Merge branch 'gzy' into 'master'

Gzy

See merge request knowledge-base-bj/deerflow-server!143
This commit is contained in:
g zy committed 2026-06-23 02:57:41 +00:00
commit 076cdc746e
8 files changed
+463 -105

No files matched your search

+3
View File
@@ -110,3 +110,6 @@ offline-backend-20260512/backend/uv.lock
# Python bytecode cache
__pycache__/
# misc
.DS_Store
+102
View File
@@ -0,0 +1,102 @@
# AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
## Project Overview
This is a customized offline deployment of **DeerFlow** — a LangGraph-based AI super agent platform. The repo contains two sub-projects:
- `offline-backend-20260512/backend/` — Python backend (FastAPI Gateway + LangGraph agent runtime)
- `frontend-web/` — Vite + React 19 frontend (TypeScript, pnpm)
Managed together via shell scripts in `scripts/`.
## Commands
### Full Application (from repo root)
```bash
./scripts/start-all.sh # Start backend + frontend as background daemons
./scripts/stop-all.sh # Stop both
./scripts/restart-all.sh # Restart both
./scripts/status.sh # Check running status
```
Logs and PID files are written to `.runtime/logs/` and `.runtime/pids/`.
### Backend Only (from `offline-backend-20260512/backend/`)
```bash
make install # Install Python dependencies (uv)
make dev # Run Gateway API with hot-reload on port 8001
make gateway # Run Gateway API without reload
make test # Run all tests: PYTHONPATH=. uv run pytest tests/ -v
make lint # Lint with ruff
make format # Format with ruff
```
Run a single test file:
```bash
PYTHONPATH=. uv run pytest tests/test_<feature>.py -v
```
### Frontend Only (from `frontend-web/`)
```bash
pnpm install # Install dependencies
pnpm dev # Start Vite dev server on port 5174
pnpm build # Production build
pnpm typecheck # TypeScript type checking (tsc --noEmit)
```
## Service Ports
| Service | Port | Notes |
|---------|------|-------|
| Backend (Gateway API) | 8001 | FastAPI + LangGraph runtime |
| Frontend (Vite) | 5174 | React SPA |
Frontend connects to backend via env vars `VITE_BACKEND_BASE_URL` and `VITE_LANGGRAPH_BASE_URL` (injected by `scripts/start-frontend.sh`).
## Architecture
### Backend
The backend (`offline-backend-20260512/backend/`) is split into two layers:
- **`packages/harness/deerflow/`** — publishable agent framework (`deerflow.*` imports): LangGraph lead agent, middleware chain, sandbox, tools, MCP, memory, models, skills. **Never imports from `app.*`.**
- **`app/`** — application layer (`app.*` imports): FastAPI Gateway routers, IM channel integrations (Feishu, Slack, Telegram, DingTalk).
The **Lead Agent** (`deerflow/agents/lead_agent/`) is the single LangGraph graph entry point. It wraps a middleware chain (~18 middlewares assembled in strict order) around LLM calls, handling: thread isolation, sandbox lifecycle, uploads, memory, plan mode, vision, subagent delegation, and loop detection.
**Middleware order matters** — middlewares are appended in a fixed sequence; `ClarificationMiddleware` must always be last. See `offline-backend-20260512/backend/AGENTS.md` for the full ordered list.
**Harness → App import firewall** is enforced by `tests/test_harness_boundary.py` (runs in CI).
### Frontend
The frontend (`frontend-web/`) is a React 19 + Vite SPA:
- **Routing**: React Router v7; top-level routes in `src/pages/PageRoutes.tsx`, workspace sub-routes in `src/pages/WorkspaceRoutes.tsx`
- **Pages**: `ChatPage` (thread chat), `AgentChatPage` (custom agent chat), `AgentsPage`/`NewAgentPage` (agent management), `ScheduledTasksPage`/`ScheduledTaskRunDetailPage` (scheduled tasks), `LightAppManagementPage`/`LightAppListPage`/`LightAppIframeView` (轻应用中心 — register/list/embed mini-apps)
- **轻应用中心 (Light App Center)**: a sibling of 任务管理 in the sidebar with two pages — 应用管理 (admin registers `window_open` or `iframe` mini-apps with a route-param builder: login params resolved from `localStorage.userInfo`, theme params literal) and 应用列表 (card grid of `window_open` apps, `window.open` launch). `iframe` apps are mounted under a chosen parent menu (XK/PG/TY/综合管理) and **dynamically injected into the sidebar** by `core/page-layout/use-sidebar-menu.ts` (`useSidebarMenuItems`), opening in the `LightAppIframeView` host. Client + React Query hooks in `strategy-components/api/light-apps.ts`; URL builder/constants in `strategy-components/lib/light-app.ts`. Backend: `/api/light-apps` (global/shared, admin-gated writes).
