effort `git fetch` first so the comparison reflects the latest
|
||||
* remote state; fetch failures (offline / no creds / no `origin`) are
|
||||
* swallowed and we fall back to whatever cached refs exist. Returns
|
||||
* `baseRef: undefined` + empty patches when no remote default is set —
|
||||
* the renderer surfaces a "noBaseRef" hint in that case.
|
||||
*
|
||||
* Patch parsing reuses the same bulk-split + size-cap path as the working
|
||||
* tree variant; status comes from each diff block's preamble (no `git
|
||||
* status` cross-reference needed since every block is from history).
|
||||
*/
|
||||
@IpcMethod()
|
||||
async getGitBranchDiff(payload: GetGitBranchDiffPayload): Promise<GitBranchDiffPatches> {
|
||||
const { path: dirPath, baseRef: baseRefOverride } = payload;
|
||||
const MAX_PATCH_BYTES = 256 * 1024;
|
||||
const execFileAsync = promisify(execFile);
|
||||
|
||||
// Step 1 — best-effort fetch so origin/<default> reflects remote HEAD.
|
||||
try {
|
||||
await execFileAsync('git', ['fetch', '--no-tags', '--quiet', 'origin'], {
|
||||
cwd: dirPath,
|
||||
timeout: 10_000,
|
||||
});
|
||||
} catch {
|
||||
// swallow — fall through to cached refs
|
||||
}
|
||||
|
||||
// Step 2 — pick the comparison base. When the caller passes an explicit
|
||||
// override (e.g. user picked a non-default branch in the UI) we trust it;
|
||||
// otherwise we resolve `refs/remotes/origin/HEAD`. The default may be
|
||||
// missing on repos cloned with --no-checkout or after a remote rename —
|
||||
// surface a "noBaseRef" empty state in that case so the user can run
|
||||
// `git remote set-head origin --auto` themselves.
|
||||
let baseRef: string | undefined = baseRefOverride;
|
||||
if (!baseRef) {
|
||||
try {
|
||||
const { stdout } = await execFileAsync(
|
||||
'git',
|
||||
['symbolic-ref', '--short', 'refs/remotes/origin/HEAD'],
|
||||
{ cwd: dirPath, timeout: 5000 },
|
||||
);
|
||||
baseRef = stdout.trim() || undefined;
|
||||
} catch {
|
||||
baseRef = undefined;
|
||||
}
|
||||
}
|
||||
|
||||
// headRef populated even when baseRef is missing so the UI can still
|
||||
// surface "fix/foo ← ?" instead of going completely blank.
|
||||
const headRef = (await this.getGitBranch(dirPath)).branch;
|
||||
|
||||
if (!baseRef) {
|
||||
return { headRef, patches: [] };
|
||||
}
|
||||
|
||||
// Step 3 — single bulk diff against the merge base. Three-dot semantics
|
||||
// (`base...HEAD`) ignore commits added to base after the branch forked,
|
||||
// matching what users expect from "compare branch" UI on GitHub. Stream
|
||||
// capture mirrors the working-tree path so multi-MB diffs land intact.
|
||||
let bulkDiff = '';
|
||||
try {
|
||||
bulkDiff = await runGitCaptureStream(
|
||||
dirPath,
|
||||
['-c', 'core.quotepath=off', 'diff', '--no-color', `${baseRef}...HEAD`],
|
||||
30_000,
|
||||
);
|
||||
} catch (error: any) {
|
||||
logger.warn('[getGitBranchDiff] diff failed', {
|
||||
baseRef,
|
||||
cwd: dirPath,
|
||||
stderr: error?.stderr?.toString?.() ?? error?.stderr,
|
||||
});
|
||||
if (typeof error?.partialStdout === 'string') bulkDiff = error.partialStdout;
|
||||
}
|
||||
|
||||
// Step 4 — split + classify per-file from the diff preamble alone.
|
||||
const patches: GitWorkingTreePatch[] = [];
|
||||
for (const block of splitBulkDiff(bulkDiff)) {
|
||||
const status = detectDiffBlockStatus(block.patch);
|
||||
patches.push(buildTrackedPatch({ filePath: block.path, status }, block, MAX_PATCH_BYTES));
|
||||
}
|
||||
|
||||
// Re-bucket so the UI sees added → modified → deleted (matches the
|
||||
// working-tree popover order).
|
||||
const order: Record<GitFileDiffStatus, number> = { added: 0, modified: 1, deleted: 2 };
|
||||
patches.sort((a, b) => order[a.status] - order[b.status]);
|
||||
|
||||
return { baseRef, headRef, patches };
|
||||
return { patches };
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -1107,70 +582,4 @@ export default class GitController extends ControllerModule {
|
||||
return { error: stderr || 'git push failed', success: false };
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Revert a single working-tree change. Mirrors what "Discard changes" does
|
||||
* in GitHub Desktop / VSCode SCM: restore the file to its HEAD state,
|
||||
* dropping any unstaged / staged edits — and physically delete the file
|
||||
* when it doesn't exist at HEAD (untracked or staged-add).
|
||||
*
|
||||
* Branch logic by HEAD presence:
|
||||
* - present at HEAD → `git checkout HEAD -- <file>` (covers modified,
|
||||
* deleted, staged-D — restores both index + worktree from HEAD)
|
||||
* - absent at HEAD → `git rm --cached` (unstage if staged-A; silent
|
||||
* no-op for untracked) + `fs.rm` to delete the file from disk
|
||||
*
|
||||
* filePath is the repo-relative path from `git status` output, the same
|
||||
* shape we hand to the renderer in `GitWorkingTreePatch.filePath`. We
|
||||
* reject absolute paths and `..` traversal so the renderer can't poke
|
||||
* outside the repo even if its payload were tampered with.
|
||||
*/
|
||||
@IpcMethod()
|
||||
async revertGitFile(payload: { filePath: string; path: string }): Promise<GitFileRevertResult> {
|
||||
const { path: dirPath, filePath } = payload;
|
||||
if (!filePath?.trim()) return { error: 'File path is required', success: false };
|
||||
if (path.isAbsolute(filePath) || filePath.split(/[/\\]/).includes('..')) {
|
||||
return { error: `Invalid file path: ${filePath}`, success: false };
|
||||
}
|
||||
|
||||
const execFileAsync = promisify(execFile);
|
||||
|
||||
// Probe HEAD via cat-file -e — exit 0 means the blob exists at HEAD.
|
||||
let existsAtHead: boolean;
|
||||
try {
|
||||
await execFileAsync('git', ['cat-file', '-e', `HEAD:${filePath}`], {
|
||||
cwd: dirPath,
|
||||
timeout: 5000,
|
||||
});
|
||||
existsAtHead = true;
|
||||
} catch {
|
||||
existsAtHead = false;
|
||||
}
|
||||
|
||||
try {
|
||||
if (existsAtHead) {
|
||||
await execFileAsync('git', ['checkout', 'HEAD', '--', filePath], {
|
||||
cwd: dirPath,
|
||||
timeout: 15_000,
|
||||
});
|
||||
} else {
|
||||
// Unstage if the file is in the index (staged-add). `git rm --cached`
|
||||
// exits non-zero on untracked paths, which is fine — swallow it.
|
||||
try {
|
||||
await execFileAsync('git', ['rm', '--cached', '--quiet', '--', filePath], {
|
||||
cwd: dirPath,
|
||||
timeout: 5000,
|
||||
});
|
||||
} catch {
|
||||
// not staged — fall through to the disk-delete
|
||||
}
|
||||
await rm(path.resolve(dirPath, filePath), { force: true, recursive: false });
|
||||
}
|
||||
return { success: true };
|
||||
} catch (error: any) {
|
||||
const stderr: string = (error?.stderr ?? error?.message ?? '').toString().trim();
|
||||
logger.debug('[revertGitFile] failed', { filePath, stderr });
|
||||
return { error: stderr || 'git revert failed', success: false };
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,12 +1,9 @@
|
||||
import type { ChildProcess } from 'node:child_process';
|
||||
import { spawn } from 'node:child_process';
|
||||
import { randomUUID } from 'node:crypto';
|
||||
import { unlinkSync } from 'node:fs';
|
||||
import { access, appendFile, mkdir, unlink, writeFile } from 'node:fs/promises';
|
||||
import os from 'node:os';
|
||||
import { createHash, randomUUID } from 'node:crypto';
|
||||
import { access, appendFile, mkdir, readFile, writeFile } from 'node:fs/promises';
|
||||
import path from 'node:path';
|
||||
import type { Readable, Writable } from 'node:stream';
|
||||
import { finished as streamFinished } from 'node:stream/promises';
|
||||
|
||||
import type { HeterogeneousAgentSessionError } from '@lobechat/electron-client-ipc';
|
||||
import {
|
||||
@@ -16,19 +13,14 @@ import {
|
||||
CODEX_CLI_INSTALL_DOCS_URL,
|
||||
HeterogeneousAgentSessionErrorCode,
|
||||
} from '@lobechat/electron-client-ipc';
|
||||
import type { AskUserBridge } from '@lobechat/heterogeneous-agents/askUser';
|
||||
import { AskUserMcpServer } from '@lobechat/heterogeneous-agents/askUser';
|
||||
import type { AgentContentBlock } from '@lobechat/heterogeneous-agents/spawn';
|
||||
import {
|
||||
AgentStreamPipeline,
|
||||
buildAgentInput,
|
||||
materializeImageToPath,
|
||||
normalizeImage,
|
||||
} from '@lobechat/heterogeneous-agents/spawn';
|
||||
import { app as electronApp, BrowserWindow } from 'electron';
|
||||
|
||||
import { getHeterogeneousAgentDriver } from '@/modules/heterogeneousAgent';
|
||||
import type { HeterogeneousAgentImageAttachment } from '@/modules/heterogeneousAgent/types';
|
||||
import { CodexFileChangeTracker } from '@/modules/heterogeneousAgent/codexFileChangeTracker';
|
||||
import type {
|
||||
HeterogeneousAgentImageAttachment,
|
||||
HeterogeneousAgentParsedOutput,
|
||||
} from '@/modules/heterogeneousAgent/types';
|
||||
import { buildProxyEnv } from '@/modules/networkProxy/envBuilder';
|
||||
import { detectHeterogeneousCliCommand } from '@/modules/toolDetectors';
|
||||
import { createLogger } from '@/utils/logger';
|
||||
@@ -60,6 +52,16 @@ const CODEX_RESUME_CWD_MISMATCH_PATTERNS = [
|
||||
/** Directory under appStoragePath for caching downloaded files */
|
||||
const FILE_CACHE_DIR = 'heteroAgent/files';
|
||||
const CLI_TRACE_DIR = '.heerogeneous-tracing';
|
||||
const IMAGE_EXTENSIONS_BY_MIME = {
|
||||
'image/gif': '.gif',
|
||||
'image/jpg': '.jpg',
|
||||
'image/jpeg': '.jpg',
|
||||
'image/pjpeg': '.jpg',
|
||||
'image/png': '.png',
|
||||
'image/webp': '.webp',
|
||||
'image/x-png': '.png',
|
||||
} as const satisfies Record<string, string>;
|
||||
const PNG_SIGNATURE = Buffer.from([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a]);
|
||||
const CODEX_STDERR_STATUS_LINE = 'Reading prompt from stdin...';
|
||||
const CODEX_WARN_LOG_PATTERN = /^\d{4}-\d{2}-\d{2}T\S+\s+WARN\s+/;
|
||||
const CODEX_LOG_PATTERN = /^\d{4}-\d{2}-\d{2}T\S+\s+(?:DEBUG|ERROR|INFO|TRACE|WARN)\s+/;
|
||||
@@ -89,12 +91,6 @@ interface StartSessionResult {
|
||||
interface SendPromptParams {
|
||||
/** Image attachments to include in the prompt (downloaded from url, cached by id) */
|
||||
imageList?: HeterogeneousAgentImageAttachment[];
|
||||
/**
|
||||
* Renderer-side operation id stamped onto every emitted `AgentStreamEvent`.
|
||||
* Required: producer-side conversion is the V3 contract — by the time events
|
||||
* reach the renderer they must already carry the operation they belong to.
|
||||
*/
|
||||
operationId: string;
|
||||
prompt: string;
|
||||
sessionId: string;
|
||||
}
|
||||
@@ -103,18 +99,6 @@ interface CancelSessionParams {
|
||||
sessionId: string;
|
||||
}
|
||||
|
||||
interface SubmitInterventionParams {
|
||||
cancelled?: boolean;
|
||||
/** When set, signals user-cancelled or timeout — the bridge resolves with isError. */
|
||||
cancelReason?: 'timeout' | 'user_cancelled';
|
||||
/** Operation id stamped on the request the renderer is responding to. */
|
||||
operationId: string;
|
||||
/** Structured user answer; ignored when `cancelled` is true. */
|
||||
result?: unknown;
|
||||
/** Correlation key carried on the original `agent_intervention_request`. */
|
||||
toolCallId: string;
|
||||
}
|
||||
|
||||
interface StopSessionParams {
|
||||
sessionId: string;
|
||||
}
|
||||
@@ -164,30 +148,12 @@ interface CliTraceSession {
|
||||
* prompt transport, resume semantics, and raw stream shape without turning
|
||||
* this controller into a giant `switch`.
|
||||
*
|
||||
* Lifecycle: startSession → sendPrompt → (heteroAgentEvent broadcasts) → stopSession
|
||||
* Lifecycle: startSession → sendPrompt → (heteroAgentRawLine broadcasts) → stopSession
|
||||
*/
|
||||
interface InterventionSlot {
|
||||
bridge: AskUserBridge;
|
||||
/** Resolves once bridge.events() iterator ends (after `cancelAll`). */
|
||||
pumpDone: Promise<void>;
|
||||
/** Path to the per-op temp `mcp.json` we wrote for `--mcp-config`. */
|
||||
tmpConfigPath: string;
|
||||
}
|
||||
|
||||
export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
static override readonly groupName = 'heterogeneousAgent';
|
||||
|
||||
private sessions = new Map<string, AgentSession>();
|
||||
/**
|
||||
* Per-operation AskUserQuestion bridge state. Keyed by `operationId` so the
|
||||
* `submitIntervention` IPC can route an answer to the right pending MCP
|
||||
* handler regardless of which `sessionId` it belongs to (one session can
|
||||
* fire many ops over its lifetime).
