feat: taskId 深链会商按任务隔离草稿 + 第三步自动结构化流程图

- 深链 ?taskId=&goPath=*-A 透传 taskId 进会商，按 taskId 隔离存取草稿（一个 taskId 多条、可新建）；
  后端新增 GET /api/roundtable-drafts/by-task/{id} 列表 + RoundtableJobRepository.status_map_by_drafts 富化。
- 第三步生成 md 报告后自动结构化输出流程图（仅 taskId 模式）：有报告基于报告、无报告基于各席位交付，
  整段内联数据来源逐条抽取；层级优先用业务链总控提示词写明的层级，否则用 stages 的 goal。
- 流程图节点加 group(层级名)标签 + detail(条目名称+理由)；强 prompt 压制 coordinatorPrompt 报告锚定，
  禁阶段编号节点；FLOW_STRUCTURE_RULE 精确画法（根=任务、每层每条成节点、按对应关系串分支、排除汇总段落）。
- flow-graph 解析容错：JSON.parse 失败退回正则逐字段抽取，兼容裸换行/尾逗号，避免节点被整体丢弃。
- 修：重开第二步后第三步基于新一轮分析重新生成（复位 step3 闸门 + 中断旧三流）。

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

offline-backend-20260512/backend/CLAUDE.md

@@ -245,7 +245,7 @@ FastAPI application on port 8001 with health check at `GET /health`. Set `GATEWA
 | **Runs** (`/api/runs`) | `POST /stream` - stateless run + SSE; `POST /wait` - stateless run + block; `GET /{rid}/messages` - paginated messages by run_id `{data, has_more}` (cursor: `after_seq`/`before_seq`); `GET /{rid}/feedback` - list feedback by run_id |
 | **Thread Shares** (`/api/thread-shares`) | Per-conversation sharing with two modes (`thread_shares.mode`). **`import`**: `POST /` `{thread_id, mode}` - create (or reuse) a revocable share code; `GET /{code}/preview` + `POST /{code}/import` - copy that conversation into the caller's account (fresh `thread_id` via `app/gateway/thread_copy.py` + new `threads_meta` row + `user-data` copy; dedup on `metadata.shared_origin`). **`view`**: a public, read-only static page ? see Public Shares below. Both modes: `GET /` - list my codes; `DELETE /{code}` - revoke. |
 | **Public Shares** (`/api/public/shares`) | **Unauthenticated** (the `/api/public/` prefix is whitelisted in `auth_middleware._PUBLIC_PATH_PREFIXES`). `GET /{code}` - read-only conversation snapshot (title + serialized messages + artifacts) for a `view`-mode share; messages are read straight from the latest checkpoint. `GET /{code}/files/{path}` - serves a file referenced by that conversation (images, Markdown, text, PDF, ?) so the shared page's links are openable; path resolution is confined to the owner's thread directory. Active content (`text/html`, `application/xhtml+xml`, `image/svg+xml`) is forced to download (`_public_share_disposition`); everything else is served inline. Missing/revoked/non-`view` codes all return 404. |
-| **Roundtable Drafts** (`/api/roundtable-drafts`) | Per-user persistence for the roundtable-planning page (replaces the old browser `localStorage`). `GET /` - list drafts (lightweight meta); `POST /` - create; `GET/PUT/DELETE /{id}` - full read / partial update / delete. A draft = one full session (Step 1 intent + Step 2 roundtable), step snapshots stored as JSON in `PortableLongText`. Recommendation history bound to a draft: `GET /{id}/recommendations` - list newest-first; `POST /{id}/recommendations` - append one run (objective/status/rationale/picks/candidates). Backed by `deerflow.persistence.roundtable_drafts` (tables `roundtable_drafts`, `roundtable_recommend_history`); store wired in `deps.py` as `app.state.roundtable_draft_store`. |
+| **Roundtable Drafts** (`/api/roundtable-drafts`) | Per-user persistence for the roundtable-planning page (replaces the old browser `localStorage`). `GET /` - list drafts (lightweight meta); `POST /` - create; `GET/PUT/DELETE /{id}` - full read / partial update / delete. **External-task binding (`task_id`)**: drafts carry an optional `task_id` (deep-link / 无界 embed); task-bound drafts are **shared** (the store ignores `user_id` for them, so a task's drafts span users). `GET /by-task/{task_id}/latest` - newest draft for a task (回显最新一条); `GET /by-task/{task_id}` - **all** drafts for a task, newest-first (taskId-mode history dropdown: 一个 taskId 多条记录), enriched with the latest background-job status per draft via `RoundtableJobRepository.status_map_by_drafts`. A draft = one full session (Step 1 intent + Step 2 roundtable), step snapshots stored as JSON in `PortableLongText`. Recommendation history bound to a draft: `GET /{id}/recommendations` - list newest-first; `POST /{id}/recommendations` - append one run (objective/status/rationale/picks/candidates). Backed by `deerflow.persistence.roundtable_drafts` (tables `roundtable_drafts`, `roundtable_recommend_history`); store wired in `deps.py` as `app.state.roundtable_draft_store`. Tests: `tests/test_roundtable_drafts_by_task.py`. |
 | **Roundtable Draft Shares** (`/api/roundtable-draft-shares`) | Per-draft sharing for the roundtable-planning page, mirroring Thread Shares but the shared resource is a `roundtable_drafts` row. Two modes (`roundtable_draft_shares.mode`). **`import`**: `POST /` `{draft_id, mode}` - create (or reuse) a revocable code; `GET /{code}/preview` + `POST /{code}/import` - copy that draft (step1/2/3) into the caller's account under a deterministic per-(code,recipient) id (`imp_<sha1>` ? re-import is a no-op). **`view`**: a public, read-only result page ? see Public Roundtable Shares. Both: `GET /` - list my codes; `DELETE /{code}` - revoke. Backed by `deerflow.persistence.roundtable_draft_shares` (table `roundtable_draft_shares`, migration `20260606_01`); store wired in `deps.py` as `app.state.roundtable_draft_share_store`. Tests: `tests/test_roundtable_draft_shares.py`. |
 | **Public Roundtable Shares** (`/api/public/roundtable-shares`) | **Unauthenticated** (`/api/public/` whitelisted). `GET /{code}` - read-only snapshot for a `view`-mode draft share: returns the Step 3??????report HTML (`step3.html`, a self-contained document) + title/summary/`has_report`. The frontend renders it in a sandboxed `iframe` (no `allow-scripts`) at `#/roundtable-share/<code>`. Missing/revoked/non-`view` codes all return 404. |
 | **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"`. |

offline-backend-20260512/backend/app/gateway/routers/_roundtable_seed_assets/roundtable-summary/SOUL.md

@@ -74,6 +74,8 @@
 - 每个节点字段：`id`（短唯一串 n1/n2…）、`label`（≤12 字）、`type`、`detail`（一两句说明，弹窗展示）、`from`（**前驱节点列表**，可空；分支边可写成 `{"id":"n3","label":"可行"}` 给边加标签）；
 - `type` 只能取：`start`（开始）/ `end`（结束）/ `stage`（阶段）/ `task`（任务动作）/ `decision`（判断分支）/ `risk`（风险点）/ `deliverable`（交付物）/ `role`（角色席位）——前端按类型着不同颜色；
 - **`nodes` 必须按流程先后顺序排列**，且每个节点的 `from` 只引用**前面已出现**的节点 id——前端解析到一个节点就画一个节点和它的连线；
+- **节点 label 命名约束（重要）**：label 必须是该层级 / 步骤对应的**具体概念或实体名**（如 目的 / 行为体 / 驱动因素，或它们下面的具体条目），**绝不能**写成「阶段1 / 阶段2 / 第N阶段 / 阶段几」这类阶段编号或泛称，也不要把「阶段」「环节」本身当成节点；不要在节点里塞阶段名称等与层级无关的内容；
+- **按业务链条层级组织**：当本轮 prompt 给了「业务链层级」（如 任务→目的→行为体→驱动因素）时，以「任务」为根节点按该层级自上而下逐层展开（每层放该层级下提炼出的具体节点）；总控编排提示里明确写了层级 / 结构时，以总控提示词为准（最高优先级）；
 - 节点 6–20 个为宜；flow-json 块**只放对话回复末尾**，不要写进 .md 报告文件；
 - 用户没有要求结构化 / 流程图时，**不要**输出该块。
 

offline-backend-20260512/backend/app/gateway/routers/roundtable_drafts.py

@@ -194,6 +194,32 @@ async def get_latest_draft_by_task(request: Request, task_id: str) -> DraftRespo
     return DraftResponse(**row)
 