- **菜单管理 (Menu Management, admin-only)**: an **overlay** over the static sidebar menu — `MenuManagementPage` (`pages/MenuManagementPage.tsx`, route `/page/strategy/admin/menu-management`, opened from the admin-only 「菜单管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`). Admins rename / 停用·启用 / reorder (↑↓ or @dnd-kit drag) / re-parent (horizontal drag **or** the edit dialog's 「移动到」parent selector) any node across 一级/二级/三级, **including injected iframe light-app nodes** (`light-app-<appId>`). The static tree (`core/page-layout/sidebar-menu.ts`) stays the source of icons/routes; only per-node deltas (`label`/`disabled`/`parentId`/`sortOrder`) persist to the backend. Merge logic in `core/page-layout/menu-overrides.ts` (`applyMenuOverrides`, applied in `use-sidebar-menu.ts` after light-app injection, before role filter; disabling a node hides its whole subtree) — strict **3-level cap** (`wouldExceedDepth`). Client `strategy-components/api/menu-overrides.ts`. Backend: `/api/menu-overrides` (global/shared; open read, admin atomic replace-all).
- **敏感词管理 (Sensitive Word Management)**: configures the **展示层脱敏映射** (原始词 → 替换词). **Gated on the username `lqq`** (not the admin role) — `getAccountDisplayName().toLowerCase() === "lqq"` (username = email `@` prefix, else `user_id`, same as the profile page); the dropdown entry, the route guard, and the page-level guard all use this check. `src/lib/desensitize.ts` ships a frozen seed map `SEED_DESENSITIZE_MAP` (the deployment seed) plus a live mutable `DESENSITIZE_MAP` (initialized from the seed so `desensitize()` works before any fetch). `DesensitizeWordsLoader` (mounted in `App.tsx` `AppProviders`) fetches `/api/sensitive-words` on startup and, if non-empty, calls `replaceDesensitizeMap(...)` to make the backend config the source of truth (empty/failed → keep seed). Page `SensitiveWordsPage.tsx` (route `/page/strategy/admin/sensitive-words`, opened from the 「敏感词管理」 item in the **bottom-left settings dropdown** of `components/page-sidebar.tsx`, present in **both** full + collapsed sidebar modes) lists/adds/edits/启停/deletes words and saves the **whole set atomically** (replace-all); a 「导入种子词」 button merges any missing `SEED_DESENSITIZE_MAP` entries into the editor. Client + hooks in `strategy-components/api/sensitive-words.ts` (`wordsToMap` folds enabled rows into the runtime map). Backend: `/api/sensitive-words` (global/shared; open read, write allowed for admin **or** the `lqq` account), mirroring 菜单管理's store shape. **侧边栏 + 导航栏 menu labels are desensitized** at the data source: `useSidebarMenuItems`/`useActiveThirdLevel` (`core/page-layout/use-sidebar-menu.ts`) map every node's `label` through a desensitizer built **directly from the `/api/sensitive-words` query** (`makeDesensitizer(wordsToMap(words))`, falling back to the global seed `desensitize` while empty) — this sidesteps the `replaceDesensitizeMap` effect-timing race. Only `label` is rewritten; `path`/`id`/`icon` are untouched so routing/highlight are unaffected. All nav surfaces (`page-sidebar.tsx`, `page-sidebar-dark.tsx`, `page-sidebar-v1.tsx`, `strategy-components/Header.tsx`, `PageRoutes.tsx`) consume this hook and are covered; `MenuManagementPage` uses the raw tree so admins still edit real labels.
- **技能地址管理 (Skill Address Management, admin-only)**: 扫描运行中的技能(`skills/{public,custom}` 下所有 `.md`/`.py`)里的 **http(s) URL 与 IP/IP:端口**,按唯一地址聚合全部出现位置(跨 .md/.py),支持**批量替换**(如把 UAT 地址一次性改成生产)。主体抽成可复用组件 `SkillAddressesPanel`(`pages/SkillAddressesPage.tsx` 导出,默认导出 `SkillAddressesPage` 仍保留旧路由 `/page/strategy/admin/skill-addresses` 作直链回退),**作为「技能地址管理」标签页嵌入管理员「技能管理」页 `pages/AdminSkillsPage.tsx`**(该页加 Tabs:「技能列表」+「技能地址管理」;入口在「设置和更多」下拉的「技能管理」`workspace-nav-menu.tsx` → `/page/workspace/admin/skills`,不再单列于 `components/page-sidebar.tsx` 左下角设置下拉):打开自动扫描并带**进度条**(扫描逐技能 / 应用逐文件 X/N,应对 150+ 技能),URL/IP 类型过滤 + 搜索 + 「片段批量套用」(如所有 `uat.4.cn` → `prod.4.cn`)、每地址「替换为」输入框(可展开看 `file:line` 片段)、内联**预览**、**应用**、**多关键词检索**(空格分隔全部命中),以及**修改记录**面板——每次应用生成一条记录(显示时间/改了哪些地址 from→to/文件数/处数),可**针对单次记录回退**(二次确认)。client + NDJSON 流式解析在 `strategy-components/api/skill-addresses.ts`。后端 `/api/skill-addresses`(**仅管理员**):所有文件 IO 走 `asyncio.to_thread` 不阻塞事件循环;`GET /scan`(+`/scan/stream`)、`POST /preview`、`POST /apply`(+`/apply/stream`)、`GET /backups`、`POST /rollback/{id}`;**子串安全替换**(基于 token span,不会误伤子串)、`expected_total` 乐观锁(409)、写前自动磁盘备份到 `{skills_root}/.address-edits/`(同时写一份 `{id}.manifest.json` 记录本次替换明细,供修改记录展示)、应用后刷新技能系统提示缓存。纯引擎 `deerflow/skills/address_scan.py`,router `app/gateway/routers/skill_addresses.py`,tests `tests/test_skill_addresses.py`。范围仅运行中技能,不动 `deploy/minimal/skills/`。