|
||||
*/
|
||||
private opIdToIntervention = new Map<string, InterventionSlot>();
|
||||
/** Lazy single MCP server, started on first claude-code prompt. */
|
||||
private askUserMcpServer?: AskUserMcpServer;
|
||||
private askUserMcpStartPromise?: Promise<AskUserMcpServer>;
|
||||
|
||||
private resolveSessionCommand(session: AgentSession): string {
|
||||
const resolvedCommand = session.command.trim();
|
||||
@@ -601,92 +567,6 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
}
|
||||
}
|
||||
|
||||
// ─── AskUserQuestion MCP server (LOBE-8725) ───
|
||||
|
||||
/**
|
||||
* Lazy single-instance MCP server for CC's AskUserQuestion replacement.
|
||||
* First claude-code prompt triggers `start()`; subsequent prompts reuse
|
||||
* the same listener. Concurrent first-callers de-dupe via the in-flight
|
||||
* promise so we don't bind two ports.
|
||||
*/
|
||||
private async ensureAskUserMcpServerStarted(): Promise<AskUserMcpServer> {
|
||||
if (this.askUserMcpServer) return this.askUserMcpServer;
|
||||
if (!this.askUserMcpStartPromise) {
|
||||
this.askUserMcpStartPromise = (async () => {
|
||||
const server = new AskUserMcpServer();
|
||||
await server.start();
|
||||
this.askUserMcpServer = server;
|
||||
logger.info('AskUserQuestion MCP server started:', server.url);
|
||||
return server;
|
||||
})().catch((err) => {
|
||||
// Reset so a later sendPrompt can retry; surface the error.
|
||||
this.askUserMcpStartPromise = undefined;
|
||||
logger.error('Failed to start AskUserQuestion MCP server:', err);
|
||||
throw err;
|
||||
});
|
||||
}
|
||||
return this.askUserMcpStartPromise;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a per-op AskUserQuestion bridge, write its temp `mcp.json`,
|
||||
* and start pumping the bridge's outbound events into the regular
|
||||
* `heteroAgentEvent` broadcast. Caller must invoke the returned cleanup
|
||||
* after the spawn finishes (success, error, or cancel) to remove the
|
||||
* temp file and tear down the bridge.
|
||||
*
|
||||
* Pump errors are logged but never thrown — they don't fail the spawn.
|
||||
*/
|
||||
private async setupInterventionForOp(
|
||||
operationId: string,
|
||||
sessionId: string,
|
||||
): Promise<{ cleanup: () => Promise<void>; tmpConfigPath: string }> {
|
||||
const server = await this.ensureAskUserMcpServerStarted();
|
||||
const bridge = server.registerOperation(operationId);
|
||||
const tmpConfigPath = path.join(os.tmpdir(), `lobe-cc-mcp-${operationId}.json`);
|
||||
|
||||
// `alwaysLoad: true` is the undocumented CC flag that promotes our
|
||||
// server's tool out of the deferred set so the model calls it directly
|
||||
// (no ToolSearch hop). See LOBE-8725 spike notes — falls back to the
|
||||
// 2-hop ToolSearch path if a future CC drops the flag, no breakage.
|
||||
const config = {
|
||||
mcpServers: {
|
||||
lobe_cc: {
|
||||
alwaysLoad: true,
|
||||
type: 'http' as const,
|
||||
url: server.urlForOperation(operationId),
|
||||
},
|
||||
},
|
||||
};
|
||||
await writeFile(tmpConfigPath, JSON.stringify(config), 'utf8');
|
||||
|
||||
// Pump bridge.events() into the `heteroAgentEvent` broadcast. The
|
||||
// iterator only ends after `cancelAll()`, so `pumpDone` resolves at
|
||||
// cleanup time and gates teardown.
|
||||
const pumpDone = (async () => {
|
||||
for await (const event of bridge.events()) {
|
||||
this.broadcast('heteroAgentEvent', { event, sessionId });
|
||||
}
|
||||
})().catch((err) => {
|
||||
logger.warn('AskUserQuestion bridge pump error:', err);
|
||||
});
|
||||
|
||||
this.opIdToIntervention.set(operationId, { bridge, pumpDone, tmpConfigPath });
|
||||
|
||||
const cleanup = async () => {
|
||||
// Unregistering on the server cancels all bridge pendings AND closes
|
||||
// the events iterator (cancelAll fires from within unregisterOperation).
|
||||
this.askUserMcpServer?.unregisterOperation(operationId);
|
||||
await pumpDone;
|
||||
this.opIdToIntervention.delete(operationId);
|
||||
await unlink(tmpConfigPath).catch(() => {
|
||||
/* file may already be gone if app crashed mid-prompt */
|
||||
});
|
||||
};
|
||||
|
||||
return { cleanup, tmpConfigPath };
|
||||
}
|
||||
|
||||
// ─── File cache ───
|
||||
|
||||
private get fileCacheDir(): string {
|
||||
@@ -694,56 +574,125 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert a desktop image attachment list into shared content blocks. Each
|
||||
* attachment's id is preserved as the cache key so repeated prompts hit the
|
||||
* same on-disk entries.
|
||||
* Derive a filesystem-safe cache key for attachments.
|
||||
*
|
||||
* Never use the raw image id as a path segment — upstream callers can persist
|
||||
* arbitrary ids and path.join would treat traversal sequences as real
|
||||
* directories. A stable hash preserves cache hits without trusting the id as a
|
||||
* filename.
|
||||
*/
|
||||
private toImageContentBlocks(
|
||||
imageList: HeterogeneousAgentImageAttachment[],
|
||||
): AgentContentBlock[] {
|
||||
return imageList.map((image) => ({
|
||||
source: { id: image.id, type: 'url', url: image.url },
|
||||
type: 'image',
|
||||
}));
|
||||
private getImageCacheKey(imageId: string): string {
|
||||
return createHash('sha256').update(imageId).digest('hex');
|
||||
}
|
||||
|
||||
/**
|
||||
* Build a Claude Code stream-json user message with text + base64 images.
|
||||
* Delegates to the shared `buildAgentInput`; the desktop wrapper exists only
|
||||
* to preserve the helper signature consumed by existing drivers.
|
||||
* Download an image by URL, with local disk cache keyed by id.
|
||||
*/
|
||||
private async buildStreamJsonInput(
|
||||
prompt: string,
|
||||
imageList: HeterogeneousAgentImageAttachment[] = [],
|
||||
): Promise<string> {
|
||||
const blocks: AgentContentBlock[] = [];
|
||||
if (prompt && prompt.length > 0) blocks.push({ text: prompt, type: 'text' });
|
||||
blocks.push(...this.toImageContentBlocks(imageList));
|
||||
private async resolveImage(
|
||||
image: HeterogeneousAgentImageAttachment,
|
||||
): Promise<{ buffer: Buffer; mimeType: string }> {
|
||||
const cacheDir = this.fileCacheDir;
|
||||
const cacheKey = this.getImageCacheKey(image.id);
|
||||
const metaPath = path.join(cacheDir, `${cacheKey}.meta`);
|
||||
const dataPath = path.join(cacheDir, cacheKey);
|
||||
|
||||
const plan = await buildAgentInput('claude-code', blocks, { cacheDir: this.fileCacheDir });
|
||||
return plan.stdin;
|
||||
// Check cache first
|
||||
try {
|
||||
const metaRaw = await readFile(metaPath, 'utf8');
|
||||
const meta = JSON.parse(metaRaw);
|
||||
const buffer = await readFile(dataPath);
|
||||
logger.debug('Image cache hit:', image.id);
|
||||
return { buffer, mimeType: meta.mimeType || 'image/png' };
|
||||
} catch {
|
||||
// Cache miss — download
|
||||
}
|
||||
|
||||
logger.info('Downloading image:', image.id);
|
||||
|
||||
const res = await fetch(image.url);
|
||||
if (!res.ok)
|
||||
throw new Error(`Failed to download image ${image.id}: ${res.status} ${res.statusText}`);
|
||||
|
||||
const arrayBuffer = await res.arrayBuffer();
|
||||
const buffer = Buffer.from(arrayBuffer);
|
||||
const mimeType = res.headers.get('content-type') || 'image/png';
|
||||
|
||||
// Write to cache
|
||||
await mkdir(cacheDir, { recursive: true });
|
||||
await writeFile(dataPath, buffer);
|
||||
await writeFile(metaPath, JSON.stringify({ id: image.id, mimeType }));
|
||||
logger.debug('Image cached:', image.id, `${buffer.length} bytes`);
|
||||
|
||||
return { buffer, mimeType };
|
||||
}
|
||||
|
||||
private normalizeMimeType(mimeType: string): string {
|
||||
return mimeType.split(';')[0]?.trim().toLowerCase() || '';
|
||||
}
|
||||
|
||||
private guessImageExtensionByBuffer(buffer: Buffer): string | undefined {
|
||||
if (buffer.subarray(0, PNG_SIGNATURE.length).equals(PNG_SIGNATURE)) return '.png';
|
||||
if (buffer[0] === 0xff && buffer[1] === 0xd8 && buffer[2] === 0xff) return '.jpg';
|
||||
|
||||
const gifSignature = buffer.subarray(0, 6).toString('ascii');
|
||||
if (gifSignature === 'GIF87a' || gifSignature === 'GIF89a') return '.gif';
|
||||
|
||||
if (
|
||||
buffer.subarray(0, 4).toString('ascii') === 'RIFF' &&
|
||||
buffer.subarray(8, 12).toString('ascii') === 'WEBP'
|
||||
) {
|
||||
return '.webp';
|
||||
}
|
||||
}
|
||||
|
||||
private guessImageExtension(
|
||||
mimeType: string,
|
||||
image: HeterogeneousAgentImageAttachment,
|
||||
buffer: Buffer,
|
||||
): string | undefined {
|
||||
const knownByMime = IMAGE_EXTENSIONS_BY_MIME[this.normalizeMimeType(mimeType)];
|
||||
if (knownByMime) return knownByMime;
|
||||
|
||||
try {
|
||||
const pathname = new URL(image.url).pathname;
|
||||
const ext = path.extname(pathname).toLowerCase();
|
||||
if (ext) return ext === '.jpeg' ? '.jpg' : ext;
|
||||
} catch {
|
||||
// Fall through to byte sniffing below.
|
||||
}
|
||||
|
||||
return this.guessImageExtensionByBuffer(buffer);
|
||||
}
|
||||
|
||||
/**
|
||||
* Materialize image attachments into stable filesystem paths for path-mode
|
||||
* agents (Codex `--image <file>`). Fails the prompt if any image cannot be
|
||||
* fetched / decoded — partially-attached prompts confuse the agent more
|
||||
* than they help.
|
||||
* Materialize an image attachment into a stable local file path so CLIs like
|
||||
* Codex can consume it through `--image <file>`.
|
||||
*/
|
||||
private async resolveCliImagePath(image: HeterogeneousAgentImageAttachment): Promise<string> {
|
||||
const { buffer, mimeType } = await this.resolveImage(image);
|
||||
const cacheKey = this.getImageCacheKey(image.id);
|
||||
const ext = this.guessImageExtension(mimeType, image, buffer);
|
||||
if (!ext) {
|
||||
throw new Error(`Unsupported image type for ${image.id}`);
|
||||
}
|
||||
|
||||
const filePath = path.join(this.fileCacheDir, `${cacheKey}${ext}`);
|
||||
|
||||
try {
|
||||
await access(filePath);
|
||||
} catch {
|
||||
await mkdir(this.fileCacheDir, { recursive: true });
|
||||
await writeFile(filePath, buffer);
|
||||
}
|
||||
|
||||
return filePath;
|
||||
}
|
||||
|
||||
private async resolveCliImagePaths(
|
||||
imageList: HeterogeneousAgentImageAttachment[] = [],
|
||||
): Promise<string[]> {
|
||||
if (imageList.length === 0) return [];
|
||||
|
||||
const cacheDir = this.fileCacheDir;
|
||||
const results = await Promise.allSettled(
|
||||
imageList.map(async (image) => {
|
||||
const normalized = await normalizeImage(
|
||||
{ id: image.id, type: 'url', url: image.url },
|
||||
{ cacheDir },
|
||||
);
|
||||
return materializeImageToPath(normalized, cacheDir);
|
||||
}),
|
||||
imageList.map((image) => this.resolveCliImagePath(image)),
|
||||
);
|
||||
|
||||
const imagePaths: string[] = [];
|
||||
@@ -769,6 +718,38 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
return imagePaths;
|
||||
}
|
||||
|
||||
/**
|
||||
* Build a stream-json user message with text + optional image content blocks.
|
||||
*/
|
||||
private async buildStreamJsonInput(
|
||||
prompt: string,
|
||||
imageList: HeterogeneousAgentImageAttachment[] = [],
|
||||
): Promise<string> {
|
||||
const content: any[] = [];
|
||||
if (prompt && prompt.length > 0) content.push({ text: prompt, type: 'text' });
|
||||
|
||||
for (const image of imageList) {
|
||||
try {
|
||||
const { buffer, mimeType } = await this.resolveImage(image);
|
||||
content.push({
|
||||
source: {
|
||||
data: buffer.toString('base64'),
|
||||
media_type: mimeType,
|
||||
type: 'base64',
|
||||
},
|
||||
type: 'image',
|
||||
});
|
||||
} catch (err) {
|
||||
logger.error(`Failed to resolve image ${image.id}:`, err);
|
||||
}
|
||||
}
|
||||
|
||||
return `${JSON.stringify({
|
||||
message: { content, role: 'user' },
|
||||
type: 'user',
|
||||
})}\n`;
|
||||
}
|
||||
|
||||
// ─── IPC methods ───
|
||||
|
||||
/**
|
||||
@@ -799,9 +780,8 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
/**
|
||||
* Send a prompt to an agent session.
