feat(ai写作): 大纲整理可见化 + 检索词结合大纲 + 素材/大纲阶段关思考

- 草稿确认卡：「给出修改意见」「让编辑继续审核」移到「确认定稿」上方。
- 大纲整理阶段文案：用户自带大纲时显示「整理你的大纲」而非「规划大纲」
  （OutlineStreamingView / 骨架屏 / 状态栏，按 request.userOutline 切换）。
- 素材收集专家：用户自带大纲时把大纲原文带入检索词生成，让关键词结合写作
  意图覆盖各章节主题（_keyword_outline_section，agent + legacy 两路）。
- 素材收集（检索词/排序）与大纲整理/生成阶段强制关闭思考
  （create_chat_model force_disable_thinking：GLM thinking.disabled +
  Qwen/vLLM enable_thinking=false），关不掉的模型仍由 ThinkTagParser 把
  <think> 分流到思考框正常展示。disable_thinking 串入
  _utils.get_model/llm_json 与 _agent_runner.stream/run_writing_agent。
- 含草稿「局部修改」WIP（writer_draft 只重写命中章节）及外观控件改动。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

offline-backend-20260512/backend/CLAUDE.md

@@ -278,6 +278,8 @@ Seeding mirrors the roundtable pattern: verified `config.yaml` + `SOUL.md` ship
 
 **Agentic skill execution (`ai_writing.researcher_skill_agent`, default false).** By default a configured non-native skill is *not* run agent-style — the node just turns its `description` into a query for the generic search provider. With this flag on, the directed-skill branch instead runs `nodes/_skill_agent.py::run_skill_search_agent`: it injects the skill's **SKILL.md** (read from `skill.skill_file`) alongside the researcher SOUL as the system prompt, binds a `search` tool to the researcher model, and runs a bounded (`_MAX_TURNS=4`) tool-call loop so the model drives the retrieval per the skill's instructions; the `SearchResult`s the tool returns are harvested directly as materials (no fuzzy text extraction). Requires a tool-calling model; if the model can't tool-call (returns no `tool_calls`) or the agent yields nothing, `_execute_skill` falls back to the legacy description→query search so materials are never empty. The built-in `knowledge-base-search` native concurrent path is unchanged. Tests: `tests/test_ai_writing_skill_agent.py`.
 