- **按钮管理 (Task Button Management, admin-only)**: configures the **可配置跳转按钮** rendered in the left task panel of the task deep-link workspaces (rwfx / 3qfx / xdfx, see `TaskFxWorkspace`). Each button = `{business, label, linkType, target, appendTaskId, idParam, idKind, enabled, sortOrder}`; `linkType` is `url` (外链 `window.open`, optional append of `?{idParam}={id}` — **`idParam` is the editable query-param name**, e.g. `id`/`task_id`), `business` (内部切换到另一业务, reuses `resolveTaskDeeplinkTarget`, always task id), or `purpose` (弹出当前任务的「任务目的」表格 via the shared `TaskPurposeDialog`, no target — configurable for any page incl. xdfx). **`idKind` (`task`/`action`) only matters for xdfx**: its deep-link `?taskId=` is an 行动id and the 任务id is resolved at login (`fetchTaskIdFromAction`) — `TaskContext` now also stashes the raw `actionId`, so a url button can append either (default `task`). Page `TaskButtonsPage.tsx` (route `/page/strategy/admin/task-buttons`, **admin-gated**, entry「按钮管理」in the bottom-left settings dropdown of `components/page-sidebar.tsx`, both full + collapsed modes) has per-business tabs, edits name/type/target/启停/排序/增删, saves the **whole set atomically** (replace-all), plus 「导入默认」 to merge code-seed defaults. **Seed/fallback** (like 敏感词管理): only when the whole table is empty (fresh deploy, never saved) do the workspace + page fall back to `defaultTaskButtons(cfg)` — rwfx's url buttons (编辑/下一步/3q详情) built from the **live** `/api/public/config/task-deeplink` plus cross-business switch buttons for **all three** businesses (each switches to the other two — rwfx→三情/行动, 3qfx→任务/行动, xdfx→任务/三情). Once saved, the store is the sole source of truth. The old hardcoded jump buttons were migrated out: `TaskFxWorkspace` no longer hardcodes 切换到三情分析, `TaskActionsPanel` keeps only the non-jump 清除记录, and `TaskPurposePanel` dropped its 3q详情 button (now configurable) **and defaults the 目的树 table to collapsed** (chevron toggle). Helpers `core/auth/task-buttons.ts` (`TaskButton`, `defaultTaskButtons`, `resolveTaskButtons`, `buttonsForBusiness`, `runTaskButton`), client+hooks `strategy-components/api/task-buttons.ts`. Backend: `/api/task-buttons` (global/shared; open read, admin replace-all), store `deerflow.persistence.task_buttons` (table `task_buttons`, auto-created by `create_all`), wired `app.state.task_button_store`. Tests: `tests/test_task_buttons.py`.
- **State**: TanStack Query for server state, context providers (`SubtasksProvider`, `ArtifactsProvider`, `PromptInputProvider`) scoped to `WorkspaceRoutes`
- **LLM streaming**: `@langchain/langgraph-sdk` streams messages from the backend via SSE
- **UI**: Radix UI primitives + TailwindCSS v4 + shadcn-style components in `src/components/ui/`
- **Shims**: `src/shims/` provides `next/link` and `next/navigation` polyfills (original code was Next.js)
- **Login URL params** (`LoginPage.tsx`, frontend-only — the backend never sees these): besides the auth params (`ticket`/`userId`/`env`/`theme`/`yUserId`/`token`/`access_token`/`authToken`/`password`), the page supports a **task deep-link** via `?taskId=&goPath=`. After login it calls the consumer API `GET {VITE_AIPI_CONSUMER_URL}/taskAnalyseSearch/cop-task-detail?taskId=` (header `Authorization: Bearer admin`, auto-injected by `utils/request.ts`), stashes the full `data` (`id/overview/taskDirection/taskName/taskContent`) into `sessionStorage["login.copTaskDetail"]`, then routes by `goPath`: base codes `3qfx`/`rwfx`/`xdfx` → that business's configured **single agent** Q&A inside a **任务工作区** (resolved via `/api/business-mapping`; `resolveTaskDeeplinkTarget` calls `persistTaskContext({taskId, agentId, openingText})` and navigates to the `…/chats` **index**, which opens the latest task conversation or 新建 — a 1:N task↔对话 workspace, NOT `pendingAgentMessage`); the `-A` suffix (`3qfx-A`/…) → **multi-agent roundtable** with `roundtablePrefill.businessCode` so the page auto-selects the configured 业务链条. **xdfx's deep-link `?taskId=` is actually an 行动id, not a 任务id** — `resolveDeeplinkTaskId(goPath, rawId)` (called in `LoginPage` before everything) detects `xdfx`/`xdfx-A` and resolves it via `GET {action_detail_url}/{actionId}` → `data.taskId` (`fetchTaskIdFromAction`; `action_test`+`mock.action_detail` for offline testing); the resolved 任务id then drives `cop-task-detail`, the purpose tree, and the 1:N binding (other businesses pass the id through unchanged). **xdfx additionally partitions its chat records by 行动id (action_id), NOT by task_id**: `resolveTaskDeeplinkTarget` sets `partitionByAction:true` + keeps the raw action_id as `TaskContext.actionId`, so new threads are tagged `metadata.