feat: 深度研究支持独立新报告与原文改写,并完善沙箱、模型管理与全文改写

新报告不再覆盖当前文件卡片,写入时打开沙箱;步骤条仅在改写原文时位于卡片上方。同时补齐改写本地回退、模型管理与会商第三步相关改动。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-08-21 21:46:04 +08:00
1 parent 11f928bc95
commit a5a9c952e8
63 files changed
+4113 -929

No files matched your search

+55 -3
View File
@@ -81,7 +81,7 @@ Per-thread isolated execution with virtual path translation:
- **Skills path**: `/mnt/skills` → `deer-flow/skills/` directory
- **Skills loading**: Recursively discovers nested `SKILL.md` files under `skills/{public,custom}` and preserves nested container paths
- **Conditional WeKnora LLMWiki**: a non-empty `llmwiki.weknora.api_base_url` enables the DeerFlow-native WeKnora BFF and UI; an empty address preserves the existing LLMWiki page. WeKnora remains independently deployed and owns its database, Redis, storage, parsers and models. DeerFlow keeps only the API/admin addresses, user/publication mappings, agent knowledge-base bindings and per-conversation selections; it stores and sends no WeKnora credential, so the endpoint must be restricted to a trusted network and allow DeerFlow traffic. Owners publish directly to the public LLMWiki without an approval queue for ordinary bases; the system-owned conversation-deposit base is always published, shared by all users, excluded from My Knowledge, immutable through user/admin detail operations, and recognized by both its reserved name and `system` owner. An existing same-name remote mapping is adopted in place as the system deposit so its mapping id and document links stay valid. Its user-facing knowledge-base description and generated document metadata use the `cmzs` brand; list/detail reads synchronize stale remote descriptions, while conversation-deposit search results, source previews and embedded-detail JSON rewrite legacy brand text to `cmzs`. Deposit requests must reference a thread accessible to the current account. Personal knowledge-base lists are scoped to the current DeerFlow account even for admins, while frontend LLMWiki query caches also include the active account id so switching accounts cannot reuse another account's list/detail data. Admins remain the only role that sees the WeKnora connection-config tab. Knowledge cards open a dedicated WeKnora-style detail route: Wiki-enabled bases default to Wiki, then documents and graph; standard bases hide Wiki and default to documents. Writable ordinary knowledge-base details expose a native multi-file upload action that submits files sequentially and reports aggregate success/failure; read-only public bases and the system deposit base do not. It supports file/URL/manual-Markdown imports, Wiki page browsing, document preview, real parsed chunks and Wiki graph nodes/edges. New chats use a compact WeKnora-style searchable/grouped multi-select inside the composer, while agent create/edit pages bind spaces through an inline panel. A single proxy service identity means DeerFlow users are isolated logically while their WeKnora entities share that identity's workspace. The read-only `llmwiki_search` tool reauthorizes the current DeerFlow user on every call and renders credential-free source previews; source previews prefer cleaned Wiki/LLMWiki text when a retrieved chunk maps to a Wiki page, with raw chunks as the fallback. The detail page first creates a signed iframe session through the normal DeerFlow API auth path, then points the iframe directly at the proxied WeKnora `/platform/...` route using the signed `deerflow_weknora_embed` cookie; global auth/CSRF bypass is limited to those signed iframe proxy requests, and HTTPS cookie attributes honor `X-Forwarded-Proto` behind reverse proxies. The iframe proxy keeps WeKnora's root-relative `/platform`, `/assets`, `/locales`, and `/api/v1/*` paths, but is registered last through `llmwiki.proxy_router` so it cannot intercept first-party Gateway APIs such as `POST /api/v1/auth/login/username`. See [docs/LLMWIKI_WEKNORA_INTEGRATION_ZH.md](docs/LLMWIKI_WEKNORA_INTEGRATION_ZH.md).
- **Enterprise Research workbench**: `/api/enterprise-research/tasks` is an independent, user-scoped evidence workbench; it never enters or changes `/api/deep-research`. DeerFlow persists each task's topic, generated queries, selected DeerFlow knowledge-base mapping IDs, collection state, and a bounded/deduplicated WeKnora evidence snapshot. Collection reuses the LLMWiki BFF's mapping-based authorization, so browsers never send a remote WeKnora ID or credential and can retrieve only sources in their own or published knowledge bases. Once collection finishes, the task can persist an editable Markdown research plan and a validated subset of its snapshot sources; the optional AI-plan endpoint improves that outline with a selected DeerFlow model without retrieving new material. Persistent `report-jobs` support initial writing, full-report rewrite, and report-only follow-up. Each job freezes its plan, source subset, model/style/length controls and before-image, streams Markdown/reasoning through DeerFlow's standard model adapter, persists the latest draft for reconnect, and commits only a successful non-follow-up report back to the owning task. Startup recovery uses compare-and-set requeue/claim, while cancellation and completion are conditional transitions so another process cannot overwrite a cancelled job. Markdown/Word delivery, clickable evidence citations, before/after comparison and reversible rewrite versions are served from the same task history without modifying an existing Deep Research report.