|
||||
*
|
||||
* Spawns the CLI process with preset flags. Pipes each stdout chunk through
|
||||
* the shared `AgentStreamPipeline` (JSONL → adapter → toStreamEvent) and
|
||||
* broadcasts the resulting `AgentStreamEvent`s on `heteroAgentEvent`.
|
||||
* Spawns the CLI process with preset flags. Broadcasts each stdout line
|
||||
* as an `heteroAgentRawLine` event — Renderer side parses and adapts.
|
||||
*/
|
||||
@IpcMethod()
|
||||
async sendPrompt(params: SendPromptParams): Promise<void> {
|
||||
@@ -817,58 +797,32 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
throw new Error(preflightError.message);
|
||||
}
|
||||
|
||||
// Stand up the AskUserQuestion MCP bridge for claude-code prompts BEFORE
|
||||
// building the spawn plan so the driver can wire the temp config path
|
||||
// into `--mcp-config`. Codex / future agents skip this entirely.
|
||||
const intervention =
|
||||
session.agentType === 'claude-code'
|
||||
? await this.setupInterventionForOp(params.operationId, session.sessionId).catch((err) => {
|
||||
logger.warn('Failed to set up AskUserQuestion bridge — proceeding without it:', err);
|
||||
return undefined;
|
||||
})
|
||||
: undefined;
|
||||
|
||||
let spawnPlan;
|
||||
let traceSession;
|
||||
let cwd: string;
|
||||
try {
|
||||
const driver = getHeterogeneousAgentDriver(session.agentType);
|
||||
spawnPlan = await driver.buildSpawnPlan({
|
||||
args: session.args,
|
||||
helpers: {
|
||||
buildClaudeStreamJsonInput: (prompt, imageList) =>
|
||||
this.buildStreamJsonInput(prompt, imageList),
|
||||
resolveCliImagePaths: (imageList) => this.resolveCliImagePaths(imageList),
|
||||
},
|
||||
imageList: params.imageList ?? [],
|
||||
mcpConfigPath: intervention?.tmpConfigPath,
|
||||
prompt: params.prompt,
|
||||
resumeSessionId: session.agentSessionId,
|
||||
});
|
||||
|
||||
// Fall back to the user's Desktop so the process never inherits
|
||||
// the Electron parent's cwd (which is `/` when launched from Finder).
|
||||
cwd = session.cwd || electronApp.getPath('desktop');
|
||||
traceSession = await this.createCliTraceSession({
|
||||
cliArgs: spawnPlan.args,
|
||||
cwd,
|
||||
imageList: params.imageList ?? [],
|
||||
session,
|
||||
stdinPayload: spawnPlan.stdinPayload,
|
||||
});
|
||||
} catch (err) {
|
||||
// We never made it to spawn — the `proc.on('exit')` cleanup path
|
||||
// won't run, so tear the intervention bridge down right here.
|
||||
if (intervention) {
|
||||
await intervention.cleanup().catch((cleanupErr) => {
|
||||
logger.warn('AskUserQuestion cleanup error during pre-spawn failure:', cleanupErr);
|
||||
});
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
const driver = getHeterogeneousAgentDriver(session.agentType);
|
||||
const spawnPlan = await driver.buildSpawnPlan({
|
||||
args: session.args,
|
||||
helpers: {
|
||||
buildClaudeStreamJsonInput: (prompt, imageList) =>
|
||||
this.buildStreamJsonInput(prompt, imageList),
|
||||
resolveCliImagePaths: (imageList) => this.resolveCliImagePaths(imageList),
|
||||
},
|
||||
imageList: params.imageList ?? [],
|
||||
prompt: params.prompt,
|
||||
resumeSessionId: session.agentSessionId,
|
||||
});
|
||||
const useStdin = spawnPlan.stdinPayload !== undefined;
|
||||
const cliArgs = spawnPlan.args;
|
||||
|
||||
// Fall back to the user's Desktop so the process never inherits
|
||||
// the Electron parent's cwd (which is `/` when launched from Finder).
|
||||
const cwd = session.cwd || electronApp.getPath('desktop');
|
||||
const traceSession = await this.createCliTraceSession({
|
||||
cliArgs,
|
||||
cwd,
|
||||
imageList: params.imageList ?? [],
|
||||
session,
|
||||
stdinPayload: spawnPlan.stdinPayload,
|
||||
});
|
||||
|
||||
return new Promise<void>((resolve, reject) => {
|
||||
logger.info('Spawning agent:', session.command, cliArgs.join(' '), `(cwd: ${cwd})`);
|
||||
|
||||
@@ -899,49 +853,42 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
}
|
||||
|
||||
session.process = proc;
|
||||
|
||||
// Producer-side conversion (V3 contract): JSONL framing + adapter +
|
||||
// toStreamEvent all run inside the shared pipeline, so renderer + future
|
||||
// server `heteroIngest` see the same `AgentStreamEvent` wire shape with
|
||||
// no per-consumer adapter. The pipeline auto-wires the Codex
|
||||
// file-change line-stat tracker when `agentType === 'codex'`, so this
|
||||
// controller stays agent-agnostic.
|
||||
const pipeline = new AgentStreamPipeline({
|
||||
agentType: session.agentType,
|
||||
operationId: params.operationId,
|
||||
});
|
||||
const streamProcessor = driver.createStreamProcessor();
|
||||
const codexFileChangeTracker =
|
||||
session.agentType === 'codex' ? new CodexFileChangeTracker() : undefined;
|
||||
let stdoutBroadcastQueue: Promise<void> = Promise.resolve();
|
||||
|
||||
const broadcastPipelineBatch = (produce: () => ReturnType<AgentStreamPipeline['push']>) => {
|
||||
const broadcastParsedOutputs = (parsedOutputs: HeterogeneousAgentParsedOutput[]) => {
|
||||
stdoutBroadcastQueue = stdoutBroadcastQueue
|
||||
.then(async () => {
|
||||
const events = await produce();
|
||||
// Adapter-extracted CC/Codex session id powers `--resume` on the
|
||||
// next prompt; surface it through the existing `getSessionInfo`
|
||||
// IPC by mirroring the freshest value onto the session record.
|
||||
if (pipeline.sessionId && pipeline.sessionId !== session.agentSessionId) {
|
||||
session.agentSessionId = pipeline.sessionId;
|
||||
}
|
||||
for (const event of events) {
|
||||
this.broadcast('heteroAgentEvent', {
|
||||
event,
|
||||
for (const parsedOutput of parsedOutputs) {
|
||||
if (parsedOutput.agentSessionId) {
|
||||
session.agentSessionId = parsedOutput.agentSessionId;
|
||||
}
|
||||
|
||||
const line = codexFileChangeTracker
|
||||
? await codexFileChangeTracker.track(parsedOutput.payload)
|
||||
: parsedOutput.payload;
|
||||
|
||||
this.broadcast('heteroAgentRawLine', {
|
||||
line,
|
||||
sessionId: session.sessionId,
|
||||
});
|
||||
}
|
||||
})
|
||||
.catch((error) => {
|
||||
logger.error('Failed to broadcast agent stream batch:', error);
|
||||
logger.error('Failed to broadcast parsed agent output:', error);
|
||||
});
|
||||
};
|
||||
|
||||
// Stream stdout events through the producer pipeline.
|
||||
// Stream stdout events as raw provider payloads to Renderer.
|
||||
const stdout = proc.stdout as Readable;
|
||||
stdout.on('data', (chunk: Buffer) => {
|
||||
void this.appendCliTraceFile(traceSession, 'stdout.jsonl', chunk);
|
||||
broadcastPipelineBatch(() => pipeline.push(chunk));
|
||||
broadcastParsedOutputs(streamProcessor.push(chunk));
|
||||
});
|
||||
stdout.on('end', () => {
|
||||
broadcastPipelineBatch(() => pipeline.flush());
|
||||
broadcastParsedOutputs(streamProcessor.flush());
|
||||
});
|
||||
|
||||
// Capture stderr
|
||||
@@ -968,68 +915,44 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
});
|
||||
|
||||
proc.on('exit', (code, signal) => {
|
||||
// Node may emit `'exit'` BEFORE stdio finishes draining (documented:
|
||||
// child_process docs note "stdio streams might still be open" at exit
|
||||
// time). Wait for stdout to fully end/close so the `stdout.on('end')`
|
||||
// handler has scheduled `pipeline.flush()` onto `stdoutBroadcastQueue`,
|
||||
// THEN wait for the queue itself to settle. Without this two-step
|
||||
// gate, trailing flushed events (final synthesized tool_end /
|
||||
// tool_result) would race against — and lose to — the
|
||||
// `heteroAgentSessionComplete` broadcast, leaving renderer-side
|
||||
// persistence to finalize on incomplete state.
|
||||
const stdoutDrained = streamFinished(stdout, { writable: false }).catch(() => {
|
||||
/* end / close / error are all "done"; we still want to settle. */
|
||||
});
|
||||
|
||||
void stdoutDrained
|
||||
.then(() => stdoutBroadcastQueue)
|
||||
.finally(async () => {
|
||||
// Tear down the AskUserQuestion bridge / temp `mcp.json` for this
|
||||
// op. Pending MCP handlers get a `session_ended` cancellation so
|
||||
// they return cleanly even if CC was killed mid-tool-call.
|
||||
if (intervention) {
|
||||
await intervention.cleanup().catch((err) => {
|
||||
logger.warn('AskUserQuestion cleanup error:', err);
|
||||
});
|
||||
}
|
||||
|
||||
void this.writeCliTraceJson(traceSession, 'exit.json', {
|
||||
code,
|
||||
finishedAt: new Date().toISOString(),
|
||||
signal,
|
||||
});
|
||||
await this.flushCliTrace(traceSession);
|
||||
|
||||
logger.info('Agent process exited:', { code, sessionId: session.sessionId, signal });
|
||||
session.process = undefined;
|
||||
|
||||
// If *we* killed it (cancel / stop / before-quit), treat the non-zero
|
||||
// exit as a clean shutdown — surfacing it as an error would make a
|
||||
// user-initiated cancel look like an agent failure, and an Electron
|
||||
// shutdown affecting OTHER running CC sessions would pollute their
|
||||
// topics with a misleading "Agent exited with code 143" message.
|
||||
if (session.cancelledByUs) {
|
||||
this.broadcast('heteroAgentSessionComplete', { sessionId: session.sessionId });
|
||||
resolve();
|
||||
return;
|
||||
}
|
||||
|
||||
if (code === 0) {
|
||||
this.broadcast('heteroAgentSessionComplete', { sessionId: session.sessionId });
|
||||
resolve();
|
||||
} else {
|
||||
const stderrOutput = stderrChunks.join('').trim();
|
||||
const errorMsg = this.getExitErrorMessage(code, session, stderrOutput);
|
||||
const sessionError = this.getSessionErrorPayload(errorMsg, session);
|
||||
this.broadcast('heteroAgentSessionError', {
|
||||
error: sessionError,
|
||||
sessionId: session.sessionId,
|
||||
});
|
||||
reject(
|
||||
new Error(typeof sessionError === 'string' ? sessionError : sessionError.message),
|
||||
);
|
||||
}
|
||||
void stdoutBroadcastQueue.finally(async () => {
|
||||
void this.writeCliTraceJson(traceSession, 'exit.json', {
|
||||
code,
|
||||
finishedAt: new Date().toISOString(),
|
||||
signal,
|
||||
});
|
||||
await this.flushCliTrace(traceSession);
|
||||
|
||||
logger.info('Agent process exited:', { code, sessionId: session.sessionId, signal });
|
||||
session.process = undefined;
|
||||
|
||||
// If *we* killed it (cancel / stop / before-quit), treat the non-zero
|
||||
// exit as a clean shutdown — surfacing it as an error would make a
|
||||
// user-initiated cancel look like an agent failure, and an Electron
|
||||
// shutdown affecting OTHER running CC sessions would pollute their
|
||||
// topics with a misleading "Agent exited with code 143" message.
|
||||
if (session.cancelledByUs) {
|
||||
this.broadcast('heteroAgentSessionComplete', { sessionId: session.sessionId });
|
||||
resolve();
|
||||
return;
|
||||
}
|
||||
|
||||
if (code === 0) {
|
||||
this.broadcast('heteroAgentSessionComplete', { sessionId: session.sessionId });
|
||||
resolve();
|
||||
} else {
|
||||
const stderrOutput = stderrChunks.join('').trim();
|
||||
const errorMsg = this.getExitErrorMessage(code, session, stderrOutput);
|
||||
const sessionError = this.getSessionErrorPayload(errorMsg, session);
|
||||
this.broadcast('heteroAgentSessionError', {
|
||||
error: sessionError,
|
||||
sessionId: session.sessionId,
|
||||
});
|
||||
reject(
|
||||
new Error(typeof sessionError === 'string' ? sessionError : sessionError.message),
|
||||
);
|
||||
}
|
||||
});
|
||||
});
|
||||
});
|
||||
}
|
||||
@@ -1127,54 +1050,10 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
}
|
||||
|
||||
/**
|
||||
* Renderer → main: deliver the user's answer to a pending CC AskUserQuestion
|
||||
* (or signal cancellation). The matching bridge resolves its blocked
|
||||
* `pending()` Promise, the local MCP handler returns to CC, and CC's
|
||||
* `tool_result` flows back through the normal stream pipeline.
|
||||
*
|
||||
* Idempotent — late submissions for already-resolved tool calls are no-ops.