{taskId,actionId}` (taskId kept only to preserve the backend「任务深链对话全局共享」semantics, which keys off `metadata.taskId`) and the conversation list filters by `actionId` (+`agent_id`) — different actions of the same task get separate lists. xdfx's first-question opening text also appends `行动id(action_id)为…` (see `buildOpeningText` / `taskThreadMetadata`). goPath→businessCode: `3qfx`→`3Q`, `rwfx`→`6BF`, `xdfx`→`7BF`. The roundtable target also threads the URL `taskId` into `roundtablePrefill.taskId` (`resolveTaskDeeplinkTarget(goPath, detail, taskId)`), which turns on two taskId-scoped behaviors: (1) **separate, unpartitioned per-task storage** — taskId 会商聊天记录 live in their **own** store/table (`roundtable_task_drafts`), keyed **only by `task_id`** (one taskId = many records, shared across users, **no user 分权** at all; `created_by` is audit-only), kept entirely out of the per-user personal store (`roundtable_drafts`, now strictly per-user) so the two never mix. Backend router `/api/roundtable-task-drafts` (`GET /by-task/{id}` + `/by-task/{id}/latest`, `POST`, `GET/PUT/DELETE /{id}` — all user-agnostic); frontend client `roundtable-planning/api/task-drafts.ts`, and `useDraftPersistence`/`useRoundtableDrafts` route **all** CRUD to it when a `taskId` is present (else the personal `drafts.ts`). The matching **background jobs** are shared by task too: `roundtable_jobs.task_id` marks a task job; reads/dedup/stream/resume/cancel pass `?task_id=` so any user opening the task sees the same running 研讨 (progress/flowchart), and the executor writes the final report back to the task-draft store. Existing rows are moved over by `scripts/migrate_roundtable_task_drafts.py` (migration `20260618_01`). The history dropdown filters to the task and 新建 keeps the binding; (2) **Step-3 auto structured output** — after the `roundtable-summary` agent writes the Markdown report it automatically runs a second round emitting a `flow-json` flowchart (`useStep3Summary` `autoFlow`+`chainLevels`), whose hierarchy follows the business chain's stage goals (任务 → 目的 → 行为体 → …; coordinatorPrompt-specified hierarchy wins) and whose nodes never carry 阶段编号/阶段名 (the prior bug). **Both targets render embedded under the 任务管理 layout** — nested routes under `task-management/<business-path>/{roundtable,agent/:agent_id/chats}` in `StrategyRoutes.tsx` (`<business-path>` = `plan-task-sentiment` / `plan-task/plan-task-fx` / `plan-task/plan-task-action`, matching the COH中任务 menu paths in `sidebar-menu.ts`) so the global sidebar keeps 任务管理 → COH中任务 → the matching business highlighted. **All three single-agent businesses share `TaskFxWorkspace`** (`task-components/TaskFxWorkspace.tsx`): left = a「当前任务」card (`readCopTaskDetail()` 任务名称 + 简介, desensitized, 留存 above 新建对话) + per-task 1:N conversation list (`useTaskThreads(taskId, agentId, actionId?)` — filtered by **both** `metadata.taskId` AND `metadata.agent_id` so the three businesses' conversations staLine truncated
- **iframe 嵌入模式 (外部系统用 iframe 套用深链问答/会商)** — 三个**按标签页**开关,全部由深链 URL 参数开启、存进同一份 `sessionStorage` 会话(`embed.session`,键名常量在 `core/embed/embed-session.ts`),跨登录跳转/刷新/页内导航存活,**绝不跨标签污染**同浏览器另开的正常系统页。核心隔离手法:用 `sessionStorage`(按标签页/浏览上下文隔离,iframe 即便同源也有独立一份)而非 `localStorage`(跨标签共享)。开关:(1) **`?embed=1`(可带 `&theme=`)** — 去全局 chrome(`PageLayout` 的 `pageSidebarAllowed && !isEmbedActive()` → 隐藏 Header + PageSidebar)+ 按外部主题色**强制**明/暗:走 next-themes 的 `forcedTheme`(`App.tsx` `AppProviders` 调 `resolveForcedEmbedTheme`,**不写** localStorage `strategy-theme`),离散映射 `dark-blue`/`dark`→深、其余→浅;嵌入侧**绝不**调 `setTheme`/`persistSidebarEnabled`(那俩落 localStorage 跨标签污染,`LoginPage` 据 `readEmbedParam` 跳过)。(2) **`?hideJump=1`** — 隐藏深链底部「快捷跳转」栏 `TaskJumpBar` 的两部分(底部「下一步」等按钮 + 右侧垂直居中悬浮菜单),单智能体问答 + 会商共用该栏,`isJumpBarHidden()` 为真时整条 `return null`。