feat(v2): S1c′ 既有上传入口的批量摄取——S1 首次端到端闭环

T00/04 §4.2 要求的"既有材料上传入口扩展"：**不建立平行上传 API**。
POST /documents 增加可选 batch_id / item_id 表单字段；不传时行为完全不变。

- api/prescreen.ingest_into_batch：清单核对 + 状态回写，仍走既有
  ProjectAssistantService.upload()，故解析、同哈希复用原件、pending_candidates、
  data_revision、mark_stale 等既有行为一字未改
- 服务端**重算** sha256 与大小，不信任客户端清单；不符则条目 failed + 422
- 返回体保持 **document 形状**（既有前端读 body.id / body.candidates），
  批次状态作为附加字段 import_batch 给出
- 拒绝重复摄入已解析条目（409）、已取消批次（409）、不在清单中的文件（404）

闭环已成立：登记批次 → 上传 → 解析定位 → 冲突检测 → 人工裁定 → 进事实。

测试：test_prescreen_api.py 新增 BatchIngestTests 10 项（含闭环与既有路径回归）。
全量 235 项 OK（225 → 235）；scripts/verify.py 9/9 PASS。
真实 app 冒烟 claude_use/T02/smoke_s1.py 15/15 PASS。

**测试隔离缺陷已修**：BatchIngestTests 初版只 patch 了 prescreen 的 service 工厂，
未 patch api.project_assistant.service，导致不传 batch_id 的上传落到**真实 v2 数据库**。
已补 patch，并清空 v2 数据根从干净状态重跑验证。

Co-Authored-By: Claude Code <noreply@anthropic.com>

backend/api/project_assistant.py

@@ -1,7 +1,7 @@
 """Unified project API. Every resource read/write derives scope from its project."""
 import base64
 from urllib.parse import quote
-from fastapi import APIRouter, Depends, HTTPException, Request, UploadFile, File
+from fastapi import APIRouter, Depends, Form, HTTPException, Request, UploadFile, File
 from fastapi.responses import Response
 from pydantic import BaseModel, Field, ConfigDict
 from api.risk_agent_access import authorize, check_project
@@ -221,7 +221,9 @@ def legacy(project_id: str, kind: str, legacy_id: str, request: Request):
 
 
 @router.post("/projects/{project_id}/documents", status_code=201)
-async def upload(project_id: str, request: Request, file: UploadFile = File(...)):
+async def upload(project_id: str, request: Request, file: UploadFile = File(...),
+                 batch_id: str | None = Form(default=None),
+                 item_id: str | None = Form(default=None)):
     guard(request, project_id)
     from services.assistant_materials import LIMIT
     try:
@@ -230,6 +232,13 @@ async def upload(project_id: str, request: Request, file: UploadFile = File(...)
         await file.close()
     # Parsing is synchronous CPU work; do not block the ASGI event loop.
     from starlette.concurrency import run_in_threadpool
+    # S1：传入 batch_id 时走批量清单核对与状态回写（api/prescreen.ingest_into_batch）。
+    # 不传时行为与既有完全一致——前端与既有调用方都不受影响。
+    if batch_id:
+        from api.prescreen import ingest_into_batch
+        return await run_in_threadpool(lambda: translate(lambda: ingest_into_batch(
+            project_id, file.filename or "material", content,
+            request.state.identity["id"], batch_id, item_id)))
     return await run_in_threadpool(lambda: translate(lambda: service().upload(project_id, file.filename or "material", content, request.state.identity["id"])))