|
||||
* No-op when called for an unknown opId; the bridge may have been cleaned
|
||||
* up already (op finished / cancelled).
|
||||
*/
|
||||
@IpcMethod()
|
||||
async submitIntervention(params: SubmitInterventionParams): Promise<void> {
|
||||
const slot = this.opIdToIntervention.get(params.operationId);
|
||||
if (!slot) {
|
||||
logger.warn('submitIntervention: no active intervention for operationId', params.operationId);
|
||||
return;
|
||||
}
|
||||
slot.bridge.resolve(params.toolCallId, {
|
||||
cancelReason: params.cancelled ? (params.cancelReason ?? 'user_cancelled') : undefined,
|
||||
cancelled: params.cancelled,
|
||||
result: params.result,
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Synchronously unlink every pending intervention's temp `mcp.json`. The
|
||||
* async exit-handler cleanup loses to Electron's main-process teardown
|
||||
* often enough that we'd leak `lobe-cc-mcp-<opId>.json` files into
|
||||
* `os.tmpdir()` on real shutdowns; sync unlink here is the only reliable
|
||||
* guarantee. Safe to call multiple times.
|
||||
*/
|
||||
private unlinkPendingInterventionConfigsSync = (): void => {
|
||||
for (const [, intervention] of this.opIdToIntervention) {
|
||||
try {
|
||||
unlinkSync(intervention.tmpConfigPath);
|
||||
} catch {
|
||||
/* file may already be gone — fine */
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
/**
|
||||
* Cleanup on app quit. `before-quit` covers the user-driven Cmd+Q /
|
||||
* `app.quit()` path; SIGTERM / SIGINT cover external kills (test
|
||||
* harnesses, OS shutdown) where Electron's lifecycle events never fire.
|
||||
* Cleanup on app quit.
|
||||
*/
|
||||
afterAppReady() {
|
||||
electronApp.on('before-quit', () => {
|
||||
this.unlinkPendingInterventionConfigsSync();
|
||||
for (const [, session] of this.sessions) {
|
||||
if (session.process && !session.process.killed) {
|
||||
session.cancelledByUs = true;
|
||||
@@ -1182,28 +1061,6 @@ export default class HeterogeneousAgentCtr extends ControllerModule {
|
||||
}
|
||||
}
|
||||
this.sessions.clear();
|
||||
// The exit handlers will tear each per-op intervention down, but if
|
||||
// CC's stdio close races shutdown we'd leave the MCP server bound to
|
||||
// a port. Stopping it here cancels every still-pending bridge with
|
||||
// `session_ended` and closes the listener.
|
||||
void this.askUserMcpServer?.stop().catch((err) => {
|
||||
logger.warn('AskUserQuestion MCP server stop error:', err);
|
||||
});
|
||||
});
|
||||
|
||||
const onSignal = (signal: NodeJS.Signals) => {
|
||||
this.unlinkPendingInterventionConfigsSync();
|
||||
// Defer to Electron's normal quit flow so the rest of the app gets a
|
||||
// chance to tear down. The `before-quit` handler above is idempotent.
|
||||
try {
|
||||
electronApp.quit();
|
||||
} catch {
|
||||
/* during late shutdown app.quit may throw — fine */
|
||||
}
|
||||
// Last-resort exit if Electron is wedged and won't quit on its own.
|
||||
setTimeout(() => process.exit(signal === 'SIGINT' ? 130 : 143), 1000).unref();
|
||||
};
|
||||
process.on('SIGTERM', onSignal);
|
||||
process.on('SIGINT', onSignal);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -38,7 +38,6 @@ import {
|
||||
} from '@lobechat/electron-client-ipc';
|
||||
import {
|
||||
editLocalFile,
|
||||
expandTilde,
|
||||
listLocalFiles,
|
||||
moveLocalFiles,
|
||||
readLocalFile,
|
||||
@@ -575,7 +574,7 @@ export default class LocalFileCtr extends ControllerModule {
|
||||
*/
|
||||
@IpcMethod()
|
||||
async handleLocalFilesSearch(params: LocalSearchFilesParams): Promise<FileResult[]> {
|
||||
const effectiveDirectory = expandTilde(params.directory ?? params.scope);
|
||||
const effectiveDirectory = params.directory ?? params.scope;
|
||||
|
||||
logger.debug('Received file search request:', {
|
||||
directory: params.directory,
|
||||
|
||||
@@ -19,26 +19,6 @@ export default class TrayMenuCtr extends ControllerModule {
|
||||
mainWindow.toggleVisible();
|
||||
}
|
||||
|
||||
/**
|
||||
* Get whether the application tray is visible.
|
||||
*/
|
||||
@IpcMethod()
|
||||
getAppTrayVisible(): boolean {
|
||||
return this.app.storeManager.get('appTrayVisible', true);
|
||||
}
|
||||
|
||||
/**
|
||||
* Persist and apply application tray visibility.
|
||||
*/
|
||||
@IpcMethod()
|
||||
setAppTrayVisible(visible: boolean) {
|
||||
logger.debug(`Set app tray visibility: ${visible}`);
|
||||
this.app.storeManager.set('appTrayVisible', visible);
|
||||
this.app.trayManager.setAppTrayVisible(visible);
|
||||
|
||||
return { success: true };
|
||||
}
|
||||
|
||||
/**
|
||||
* Show tray balloon notification
|
||||
* @param options Balloon options
|
||||
|
||||
@@ -433,23 +433,18 @@ describe('GatewayConnectionCtr', () => {
|
||||
}
|
||||
|
||||
it.each([
|
||||
['readFile', 'readFile', mockLocalFileCtr],
|
||||
['listFiles', 'listLocalFiles', mockLocalFileCtr],
|
||||
['moveFiles', 'handleMoveFiles', mockLocalFileCtr],
|
||||
['searchFiles', 'handleLocalFilesSearch', mockLocalFileCtr],
|
||||
['writeFile', 'handleWriteFile', mockLocalFileCtr],
|
||||
['editFile', 'handleEditFile', mockLocalFileCtr],
|
||||
['globFiles', 'handleGlobFiles', mockLocalFileCtr],
|
||||
['readLocalFile', 'readFile', mockLocalFileCtr],
|
||||
['listLocalFiles', 'listLocalFiles', mockLocalFileCtr],
|
||||
['moveLocalFiles', 'handleMoveFiles', mockLocalFileCtr],
|
||||
['renameLocalFile', 'handleRenameFile', mockLocalFileCtr],
|
||||
['searchLocalFiles', 'handleLocalFilesSearch', mockLocalFileCtr],
|
||||
['writeLocalFile', 'handleWriteFile', mockLocalFileCtr],
|
||||
['editLocalFile', 'handleEditFile', mockLocalFileCtr],
|
||||
['globLocalFiles', 'handleGlobFiles', mockLocalFileCtr],
|
||||
['grepContent', 'handleGrepContent', mockLocalFileCtr],
|
||||
['runCommand', 'handleRunCommand', mockShellCommandCtr],
|
||||
['getCommandOutput', 'handleGetCommandOutput', mockShellCommandCtr],
|
||||
['killCommand', 'handleKillCommand', mockShellCommandCtr],
|
||||
// Legacy aliases — older Gateway versions may still send the long form.
|
||||
// `renameLocalFile` is kept even though the new surface drops rename.
|
||||
['readLocalFile', 'readFile', mockLocalFileCtr],
|
||||
['listLocalFiles', 'listLocalFiles', mockLocalFileCtr],
|
||||
['writeLocalFile', 'handleWriteFile', mockLocalFileCtr],
|
||||
['renameLocalFile', 'handleRenameFile', mockLocalFileCtr],
|
||||
] as const)('should route %s to %s', async (apiName, methodName, controller) => {
|
||||
const client = await connectAndOpen();
|
||||
const args = { test: 'arg' };
|
||||
@@ -475,7 +470,7 @@ describe('GatewayConnectionCtr', () => {
|
||||
});
|
||||
const client = await connectAndOpen();
|
||||
|
||||
client.simulateToolCallRequest('readFile', { path: '/a.txt' }, 'req-42');
|
||||
client.simulateToolCallRequest('readLocalFile', { path: '/a.txt' }, 'req-42');
|
||||
await vi.advanceTimersByTimeAsync(0);
|
||||
|
||||
expect(client.sendToolCallResponse).toHaveBeenCalledWith({
|
||||
@@ -502,7 +497,7 @@ describe('GatewayConnectionCtr', () => {
|
||||
vi.mocked(mockLocalFileCtr.readFile).mockRejectedValueOnce(new Error('File not found'));
|
||||
const client = await connectAndOpen();
|
||||
|
||||
client.simulateToolCallRequest('readFile', { path: '/missing' }, 'req-err');
|
||||
client.simulateToolCallRequest('readLocalFile', { path: '/missing' }, 'req-err');
|
||||
await vi.advanceTimersByTimeAsync(0);
|
||||
|
||||
expect(client.sendToolCallResponse).toHaveBeenCalledWith({
|
||||
|
||||
@@ -1,81 +0,0 @@
|
||||
import { describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import { dequoteGitPath, quoteGitPath } from '../GitCtr';
|
||||
|
||||
vi.mock('@/utils/logger', () => ({
|
||||
createLogger: () => ({
|
||||
debug: vi.fn(),
|
||||
info: vi.fn(),
|
||||
warn: vi.fn(),
|
||||
error: vi.fn(),
|
||||
}),
|
||||
}));
|
||||
|
||||
describe('quoteGitPath', () => {
|
||||
it('leaves plain ASCII paths unquoted (including spaces)', () => {
|
||||
expect(quoteGitPath('a/', 'src/foo.ts')).toBe('a/src/foo.ts');
|
||||
expect(quoteGitPath('b/', 'src/foo bar.ts')).toBe('b/src/foo bar.ts');
|
||||
expect(quoteGitPath('a/', 'with-dash_and.underscore')).toBe('a/with-dash_and.underscore');
|
||||
});
|
||||
|
||||
it('C-style escapes TAB / LF / CR / quote / backslash', () => {
|
||||
expect(quoteGitPath('b/', 'with\ttab.txt')).toBe('"b/with\\ttab.txt"');
|
||||
expect(quoteGitPath('b/', 'with\nlf.txt')).toBe('"b/with\\nlf.txt"');
|
||||
expect(quoteGitPath('b/', 'with\rcr.txt')).toBe('"b/with\\rcr.txt"');
|
||||
expect(quoteGitPath('b/', 'with"quote.txt')).toBe('"b/with\\"quote.txt"');
|
||||
expect(quoteGitPath('b/', 'with\\backslash.txt')).toBe('"b/with\\\\backslash.txt"');
|
||||
});
|
||||
|
||||
it('octal-escapes other control bytes (NUL, 0x1F, DEL)', () => {
|
||||
expect(quoteGitPath('a/', 'nul\x00here')).toBe('"a/nul\\000here"');
|
||||
expect(quoteGitPath('a/', 'unit\x1Fsep')).toBe('"a/unit\\037sep"');
|
||||
expect(quoteGitPath('a/', 'del\x7Fchar')).toBe('"a/del\\177char"');
|
||||
});
|
||||
|
||||
it('puts the prefix inside the quotes', () => {
|
||||
// Real git output for `git diff` of a tab-containing file:
|
||||
// diff --git "a/with\there" "b/with\there"
|
||||
expect(quoteGitPath('a/', 'with\there')).toBe('"a/with\\there"');
|
||||
expect(quoteGitPath('b/', 'with\there')).toBe('"b/with\\there"');
|
||||
});
|
||||
|
||||
it('round-trips through dequoteGitPath for problem characters', () => {
|
||||
const cases = [
|
||||
'with\ttab.txt',
|
||||
'with\nlf.txt',
|
||||
'with\rcr.txt',
|
||||
'with"quote.txt',
|
||||
'with\\backslash.txt',
|
||||
'nul\x00inside',
|
||||
'mix\t"of\\everything\n',
|
||||
];
|
||||
for (const original of cases) {
|
||||
const quoted = quoteGitPath('b/', original);
|
||||
// Strip the surrounding quotes + b/ prefix, then de-escape.
|
||||
expect(quoted.startsWith('"b/')).toBe(true);
|
||||
expect(quoted.endsWith('"')).toBe(true);
|
||||
const stripped = quoted.slice(1, -1).slice('b/'.length);
|
||||
expect(dequoteGitPath(stripped)).toBe(original);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('dequoteGitPath', () => {
|
||||
it('decodes named C-style escapes', () => {
|
||||
expect(dequoteGitPath('with\\ttab')).toBe('with\ttab');
|
||||
expect(dequoteGitPath('with\\nlf')).toBe('with\nlf');
|
||||
expect(dequoteGitPath('with\\rcr')).toBe('with\rcr');
|
||||
expect(dequoteGitPath('with\\"quote')).toBe('with"quote');
|
||||
expect(dequoteGitPath('with\\\\bs')).toBe('with\\bs');
|
||||
});
|
||||
|
||||
it('decodes 3-digit octal escapes', () => {
|
||||
expect(dequoteGitPath('nul\\000here')).toBe('nul\x00here');
|
||||
expect(dequoteGitPath('unit\\037sep')).toBe('unit\x1Fsep');
|
||||
expect(dequoteGitPath('del\\177char')).toBe('del\x7Fchar');
|
||||
});
|
||||
|
||||
it('leaves unescaped chars alone', () => {
|
||||
expect(dequoteGitPath('plain ascii here')).toBe('plain ascii here');
|
||||
});
|
||||
});
|
||||
@@ -11,12 +11,8 @@ import HeterogeneousAgentCtr from '../HeterogeneousAgentCtr';
|
||||
|
||||
const FAKE_DESKTOP_PATH = '/Users/fake/Desktop';
|
||||
|
||||
const { mockGetAllWindows } = vi.hoisted(() => ({
|
||||
mockGetAllWindows: vi.fn<() => any[]>(() => []),
|
||||
}));
|
||||
|
||||
vi.mock('electron', () => ({
|
||||
BrowserWindow: { getAllWindows: () => mockGetAllWindows() },
|
||||
BrowserWindow: { getAllWindows: () => [] },
|
||||
app: {
|
||||
getPath: vi.fn((name: string) => (name === 'desktop' ? FAKE_DESKTOP_PATH : `/fake/${name}`)),
|
||||
isPackaged: false,
|
||||
@@ -118,24 +114,13 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
await rm(appStoragePath, { force: true, recursive: true });
|
||||
});
|
||||
|
||||
describe('image cache (delegates to shared `normalizeImage`)', () => {
|
||||
// Image fetch + cache moved to `@lobechat/heterogeneous-agents/spawn`'s
|
||||
// `normalizeImage`. The desktop controller passes its own cacheDir so the
|
||||
// path-traversal invariant — id segments like `../../foo` MUST be hashed,
|
||||
// never used as path segments — is enforced by the shared helper. Verify
|
||||
// that invariant against the same cacheDir the controller would use.
