sync update from LAN repo (source dhk-1 @ c21a2a4a)
This commit is contained in:
1 parent
264e2200d6
commit
a1fa13a238
122 files changed
+8881
-623
No files matched your search
@@ -1,5 +1,27 @@
|
||||
# CLAUDE.md
|
||||
|
||||
## Model-independent skill invocation attribution (2026-11-07)
|
||||
|
||||
Never derive skill-use UI or counters from model narration or the optional tool
|
||||
`description`. The canonical signals are a successful `skill_view`, a successful
|
||||
`read_file` under `/mnt/skills/{public,custom}/<skill>/...`, and an executed
|
||||
`bash` command containing such a skill path. `sandbox/tools.py` resolves names
|
||||
through the active skill view so a directory/frontmatter-name mismatch remains
|
||||
correct; both public and custom skills count.
|
||||
|
||||
`skills/usage.py::bump_use(..., event_key=run_id)` de-duplicates all file/script
|
||||
signals to one use per skill per user run. It updates `.usage.json` and schedules
|
||||
an absolute, monotonic update of the `skills` MySQL catalog projection on the
|
||||
engine home loop. Keep this bridge inside `deerflow.*`; the harness must not
|
||||
import `app.*`. The skill-card counter is intentionally independent of the
|
||||
heavier full-tool audit switch. `skill_metrics_enabled` defaults on and mounts
|
||||
`ToolMetricsMiddleware(skill_only=True)` while `tool_metrics_enabled` is off;
|
||||
non-skill calls pass through without DB work, but attributed skill calls still
|
||||
feed audit pages and leaderboards. Frontend labels are recovered by
|
||||
`core/tools/skill-invocation.ts` from explicit skill-tool arguments or skill
|
||||
paths. Regression coverage lives in `test_skill_usage_signals.py`,
|
||||
`test_skill_view_fast_path.py`, and `skill-invocation.test.ts`.
|
||||
|
||||
## Cold agent construction (2026-10-30)
|
||||
|
||||
`runtime/runs/worker.py` dispatches opted-in synchronous factories through
|
||||
@@ -549,7 +571,10 @@ handoff replaces the foreground lease with the durable job occupancy. There is
|
||||
no per-user pool. Admission is serialized by a database gate row, and the cap
|
||||
is enforced at acquire, init, every model-producing run, and background-job
|
||||
start. Full pools return HTTP 409; an enabled gate with missing storage or a
|
||||
missing session id fails closed. The switch applies on the next admission
|
||||
missing session id fails closed. Foreground leases last ``lease_minutes``
|
||||
(default 5, range 1–60) and are renewed by the browser heartbeat; changing the
|
||||
setting applies on the next admission or heartbeat and never extends
|
||||
``max_hold_minutes``. The switch applies on the next admission
|
||||
without a restart. Position and eight-department roundtables are not counted.
|
||||
|
||||
Roundtable backend jobs use a database unique active-dedupe key plus a leased
|
||||
@@ -837,7 +862,7 @@ FastAPI application on port 8001 with health checks at `GET|HEAD /health`, `/api
|
||||
| **Task Deep-link Threads** (`/api/task-deeplink-threads`) | Dedicated shared history index for the `3qfx` / `rwfx` / `xdfx` single-agent task workspaces. `GET /?task_id=&go_path=&limit=` performs an indexed `(task_id, go_path)` lookup in `task_deeplink_threads` and joins `threads_meta` by `thread_id` for the current title/status/timestamps; LangGraph checkpoints remain the source of truth for messages. Thread metadata carrying `taskRecordId + taskGoPath` is dual-written atomically by both SQL and memory thread stores and deleted with the thread. `3qfx/rwfx` use the task id as `taskRecordId`; `xdfx` uses the original action id while retaining the resolved real task id in `metadata.taskId`. `thread_type=task_deeplink` keeps these rows out of general recent chats; explicit `taskId` searches still opt out of that exclusion for compatibility. Alembic `20261019_01` is schema-only and intentionally does **not** backfill legacy task threads. Frontend hook: `core/threads/use-task-deeplink-threads.ts`. Tests: `packages/harness/tests/test_task_deeplink_threads.py`, `packages/harness/tests/test_thread_meta_task_lookup.py`. |
|
||||
| **Threads** (`/api/threads/{id}`) | `DELETE /` - remove DeerFlow-managed local thread data after LangGraph thread deletion; unexpected failures are logged server-side and return a generic 500 detail |
|
||||
| **Threads search** (`POST /threads/search`, LangGraph-compat) | Conversation listing. **System threads are excluded by default**: rows whose `metadata.system` is truthy (scheduler runs, roundtable workers) or whose `thread_type` is a known system type (`task-analysis` seat runs included; older seat rows are also matched by `task_analysis_seat`) never crowd the user's list; a caller whose `metadata` filter explicitly references `thread_type`/`system` (e.g. studio notebooks) opts out of the exclusion. New `query` field = case-insensitive title (`display_name`) substring search, used by the chats page's server-side pagination. `POST /threads/count` takes the same request body (limit/offset ignored) and returns `{total}` under identical filtering/exclusion semantics ? powers the chats page's ??/??? display without fetching rows (`ThreadMetaStore.count`). `ThreadMetaStore.search` gained `exclude_system`/`query` params; JSON-blob filters batch-scan until the requested `limit`/`offset` window is full (so pagination over a heavily-filtered set never under-fills), with a `thread_id` tie-breaker on the `updated_at DESC` ordering for stable OFFSET paging. Tests: `tests/test_thread_meta_search.py` |
|
||||
| **Artifacts** (`/api/threads/{id}/artifacts`, `/api/artifact-library`, `/api/strategy-project-artifacts/{id}/download`) | `GET /{path}` streams thread artifacts; active content types (`text/html`, `application/xhtml+xml`, `image/svg+xml`) are always forced as download attachments to reduce XSS risk; `?download=true` still forces download for other file types. `GET /api/threads/{id}/artifact-preview?path=` returns bounded text, using streaming statistics plus deterministic head/middle/tail samples above the database threshold. `GET /api/artifact-library` combines every current-user normal thread's authoritative `outputs/` files with completed strategy-selection syntheses projected from the owner-scoped `parallel_agent_tasks.messages` snapshot. Strategy items use `source_type=strategy`, carry `strategy_project_id` / `strategy_name` / `strategy_stale`, and explicitly distinguish `strategy_source_kind=strategy_selection` from an `analysis_project_mode=strategy` thread (`analysis_project`); virtual items also expose `download_url`, so clients never infer routing from sentinel thread/path values. Search/source filters cover both. `workflowStale=true` keeps the last completed historical synthesis visible and downloadable. The dedicated strategy download route revalidates current-user ownership and snapshot completion and serves Markdown without pretending the virtual item is a thread artifact. Uploads and image/audio/video media remain excluded. Library metadata is persisted in `artifact_library_items`; list/search/filter/count/pagination read only this user-scoped SQL index. A generation-fenced `artifact_library_sync_states` lease schedules low-concurrency filesystem/task reconciliation in the background on first/stale reads or `refresh=true`, keeps the last successful snapshot visible during refresh/failure, and reports `sync_status` / `syncing` / `indexed_at` / `sync_error` to the client. Files themselves remain authoritative on disk and are never copied into the database. |
|
||||
| **Artifacts** (`/api/threads/{id}/artifacts`, `/api/artifact-library`, `/api/strategy-project-artifacts/{id}/download`) | `GET /{path}` streams thread artifacts; active content types (`text/html`, `application/xhtml+xml`, `image/svg+xml`) are always forced as download attachments to reduce XSS risk; `?download=true` still forces download for other file types. HTML/XHTML additionally accepts `offline_bundle=true`: it returns `{stem}-离线包.zip` with `index.html`, the referenced trusted Gateway runtime/image dependencies rewritten under `assets/`, a manifest/README and relevant third-party licenses; public view-share files support the same query. The builder never fetches arbitrary remote URLs, and records remaining Leaflet tile/user-supplied external URLs in the manifest. `GET /api/threads/{id}/artifact-preview?path=` returns bounded text, using streaming statistics plus deterministic head/middle/tail samples above the database threshold. `GET /api/artifact-library` combines every current-user normal thread's authoritative `outputs/` files with completed strategy-selection syntheses projected from the owner-scoped `parallel_agent_tasks.messages` snapshot. Strategy items use `source_type=strategy`, carry `strategy_project_id` / `strategy_name` / `strategy_stale`, and explicitly distinguish `strategy_source_kind=strategy_selection` from an `analysis_project_mode=strategy` thread (`analysis_project`); virtual items also expose `download_url`, so clients never infer routing from sentinel thread/path values. Search/source filters cover both. `workflowStale=true` keeps the last completed historical synthesis visible and downloadable. The dedicated strategy download route revalidates current-user ownership and snapshot completion and serves Markdown without pretending the virtual item is a thread artifact. Uploads and image/audio/video media remain excluded. Library metadata is persisted in `artifact_library_items`; list/search/filter/count/pagination read only this user-scoped SQL index. A generation-fenced `artifact_library_sync_states` lease schedules low-concurrency filesystem/task reconciliation in the background on first/stale reads or `refresh=true`, keeps the last successful snapshot visible during refresh/failure, and reports `sync_status` / `syncing` / `indexed_at` / `sync_error` to the client. Files themselves remain authoritative on disk and are never copied into the database. |
|
||||
| **Word export** (`POST /api/writing/export/docx`) | Shared Markdown → DOCX generator used by conversation, artifact, scheduled-task, Deep Research, and AI-writing download surfaces. `app/gateway/word_export.py` builds OOXML with no Python conversion dependency: A4 portrait, 3.7/3.5/2.8/2.6 cm margins, real multilevel heading numbering (`一、` / `(一)` / `1.`), two-character first-line indent on heading levels 1–3, formal body/table styles, page numbers beginning at 1 with odd pages left-aligned and even pages right-aligned, and embedded `app/gateway/assets/fonts/方正小标宋简体.ttf`. Before numbering it removes complete manual heading prefixes (including `2.1` / `2.1.1`) and drops Markdown horizontal rules from Word output. The ordinary-Q&A Lead Agent can emit the matching Markdown heading forms and avoid unordered bullet lists when the admin enables `prompt_prefix.ordinary_qa_markdown_format_enabled` in `system_settings.json`; the switch defaults off, while writing setup, writing mode, notebook, scheduled runs, and SOUL-driven custom agents keep their independent prompts. The font loader validates its internal family, SHA-256, and OpenType embedding permission (`OS/2.fsType`) before export. Tests: `tests/test_word_export.py`, `tests/test_es_query_routing_prompt.py`. |
|
||||
| **Deep Research** (`/api/deep-research`) | Durable, user-owned research sessions/jobs with replayable SSE events and hidden-thread artifacts. `basic`/`quick` use the compact runner; `detailed` creates bounded subtopics, searches/writes sections concurrently, and assembles a report; `deep` recursively searches follow-up questions under a deterministic breadth/depth query budget. `multi_agent` is a LangGraph 1.x editor/researcher/writer/reviewer graph: its initial plan emits `awaiting_input`, the recorder stores the interrupt and releases the lease, and `POST /jobs/{id}/resume` rebuilds the graph from the persisted approved/revised plan. A bounded `custom_outline` is frozen into the session; headings/list entries deterministically supply the detailed and multi-agent plan, and the shared writer receives it only as a guarded content constraint. The compact writer validates generated Markdown against that frozen selection: `fixed` requires every non-placeholder heading with the same level and order, while `adaptive` retries only when no core template heading survives. That correction shares the single existing retry budget (never more than two writer calls), and its deterministic fallback is outline-shaped as well. When `custom_outline` is empty (the workbench default — the user did not pick a report structure), chat collection first calls `POST /sessions/{id}/intent-outline` after the collector turn ends: the chosen model plans a Markdown skeleton from the topic plus collected materials, the outline is frozen into the session snapshot and shown in the「开始撰写」form for editing. If that step is skipped or fails, `basic`/`quick` still call `generate_intent_outline` at write time, emit `plan_created` (`source: intent`), then write through the same shared writer; generation failure is a recoverable `intent_outline_fallback` warning and does not abort the report. Completed reports support owner-scoped follow-up (`GET /sessions/{id}/messages`, `POST /sessions/{id}/chat`): context is only the current report, selected sources and recent messages; source-id citations are persisted, while `allow_new_research=true` is explicitly rejected. Owners may change that evidence set only after the job stops via `PATCH /sessions/{id}/sources/{source_id}`; this applies to future follow-ups rather than rewriting a completed report. Optional report illustrations are gated by `config.yaml -> deep_research.image_generation`: the Harness `OpenAICompatibleImageProvider` requires base64 output, the shared runner step writes only bounded `research-image-01..04.(png|jpg|webp)` artifacts and Markdown uses private `deep-research://` links. `GET /sessions/{id}/artifacts/{name}` checks session ownership before serving an image; an unavailable provider yields a warning but never fails the text report. Runners live in `packages/harness/deerflow/agents/deep_research/runners/`, may never import `app.*`, and use only the `AdapterBundle`. |
|
||||
| **Gateway auth** | Owner-scoped Deep Research routes await the platform's asynchronous `get_current_user` resolver before they read or write persistence, ensuring each session and job operation receives a concrete user ID. Deep Research artifacts are always resolved from a whitelisted filename via `/mnt/user-data/outputs/<name>` before mapping to a host path, preserving the sandbox guard on native Windows and Linux hosts. |
|
||||
|
||||
Reference in new issue
Block a user