feat: 产品内知识库(obsidian-wiki 兼容 vault)

后端:新增自包含 deerflow.knowledge 模块(models/repository/schemas/
extractor/sources/markdown_vault/manifest/obsidian_adapter/exporter/
search/service),通过 deps.py 装配为 app.state.knowledge_service,
挂载 /api/knowledge 路由;config.yaml 增加 knowledge 配置段,
AppConfig 注册 KnowledgeConfig,ORM 注册 4 张 knowledge_* 表。

前端:新增知识库页面(KnowledgeBasePage/KnowledgeGraphPage)、
core/knowledge api/hooks/types、聊天侧 knowledge-save-trigger,
侧边栏增加「知识库」入口。

知识库为全局共享,不做 user_id 隔离,写入记录 created_by/updated_by
作为审计。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
AdministratorandClaude Opus 4.8 committed 2026-06-08 17:38:28 +08:00
1 parent 80d2db6315
commit cc99ebba81
28 files changed
+3590 -6

No files matched your search

+11 -1
View File
@@ -250,7 +250,7 @@ FastAPI application on port 8001 with health check at `GET /health`. Set `GATEWA
| **Scheduled Tasks** (`/api/scheduled-tasks`) | Per-user cron-like agent tasks. `GET/POST /` - list/create owned tasks; `PATCH/DELETE /{id}` - update/delete (owner); `POST /{id}/{pause,resume,trigger}`; `GET /{id}/runs`, `GET /runs/{rid}`, run-file preview/edit/download; `GET /runs/{rid}/messages` - agent messages for the run's underlying agent run (used to inspect a stuck/running run; authorized via `_load_run`); `GET /runs/{rid}/html` - generated HTML document for an `html_page` run; `DELETE /runs/{rid}` - owner-scoped, with an admin fallback so admins can delete any user's run; publish/subscribe under `/{id}/{publish,unpublish,subscribe}` and `GET /published`. **Admin (cross-user):** `GET /admin/all` - every task; `PATCH/DELETE /admin/{id}` - edit/delete any task; `POST /admin/{id}/trigger`; `GET /admin/{id}/runs`. Admin routes require `system_role == "admin"`. |
| **HTML Page Favorites** (`/api/html-page-favorites`) | Bookmarked generated HTML pages, owner-scoped. `GET /` - list; `POST /` `{page_id, title?, description?, tags?}` - bookmark a `scheduled_html_pages` row (extracts a reusable style/layout summary via GLM5 at favorite time); a page can only be favorited once per user (`DuplicateFavoriteError` → HTTP 409). `GET/DELETE /{id}` - read/delete (the create-task reference picker deletes favorites here). A favorite can be selected as a style reference when creating a new `html_page` task. |
| **Public Scheduled Tasks** (`/api/public/scheduled-tasks`) | **Unauthenticated** mirror for embedding. Adds `GET /runs/{rid}/html` and `GET /{task_id}/latest-html` for the `html_page` preview; the run result keeps `result.html` (only file paths are redacted). |
| **Public Leaderboard** (`/api/public/leaderboard`) | **Unauthenticated** read-only user leaderboard snapshot powering the public publish page (`#/public/leaderboard`). `GET /` returns the same `AdminLeaderboardResponse` as the admin endpoint, reusing `_load_or_schedule_daily_leaderboard` and honoring the system-wide leaderboard settings (excluded users, scheduled/admin/failed inclusion). No admin controls, no mutations. Router: `app/gateway/routers/public_leaderboard.py`. |
| **Knowledge** (`/api/knowledge`) | Product knowledge base, **global/shared** (no user isolation; writes record `created_by`/`updated_by` for audit). `POST /ingest/thread/{thread_id}` - sediment one thread into a note (reads messages from the checkpointer, `threads:read` owner-checked); `POST /ingest/threads/batch` - batch-sediment the caller's recent threads (`skip_existing` via `.manifest.json` dedup); `POST /ingest/search` - sediment search/tool results as a reference note; `POST /notes` - manual note; `GET /notes` (keyword/tag/source_type/status + pagination); `GET/PUT/DELETE /notes/{id}` (DELETE is soft = archive, `?hard=true` removes the vault file); `POST /search` - keyword/frontmatter/Markdown content search (vector/hybrid fall back to keyword in v1); `POST /export/graph` + `GET /export/files/{graph.json\|graph.html\|graph.graphml\|cypher.txt}` - obsidian-wiki `wiki-export` artifacts (self-contained `graph.html` for iframe). Backed by the `deerflow.knowledge` module (see below). |
Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` → Gateway.
@@ -274,6 +274,16 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