(3) **登录用户隔离** — 嵌入态下鉴权/身份键(`deerflow.auth` token、`userInfo`、`login.*`、`tools_token`、maxkey/userDetail token)全部经 `core/auth/scoped-storage.ts` 的 `authStorage()`(嵌入→sessionStorage / 正常→localStorage)读写,使 iframe 里登录的用户与正常登录用户**完全隔离**、互不覆盖;所有 token 读取都过 `getStoredAuth()`/`getAuthorizationHeaderValue()`(API 客户端 `core/api/*` 全走这俩),改中心函数即让全体调用方自动隔离;跨标签账号变更监听 `AuthSyncWatcher`(`core/auth/sync.tsx`)在嵌入态禁用。嵌入会话在 `main.tsx` 渲染前 `syncEmbedSessionFromCurrentUrl()` 同步启用(早于任何鉴权写入,避免首帧 effect 顺序漏写 localStorage);`AppProviders` 的 effect 再按 SPA 导航同步。`embed=0`/`hideJump=0` 可显式关闭。正常(非嵌入)标签页所有 `isXxx()` 恒 false,行为**零变化**。第三个开关 `?isolate=1`(**独立登录会话**)把同一套**登录用户隔离**单独提供给**普通(带 chrome)标签页**——只切换鉴权存储、不去 chrome / 不强制主题 / 不动跳转栏:`authStorage()` 的条件从「仅嵌入」放宽为 `isEmbedActive() || isIsolatedSession()`,`AuthSyncWatcher` 的跨标签监听对嵌入态**或**独立态都即时忽略(handler 内实时判,运行时开关也即刻生效)。除 URL 参数外,**设置 → 外观 →「登录会话」** 有一个 Switch「独立登录会话(本标签页)」运行时切换(`setIsolatedSession`,`appearance-settings-page.tsx`):**开启时先 `migrateAuthToSession()`**(`scoped-storage.ts`,把 localStorage 的受保护键 `deerflow.auth`/`userInfo`/`userId`/`tools_token` + `login.*` 前缀快照搬进 sessionStorage)再翻标志,故无感不登出;此后本标签页登录态独立——别处登录/换号影响不到它,它换号也影响不到别人,但关掉该标签即结束(需重登)。开启给 toast 提示。
### Configuration
Backend config lives in `offline-backend-20260512/backend/config.yaml`. Values starting with `$` resolve as environment variables (e.g., `$OPENAI_API_KEY`). MCP servers and skills are configured in `extensions_config.json` in the same directory.
## Detailed Backend Reference
The backend has its own comprehensive documentation at:
- `offline-backend-20260512/backend/AGENTS.md` — architecture, middleware chain, all API routes, config schema, sandbox/memory/subagent systems
- `offline-backend-20260512/backend/README.md` — setup guide, technology stack
@@ -32,6 +32,10 @@ interface AgentSelectorProps {
disabled?: boolean;
/** 紧凑模式(CM 参考图):触发器改为灰底胶囊 + 主色机器人图标。 */
compact?: boolean;
/** 图标模式:用于 iframe 等底栏场景,仅显示机器人图标和可选清空按钮。 */
triggerVariant?: "default" | "icon";
iconButtonClassName?: string;
iconActiveClassName?: string;
}
/**
@@ -48,6 +52,9 @@ export function AgentSelector({
onAgentChange,
disabled,
compact = false,
triggerVariant = "default",
iconButtonClassName,
iconActiveClassName,
}: AgentSelectorProps) {
const [open, setOpen] = useState(false);
const [manageOpen, setManageOpen] = useState(false);
@@ -79,48 +86,84 @@ export function AgentSelector({
};
const triggerLabel = selectedAgent ? desensitize(selectedAgent.name) : "选择 Agent";
const iconMode = triggerVariant === "icon";
return (
<>
<Dialog open={open} onOpenChange={setOpen}>
<DialogTrigger asChild>
<PromptInputButton
type="button"
disabled={disabled}
className={cn(
"gap-1.5! rounded-full border px-3! shadow-none transition-colors",
compact && "rounded-lg px-2.5! py-1! text-[11px] font-medium",
compact
? "border-transparent bg-gray-50/60 text-gray-600 hover:bg-gray-100/80 hover:text-gray-800 dark:bg-slate-700/50 dark:text-slate-300 dark:hover:bg-slate-700"
: selectedAgent
? "border-[#d6a868] bg-[#fff3df] text-[#7a5417] hover:bg-[#ffe8c4]"
: "border-[#eee3d5] bg-[#fffaf5] text-[#7e6a57] hover:bg-white dark:border-slate-600 dark:bg-slate-700/50 dark:text-slate-300 dark:hover:bg-slate-700",
)}
>
<BotIcon
className={cn("size-3", compact && "text-[var(--primary)]")}
/>
<span className="max-w-[140px] truncate text-xs font-normal">
{triggerLabel}
</span>
{selectedAgent && (
<span
role="button"
tabIndex={0}
aria-label="清除已选 agent"
className="ml-0.5 inline-flex items-center justify-center rounded-full p-0.5 hover:bg-[#ffd9a7]"
onClick={handleClear}
onKeyDown={(e) => {
if (e.key === "Enter" || e.key === " ") {
e.preventDefault();
onAgentChange(null);
}
}}
>
<XIcon className="size-3" />
{iconMode ? (
<Button
type="button"
variant="ghost"
size="icon"
disabled={disabled}
aria-label={selectedAgent ? `已选择智能体:${triggerLabel}` : "选择智能体"}
className={cn(
"relative size-9 rounded-full text-muted-foreground shadow-none hover:bg-muted/60 hover:text-foreground",
selectedAgent && "text-amber-600 hover:text-amber-700",
selectedAgent && iconActiveClassName,
iconButtonClassName,
)}
>
<BotIcon className="size-4" />
{selectedAgent && (
<span
role="button"
tabIndex={0}
aria-label="清除已选 agent"
className="absolute -right-1 -top-1 inline-flex size-4 items-center justify-center rounded-full border bg-background text-foreground shadow-sm hover:bg-muted"
