fix: 批量任务明细写完再排队（CREATING 状态）

`create_job` 先把任务行以 QUEUED 入库（引擎立刻可见），再逐条登记明细（扫描媒体库时 500+ 条要数秒）；引擎轮询到的快照可能还没包含剩余明细，收尾时"无未结束明细"检查也看不到它们，于是把任务误标 COMPLETED，剩余视频永远不再被处理。 - 任务行改以 `CREATING` 入库，明细全部登记完才置 QUEUED（引擎只取 QUEUED，看不到半成品）；登记中途异常置 FAILED 并把异常交给路由层。 - 启动时把上一进程遗留的 CREATING 统一置 FAILED（`fail_creating_batch_jobs`），避免明细写一半被热重载/强杀后留下看不见的残留任务。 - 回归测试：明细每写一条就问一次引擎队列（写入过程中取不到任务）；中途失败记 FAILED；启动清理遗留 CREATING。
2026-09-18 22:23:39 +08:00
parent 3f4478523e
commit 7a2dee9b64
5 changed files with 159 additions and 24 deletions
@@ -748,3 +748,88 @@ def test_worker_clears_stale_keep_model_flag_before_stage(tmp_path: Path, monkey
    # 验证结果：prep（非 LLM）看不到残留标志；translate（LLM 阶段）才写入；
    # post（非 LLM）不再看到它。
    assert flag_trace == [("prep", False), ("translate", True), ("post", False)]
+
+
+def test_job_hidden_from_engine_until_details_written(tmp_path: Path, monkeypatch) -> None:
+    """建任务期间任务对引擎不可见：明细写完前不被拾起，避免半成品被标完成。
+
+    曾因任务行先入库、524 条明细后写，引擎在明细写一半时拾起任务、收尾时快照
+    里没有剩余明细，把任务误标 COMPLETED（视频永远不再被处理）。
+    """
+    # 数据：3 个待处理视频的媒体库。
+    folder = tmp_path / "videos"
+    for name in ("a.mp4", "b.mp4", "c.mp4"):
+        _make_video(folder / name)
+    db = _published_db(tmp_path)
+    probes: list[str | None] = []
+    original = db.create_batch_video
+
+    def _probe_after_insert(item: dict) -> None:
+        """每写完一条明细，立刻问一次引擎队列（模拟轮询线程的拾取时机）。"""
+        original(item)
+        picked = db.next_queued_batch_job()
+        probes.append(picked["id"] if picked else None)
+
+    monkeypatch.setattr(db, "create_batch_video", _probe_after_insert)
+
+    # 测试过程
+    job_id = create_job(db, str(folder), "wf", recursive=False)
+
+    # 验证结果：写入过程中引擎始终取不到任务；写完后才是 QUEUED 且明细完整。
+    assert probes == [None, None, None]
+    job = db.get_batch_job(job_id)
+    assert job["status"] == "QUEUED"
+    assert job["total"] == 3
+    assert len(db.list_batch_videos(job_id)) == 3
+    assert db.next_queued_batch_job()["id"] == job_id
+
+
+def test_create_job_marks_failed_when_detail_insert_breaks(tmp_path: Path, monkeypatch) -> None:
+    """明细写入中途失败时任务记 FAILED 并留下错误，不产生看不见的残留任务。"""
+    # 数据：2 个视频，第二条明细写入时抛异常。
+    folder = tmp_path / "videos"
+    for name in ("a.mp4", "b.mp4"):
+        _make_video(folder / name)
+    db = _published_db(tmp_path)
+    original = db.create_batch_video
+    calls = {"n": 0}
+
+    def _fail_second(item: dict) -> None:
+        calls["n"] += 1
+        if calls["n"] == 2:
+            raise RuntimeError("磁盘写满")
+        original(item)
+
+    monkeypatch.setattr(db, "create_batch_video", _fail_second)
+
+    # 测试过程 + 验证结果：异常继续抛出，任务可被观察到且为 FAILED。
+    with pytest.raises(RuntimeError):
+        create_job(db, str(folder), "wf", recursive=False)
+    job = db.list_batch_jobs(limit=10)[0]
+    assert job["status"] == "FAILED"
+    assert "磁盘写满" in (job["error"] or "")
+    assert db.next_queued_batch_job() is None
+
+
+def test_worker_start_fails_leftover_creating_job(tmp_path: Path) -> None:
+    """进程中断留下的 CREATING 任务在引擎启动时记为 FAILED，不静默残留。"""
+    # 数据：一条只登记到一半的任务（模拟明细写入中途进程被杀/热重载）。
+    db = _published_db(tmp_path)
+    db.create_batch_job({
+        "id": "batch_halfway", "folder_path": "/videos", "workflow_id": "wf",
+        "recursive": 0, "status": "CREATING", "progress": 0, "total": 0, "done": 0,
+        "failed": 0, "current_video": None, "error": None,
+        "created_at": "2026-09-18T00:00:00+00:00", "updated_at": "2026-09-18T00:00:00+00:00",
+    })
+    worker = BatchWorker(db, interval_seconds=999)
+
+    # 测试过程
+    worker.start()
+    try:
+        # 验证结果：任务变为可见的 FAILED，且不会被引擎当排队任务拾起。
+        job = db.get_batch_job("batch_halfway")
+        assert job["status"] == "FAILED"
+        assert "中断" in (job["error"] or "")
+        assert db.next_queued_batch_job() is None
+    finally:
+        worker.stop()