fix: improve import, evidence indexing and material-scoped grading

Preserve document revisions and evidence, harden indexing and export behavior, add explicit material selection and direct-folder import, validate model JSON schemas with safe error messages, and retain student selection while loading scoring data.

backend/wisegrade/agent_tools.py

@@ -11,7 +11,7 @@ from .actions import prepare, require_scope
 from .evidence import CONTENT_ALLOWED, STRUCTURE_ALLOWED
 from .exports import STATUS_LABELS, batch_projects, page_type_label, project_result
 from .knowledge_pages import page_links
-from .models import (Conversation, Course, CourseVersion, IndexTask, KnowledgeChunk, KnowledgeDocument,
+from .models import (Conversation, Course, CourseVersion, IndexTask, KnowledgeChunk, KnowledgeDocument, KnowledgePage,
                      Project, RubricVersion, ScoringBatch, Student, SubmissionFile)
 from .pages import toc_entries
 from .rag import retrieve
@@ -233,7 +233,8 @@ def _search(db, version_id, project_id, query, *, public_only=False, scopes=None
                           "source_role": "structure" if "structure" in scopes else "content",
                           # Stable identity so an answer can cite exactly what it used.
                           "citation_id": f"chunk:{chunk['chunk_id']}",
-                          **links})
+                          "answer_url": f"{links['url']}#chunk-{chunk['chunk_id']}",
+                          "url": links["url"], "image_url": links["image_url"]})
     return {"citations": citations, "found": bool(citations), "scopes": list(scopes)}
 
 
@@ -271,9 +272,10 @@ def search_structure(db, convo, args, _user):
             "section": chunk.get("section") or "", "block_type": chunk.get("block_type") or "body",
             "source_role": "structure",
             "citation_id": f"chunk:{chunk['chunk_id']}",
+            "answer_url": f"{links['url']}#chunk-{chunk['chunk_id']}",
             "toc_entries": toc_entries([{"kind": "toc", "text": chunk["text"]}])[:40]
                            if page_type == "toc" else [],
-            **links})
+            "url": links["url"], "image_url": links["image_url"]})
     return {"citations": citations, "found": bool(citations), "scopes": ["structure"],
             "note": "这些是结构或目录信息，只能说明章节安排，不能证明章节内容。"}
 
@@ -281,16 +283,18 @@ def search_structure(db, convo, args, _user):
 def get_document_pages(db, convo, args, _user):
     """List a document's pages with page type, so a caller can navigate precisely."""
     _document(db, convo, args.document_id)
-    rows = db.scalars(select(KnowledgeChunk).where(KnowledgeChunk.document_id == args.document_id)
-                      .order_by(KnowledgeChunk.page, KnowledgeChunk.id)).all()
+    rows = db.scalars(select(KnowledgePage).where(KnowledgePage.document_id == args.document_id)
+                      .order_by(KnowledgePage.page)).all()
     pages: dict[int, dict] = {}
     for chunk in rows:
         entry = pages.setdefault(chunk.page, {"page": chunk.page, "page_type": chunk.page_type,
                                               "page_type_label": page_type_label(chunk.page_type),
                                               "chapter": chunk.chapter, "section": chunk.section,
                                               "block_types": []})
-        if chunk.block_type not in entry["block_types"]:
-            entry["block_types"].append(chunk.block_type)
+        for block in (chunk.classification or {}).get("blocks", []):
+            kind = block.get("kind")
+            if kind and kind not in entry["block_types"]:
+                entry["block_types"].append(kind)
         if chunk.section:
             entry["section"] = chunk.section
     return {"document_id": args.document_id, "count": len(pages),
@@ -300,9 +304,9 @@ def get_document_pages(db, convo, args, _user):
 def search_document(db, convo, args, _user):
     """Content search restricted to one document, under the same page-type policy."""
     document = _document(db, convo, args.document_id)
-    chunks = retrieve(db, course_version_id=document.course_version_id, project_id=document.project_id or 0,
+    chunks = retrieve(db, course_version_id=document.course_version_id, project_id=document.project_id,
                       query=args.query, limit=6, include_public=False,
-                      allowed_page_types=sorted(CONTENT_ALLOWED), substantive_only=True)
+                      allowed_page_types=sorted(CONTENT_ALLOWED), substantive_only=True, document_id=document.id)
     citations = []
     for chunk in chunks:
         if chunk["document_id"] != document.id:
@@ -313,7 +317,9 @@ def search_document(db, convo, args, _user):
                           "project_id": chunk["project_id"], "page_type": chunk.get("page_type"),
                           "page_type_label": page_type_label(chunk.get("page_type")),
                           "section": chunk.get("section") or "", "source_role": "content",
-                          "citation_id": f"chunk:{chunk['chunk_id']}", **links})
+                          "citation_id": f"chunk:{chunk['chunk_id']}",
+                          "answer_url": f"{links['url']}#chunk-{chunk['chunk_id']}",
+                          "url": links["url"], "image_url": links["image_url"]})
     return {"citations": citations, "found": bool(citations), "scopes": ["content"]}
 
 
@@ -402,7 +408,7 @@ def scores(db, convo, args, _user):
                                   "target_label": str(evidence.get("target_label") or "")[:120],
                                   "historical": bool(evidence.get("historical")),
                                   "source": "historical_score_evidence" if evidence.get("historical") else "score_evidence",
-                                  **links, "score_url": url})
+                                  "url": links["url"], "image_url": links["image_url"], "score_url": url})
     if citations:
         # Scoring quotations are never presented as report body evidence in an answer.
         for citation in citations: