fix: improve OCR indexing and evidence review

backend/wisegrade/scoring.py

@@ -8,7 +8,7 @@ from .llm import ConsistencyResult, FactResult, ModelError, ScoreResult, validat
 from .models import (CriterionScore, KnowledgeDocument, Project, ScoreEvidence, ScoringBatch,
                      SubmissionFile, now)
 from .parsing import parse_document
-from .rag import ingest, retrieve
+from .rag import INDEX_VERSION, ingest, retrieve
 from .storage import secure_path, sha256
 from .settings_store import client_for_batch
 
@@ -20,6 +20,18 @@ def parse_submission(db, file: SubmissionFile, *, embedder=None):
         db.commit()
         raise ValueError(file.parse_error)
     if file.parse_status == "ready" and file.parsed:
+        document = db.scalar(select(KnowledgeDocument).where(KnowledgeDocument.submission_file_id == file.id))
+        if not document or document.source_hash != file.sha256 or document.index_version != INDEX_VERSION or document.status != "ready":
+            project = db.get(Project, file.project_id)
+            kwargs = {"embedder": embedder} if embedder else {}
+            try:
+                ingest(db, course_version_id=project.course_version_id, project_id=project.id,
+                       submission_file_id=file.id, title=path.name, category=file.category,
+                       source_hash=file.sha256, pages=file.parsed["pages"], **kwargs)
+            except Exception as exc:
+                file.parse_status, file.parse_error = "failed", str(exc)[:1000]
+                db.commit()
+                raise
         return file.parsed
     settings = get_settings()
     try:
@@ -99,7 +111,16 @@ def _score_criterion(db, batch, project, criterion, client, *, retriever):
                "required_output": {"criterion_id": "string", "score": "number", "max_score": "number", "reason": "string",
                                    "evidence": [{"chunk_id": "integer", "page": "integer", "quote": "exact substring"}],
                                    "missing_evidence": ["string"], "suggestion": "string", "confidence": "0..1"}}
-    result = validate_score(client.json_call(batch.course_snapshot["prompts"]["score"], payload, ScoreResult, images=images), criterion, chunks)
+    prompt = (batch.course_snapshot["prompts"]["score"] +
+              " 证据quote必须从所引用chunk_id的text逐字复制连续片段，保留原文标点和换行；page必须等于该片段的page。不要改写、缩写或拼接引文。")
+    for attempt in range(2):
+        try:
+            result = validate_score(client.json_call(prompt, payload, ScoreResult, images=images), criterion, chunks)
+            break
+        except ModelError:
+            if attempt:
+                raise
+            prompt += " 上次回答的证据未通过原文和页码校验；请重新选择片段并逐字复制quote。"
     score.model_score, score.model_comment, score.confidence = result.score, result.reason, result.confidence
     score.missing_evidence, score.suggestion, score.status, score.error = result.missing_evidence, result.suggestion, "scored", ""
     for evidence in db.scalars(select(ScoreEvidence).where(ScoreEvidence.score_id == score.id)).all():
@@ -122,7 +143,7 @@ def _run_project(batch_id, project_id, session_factory, client_factory, embedder
         client = client_factory(db, batch)
         files = db.scalars(select(SubmissionFile).where(SubmissionFile.project_id == project.id)).all()
         for file in files:
-            if file.recognition_status == "recognized" and file.parse_status != "ready":
+            if file.recognition_status == "recognized":
                 try:
                     parse_submission(db, file, embedder=embedder)
                 except Exception:
@@ -159,7 +180,7 @@ def run_batch(batch_id: int, *, session_factory=SessionLocal, client_factory=cli
             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()
         criteria = batch.rubric_snapshot["criteria"]
-        batch.status, batch.progress_total, batch.progress_done = "running", len(project_ids) * len(criteria), 0
+        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)