- **Enterprise Research workbench (temporarily disabled)**: the independent `/api/enterprise-research` router, its report executor, and its ORM table registration are intentionally inactive. The implementation remains in the repository, but startup does not create or alter `enterprise_research_tasks` or `enterprise_research_report_jobs`; this keeps the active Deep Research workflow independent of the paused workbench and avoids MySQL schema errors.
- **Embedded WeKnora detail chrome**: the proxy hides WeKnora's application sidebar (`.main > .aside_box`) and expands the detail outlet to the full iframe width, while preserving the Wiki page's own index/navigation panel.
- **Embedded WeKnora knowledge-base switching**: the original breadcrumb picker works inside the iframe, but lists only the signed-in user's own and published knowledge bases. Every switch is reauthorized through DeerFlow and receives a fresh short-lived iframe session, so it never exposes the upstream service-admin knowledge-base list.
- **Prefixed WeKnora deployment**: the frontend may be published under a separate prefix such as `/magentweb`, while embedded WeKnora detail traffic is served by the Gateway under `/deerflow`. The Gateway rewrites HTML root assets, WeKnora API URLs, redirects, and Vite dynamic dependency maps so page assets stay under `/deerflow`; the prefixed proxy routes must be registered before the unprefixed fallback. The signed embed cookie covers `/deerflow`, and auth/CSRF recognition includes all supported static directories.
@@ -153,8 +153,8 @@ FastAPI application providing REST endpoints for frontend integration:
| `GET /api/threads/{id}/uploads/list` | List uploaded files |
| `DELETE /api/threads/{id}` | Delete DeerFlow-managed local thread data after LangGraph thread deletion; unexpected failures are logged server-side and return a generic 500 detail |
| `GET /api/threads/{id}/artifacts/{path}` | Serve generated artifacts |
| `GET/POST /api/deep-research/*` | Durable Deep Research sessions and jobs. `quick`/`basic` run the compact report flow; `detailed` plans subtopics and writes independent sections; `deep` recursively investigates bounded follow-up branches. All modes reuse DeerFlow's configured material provider, LLM factory, hidden-thread artifacts, and SSE event log. Deep Research session/job/event/source/message writes serialise their rows in the writer transaction, rather than doing a post-commit ORM refresh or readback; this prevents MySQL read/write-splitting replica lag from failing “start writing”, dispatcher claim, report persistence, or follow-up history. A report is written to the session and confirmed before its Job becomes `completed`; an unconfirmed write is retried and never exposed as a false completion. Retrying an already-created queued job re-nudges the dispatcher, recovering an interrupted HTTP response without creating a second report. If progress-event persistence, durable replay, or live fan-out is briefly unavailable, the worker/stream logs the degradation and continues or reconnects rather than failing the whole job. Optional report illustrations use a separately configured OpenAI-compatible image endpoint and are served only through the owning session's authenticated artifact route. |
| `GET/POST/PUT/DELETE /api/enterprise-research/tasks*` | Independent enterprise-research evidence tasks. The authenticated DeerFlow account owns the task and all saved evidence snapshots; collection calls the configured WeKnora service only after resolving selected mapping IDs through normal visibility and permission checks. `POST /{id}/plan/draft` creates an editable deterministic plan, `POST /{id}/plan/ai` optionally improves it with the configured model, and `PUT /{id}/plan` persists its Markdown plus a source subset revalidated against that task's snapshot. `POST /{id}/report-jobs` freezes those inputs and accepts `initial` / `rewrite` / `followup` plus model, style and length controls; the job list is durable history, its SSE route replays the latest persisted draft before live Markdown/reasoning deltas, `/cancel` safely stops an active job, and `/restore` creates another reversible version while restoring a completed rewrite's before-image. It deliberately cannot change existing Deep Research reports or knowledge bases. |
| `GET/POST /api/deep-research/*` | Durable Deep Research sessions and jobs. `quick`/`basic` run the compact report flow; `detailed` plans subtopics and writes independent sections; `deep` recursively investigates bounded follow-up branches. All modes reuse DeerFlow's configured material provider, LLM factory, hidden-thread artifacts, and SSE event log. Deep Research session/job/event/source/message writes serialise their rows in the writer transaction, rather than doing a post-commit ORM refresh or readback; this prevents MySQL read/write-splitting replica lag from failing “start writing”, dispatcher claim, report persistence, or follow-up history. Whole-document artifact/report rewrites likewise create their reversible version snapshots from writer-local ORM data and never refresh after commit, so replica lag cannot restore an otherwise successful rewrite. A report is written to the session and confirmed before its Job becomes `completed`; an unconfirmed write is retried and never exposed as a false completion. Retrying an already-created queued job re-nudges the dispatcher, recovering an interrupted HTTP response without creating a second report. If progress-event persistence, durable replay, or live fan-out is briefly unavailable, the worker/stream logs the degradation and continues or reconnects rather than failing the whole job. Whole-report rewrite accepts an optional `reportOutline` Markdown template; the durable job persists it and applies it as the chapter structure constraint. Optional report illustrations use a separately configured OpenAI-compatible image endpoint and are served only through the owning session's authenticated artifact route. |