 
+@router.get("/by-task/{task_id}", response_model=DraftListResponse)
+async def list_drafts_by_task(request: Request, task_id: str) -> DraftListResponse:
+    """按外部任务 id 列出该任务全部草稿（轻量 meta，newest first，**不按 user 分权**）。
+
+    taskId 深链模式下历史下拉用：一个 taskId 可有多条会商记录；同 `list_drafts`
+    一样用最近后台作业状态富化（job store 缺失/失败时静默退化为无状态）。
+    """
+    store = _get_store(request)
+    rows = await store.list_drafts_by_task(task_id)
+    job_store = getattr(request.app.state, "roundtable_job_store", None)
+    if job_store is not None and rows:
+        try:
+            status_map = await job_store.status_map_by_drafts([r.get("id") for r in rows])
+        except AttributeError:
+            status_map = {}
+        except Exception:  # noqa: BLE001 — 富化失败不能拖垮列表
+            logger.warning("roundtable draft by-task list: job status enrichment failed", exc_info=True)
+            status_map = {}
+        for r in rows:
+            info = status_map.get(r.get("id"))
+            if info:
+                r["status"] = info.get("status")
+                r["job_id"] = info.get("jobId")
+    return DraftListResponse(drafts=[DraftMetaResponse(**r) for r in rows])
+
+
 @router.get("/{draft_id}", response_model=DraftResponse)
 async def get_draft(request: Request, draft_id: str) -> DraftResponse:
     store = _get_store(request)

offline-backend-20260512/backend/packages/harness/deerflow/persistence/roundtable_drafts/sql.py

@@ -100,6 +100,21 @@ class RoundtableDraftRepository:
             row = result.scalars().first()
             return self._draft_to_dict(row) if row is not None else None
 
+    async def list_drafts_by_task(self, task_id: str, *, limit: int = 100) -> list[dict[str, Any]]:
+        """按外部任务 id 列出全部草稿（轻量 meta，newest first，**忽略 user_id** 不分权）。
+
+        taskId 深链模式下历史下拉用：一个 taskId 可有多条会商记录。
+        """
+        stmt = (
+            select(RoundtableDraftRow)
+            .where(RoundtableDraftRow.task_id == task_id)
+            .order_by(RoundtableDraftRow.updated_at.desc())
+            .limit(limit)
+        )
+        async with self._sf() as session:
+            result = await session.execute(stmt)
+            return [self._draft_to_meta(row) for row in result.scalars()]
+
     async def create_draft(self, user_id: str, data: dict[str, Any]) -> dict[str, Any]:
         now = datetime.now(UTC)
         row = RoundtableDraftRow(

offline-backend-20260512/backend/packages/harness/deerflow/persistence/roundtable_jobs/sql.py

@@ -236,6 +236,36 @@ class RoundtableJobRepository:
                 out[draft_id] = {"jobId": job_id, "status": status}
         return out
 
+    async def status_map_by_drafts(
+        self,
+        draft_ids: list[str],
+        *,
+        limit: int = 400,
+    ) -> dict[str, dict[str, str]]:
+        """``{draft_id: {"jobId": ..., "status": ...}}`` for the latest job per draft.
+
+        Like :meth:`status_map_by_user` but filtered by an explicit draft-id list
+        instead of by owner — used by the taskId-mode history dropdown, where a
+        task's drafts may span multiple users (task-bound drafts are shared).
+        """
+        ids = [d for d in draft_ids if d]
+        if not ids:
+            return {}
+        stmt = (
+            select(RoundtableJobRow.id, RoundtableJobRow.draft_id, RoundtableJobRow.status)
+            .where(RoundtableJobRow.draft_id.in_(ids))
+            .order_by(RoundtableJobRow.updated_at.desc())
+            .limit(limit)
+        )
+        out: dict[str, dict[str, str]] = {}
+        async with self._sf() as session:
+            result = await session.execute(stmt)
+            for job_id, draft_id, status in result.all():
+                if draft_id is None or draft_id in out:
+                    continue
+                out[draft_id] = {"jobId": job_id, "status": status}
+        return out
+
     # ── delete / cleanup ─────────────────────────────────────────────────────
 
     async def delete(