|
||||
const fixtureCacheDir = (storage: string) => path.join(storage, 'heteroAgent/files');
|
||||
const importNormalize = async () => {
|
||||
const { mkdir } = await import('node:fs/promises');
|
||||
const mod = await import('@lobechat/heterogeneous-agents/spawn');
|
||||
return { mkdir, normalizeImage: mod.normalizeImage };
|
||||
};
|
||||
|
||||
describe('resolveImage', () => {
|
||||
it('stores traversal-looking ids inside the cache root via a stable hash key', async () => {
|
||||
const { mkdir, normalizeImage } = await importNormalize();
|
||||
const cacheDir = fixtureCacheDir(appStoragePath);
|
||||
await mkdir(cacheDir, { recursive: true });
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
const cacheDir = path.join(appStoragePath, 'heteroAgent/files');
|
||||
const escapedTargetName = `${path.basename(appStoragePath)}-outside-storage`;
|
||||
const escapePath = path.join(cacheDir, `../../../${escapedTargetName}`);
|
||||
|
||||
@@ -145,14 +130,10 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
// best-effort cleanup
|
||||
}
|
||||
|
||||
await normalizeImage(
|
||||
{
|
||||
id: `../../../${escapedTargetName}`,
|
||||
type: 'url',
|
||||
url: 'data:text/plain;base64,T1VUU0lERQ==',
|
||||
},
|
||||
{ cacheDir, fetcher: (async () => new Response('OUTSIDE', { status: 200 })) as any },
|
||||
);
|
||||
await (ctr as any).resolveImage({
|
||||
id: `../../../${escapedTargetName}`,
|
||||
url: 'data:text/plain;base64,T1VUU0lERQ==',
|
||||
});
|
||||
|
||||
const cacheEntries = await readdir(cacheDir);
|
||||
|
||||
@@ -168,10 +149,11 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
});
|
||||
|
||||
it('does not trust pre-seeded out-of-root traversal cache files as cache hits', async () => {
|
||||
const { mkdir, normalizeImage } = await importNormalize();
|
||||
const cacheDir = fixtureCacheDir(appStoragePath);
|
||||
await mkdir(cacheDir, { recursive: true });
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
const cacheDir = path.join(appStoragePath, 'heteroAgent/files');
|
||||
const traversalId = '../../preexisting-secret';
|
||||
const outOfRootDataPath = path.join(cacheDir, traversalId);
|
||||
const outOfRootMetaPath = path.join(cacheDir, `${traversalId}.meta`);
|
||||
@@ -182,20 +164,13 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
JSON.stringify({ id: traversalId, mimeType: 'text/plain' }),
|
||||
);
|
||||
|
||||
const result = await normalizeImage(
|
||||
{ id: traversalId, type: 'url', url: 'data:text/plain;base64,SUdOT1JFRA==' },
|
||||
{
|
||||
cacheDir,
|
||||
fetcher: (async () =>
|
||||
new Response('IGNORED', {
|
||||
headers: { 'content-type': 'text/plain' },
|
||||
status: 200,
|
||||
})) as any,
|
||||
},
|
||||
);
|
||||
const result = await (ctr as any).resolveImage({
|
||||
id: traversalId,
|
||||
url: 'data:text/plain;base64,SUdOT1JFRA==',
|
||||
});
|
||||
|
||||
expect(Buffer.from(result.buffer).toString('utf8')).toBe('IGNORED');
|
||||
expect(result.mediaType).toBe('text/plain');
|
||||
expect(result.mimeType).toBe('text/plain');
|
||||
await expect(readFile(outOfRootDataPath, 'utf8')).resolves.toBe('SECRET');
|
||||
});
|
||||
});
|
||||
@@ -224,7 +199,7 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
command: 'claude',
|
||||
...sessionOverrides,
|
||||
});
|
||||
await ctr.sendPrompt({ operationId: 'op-test', prompt, sessionId, ...sendPromptOverrides });
|
||||
await ctr.sendPrompt({ prompt, sessionId, ...sendPromptOverrides });
|
||||
|
||||
const { args: cliArgs, command, options } = spawnCalls[0];
|
||||
return { cliArgs, command, ctr, options, sessionId, writes };
|
||||
@@ -339,7 +314,7 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
command: 'codex',
|
||||
...sessionOverrides,
|
||||
});
|
||||
await ctr.sendPrompt({ operationId: 'op-test', prompt, sessionId, ...sendPromptOverrides });
|
||||
await ctr.sendPrompt({ prompt, sessionId, ...sendPromptOverrides });
|
||||
|
||||
const { args: cliArgs, command, options } = spawnCalls[0];
|
||||
return { cliArgs, command, ctr, options, sessionId, writes };
|
||||
@@ -357,9 +332,9 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
command: 'codex',
|
||||
});
|
||||
|
||||
await expect(
|
||||
ctr.sendPrompt({ operationId: 'op-test', prompt: 'hello', sessionId }),
|
||||
).rejects.toThrow('Codex CLI was not found');
|
||||
await expect(ctr.sendPrompt({ prompt: 'hello', sessionId })).rejects.toThrow(
|
||||
'Codex CLI was not found',
|
||||
);
|
||||
|
||||
expect(detect).toHaveBeenCalledWith('codex', true);
|
||||
expect(spawnCalls).toHaveLength(0);
|
||||
@@ -377,9 +352,9 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
command: 'claude',
|
||||
});
|
||||
|
||||
await expect(
|
||||
ctr.sendPrompt({ operationId: 'op-test', prompt: 'hello', sessionId }),
|
||||
).rejects.toThrow('Claude Code CLI was not found');
|
||||
await expect(ctr.sendPrompt({ prompt: 'hello', sessionId })).rejects.toThrow(
|
||||
'Claude Code CLI was not found',
|
||||
);
|
||||
|
||||
expect(detect).toHaveBeenCalledWith('claude', true);
|
||||
expect(spawnCalls).toHaveLength(0);
|
||||
@@ -415,9 +390,9 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
command: 'claude-alt',
|
||||
});
|
||||
|
||||
await expect(
|
||||
ctr.sendPrompt({ operationId: 'op-test', prompt: 'hello', sessionId }),
|
||||
).rejects.toThrow('Claude Code CLI was not found');
|
||||
await expect(ctr.sendPrompt({ prompt: 'hello', sessionId })).rejects.toThrow(
|
||||
'Claude Code CLI was not found',
|
||||
);
|
||||
|
||||
expect(detect).not.toHaveBeenCalled();
|
||||
expect(spawnCalls).toHaveLength(0);
|
||||
@@ -518,7 +493,6 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
await expect(
|
||||
ctr.sendPrompt({
|
||||
imageList,
|
||||
operationId: 'op-test',
|
||||
prompt: 'inspect the screenshots',
|
||||
sessionId,
|
||||
}),
|
||||
@@ -552,9 +526,9 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
command: 'codex',
|
||||
});
|
||||
|
||||
await expect(
|
||||
ctr.sendPrompt({ operationId: 'op-test', prompt: 'hello', sessionId }),
|
||||
).rejects.toThrow('Agent exited with code 1');
|
||||
await expect(ctr.sendPrompt({ prompt: 'hello', sessionId })).rejects.toThrow(
|
||||
'Agent exited with code 1',
|
||||
);
|
||||
});
|
||||
|
||||
it('uses codex exec resume syntax when continuing an existing thread', async () => {
|
||||
@@ -698,235 +672,4 @@ describe('HeterogeneousAgentCtr', () => {
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
/**
|
||||
* Node may emit `proc.on('exit')` BEFORE stdout fully drains (documented in
|
||||
* child_process docs as "stdio streams might still be open"). The phase 0
|
||||
* refactor moved adapter ownership to main, so renderer no longer flushes
|
||||
* its own adapter on session-complete — meaning trailing events from
|
||||
* `pipeline.flush()` (e.g. Codex's synthesized `tool_end` for unfinished
|
||||
* tool calls) would race against — and lose to — the
|
||||
* `heteroAgentSessionComplete` broadcast without an explicit gate.
|
||||
*
|
||||
* The fix in `proc.on('exit')` is to await stdout `'end'/'close'` (so the
|
||||
* `stdout.on('end')` handler can schedule `pipeline.flush()` onto the
|
||||
* broadcast queue), then drain the queue, then broadcast complete.
|
||||
*/
|
||||
describe('exit-before-end ordering (LOBE-8516 phase 0 race)', () => {
|
||||
let broadcasts: Array<{ channel: string; data: any }>;
|
||||
|
||||
beforeEach(() => {
|
||||
spawnCalls.length = 0;
|
||||
execFileMock.mockReset();
|
||||
broadcasts = [];
|
||||
mockGetAllWindows.mockImplementation(() => [
|
||||
{
|
||||
isDestroyed: () => false,
|
||||
webContents: {
|
||||
send: (channel: string, data: any) => broadcasts.push({ channel, data }),
|
||||
},
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
mockGetAllWindows.mockReset();
|
||||
mockGetAllWindows.mockReturnValue([]);
|
||||
});
|
||||
|
||||
it('delivers pipeline.flush() events BEFORE heteroAgentSessionComplete even when proc exit precedes stdout end', async () => {
|
||||
// Codex `item.started` for a tool — adapter buffers it as a pending
|
||||
// tool call. On flush, adapter synthesizes a trailing `tool_end`. This
|
||||
// is exactly the kind of event the race would lose against complete.
|
||||
const itemStarted = `${JSON.stringify({
|
||||
item: {
|
||||
aggregated_output: '',
|
||||
command: 'echo hi',
|
||||
id: 'cmd-1',
|
||||
status: 'in_progress',
|
||||
type: 'command_execution',
|
||||
},
|
||||
type: 'item.started',
|
||||
})}\n`;
|
||||
const threadStarted = `${JSON.stringify({ thread_id: 't1', type: 'thread.started' })}\n`;
|
||||
|
||||
const proc = new EventEmitter() as any;
|
||||
const stdout = new PassThrough();
|
||||
const stderr = new PassThrough();
|
||||
proc.stdout = stdout;
|
||||
proc.stderr = stderr;
|
||||
proc.stdin = {
|
||||
end: vi.fn(),
|
||||
write: vi.fn((_chunk: any, cb?: () => void) => {
|
||||
cb?.();
|
||||
return true;
|
||||
}),
|
||||
};
|
||||
proc.kill = vi.fn();
|
||||
proc.killed = false;
|
||||
proc.__start = () => {
|
||||
setImmediate(() => {
|
||||
stdout.write(threadStarted);
|
||||
stdout.write(itemStarted);
|
||||
stderr.end();
|
||||
// ⚠️ Reproduce the documented Node race: emit exit BEFORE stdout
|
||||
// ends. Without the streamFinished gate in the controller, the
|
||||
// broadcast queue settles immediately (no flush queued yet) and
|
||||
// complete fires before the trailing tool_end ever broadcasts.
|
||||
proc.emit('exit', 0);
|
||||
setImmediate(() => stdout.end());
|
||||
});
|
||||
};
|
||||
nextFakeProc = proc;
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
const { sessionId } = await ctr.startSession({ agentType: 'codex', command: 'codex' });
|
||||
await ctr.sendPrompt({ operationId: 'op-test', prompt: 'hello', sessionId });
|
||||
|
||||
const events = broadcasts.filter((b) => b.channel === 'heteroAgentEvent');
|
||||
const completeIdx = broadcasts.findIndex((b) => b.channel === 'heteroAgentSessionComplete');
|
||||
const lastEventIdx = broadcasts.findLastIndex((b) => b.channel === 'heteroAgentEvent');
|
||||
|
||||
expect(completeIdx).toBeGreaterThan(-1);
|
||||
expect(events.length).toBeGreaterThan(0);
|
||||
// Every stream event must land before complete — no trailing events
|
||||
// sneak in after the renderer has been told the session is done.
|
||||
expect(lastEventIdx).toBeLessThan(completeIdx);
|
||||
|
||||
// Specifically: the synthesized tool_end for the pending command
|
||||
// execution (emitted only by adapter.flush()) is in the broadcast.
|
||||
const toolEnds = events.filter((b) => (b.data as any)?.event?.type === 'tool_end');
|
||||
expect(toolEnds.length).toBeGreaterThan(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('app-quit cleanup of AskUserQuestion temp configs (LOBE-8725)', () => {
|
||||
// The async exit-handler cleanup races Electron's main-process teardown
|
||||
// and used to leak `lobe-cc-mcp-<opId>.json` files in `os.tmpdir()` on
|
||||
// every quit. The controller now unlinks pending intervention temp
|
||||
// configs *synchronously* from `before-quit` AND from process signal
|
||||
// handlers (SIGTERM / SIGINT — `before-quit` doesn't fire on external
|
||||
// kills). These tests exercise both paths against real files.
|
||||
|
||||
/**
|
||||
* Drop a temp `lobe-cc-mcp-<id>.json` and stash it on the controller's
|
||||
* `opIdToIntervention` map under the same key, so the quit hook treats
|
||||
* it like a real pending intervention and tries to unlink it.