onClick={handleClear}
onKeyDown={(e) => {
if (e.key === "Enter" || e.key === " ") {
e.preventDefault();
onAgentChange(null);
}
}}
>
<XIcon className="size-2.5" />
</span>
)}
</Button>
) : (
<PromptInputButton
type="button"
disabled={disabled}
className={cn(
"gap-1.5! rounded-full border px-3! shadow-none transition-colors",
compact && "rounded-lg px-2.5! py-1! text-[11px] font-medium",
compact
? "border-transparent bg-gray-50/60 text-gray-600 hover:bg-gray-100/80 hover:text-gray-800 dark:bg-slate-700/50 dark:text-slate-300 dark:hover:bg-slate-700"
: selectedAgent
? "border-[#d6a868] bg-[#fff3df] text-[#7a5417] hover:bg-[#ffe8c4]"
: "border-[#eee3d5] bg-[#fffaf5] text-[#7e6a57] hover:bg-white dark:border-slate-600 dark:bg-slate-700/50 dark:text-slate-300 dark:hover:bg-slate-700",
)}
>
<BotIcon
className={cn("size-3", compact && "text-[var(--primary)]")}
/>
<span className="max-w-[140px] truncate text-xs font-normal">
{triggerLabel}
</span>
)}
</PromptInputButton>
{selectedAgent && (
<span
role="button"
tabIndex={0}
aria-label="清除已选 agent"
className="ml-0.5 inline-flex items-center justify-center rounded-full p-0.5 hover:bg-[#ffd9a7]"
onClick={handleClear}
onKeyDown={(e) => {
if (e.key === "Enter" || e.key === " ") {
e.preventDefault();
onAgentChange(null);
}
}}
>
<XIcon className="size-3" />
</span>
)}
</PromptInputButton>
)}
</DialogTrigger>
<DialogContent className="overflow-hidden p-0 sm:max-w-md">
<DialogTitle className="sr-only">选择 Agent</DialogTitle>
+116 -69
View File
@@ -5,8 +5,8 @@ import {
BrainCircuitIcon,
FileTextIcon,
GraduationCapIcon,
ShrinkIcon,
} from "lucide-react";
import { useRouter } from "next/navigation";
import { useCallback, useEffect, useMemo, useRef, useState } from "react";
import { type PromptInputMessage } from "@/components/ai-elements/prompt-input";
@@ -46,6 +46,8 @@ import {
type BrainyChatSubmitMessage,
parseBrainyChatSubmitMessage,
} from "./iframe-chat-submit";
import { resolveIframeAssistantId } from "./iframe-chat-agent";
import { buildIframeModeButtons } from "./iframe-chat-mode-buttons";
type BrainyChatStatus = "started" | "finished";
type BrainyAuthTokenMessage = {
@@ -93,7 +95,6 @@ function postBrainyAuthToken(accessToken: string) {
export default function IframeChatPage() {
const routeBase = useRouteBase();
const router = useRouter();
const { t } = useI18n();
const [hasStartedConversation, setHasStartedConversation] = useState(false);
const { threadId, setThreadId, isNewThread, setIsNewThread, isMock } =
@@ -152,11 +153,19 @@ export default function IframeChatPage() {
}, [selectedAgentId, selectorAgents, selectorLoading]);
const { showNotification } = useNotification();
const activeAssistantId = resolveIframeAssistantId({
selectedAgentId,
threadMetadataAgentId: null,
});
const [thread, sendMessage, isUploading] = useThreadStream({
threadId: isNewThread ? undefined : threadId,
context: settings.context,
context: {
...settings.context,
...(activeAssistantId ? { agent_id: activeAssistantId } : {}),
},
isMock,
assistantId: activeAssistantId,
onStart: (createdThreadId) => {
setThreadId(createdThreadId);
setIsNewThread(false);
@@ -193,6 +202,22 @@ export default function IframeChatPage() {
},
});
const threadMetadataAgentId = (() => {
const metadata = (thread as { metadata?: Record<string, unknown> | null })
.metadata;
return typeof metadata?.agent_id === "string" ? metadata.agent_id : null;
})();
useEffect(() => {
const resolvedAgentId = resolveIframeAssistantId({
selectedAgentId,
threadMetadataAgentId,
});
if (resolvedAgentId && resolvedAgentId !== selectedAgentId) {
setSelectedAgentId(resolvedAgentId);
}
}, [selectedAgentId, threadMetadataAgentId]);
const writingArtifactPath = useMemo(() => {
const isMarkdown = (path: string | null | undefined) =>
!!path && /\.(md|markdown)(?:$|[?#])/i.test(path);
@@ -210,31 +235,15 @@ export default function IframeChatPage() {
externalContext?: Record<string, unknown>,
options?: { additionalKwargs?: Record<string, unknown> },
) => {
if (
selectedAgentId &&
isNewThread &&
!hasStartedConversation &&
message.text &&
(!message.files || message.files.length === 0)
) {
try {
sessionStorage.setItem(
"pendingAgentMessage",
JSON.stringify({ agentId: selectedAgentId, text: message.text }),
);
} catch {
// sessionStorage may be unavailable in private mode; fall through.