| `/api/enterprise-research/*` | Temporarily disabled. Its router and persistence initialization are not registered, so these endpoints return 404 and no enterprise-research tables are created or migrated during startup. |
| `POST /api/ai-writing/sample/extract` | Extract text from Word/PDF/Markdown/TXT samples for AI-writing imitation mode |
| `POST /cop/saveSuperiorTask` | TaskCOP compatibility API (DeerFlow Bearer/session authentication required): create a situation-overview task with a sequential four-digit id (`0001`, `0002`, ...) and return the legacy `{state, msg, data}` envelope |
| `POST /api/taskcop/import/tasks` | TaskCOP compatibility API (authenticated): import tasks from a JSON array or `tasks`/`records` envelope; every row's supplied `id`/`taskId` is authoritative and a duplicate id completely replaces the stored task |
@@ -234,6 +234,28 @@ per-user concurrency slot.
Saved `draft` sessions do not consume a concurrency slot; the two-job limit
only applies to sessions with a `running` or `awaiting_input` durable job.
Whole-report rewrite builds its requirement plan locally from the selected
style and instruction, publishes that plan immediately, and then opens only
one model stream for the actual Markdown writer. This avoids making users wait
for a separate model-thinking/planning pass before sandbox output begins.
`POST /api/deep-research/sessions/{id}/report-variants` is the structural
regeneration boundary: it copies the completed report and selected evidence
into a new session (including both saved `[来源:id]` and legacy streamed
`[[source:id]]` citation markers remapped to the cloned ids). The following
durable writer is explicitly queued with `operation=generate`: it does not send
the inherited report to the model as text to edit, and instead writes a fresh
report from the complete selected evidence set plus the newly confirmed
outline. Model reasoning remains a live SSE event before the first Markdown
token. New output uses display-ready `[来源:id]` citations; validation repairs
only unique near-complete `drs_src_*` ids (for example a provider-truncated
suffix) and still rejects genuinely unknown evidence ids.
The report-only model stream requests an 8192-token completion budget so a
normal multi-section report and its reference list do not stop at the common
4096-token provider default; malformed trailing citation syntax is rejected
rather than committed as a partial document.
The original report therefore remains independently available in history even
if the new report is cancelled or fails.
#### Optional report illustrations
DeerFlow's stock configuration includes image recognition but no image-generation
@@ -625,6 +647,12 @@ the rest of the visual tokens; the optional `overrides` object only exposes
must use the `custom-theme-` prefix. Disabled or removed custom themes cannot
remain the system default and automatically fall back to `light`.
Compact top-bar shortcuts use the same appearance endpoint. In addition to
login and theme query parameters, each shortcut may include ordered keyless
`path` parameters. The frontend resolves each selected login field and appends
it as an encoded path segment (including inside a `#/…` hash route); password
remains an ordinary login query parameter with the key `password`.
---
## Technology Stack
@@ -739,3 +767,27 @@ without deleting the audit row. DeerFlow stores only the artifact reference
(`threadId` + sandbox `path`, plus the optional session/node/name/MIME fields),
never the Markdown body and never a task-system delivery. Continue to preview
the file through the existing thread-artifact endpoint.
## Document rewrite fallback
Whole-document rewrite commits the artifact/report before it attempts to store
the optional reversible before-image. If that version-snapshot write fails, the
rewritten content remains available and Gateway logs the exception; it never
restores the original solely because undo history is unavailable. The durable
result marks `versionSnapshotFailed`, allowing the sandbox to enable its normal
manual-save action without showing the user an error notification.
The optional rewrite-history hydration endpoints scope results to the
authenticated job owner. They deliberately return an empty list rather than
performing a second thread-owner check, so a legacy guest/SSO display alias
cannot make an otherwise usable sandbox report fail with a history-only 404.
Artifact and rewrite path resolution uses the persisted thread creator's
directory when metadata exists, after the route's normal ownership check. This
prevents a missing request context from incorrectly looking under
`users/default` and returning 404 for an existing sandbox file.
The final rewrite commit uses a deliberately short sibling temporary filename,
which keeps long Windows artifact paths below the path-length limit. It also
recreates a missing `outputs` parent before retrying, so transient
sandbox-directory recreation cannot discard a completed rewrite.