feat: add persistent chat agent and indexed batch workflows

backend/wisegrade/scoring.py

@@ -1,4 +1,6 @@
 from concurrent.futures import ThreadPoolExecutor, as_completed
+from contextlib import contextmanager
+import fcntl
 
 from sqlalchemy import select, update
 
@@ -13,7 +15,25 @@ from .storage import secure_path, sha256
 from .settings_store import client_for_batch
 
 
+@contextmanager
+def file_index_lock(file_id: int):
+    root = get_settings().processed_path
+    root.mkdir(parents=True, exist_ok=True)
+    with (root / f"file-{file_id}.lock").open("a+b") as handle:
+        fcntl.flock(handle, fcntl.LOCK_EX)
+        try:
+            yield
+        finally:
+            fcntl.flock(handle, fcntl.LOCK_UN)
+
+
 def parse_submission(db, file: SubmissionFile, *, embedder=None):
+    with file_index_lock(file.id):
+        db.refresh(file)
+        return _parse_submission_locked(db, file, embedder=embedder)
+
+
+def _parse_submission_locked(db, file: SubmissionFile, *, embedder=None):
     path = secure_path(file.relative_path)
     if sha256(path) != file.sha256:
         file.parse_status, file.parse_error = "changed", "源文件已变化，请重新扫描并确认导入"
@@ -59,6 +79,8 @@ def _project_facts(db, project, course_snapshot, client, *, retriever):
                                   category=category, query="项目名称 目标 指标 硬件 软件 实验 数据 成本 结论", limit=3, include_public=False))
     if not snippets:
         return {}
+    if client is None:
+        raise ModelError("未配置或无法连接评分模型")
     facts = client.json_call(prompts["facts"], {"evidence": snippets}, FactResult).model_dump()
     from .models import Student
     student = db.get(Student, project.student_id)
@@ -102,6 +124,8 @@ def _score_criterion(db, batch, project, criterion, client, *, retriever):
         score.status, score.error = "unscorable", "无可检索的材料证据"
         db.commit()
         return score
+    if client is None:
+        raise ModelError("未配置或无法连接评分模型")
     page_paths = {page["page_number"]: page.get("rendered_image_path") for page in ready[0].parsed["pages"]}
     images = [page_paths[page] for page in dict.fromkeys(chunk["page"] for chunk in chunks[:2]) if page_paths.get(page)]
     public_context = retriever(db, course_version_id=batch.course_version_id, project_id=project.id,
@@ -140,7 +164,10 @@ def _run_project(batch_id, project_id, session_factory, client_factory, embedder
     with session_factory() as db:
         batch = db.get(ScoringBatch, batch_id)
         project = db.get(Project, project_id)
-        client = client_factory(db, batch)
+        try:
+            client = client_factory(db, batch)
+        except Exception:
+            client = None
         files = db.scalars(select(SubmissionFile).where(SubmissionFile.project_id == project.id)).all()
         for file in files:
             if file.recognition_status == "recognized":
@@ -178,16 +205,11 @@ def run_batch(batch_id: int, *, session_factory=SessionLocal, client_factory=cli
         batch = db.get(ScoringBatch, batch_id)
         if not batch:
             raise ValueError("评分批次不存在")
-        project_ids = db.scalars(select(Project.id).where(Project.course_version_id == batch.course_version_id).order_by(Project.id)).all()
+        project_ids = batch.project_ids if batch.project_ids is not None else db.scalars(
+            select(Project.id).where(Project.course_version_id == batch.course_version_id).order_by(Project.id)).all()
         criteria = batch.rubric_snapshot["criteria"]
         batch.status, batch.progress_total, batch.progress_done, batch.finished_at = "running", len(project_ids) * len(criteria), 0, None
         db.commit()
-        try:
-            client_factory(db, batch)
-        except Exception as exc:
-            batch.status, batch.error, batch.finished_at = "failed", str(exc), now()
-            db.commit()
-            return
         failures = 0
         with ThreadPoolExecutor(max_workers=max(1, int(batch.model_config_snapshot.get("concurrency", 1)))) as pool:
             futures = [pool.submit(_run_project, batch_id, project_id, session_factory, client_factory, embedder, retriever) for project_id in project_ids]