}
router.push(`/page/workspace/agents/${selectedAgentId}/chats/new`);
return;
}
setHasStartedConversation(true);
window.dispatchEvent(
new CustomEvent("workspace:sandbox-resume-autoscroll"),
);
const extraContext: Record<string, unknown> = {};
if (activeAssistantId) {
extraContext.agent_id = activeAssistantId;
}
if (settings.context.writing_mode && writingArtifactPath) {
extraContext.writing_artifact_path = writingArtifactPath;
}
@@ -250,10 +259,8 @@ export default function IframeChatPage() {
);
},
[
activeAssistantId,
hasStartedConversation,
isNewThread,
router,
selectedAgentId,
sendMessage,
settings.context.writing_mode,
threadId,
@@ -277,6 +284,8 @@ export default function IframeChatPage() {
const ragModeLocked = isThreadRagModeLocked(threadId);
const ragModeEnabled =
localSettings.display.ragModeEnabled || ragModeLocked;
const contextCompressionEnabled =
localSettings.display.contextCompressionEnabled ?? false;
const proModeEnabled = settings.context.mode === "pro";
const toggleWritingMode = useCallback(() => {
@@ -301,6 +310,12 @@ export default function IframeChatPage() {
});
}, [ragModeEnabled, ragModeLocked, setLocalSettings]);
const toggleContextCompression = useCallback(() => {
setLocalSettings("display", {
contextCompressionEnabled: !contextCompressionEnabled,
});
}, [contextCompressionEnabled, setLocalSettings]);
const toggleProMode = useCallback(() => {
setSettings("context", {
mode: proModeEnabled ? "flash" : "pro",
@@ -333,28 +348,29 @@ export default function IframeChatPage() {
const data = event.data;
if (data?.source !== "brainy-extension") return;
if (data?.type === "brainy:chat-interrupt") {
void handleInterrupt(data);
void handleInterrupt(data as BrainyChatInterruptMessage);
return;
}
if (data?.type !== "brainy:chat-submit") return;
const submitMessage = data as BrainyChatSubmitMessage;
const { submitText, files, iframeContext, additionalKwargs } =
parseBrainyChatSubmitMessage(data);
parseBrainyChatSubmitMessage(submitMessage);
console.log("收到插件消息", {
text: data.payload?.text,
prompt: data.payload?.prompt,
pageContext: data.payload?.pageContext,
screenshot: data.payload?.screenshot,
model: data.payload?.model,
requestId: data.requestId,
text: submitMessage.payload?.text,
prompt: submitMessage.payload?.prompt,
pageContext: submitMessage.payload?.pageContext,
screenshot: submitMessage.payload?.screenshot,
model: submitMessage.payload?.model,
requestId: submitMessage.requestId,
filesCount: files.length,
iframeContext,
});
if (!submitText && files.length === 0) return;
pendingRequestIdRef.current = data.requestId ?? null;
pendingRequestIdRef.current = submitMessage.requestId ?? null;
handleSubmit(
{ text: submitText, files },
@@ -371,41 +387,59 @@ export default function IframeChatPage() {
const isLandingState = isNewThread && !hasStartedConversation;
const bottomBarHeightClass = "pb-24";
const modeButtons = [
{
key: "writing",
label: "写作",
icon: FileTextIcon,
active: !!settings.context.writing_mode,
onClick: toggleWritingMode,
activeClassName: "text-amber-600 hover:text-amber-700",
},
{
key: "memory",
label: "记忆",
icon: BrainCircuitIcon,
active: settings.context.memory_injection_enabled ?? true,
onClick: toggleMemoryInjection,
activeClassName: "text-blue-600 hover:text-blue-700",
},
{
key: "references",
label: "参考文献",
icon: BookMarkedIcon,
active: ragModeEnabled,
onClick: toggleRagMode,
disabled: ragModeLocked,
activeClassName: "text-emerald-600 hover:text-emerald-700",
},
{
key: "pro",
label: "专业问答",
icon: GraduationCapIcon,
active: proModeEnabled,
onClick: toggleProMode,
activeClassName: "text-violet-600 hover:text-violet-700",
},
] as const;
const modeButtons = buildIframeModeButtons({
agentSelected: !!selectedAgentId,
writingModeEnabled: !!settings.context.writing_mode,
memoryInjectionEnabled: Boolean(
settings.context.memory_injection_enabled ?? true,
),
ragModeEnabled,
ragModeLocked,
contextCompressionEnabled,
proModeEnabled,
}).map((button) => {
switch (button.key) {
case "agent":
return button;
case "writing":
return {
...button,
icon: FileTextIcon,
onClick: toggleWritingMode,
activeClassName: "text-amber-600 hover:text-amber-700",
};
case "memory":
return {
...button,
icon: BrainCircuitIcon,
onClick: toggleMemoryInjection,
activeClassName: "text-blue-600 hover:text-blue-700",
};
case "references":
return {
...button,
icon: BookMarkedIcon,
onClick: toggleRagMode,
activeClassName: "text-emerald-600 hover:text-emerald-700",
};
case "contextCompression":
return {
...button,
icon: ShrinkIcon,
onClick: toggleContextCompression,
activeClassName: "text-violet-600 hover:text-violet-700",
};
case "pro":
return {
...button,
icon: GraduationCapIcon,
onClick: toggleProMode,
activeClassName: "text-fuchsia-600 hover:text-fuchsia-700",
};
default:
return button;
}
});
return (
<ThreadContext.Provider value={{ thread, isMock }}>
@@ -496,6 +530,19 @@ export default function IframeChatPage() {
<TooltipProvider delayDuration={250}>
<div className="mx-auto flex max-w-(--container-width-lg) flex-wrap items-center justify-center gap-0 px-0 py-1">
{modeButtons.map((button) => {
if (button.key === "agent") {
return (
<AgentSelector
key={button.key}
selectedAgentId={selectedAgentId}
onAgentChange={handleAgentChange}
disabled={isUploading}
triggerVariant="icon"
iconButtonClassName="size-9 rounded-full text-muted-foreground shadow-none hover:bg-muted/60 hover:text-foreground"
iconActiveClassName="text-amber-600 hover:text-amber-700"
/>
);
}
const Icon = button.icon;
return (
<Tooltip key={button.key} content={button.label}>
@@ -0,0 +1,35 @@
import assert from "node:assert/strict";
import test from "node:test";
// @ts-ignore Node's test runner resolves the local .ts module directly.