|
||||
*/
|
||||
const seedPendingIntervention = async (ctr: HeterogeneousAgentCtr, opId: string) => {
|
||||
const tmpConfigPath = path.join(tmpdir(), `lobe-cc-mcp-test-${opId}.json`);
|
||||
await writeFile(tmpConfigPath, '{"mcpServers":{}}');
|
||||
const slot = {
|
||||
bridge: {} as any,
|
||||
pumpDone: Promise.resolve(),
|
||||
tmpConfigPath,
|
||||
};
|
||||
(ctr as any).opIdToIntervention.set(opId, slot);
|
||||
return tmpConfigPath;
|
||||
};
|
||||
|
||||
const captureRegisteredHandler = (
|
||||
registerSpy: ReturnType<typeof vi.fn> | ReturnType<typeof vi.spyOn>,
|
||||
eventName: string,
|
||||
): (() => void) => {
|
||||
const calls = (registerSpy as any).mock.calls as Array<[string, () => void]>;
|
||||
const match = calls.findLast(([evt]) => evt === eventName);
|
||||
if (!match) throw new Error(`no handler registered for "${eventName}"`);
|
||||
return match[1];
|
||||
};
|
||||
|
||||
it('before-quit synchronously unlinks every pending intervention temp config', async () => {
|
||||
const electron = (await import('electron')) as any;
|
||||
electron.app.on.mockClear();
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
|
||||
const fileA = await seedPendingIntervention(ctr, 'opA');
|
||||
const fileB = await seedPendingIntervention(ctr, 'opB');
|
||||
|
||||
ctr.afterAppReady();
|
||||
const beforeQuit = captureRegisteredHandler(electron.app.on, 'before-quit');
|
||||
beforeQuit();
|
||||
|
||||
await expect(access(fileA)).rejects.toThrow();
|
||||
await expect(access(fileB)).rejects.toThrow();
|
||||
});
|
||||
|
||||
it('SIGTERM handler unlinks pending intervention temp configs (external-kill path)', async () => {
|
||||
// External kills (test harness, OS shutdown) skip Electron's lifecycle
|
||||
// events entirely — `before-quit` never fires, so the controller has to
|
||||
// hook the raw process signal too. Stub `process.on` so the handler is
|
||||
// *recorded* but never actually attached to the test runner's process
|
||||
// (otherwise the test leaks a SIGTERM listener that survives the test).
|
||||
// Same for `process.exit` — the controller's fail-safe shouldn't get a
|
||||
// chance to actually exit the worker if its `setTimeout(...).unref()`
|
||||
// ever fires before mockRestore.
|
||||
const electron = (await import('electron')) as any;
|
||||
electron.app.on.mockClear();
|
||||
const processOnSpy = vi.spyOn(process, 'on').mockImplementation(() => process);
|
||||
const processExitSpy = vi.spyOn(process, 'exit').mockImplementation(() => undefined as never);
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
const file = await seedPendingIntervention(ctr, 'opSigterm');
|
||||
|
||||
ctr.afterAppReady();
|
||||
const sigterm = captureRegisteredHandler(processOnSpy, 'SIGTERM');
|
||||
sigterm();
|
||||
|
||||
await expect(access(file)).rejects.toThrow();
|
||||
|
||||
processOnSpy.mockRestore();
|
||||
processExitSpy.mockRestore();
|
||||
});
|
||||
|
||||
it('SIGINT handler unlinks pending intervention temp configs (Ctrl-C path)', async () => {
|
||||
const electron = (await import('electron')) as any;
|
||||
electron.app.on.mockClear();
|
||||
const processOnSpy = vi.spyOn(process, 'on').mockImplementation(() => process);
|
||||
const processExitSpy = vi.spyOn(process, 'exit').mockImplementation(() => undefined as never);
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
const file = await seedPendingIntervention(ctr, 'opSigint');
|
||||
|
||||
ctr.afterAppReady();
|
||||
const sigint = captureRegisteredHandler(processOnSpy, 'SIGINT');
|
||||
sigint();
|
||||
|
||||
await expect(access(file)).rejects.toThrow();
|
||||
|
||||
processOnSpy.mockRestore();
|
||||
processExitSpy.mockRestore();
|
||||
});
|
||||
|
||||
it('cleanup is idempotent — already-deleted files do not throw', async () => {
|
||||
const electron = (await import('electron')) as any;
|
||||
electron.app.on.mockClear();
|
||||
|
||||
const ctr = new HeterogeneousAgentCtr({
|
||||
appStoragePath,
|
||||
storeManager: { get: vi.fn() },
|
||||
} as any);
|
||||
const file = await seedPendingIntervention(ctr, 'opIdempotent');
|
||||
|
||||
// Pre-delete the file out from under the controller — simulates a
|
||||
// partial cleanup race where the async exit handler beat us to it.
|
||||
await unlink(file);
|
||||
|
||||
ctr.afterAppReady();
|
||||
const beforeQuit = captureRegisteredHandler(electron.app.on, 'before-quit');
|
||||
expect(() => beforeQuit()).not.toThrow();
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,176 +0,0 @@
|
||||
import fs from 'node:fs';
|
||||
import { mkdir, writeFile } from 'node:fs/promises';
|
||||
import os from 'node:os';
|
||||
import path from 'node:path';
|
||||
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import { type App } from '@/core/App';
|
||||
|
||||
import LocalFileCtr from '../LocalFileCtr';
|
||||
|
||||
// Real fs + real @lobechat/file-loaders end-to-end. We only mock the
|
||||
// boundaries we genuinely cannot run in a test process: electron IPC,
|
||||
// execa shell-outs, logger, net fetch.
|
||||
vi.mock('electron', () => ({
|
||||
dialog: { showOpenDialog: vi.fn(), showSaveDialog: vi.fn() },
|
||||
ipcMain: { handle: vi.fn() },
|
||||
shell: { openPath: vi.fn() },
|
||||
}));
|
||||
|
||||
vi.mock('execa', () => ({ execa: vi.fn() }));
|
||||
|
||||
vi.mock('@/utils/logger', () => ({
|
||||
createLogger: () => ({
|
||||
debug: vi.fn(),
|
||||
error: vi.fn(),
|
||||
info: vi.fn(),
|
||||
warn: vi.fn(),
|
||||
}),
|
||||
}));
|
||||
|
||||
vi.mock('@/utils/net-fetch', () => ({ netFetch: vi.fn() }));
|
||||
|
||||
vi.mock('@/utils/file-system', () => ({ makeSureDirExist: vi.fn() }));
|
||||
|
||||
const mockApp = {
|
||||
appStoragePath: '/mock/app/storage',
|
||||
getService: vi.fn(),
|
||||
toolDetectorManager: { getBestTool: vi.fn(() => null) },
|
||||
} as unknown as App;
|
||||
|
||||
describe('LocalFileCtr — readFile / readFiles (real fs)', () => {
|
||||
const tmpDir = path.join(os.tmpdir(), 'localfilectr-readfile-test-' + process.pid);
|
||||
let localFileCtr: LocalFileCtr;
|
||||
|
||||
beforeEach(async () => {
|
||||
vi.clearAllMocks();
|
||||
await mkdir(tmpDir, { recursive: true });
|
||||
localFileCtr = new LocalFileCtr(mockApp);
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
fs.rmSync(tmpDir, { force: true, recursive: true });
|
||||
});
|
||||
|
||||
describe('readFile', () => {
|
||||
it('should read file successfully with default location', async () => {
|
||||
const filePath = path.join(tmpDir, 'test.txt');
|
||||
const content = 'line1\nline2\nline3\nline4\nline5';
|
||||
await writeFile(filePath, content);
|
||||
|
||||
const result = await localFileCtr.readFile({ path: filePath });
|
||||
|
||||
expect(result).toEqual({
|
||||
charCount: 29,
|
||||
content,
|
||||
createdTime: expect.any(Date),
|
||||
fileType: 'txt',
|
||||
filename: 'test.txt',
|
||||
lineCount: 5,
|
||||
loc: [0, 200],
|
||||
modifiedTime: expect.any(Date),
|
||||
totalCharCount: 29,
|
||||
totalLineCount: 5,
|
||||
});
|
||||
});
|
||||
|
||||
it('should read file with custom location range', async () => {
|
||||
const filePath = path.join(tmpDir, 'range.txt');
|
||||
await writeFile(filePath, 'line1\nline2\nline3\nline4\nline5');
|
||||
|
||||
const result = await localFileCtr.readFile({ loc: [1, 3], path: filePath });
|
||||
|
||||
expect(result).toEqual({
|
||||
charCount: 11,
|
||||
content: 'line2\nline3',
|
||||
createdTime: expect.any(Date),
|
||||
fileType: 'txt',
|
||||
filename: 'range.txt',
|
||||
lineCount: 2,
|
||||
loc: [1, 3],
|
||||
modifiedTime: expect.any(Date),
|
||||
totalCharCount: 29,
|
||||
totalLineCount: 5,
|
||||
});
|
||||
});
|
||||
|
||||
it('should read full file content when fullContent is true', async () => {
|
||||
const filePath = path.join(tmpDir, 'full.txt');
|
||||
const content = 'line1\nline2\nline3\nline4\nline5';
|
||||
await writeFile(filePath, content);
|
||||
|
||||
const result = await localFileCtr.readFile({ fullContent: true, path: filePath });
|
||||
|
||||
expect(result).toEqual({
|
||||
charCount: 29,
|
||||
content,
|
||||
createdTime: expect.any(Date),
|
||||
fileType: 'txt',
|
||||
filename: 'full.txt',
|
||||
lineCount: 5,
|
||||
loc: [0, 5],
|
||||
modifiedTime: expect.any(Date),
|
||||
totalCharCount: 29,
|
||||
totalLineCount: 5,
|
||||
});
|
||||
});
|
||||
|
||||
it('should handle file read error', async () => {
|
||||
const result = await localFileCtr.readFile({
|
||||
path: path.join(tmpDir, 'does-not-exist.txt'),
|
||||
});
|
||||
|
||||
expect(result).toEqual({
|
||||
charCount: 0,
|
||||
content: expect.stringContaining('Error accessing or processing file'),
|
||||
createdTime: expect.any(Date),
|
||||
fileType: 'txt',
|
||||
filename: 'does-not-exist.txt',
|
||||
lineCount: 0,
|
||||
loc: [0, 0],
|
||||
modifiedTime: expect.any(Date),
|
||||
totalCharCount: 0,
|
||||
totalLineCount: 0,
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('readFiles', () => {
|
||||
it('should read multiple files successfully', async () => {
|
||||
const file1 = path.join(tmpDir, 'a.txt');
|
||||
const file2 = path.join(tmpDir, 'b.txt');
|
||||
await writeFile(file1, 'content a');
|
||||
await writeFile(file2, 'content b');
|
||||
|
||||
const result = await localFileCtr.readFiles({ paths: [file1, file2] });
|
||||
|
||||
expect(result).toEqual([
|
||||
{
|
||||
charCount: 9,
|
||||
content: 'content a',
|
||||
createdTime: expect.any(Date),
|
||||
fileType: 'txt',
|
||||
filename: 'a.txt',
|
||||
lineCount: 1,
|
||||
loc: [0, 200],
|
||||
modifiedTime: expect.any(Date),
|
||||
totalCharCount: 9,
|
||||
totalLineCount: 1,
|
||||
},
|
||||
{
|
||||
charCount: 9,
|
||||
content: 'content b',
|
||||
createdTime: expect.any(Date),
|
||||
fileType: 'txt',
|
||||
filename: 'b.txt',
|
||||
lineCount: 1,
|
||||
loc: [0, 200],
|
||||
modifiedTime: expect.any(Date),
|
||||
totalCharCount: 9,
|
||||
totalLineCount: 1,
|
||||
},
|
||||
]);
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -106,6 +106,7 @@ const mockApp = {
|
||||
describe('LocalFileCtr', () => {
|
||||
let localFileCtr: LocalFileCtr;
|
||||
let mockShell: any;
|
||||
let mockLoadFile: any;
|
||||
let mockFsPromises: any;
|
||||
|
||||
beforeEach(async () => {
|
||||
@@ -113,6 +114,7 @@ describe('LocalFileCtr', () => {
|
||||
|
||||
// Import mocks
|
||||
mockShell = (await import('electron')).shell;
|
||||
mockLoadFile = (await import('@lobechat/file-loaders')).loadFile;
|
||||
mockFsPromises = await import('node:fs/promises');
|
||||
|
||||
localFileCtr = new LocalFileCtr(mockApp);
|
||||
@@ -176,9 +178,91 @@ describe('LocalFileCtr', () => {
|
||||
});
|
||||
});
|
||||
|
||||
// readFile / readFiles e2e tests live in LocalFileCtr.readFile.test.ts so
|
||||
// they exercise real fs + file-loaders without fighting the heavy mocks
|
||||
// this suite needs for execa-driven tools, electron, and the like.
|
||||
describe('readFile', () => {
|
||||
it('should read file successfully with default location', async () => {
|
||||
const mockFileContent = 'line1\nline2\nline3\nline4\nline5';
|
||||
vi.mocked(mockLoadFile).mockResolvedValue({
|
||||
content: mockFileContent,
|
||||
filename: 'test.txt',
|
||||
fileType: 'txt',
|
||||
createdTime: new Date('2024-01-01'),
|
||||
modifiedTime: new Date('2024-01-02'),
|
||||
});
|
||||
|
||||
const result = await localFileCtr.readFile({ path: '/test/file.txt' });
|
||||
|
||||
expect(result.filename).toBe('test.txt');
|
||||
expect(result.fileType).toBe('txt');
|
||||
expect(result.totalLineCount).toBe(5);
|
||||
expect(result.content).toBe(mockFileContent);
|
||||
});
|
||||
|
||||
it('should read file with custom location range', async () => {
|
||||
const mockFileContent = 'line1\nline2\nline3\nline4\nline5';
|
||||
vi.mocked(mockLoadFile).mockResolvedValue({
|
||||
content: mockFileContent,
|
||||
filename: 'test.txt',
|
||||
fileType: 'txt',
|
||||
createdTime: new Date('2024-01-01'),
|
||||
modifiedTime: new Date('2024-01-02'),
|
||||
});
|
||||
|
||||
const result = await localFileCtr.readFile({ path: '/test/file.txt', loc: [1, 3] });
|
||||
|
||||
expect(result.content).toBe('line2\nline3');
|
||||
expect(result.lineCount).toBe(2);
|
||||
expect(result.totalLineCount).toBe(5);
|
||||
});
|
||||
|
||||
it('should read full file content when fullContent is true', async () => {
|
||||
const mockFileContent = 'line1\nline2\nline3\nline4\nline5';
|
||||
vi.mocked(mockLoadFile).mockResolvedValue({
|
||||
content: mockFileContent,
|
||||
filename: 'test.txt',
|
||||
fileType: 'txt',
|
||||
createdTime: new Date('2024-01-01'),
|
||||
modifiedTime: new Date('2024-01-02'),
|
||||
});
|
||||
|
||||
const result = await localFileCtr.readFile({ path: '/test/file.txt', fullContent: true });
|
||||
|
||||
expect(result.content).toBe(mockFileContent);
|
||||
expect(result.lineCount).toBe(5);
|
||||
expect(result.charCount).toBe(mockFileContent.length);
|
||||
expect(result.totalLineCount).toBe(5);
|
||||
expect(result.totalCharCount).toBe(mockFileContent.length);
|
||||
expect(result.loc).toEqual([0, 5]);
|
||||
});
|
||||
|
||||
it('should handle file read error', async () => {
|
||||
vi.mocked(mockLoadFile).mockRejectedValue(new Error('File not found'));
|
||||
|
||||
const result = await localFileCtr.readFile({ path: '/test/missing.txt' });
|
||||
|
||||
expect(result.content).toContain('Error accessing or processing file');
|
||||
expect(result.lineCount).toBe(0);
|
||||
expect(result.charCount).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('readFiles', () => {
|
||||
it('should read multiple files successfully', async () => {
|
||||
vi.mocked(mockLoadFile).mockResolvedValue({
|
||||
content: 'file content',
|
||||
filename: 'test.txt',
|
||||
fileType: 'txt',
|
||||
createdTime: new Date('2024-01-01'),
|
||||
modifiedTime: new Date('2024-01-02'),
|
||||
});
|
||||
|
||||
const result = await localFileCtr.readFiles({
|
||||
paths: ['/test/file1.txt', '/test/file2.txt'],
|
||||
});
|
||||
|
||||
expect(result).toHaveLength(2);
|
||||
expect(mockLoadFile).toHaveBeenCalledTimes(2);
|
||||
});
|
||||
});
|
||||
|
||||
describe('handleWriteFile', () => {
|
||||
it('should write file successfully', async () => {
|
||||
|
||||
@@ -40,21 +40,13 @@ const mockDisplayBalloon = vi.fn();
|
||||
const mockUpdateIcon = vi.fn();
|
||||
const mockUpdateTooltip = vi.fn();
|
||||
const mockGetMainTray = vi.fn();
|
||||
const mockSetAppTrayVisible = vi.fn();
|
||||
const mockStoreGet = vi.fn(() => true);
|
||||
const mockStoreSet = vi.fn();
|
||||
|
||||
const mockApp = {
|
||||
browserManager: {
|
||||
getMainWindow: mockGetMainWindow,
|
||||
},
|
||||
storeManager: {
|
||||
get: mockStoreGet,
|
||||
set: mockStoreSet,
|
||||
},
|
||||
trayManager: {
|
||||
getMainTray: mockGetMainTray,
|
||||
setAppTrayVisible: mockSetAppTrayVisible,
|
||||
},
|
||||
} as unknown as App;
|
||||
|
||||
@@ -66,31 +58,9 @@ describe('TrayMenuCtr', () => {
|
||||
ipcMainHandleMock.mockClear();
|
||||
// Reset mockedTray for each test
|
||||
mockGetMainTray.mockReset();
|
||||
mockStoreGet.mockReturnValue(true);
|
||||
trayMenuCtr = new TrayMenuCtr(mockApp);
|
||||
});
|
||||
|
||||
describe('getAppTrayVisible', () => {
|
||||
it('should return stored app tray visibility', () => {
|
||||
mockStoreGet.mockReturnValue(false);
|
||||
|
||||
const result = trayMenuCtr.getAppTrayVisible();
|
||||
|
||||
expect(mockStoreGet).toHaveBeenCalledWith('appTrayVisible', true);
|
||||
expect(result).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe('setAppTrayVisible', () => {
|
||||
it('should persist and apply app tray visibility', () => {
|
||||
const result = trayMenuCtr.setAppTrayVisible(false);
|
||||
|
||||
expect(mockStoreSet).toHaveBeenCalledWith('appTrayVisible', false);
|
||||
expect(mockSetAppTrayVisible).toHaveBeenCalledWith(false);
|
||||
expect(result).toEqual({ success: true });
|
||||
});
|
||||
});
|
||||
|
||||
// Restore platform settings after all tests complete
|
||||
afterAll(() => {
|
||||
// Restore the original platform
|
||||
|
||||
@@ -39,12 +39,6 @@ export class TrayManager {
|
||||
initializeTrays() {
|
||||
logger.debug('Initialize application tray');
|
||||
|
||||
if (!this.app.storeManager.get('appTrayVisible', true)) {
|
||||
logger.debug('Application tray is disabled by user settings');
|
||||
this.destroyAll();
|
||||
return;
|
||||
}
|
||||
|
||||
// Initialize main tray
|
||||
const mainTray = this.initializeMainTray();
|
||||
|
||||
@@ -64,19 +58,6 @@ export class TrayManager {
|
||||
return this.retrieveByIdentifier('main');
|
||||
}
|
||||
|
||||
/**
|
||||
* Toggle the application tray at runtime.
|
||||
*/
|
||||
setAppTrayVisible(visible: boolean) {
|
||||
logger.debug(`Set application tray visible: ${visible}`);
|
||||
|
||||
if (visible) {
|
||||
this.initializeTrays();
|
||||
} else {
|
||||
this.destroyAll();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Initialize main tray. On macOS we ship a template image (black + alpha)
|
||||
* so the system recolors it automatically for light / dark menu bars.
|
||||
|
||||
@@ -55,9 +55,6 @@ describe('TrayManager', () => {
|
||||
menuManager: {
|
||||
buildTrayMenu: vi.fn(() => ({ _mockMenu: true }) as any),
|
||||
},
|
||||
storeManager: {
|
||||
get: vi.fn(() => true),
|
||||
},
|
||||
} as unknown as App;
|
||||
|
||||
// Mock Tray constructor
|
||||
@@ -96,15 +93,6 @@ describe('TrayManager', () => {
|
||||
expect(mockApp.menuManager.buildTrayMenu).toHaveBeenCalled();
|
||||
expect(mockTray.setMenu).toHaveBeenCalledWith({ _mockMenu: true });
|
||||
});
|
||||
|
||||
it('should skip tray initialization when app tray is disabled', () => {
|
||||
vi.mocked(mockApp.storeManager.get).mockReturnValue(false);
|
||||
|
||||
trayManager.initializeTrays();
|
||||
|
||||
expect(Tray).not.toHaveBeenCalled();
|
||||
expect(trayManager.trays.size).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('initializeMainTray', () => {
|
||||
@@ -285,24 +273,6 @@ describe('TrayManager', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('setAppTrayVisible', () => {
|
||||
it('should initialize trays when visible is true', () => {
|
||||
trayManager.setAppTrayVisible(true);
|
||||
|
||||
expect(Tray).toHaveBeenCalled();
|
||||
expect(trayManager.trays.has('main')).toBe(true);
|
||||
});
|
||||
|
||||
it('should destroy all trays when visible is false', () => {
|
||||
trayManager.initializeTrays();
|
||||
|
||||
trayManager.setAppTrayVisible(false);
|
||||
|
||||
expect(mockTray.destroy).toHaveBeenCalled();
|
||||
expect(trayManager.trays.size).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('retrieveOrInitialize (private method)', () => {
|
||||
it('should create new tray when it does not exist', () => {
|
||||
const options = {
|
||||
|
||||
@@ -75,7 +75,6 @@ const menu = {
|
||||
'tray.open': 'Open {{appName}}',
|
||||
'tray.quickChat': 'Quick Chat',
|
||||
'tray.quit': 'Quit',
|
||||
'tray.settings': 'Settings',
|
||||
'tray.show': 'Show {{appName}}',
|
||||
'view.forceReload': 'Force Reload',
|
||||
'view.reload': 'Reload',
|
||||
|
||||
@@ -63,9 +63,7 @@ const createMockApp = () => {
|
||||
'dev.devPanel': 'Dev Panel',
|
||||
'tray.openMiniToolbar': 'Quick Composer',
|
||||
'tray.open': `Open ${params?.appName || 'App'}`,
|
||||
'tray.quickChat': 'Quick Chat',
|
||||
'tray.quit': 'Quit',
|
||||
'tray.settings': 'Settings',
|
||||
};
|
||||
return translations[key] || key;
|
||||
});
|
||||
@@ -199,7 +197,6 @@ describe('LinuxMenu', () => {
|
||||
const template = (Menu.buildFromTemplate as any).mock.calls[0][0];
|
||||
expect(template.length).toBeGreaterThan(0);
|
||||
expect(template.some((item: any) => item.label?.includes('Open'))).toBe(true);
|
||||
expect(template.some((item: any) => item.label === 'Settings')).toBe(true);
|
||||
expect(template.some((item: any) => item.label === 'Quit')).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -466,7 +466,7 @@ export class LinuxMenu extends BaseMenuPlatform implements IMenuPlatform {
|
||||
{ type: 'separator' },
|
||||
{
|
||||
click: () => this.app.browserManager.retrieveByIdentifier('settings').show(),
|
||||
label: t('tray.settings'),
|
||||
label: t('file.preferences'),
|
||||
},
|
||||
{ type: 'separator' },
|
||||
{ label: t('tray.quit'), role: 'quit' },
|
||||
|
||||
@@ -31,19 +31,6 @@ vi.mock('electron', () => ({
|
||||
},
|
||||
}));
|
||||
|
||||
vi.mock('electron-is', () => ({
|
||||
macOS: vi.fn(() => true),
|
||||
}));
|
||||
|
||||
vi.mock('@/utils/logger', () => ({
|
||||
createLogger: () => ({
|
||||
debug: vi.fn(),
|
||||
error: vi.fn(),
|
||||
info: vi.fn(),
|
||||
warn: vi.fn(),
|
||||
}),
|
||||
}));
|
||||
|
||||
// Mock isDev
|
||||
vi.mock('@/const/env', () => ({
|
||||
isDev: false,
|
||||
@@ -190,7 +177,6 @@ describe('MacOSMenu', () => {
|
||||
const template = (Menu.buildFromTemplate as any).mock.calls[0][0];
|
||||
expect(template.length).toBeGreaterThan(0);
|
||||
expect(template.some((item: any) => item.label?.includes('Show'))).toBe(true);
|
||||
expect(template.some((item: any) => item.label === 'Settings')).toBe(true);
|
||||
expect(template.some((item: any) => item.label === 'Quit')).toBe(true);
|
||||
});
|
||||
|
||||
|
||||
@@ -694,7 +694,7 @@ export class MacOSMenu extends BaseMenuPlatform implements IMenuPlatform {
|
||||
mainWindow.show();
|
||||
mainWindow.broadcast('navigate', { path: '/settings' });
|
||||
},
|
||||
label: t('tray.settings'),
|
||||
label: t('file.preferences'),
|
||||
},
|
||||
{ type: 'separator' },
|
||||
{ label: t('tray.quit'), role: 'quit' },
|
||||
|
||||
@@ -58,9 +58,7 @@ const createMockApp = () => {
|
||||
'dev.devPanel': 'Dev Panel',
|
||||
'tray.openMiniToolbar': 'Quick Composer',
|
||||
'tray.open': `Open ${params?.appName || 'App'}`,
|
||||
'tray.quickChat': 'Quick Chat',
|
||||
'tray.quit': 'Quit',
|
||||
'tray.settings': 'Settings',
|
||||
};
|
||||
return translations[key] || key;
|
||||
});
|
||||
@@ -181,7 +179,6 @@ describe('WindowsMenu', () => {
|
||||
const template = (Menu.buildFromTemplate as any).mock.calls[0][0];
|
||||
expect(template.length).toBeGreaterThan(0);
|
||||
expect(template.some((item: any) => item.label?.includes('Open'))).toBe(true);
|
||||
expect(template.some((item: any) => item.label === 'Settings')).toBe(true);
|
||||
expect(template.some((item: any) => item.label === 'Quit')).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -473,7 +473,7 @@ export class WindowsMenu extends BaseMenuPlatform implements IMenuPlatform {
|
||||
{ type: 'separator' },
|
||||
{
|
||||
click: () => this.app.browserManager.retrieveByIdentifier('settings').show(),
|
||||
label: t('tray.settings'),
|
||||
label: t('file.preferences'),
|
||||
},
|
||||
{ type: 'separator' },
|
||||
{ label: t('tray.quit'), role: 'quit' },
|
||||
|
||||
@@ -1,48 +0,0 @@
|
||||
import { describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import { buildFilenameKeywordExpression } from '../impl/macOS';
|
||||
|
||||
vi.mock('@/utils/logger', () => ({
|
||||
createLogger: () => ({
|
||||
debug: vi.fn(),
|
||||
error: vi.fn(),
|
||||
info: vi.fn(),
|
||||
warn: vi.fn(),
|
||||
}),
|
||||
}));
|
||||
|
||||
describe('buildFilenameKeywordExpression', () => {
|
||||
it('produces a single substring term for one keyword', () => {
|
||||
expect(buildFilenameKeywordExpression('package.json')).toBe(
|
||||
'kMDItemFSName == "*package.json*"cd',
|
||||
);
|
||||
});
|
||||
|
||||
it('splits whitespace-separated keywords into AND-ed substring terms', () => {
|
||||
// Critical fix: a free-form keyword string from the LLM (e.g. "LobeHub
|
||||
// Financial Statement") used to require that exact phrase to appear in the
|
||||
// filename. Real files reorder words and use _/-/. as separators, so the
|
||||
// literal phrase almost never matched. AND-ing per-token substrings keeps
|
||||
// each token literal but removes the order constraint.