**HTML skills (tools the render step uses).** Two offline skills under `skills/public/` shape the generated HTML and are toggled in the skills settings page (enabled by default): `html-page-builder` (a self-contained inline-CSS design system — colors/cards/tables/KPI/responsive) and `html-charts` (inline-SVG charts that render in the no-`allow-scripts` preview iframe; optional local ECharts documented in its `assets/README.md`). A skill opts into HTML injection via `metadata.kind: html_page` in its SKILL.md frontmatter; `_collect_html_skill_instructions()` reads the bodies of **enabled** such skills and `build_generation_prompt(skill_instructions=…)` injects them, so the (raw-model) render step honors the user's skill selection. The data-gathering step and the render/repair/style passes all use the task's selected `model_name` (no silent fallback to the default model — and there is **no hardcoded GLM-5**; an unset selection falls back to config `models[0]`). To stop auxiliary LLM calls from leaking onto the default model, **`TitleMiddleware` is skipped when `is_scheduled_run` is set** (`_build_middlewares` in `lead_agent/agent.py`) — scheduled/HTML runs use throwaway threads whose titles are never shown, and `config.title.model_name` is usually unset (→ would call `models[0]`, not the chosen model). The completeness gate (`validate_html`) also requires a non-empty `<title>` and forbids external stylesheets, on top of the doctype/html/head/body + non-empty-body + no-script checks.
### Knowledge Base (`packages/harness/deerflow/knowledge/`)
Self-contained product knowledge base. **All knowledge capability lives in this one module** (harness layer, `deerflow.*` only — no `app.*` imports). Wired as `app.state.knowledge_service` in `deps.py` via `make_knowledge_service(sf, config.knowledge)` (returns `None` on the memory backend or when `knowledge.enabled=false` → router 503). Surfaced by `app/gateway/routers/knowledge.py` (`/api/knowledge`). Config: `config.yaml` → `knowledge` (`deerflow/config/knowledge_config.py`).
**Two stores, kept in sync on every write:**
- **DB mirror** — tables `knowledge_notes` / `knowledge_sources` / `knowledge_tags` / `knowledge_note_tags` (`knowledge/models.py`, registered in `persistence/models/__init__.py`, auto-created by `Base.metadata.create_all`; portable types `PortableLongText`/`BeijingDateTime`). Powers listing/filter/search/audit. Global/shared — no `user_id` column; `created_by`/`updated_by` are audit-only (resolved via `get_effective_user_id()`).
- **Markdown vault** — obsidian-wiki compatible, default `{$DEER_FLOW_HOME}/data/knowledge/obsidian-vault`. `ObsidianWikiAdapter` (`obsidian_adapter.py`) writes wiki-capture frontmatter+body, and after **every** write syncs `index.md` / `log.md` (CAPTURE/INGEST/UPDATE/ARCHIVE/EXPORT) / `hot.md` / `.manifest.json` (source-hash dedup for `skip_existing`). `markdown_vault.py` handles frontmatter build/parse, slugging, wikilink extraction and **path-traversal-proof** resolution.
**Module layout:** `models.py` (ORM) · `repository.py` (DB only, no LLM) · `schemas.py` (NoteDraft/SourceDraft DTOs) · `skill_templates.py` (wiki-capture/query/export constants) · `markdown_vault.py` · `manifest.py` · `extractor.py` (rule-based thread/search → NoteDraft; turn splitting, greeting filter, 5-section declarative body, ≥2 wikilinks; LLM extractor is a future drop-in) · `sources.py` (reference-batch / search-result → SourceDraft) · `exporter.py` (`graph.json`/`graph.graphml`/`cypher.txt` + self-contained vanilla-JS `graph.html`, no CDN) · `search.py` (keyword/frontmatter/content scoring; vector/hybrid reserved for phase 2) · `obsidian_adapter.py` · `service.py` (`KnowledgeService` orchestrator — the only thing the router touches). Tests: `tests/test_knowledge.py`. Frontend: `frontend-web/src/core/knowledge/*` + `pages/KnowledgeBasePage.tsx` / `KnowledgeGraphPage.tsx` + chat `knowledge-save-trigger.tsx`; spec at `frontend-web/docs/product-knowledge-base-dev.md`.
### Custom Agent Persistence
Custom agent metadata lives in the `agents` ORM table (`deerflow.persistence.agents`). `agents.id` is the stable runtime id and the filesystem directory name under `.deer-flow/agents/{id}/`; `agents.name` is display-only, can contain Chinese characters, and is not unique. `user_id IS NULL` marks built-in agents, user-owned agents are visible only to their owner unless `published = true`, and update/delete operations require ownership. The runtime accepts `agent_id` in context/configurable, and non-default `assistant_id` values are treated as agent ids after visibility checks.