import { resolveIframeAssistantId } from "./iframe-chat-agent.ts";
test("prefers the currently selected iframe agent", () => {
assert.equal(
resolveIframeAssistantId({
selectedAgentId: "roundtable-structure",
threadMetadataAgentId: "lead_agent",
}),
"roundtable-structure",
);
});
test("reuses the thread-bound agent when reopening an iframe thread", () => {
assert.equal(
resolveIframeAssistantId({
selectedAgentId: null,
threadMetadataAgentId: "roundtable-structure",
}),
"roundtable-structure",
);
});
test("falls back to lead-agent mode when no agent is selected or bound", () => {
assert.equal(
resolveIframeAssistantId({
selectedAgentId: null,
threadMetadataAgentId: null,
}),
undefined,
);
});
@@ -0,0 +1,19 @@
type ResolveIframeAssistantIdInput = {
selectedAgentId: string | null;
threadMetadataAgentId: string | null;
};
function normalizeAgentId(agentId: string | null | undefined): string | undefined {
const trimmed = agentId?.trim();
return trimmed ? trimmed : undefined;
}
export function resolveIframeAssistantId({
selectedAgentId,
threadMetadataAgentId,
}: ResolveIframeAssistantIdInput): string | undefined {
return (
normalizeAgentId(selectedAgentId) ??
normalizeAgentId(threadMetadataAgentId)
);
}
@@ -0,0 +1,43 @@
import assert from "node:assert/strict";
import test from "node:test";
// @ts-ignore Node's test runner resolves the local .ts module directly.
import { buildIframeModeButtons } from "./iframe-chat-mode-buttons.ts";
test("includes the context compression toggle in the iframe chat toolbar", () => {
const buttons = buildIframeModeButtons({
agentSelected: false,
writingModeEnabled: false,
memoryInjectionEnabled: true,
ragModeEnabled: false,
ragModeLocked: false,
contextCompressionEnabled: false,
proModeEnabled: false,
});
assert.deepEqual(
buttons.map((button) => button.key),
[
"writing",
"memory",
"references",
"contextCompression",
"pro",
"agent",
],
);
});
test("returns only concrete toolbar button configs", () => {
const buttons = buildIframeModeButtons({
agentSelected: true,
writingModeEnabled: false,
memoryInjectionEnabled: true,
ragModeEnabled: false,
ragModeLocked: false,
contextCompressionEnabled: false,
proModeEnabled: false,
});
assert.equal(buttons.every((button) => typeof button.key === "string"), true);
});
@@ -0,0 +1,66 @@
export type IframeModeButtonState = {
key:
| "agent"
| "writing"
| "memory"
| "references"
| "contextCompression"
| "pro";
label: string;
active: boolean;
disabled?: boolean;
};
type BuildIframeModeButtonsInput = {
agentSelected: boolean;
writingModeEnabled: boolean;
memoryInjectionEnabled: boolean;
ragModeEnabled: boolean;
ragModeLocked: boolean;
contextCompressionEnabled: boolean;
proModeEnabled: boolean;
};
export function buildIframeModeButtons({
agentSelected,
writingModeEnabled,
memoryInjectionEnabled,
ragModeEnabled,
ragModeLocked,
contextCompressionEnabled,
proModeEnabled,
}: BuildIframeModeButtonsInput): IframeModeButtonState[] {
return [
{
key: "writing",
label: "写作",
active: writingModeEnabled,
},
{
key: "memory",
label: "记忆",
active: memoryInjectionEnabled,
},
{
key: "references",
label: "参考文献",
active: ragModeEnabled,
disabled: ragModeLocked,
},
{
key: "contextCompression",
label: "上下文压缩",
active: contextCompressionEnabled,
},
{
key: "pro",
label: "专业问答",
active: proModeEnabled,
},
{
key: "agent",
label: "智能体",
active: agentSelected,
},
];
}