|
||||
expect(buildFilenameKeywordExpression('LobeHub Financial Statement')).toBe(
|
||||
'(kMDItemFSName == "*LobeHub*"cd && kMDItemFSName == "*Financial*"cd && kMDItemFSName == "*Statement*"cd)',
|
||||
);
|
||||
});
|
||||
|
||||
it('collapses repeated whitespace and trims surrounding spaces', () => {
|
||||
expect(buildFilenameKeywordExpression(' foo \t\n bar ')).toBe(
|
||||
'(kMDItemFSName == "*foo*"cd && kMDItemFSName == "*bar*"cd)',
|
||||
);
|
||||
});
|
||||
|
||||
it('escapes embedded double quotes in each token', () => {
|
||||
expect(buildFilenameKeywordExpression('foo "bar" baz')).toBe(
|
||||
'(kMDItemFSName == "*foo*"cd && kMDItemFSName == "*\\"bar\\"*"cd && kMDItemFSName == "*baz*"cd)',
|
||||
);
|
||||
});
|
||||
|
||||
it('returns an empty string when keywords are blank', () => {
|
||||
expect(buildFilenameKeywordExpression('')).toBe('');
|
||||
expect(buildFilenameKeywordExpression(' \t ')).toBe('');
|
||||
});
|
||||
});
|
||||
@@ -1,69 +0,0 @@
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
import { LinuxSearchServiceImpl } from '../impl/linux';
|
||||
|
||||
vi.mock('node:os', () => ({
|
||||
homedir: vi.fn().mockReturnValue('/Users/test-home'),
|
||||
platform: vi.fn().mockReturnValue('linux'),
|
||||
}));
|
||||
|
||||
vi.mock('@/utils/logger', () => ({
|
||||
createLogger: () => ({
|
||||
debug: vi.fn(),
|
||||
error: vi.fn(),
|
||||
info: vi.fn(),
|
||||
warn: vi.fn(),
|
||||
}),
|
||||
}));
|
||||
|
||||
const fgMock = vi.fn();
|
||||
vi.mock('fast-glob', () => ({
|
||||
default: (...args: unknown[]) => fgMock(...args),
|
||||
}));
|
||||
|
||||
const execaMock = vi.fn();
|
||||
vi.mock('execa', () => ({
|
||||
execa: (...args: unknown[]) => execaMock(...args),
|
||||
}));
|
||||
|
||||
vi.mock('node:fs/promises', () => ({
|
||||
stat: vi.fn().mockResolvedValue({
|
||||
atime: new Date(),
|
||||
birthtime: new Date(),
|
||||
isDirectory: () => false,
|
||||
mtime: new Date(),
|
||||
size: 0,
|
||||
}),
|
||||
}));
|
||||
|
||||
describe('UnixFileSearch glob fallback root', () => {
|
||||
beforeEach(() => {
|
||||
fgMock.mockReset();
|
||||
execaMock.mockReset();
|
||||
// Force the Unix tool selection to fall through to fast-glob so we
|
||||
// don't have to mock fd/find availability checks.
|
||||
execaMock.mockRejectedValue(new Error('command not found'));
|
||||
fgMock.mockResolvedValue([]);
|
||||
});
|
||||
|
||||
it('runs glob inside the user home directory when no scope is provided', async () => {
|
||||
// Regression: previously fell back to process.cwd(), which inside a
|
||||
// packaged Electron app is the bundle path — making `**/*foo*` searches
|
||||
// effectively look at nothing user-visible.
|
||||
const impl = new LinuxSearchServiceImpl();
|
||||
await impl.glob({ pattern: '**/*report*' });
|
||||
|
||||
expect(fgMock).toHaveBeenCalledTimes(1);
|
||||
const [pattern, options] = fgMock.mock.calls[0] as [string, { cwd: string }];
|
||||
expect(pattern).toBe('**/*report*');
|
||||
expect(options.cwd).toBe('/Users/test-home');
|
||||
});
|
||||
|
||||
it('honors an explicit scope over the home-directory fallback', async () => {
|
||||
const impl = new LinuxSearchServiceImpl();
|
||||
await impl.glob({ pattern: '**/*.ts', scope: '/Users/test-home/Downloads' });
|
||||
|
||||
const [, options] = fgMock.mock.calls[0] as [string, { cwd: string }];
|
||||
expect(options.cwd).toBe('/Users/test-home/Downloads');
|
||||
});
|
||||
});
|
||||
@@ -13,29 +13,6 @@ import { UnixFileSearch } from './unix';
|
||||
|
||||
const logger = createLogger('module:FileSearch:macOS');
|
||||
|
||||
/**
|
||||
* Build the kMDItemFSName expression for a free-form keyword string.
|
||||
*
|
||||
* Splits on whitespace and ANDs each token as a case/diacritic-insensitive
|
||||
* substring match, so "Foo Bar" matches both `Bar_Foo.pdf` and `Foo Bar.pdf`
|
||||
* — instead of requiring the literal phrase "Foo Bar" to appear.
|
||||
*
|
||||
* Returns an empty string when the keywords contain no usable token.
|
||||
*/
|
||||
export const buildFilenameKeywordExpression = (keywords: string): string => {
|
||||
const tokens = keywords
|
||||
.trim()
|
||||
.split(/\s+/)
|
||||
.filter(Boolean)
|
||||
.map((token) => token.replaceAll('"', '\\"'));
|
||||
|
||||
if (tokens.length === 0) return '';
|
||||
|
||||
const term = (token: string) => `kMDItemFSName == "*${token}*"cd`;
|
||||
if (tokens.length === 1) return term(tokens[0]);
|
||||
return `(${tokens.map(term).join(' && ')})`;
|
||||
};
|
||||
|
||||
/**
|
||||
* Fallback tool type for macOS file search
|
||||
* Priority: mdfind > fd > find > fast-glob
|
||||
@@ -118,16 +95,7 @@ export class MacOSSearchServiceImpl extends UnixFileSearch {
|
||||
* Search using Spotlight (mdfind)
|
||||
*/
|
||||
private async searchWithSpotlight(options: SearchOptions): Promise<FileResult[]> {
|
||||
const { cmd, args, commandString, hasQuery } = this.buildSearchCommand(options);
|
||||
|
||||
// Spotlight (mdfind) requires a query expression; running it with only flags
|
||||
// (e.g. -onlyin) makes mdfind print its usage to stdout and we'd treat each
|
||||
// line as a fake file. Short-circuit to an empty result instead.
|
||||
if (!hasQuery) {
|
||||
logger.warn('Skipping mdfind: no keywords/contentContains/fileTypes/date filter provided');
|
||||
return [];
|
||||
}
|
||||
|
||||
const { cmd, args, commandString } = this.buildSearchCommand(options);
|
||||
logger.debug(`Executing command: ${commandString}`);
|
||||
|
||||
try {
|
||||
@@ -208,7 +176,6 @@ export class MacOSSearchServiceImpl extends UnixFileSearch {
|
||||
args: string[];
|
||||
cmd: string;
|
||||
commandString: string;
|
||||
hasQuery: boolean;
|
||||
} {
|
||||
const cmd = 'mdfind';
|
||||
const args: string[] = [];
|
||||
@@ -237,7 +204,7 @@ export class MacOSSearchServiceImpl extends UnixFileSearch {
|
||||
|
||||
if (options.keywords) {
|
||||
if (!options.keywords.includes('kMDItem')) {
|
||||
queryExpression = buildFilenameKeywordExpression(options.keywords);
|
||||
queryExpression = `kMDItemFSName == "*${options.keywords.replaceAll('"', '\\"')}*"cd`;
|
||||
} else {
|
||||
queryExpression = options.keywords;
|
||||
}
|
||||
@@ -304,15 +271,13 @@ export class MacOSSearchServiceImpl extends UnixFileSearch {
|
||||
}
|
||||
}
|
||||
|
||||
const hasQuery = Boolean(queryExpression);
|
||||
|
||||
if (hasQuery) {
|
||||
if (queryExpression) {
|
||||
args.push(queryExpression);
|
||||
}
|
||||
|
||||
const commandString = `${cmd} ${args.map((arg) => (arg.includes(' ') || arg.includes('*') ? `"${arg}"` : arg)).join(' ')}`;
|
||||
|
||||
return { args, cmd, commandString, hasQuery };
|
||||
return { args, cmd, commandString };
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -323,7 +288,7 @@ export class MacOSSearchServiceImpl extends UnixFileSearch {
|
||||
options: SearchOptions,
|
||||
engine?: string,
|
||||
): Promise<FileResult[]> {
|
||||
const resultPromises = filePaths.map(async (filePath): Promise<FileResult | null> => {
|
||||
const resultPromises = filePaths.map(async (filePath) => {
|
||||
try {
|
||||
const stats = await stat(filePath);
|
||||
|
||||
@@ -348,15 +313,23 @@ export class MacOSSearchServiceImpl extends UnixFileSearch {
|
||||
|
||||
return result;
|
||||
} catch (error) {
|
||||
// Drop the row instead of fabricating a 0-byte placeholder. mdfind
|
||||
// occasionally returns non-path lines (e.g. usage text when the query
|
||||
// is malformed) which would otherwise render as phantom files.
|
||||
logger.warn(`Dropping unstattable search hit ${filePath}: ${(error as Error).message}`);
|
||||
return null;
|
||||
logger.warn(`Error processing file stats for ${filePath}: ${(error as Error).message}`);
|
||||
return {
|
||||
contentType: 'unknown',
|
||||
createdTime: new Date(),
|
||||
engine,
|
||||
isDirectory: false,
|
||||
lastAccessTime: new Date(),
|
||||
modifiedTime: new Date(),
|
||||
name: path.basename(filePath),
|
||||
path: filePath,
|
||||
size: 0,
|
||||
type: path.extname(filePath).toLowerCase().replace('.', ''),
|
||||
};
|
||||
}
|
||||
});
|
||||
|
||||
let results = (await Promise.all(resultPromises)).filter((r): r is FileResult => r !== null);
|
||||
let results = await Promise.all(resultPromises);
|
||||
|
||||
if (options.sortBy) {
|
||||
results = this.sortResults(results, options.sortBy, options.sortDirection);
|
||||
|
||||
@@ -337,7 +337,7 @@ export abstract class UnixFileSearch extends BaseFileSearch {
|
||||
* @returns Glob results
|
||||
*/
|
||||
protected async globWithFd(params: GlobFilesParams): Promise<GlobFilesResult> {
|
||||
const searchPath = params.scope || os.homedir() || process.cwd();
|
||||
const searchPath = params.scope || process.cwd();
|
||||
const logPrefix = `[glob:fd: ${params.pattern}]`;
|
||||
|
||||
logger.debug(`${logPrefix} Starting fd glob`, { searchPath });
|
||||
@@ -393,7 +393,7 @@ export abstract class UnixFileSearch extends BaseFileSearch {
|
||||
* @returns Glob results
|
||||
*/
|
||||
protected async globWithFind(params: GlobFilesParams): Promise<GlobFilesResult> {
|
||||
const searchPath = params.scope || os.homedir() || process.cwd();
|
||||
const searchPath = params.scope || process.cwd();
|
||||
const logPrefix = `[glob:find: ${params.pattern}]`;
|
||||
|
||||
logger.debug(`${logPrefix} Starting find glob`, { searchPath });
|
||||
@@ -455,7 +455,7 @@ export abstract class UnixFileSearch extends BaseFileSearch {
|
||||
* @returns Glob results
|
||||
*/
|
||||
protected async globWithFastGlob(params: GlobFilesParams): Promise<GlobFilesResult> {
|
||||
const searchPath = params.scope || os.homedir() || process.cwd();
|
||||
const searchPath = params.scope || process.cwd();
|
||||
const logPrefix = `[glob:fast-glob: ${params.pattern}]`;
|
||||
|
||||
logger.debug(`${logPrefix} Starting fast-glob`, { searchPath });
|
||||
|
||||
@@ -335,7 +335,7 @@ export class WindowsSearchServiceImpl extends BaseFileSearch {
|
||||
* @returns Glob results
|
||||
*/
|
||||
private async globWithFd(params: GlobFilesParams): Promise<GlobFilesResult> {
|
||||
const searchPath = params.scope || os.homedir() || process.cwd();
|
||||
const searchPath = params.scope || process.cwd();
|
||||
const logPrefix = `[glob:fd: ${params.pattern}]`;
|
||||
|
||||
logger.debug(`${logPrefix} Starting fd glob`, { searchPath });
|
||||
@@ -390,7 +390,7 @@ export class WindowsSearchServiceImpl extends BaseFileSearch {
|
||||
* @returns Glob results
|
||||
*/
|
||||
private async globWithFastGlob(params: GlobFilesParams): Promise<GlobFilesResult> {
|
||||
const searchPath = params.scope || os.homedir() || process.cwd();
|
||||
const searchPath = params.scope || process.cwd();
|
||||
const logPrefix = `[glob:fast-glob: ${params.pattern}]`;
|
||||
|
||||
logger.debug(`${logPrefix} Starting fast-glob`, { searchPath });
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user