+**Targeted user revision (局部修改 — 只改命中章节).** When the user submits a free-text 修改意见 on the draft-confirm card (`action == "user_revise"`), `writer_draft_node` no longer always rewrites the whole article section-by-section. Before the full-rewrite loop it tries `_targeted_user_revision` (`nodes/writer_draft.py`): `_split_draft_sections` parses the previous `current_draft.full_markdown` into `(article_title, [(section_title, body)], references_block)` (level-1 `#` title, level-2 `##` sections, trailing `## 参考文献` pulled out and kept verbatim), then `_detect_revision_scope` runs a small `llm_json` classifier (prompts `DRAFT_REVISE_SCOPE_{SYSTEM,USER}`) that maps the note to the section indices it targets ("第一段/开头/引言"→0, "结尾/结论"→last, by title/topic, etc.). **Only the hit sections are rewritten** via `_stream_revise_section` (prompt `DRAFT_REVISE_SECTION_USER`, streamed as `draft_chunk` so the user watches the edit); **every unhit section is preserved byte-for-byte** and emitted to the stream as one full-text `draft_chunk` + `is_section_done` so the frontend's `streamingDraftSections` rebuilds the complete article (it was reset to `[]` on entering `revising`). The classifier returns `whole_article=true` (整体性意见 like 「整体语气更正式」/「全文都改」, or any structure-changing ask) → `_detect_revision_scope` yields `None` → `_targeted_user_revision` returns `None` → the node **falls back to the existing whole-article rewrite** (which still runs `_revise_outline_with_notes` for title/structure changes). Also falls back when there is no prior draft, an empty note, or scope detection errors. Editor-review revisions (`accept_review`) are unaffected — they keep the holistic rewrite. Reassembly preserves the article title + section structure and re-appends the original references block; word count is computed on the body (excluding references), matching the main path. Tests: `tests/test_ai_writing_targeted_revision.py`.
+
 **Background suspend (后台挂起).** A writing session can be handed off to the server to auto-drive the remaining flow to finalize, surviving page leave / refresh / account switch. `POST /api/ai-writing/sessions/{id}/background` (owner-checked, idempotent) starts `AIWritingJobExecutor` (`app/gateway/ai_writing_job_executor.py`), wired in `deps.py` as `app.state.ai_writing_job_executor`. The executor **drives the same `ai_writing` graph in-process** — it builds `make_ai_writing_graph()`, attaches the shared `app.state.checkpointer` (the very saver the runtime worker uses, so it continues the real thread state the frontend already wrote), sets the owning user via `set_current_user`, and loops `aget_state` → `ainvoke(Command(resume=…))` until `status==done`. **Auto-action per interrupt**: material/outline confirm → `confirm`; section_help → every blocked section `loose` (continue with general knowledge, never re-loop to research); draft_confirm → `to_editor` until reviewed, then `finalize` (on pass, or when `revision_count >= max_revisions`); review_confirm → `accept_review` (revise & re-review until pass or budget exhausted, then forced finalize). To avoid racing a still-running runtime worker (suspend mid-node), the driver **waits for an actionable state** (`_wait_for_actionable`): it only acts when the graph is at an interrupt / done, or when the checkpoint stops advancing (no worker → abandoned/restart). No new table — the graph checkpoint + `ai_writing_sessions` already hold all state; `status="background"` marks 挂起中 (surfaced in the history dropdown), nodes write `draft`/`review_result`/`status=done` as usual, so the user reopens the finished article from history. Per-user concurrency cap `AI_WRITING_BACKGROUND_SLOTS_PER_USER` (default 2, same SQLite-lock rationale as the roundtable executor). Startup `reconcile` (in `deps.py`) relaunches drivers for sessions left `background` after a restart (`AIWritingSessionRepository.list_by_status`). **Progress flowchart popup**: `GET /api/ai-writing/sessions/{id}/progress` (owner-checked) reads the graph checkpoint via `executor.get_progress` and derives a canonical pipeline `stage` key (`intent/research/material_confirm/outline/outline_confirm/draft/draft_confirm/review/done`, from the pending interrupt's `pause_point` or `snapshot.next` node) + `note` (素材不足求助 / 编辑打回) + review progress + `isRunning`. Frontend: 「后台挂起」 button + auto-suspend on route unmount / `beforeunload` (`AIWritingPanel.tsx`, `suspendAIWritingToBackground[Keepalive]` in `api/ai-writing-sessions.ts`); 挂起中 badge in `AIWritingHistoryDropdown.tsx`, and **clicking a 挂起中 history record opens a flowchart dialog** (`AIWritingFlowDialog.tsx` polls `getAIWritingProgress` every 2.5s, renders the fixed vertical pipeline `AIWritingFlowChart.tsx` lit by the live `stage`) so the user sees how far the background run has gotten without reopening/taking over the session. **Transcript consistency**: the rich history timeline (`AIWritingHistoryView` → `AIWritingTimeline`) replays `transcript = {progressEvents, completedInterventions}`, normally assembled+saved client-side. A background run has no client, so the executor rebuilds it at the end (`_save_transcript`/`_build_transcript_from_checkpoint`) **entirely from the final checkpoint** — both `progressEvents` and `completedInterventions` are derived from the same set of `resumed` events (every pause-resume emits exactly one), so they are always 1:1 aligned. For each `resumed`: classify its message → `(pausePoint, action)` (`_classify_resumed`, matched against `graph.py`'s resume messages), insert an `await_user` (with the pause prompt) before it, and build a **rich** intervention card enriched from final state (material_confirm→`materials`, outline_confirm→`outline`, draft_confirm→`draftTitle`/`draftWordCount`/`reviewResult`, review_confirm→`reviewResult`); `materials_ready` is inserted before the first material-confirm. (Earlier code merged the frontend's pre-suspend `completedInterventions` with auto ones and aligned by index — but the frontend's last save can predate its most recent decision, so the counts drifted and cards rendered off-by-one with empty data; deriving everything from the checkpoint root-fixes both.) Raw (snake_case) events **and** intervention data are normalized on load by the **exported** `normalizeProgressDict` / `normalize{Material,Outline,ReviewResult}` (idempotent on already-camelCase live transcripts — one normalize path for both sources), so reopening a background-completed session shows the same cards as a frontend-driven one. Tests: `tests/test_ai_writing_background.py`.
 
 ### Admin Leaderboard Snapshots (`/api/admin/users/leaderboard*`)