feat: separate contents, abstract and body evidence

backend/wisegrade/chat_api.py

@@ -1,6 +1,8 @@
 """Persistent teacher conversations and SSE agent orchestration."""
 import json
+import re
 import time
+import unicodedata
 from concurrent.futures import ThreadPoolExecutor
 from datetime import timedelta
 from threading import Lock
@@ -170,7 +172,8 @@ def _safe_arguments(arguments):
     if not isinstance(arguments, dict):
         return {}
     numeric = {"course_version_id", "batch_id", "project_id", "score_id", "task_id",
-               "rubric_version_id", "score", "offset", "limit", "project_offset", "criterion_offset"}
+               "rubric_version_id", "score", "offset", "limit", "project_offset", "criterion_offset",
+               "document_id"}
     text_limits = {"query": 300, "criterion_id": 100, "format": 20, "status": 30,
                    "student_no": 50, "relative_dir": 500}
     result = {}
@@ -219,26 +222,58 @@ def _result_summary(result):
 def _safe_citation(item):
     if not isinstance(item, dict):
         return None
-    return {key: value[:limit] if isinstance(value, str) else value for key, limit in
-            (("title", 200), ("quote", 500), ("url", 500), ("image_url", 500), ("score_url", 500))
+    # The evidence-policy fields travel with the citation so the interface can tell a
+    # report body page from a contents page, and an answer's source from a historical
+    # scoring quotation.
+    label_limits = (("title", 200), ("quote", 500), ("url", 500), ("image_url", 500), ("score_url", 500),
+                    ("citation_id", 80), ("page_type", 20), ("page_type_label", 30),
+                    ("source_role", 20), ("source", 40), ("usage", 60), ("target_label", 120))
+    return {key: value[:limit] if isinstance(value, str) else value for key, limit in label_limits
             if isinstance((value := item.get(key)), str)} | {
-            key: item[key] for key in ("chunk_id", "document_id", "page", "project_id")
-            if isinstance(item.get(key), int)}
+            key: item[key] for key in ("chunk_id", "document_id", "page", "project_id", "historical")
+            if isinstance(item.get(key), (int, bool)) and not isinstance(item.get(key), str)}
 
 
-def _answer_citations(items):
-    """Keep each distinct source passage, including later tool calls and pages cited by the answer."""
+def _comparable_text(value):
+    return "".join(char for char in unicodedata.normalize("NFKC", str(value or "")) if not char.isspace())
+
+
+def _cited_pages(content: str) -> set[int]:
+    """Page and slide numbers the answer actually refers to."""
+    numbers = set()
+    for match in re.finditer(r"第\s*(\d{1,4})\s*(?:页|张幻灯片|页幻灯片)", str(content or "")):
+        numbers.add(int(match.group(1)))
+    return numbers
+
+
+def _answer_citations(items, content: str = ""):
+    """Attach only the citations the answer actually used.
+
+    Collecting every tool hit would list material the answer never drew on. A passage is
+    kept when the answer quotes it, or when the answer names the page it sits on. When
+    the answer names no page and quotes nothing, no citation is attached: the answer made
+    no specific evidential claim.
+    """
     seen = set()
     citations = []
+    answer = _comparable_text(content)
+    pages = _cited_pages(content)
     for item in items:
         safe = _safe_citation(item)
         if not safe:
             continue
         key = (safe.get("document_id"), safe.get("chunk_id"), safe.get("title"),
                safe.get("page"), safe.get("quote"), safe.get("url"), safe.get("score_url"))
-        if key not in seen:
-            seen.add(key)
-            citations.append(safe)
+        if key in seen:
+            continue
+        quote = _comparable_text(safe.get("quote"))
+        used = bool(quote) and len(quote) >= 6 and quote[:80] in answer
+        if not used and pages and isinstance(safe.get("page"), int):
+            used = safe["page"] in pages
+        if not used:
+            continue
+        seen.add(key)
+        citations.append(safe)
     return citations
 
 
@@ -326,7 +361,7 @@ def _run_agent(factory, conversation_id, run_id, user_text):
                     content = reply.get("content")
                     if not isinstance(content, str) or not content.strip():
                         raise ModelError("会话模型未返回文字或工具调用")
-                    answer_citations = _answer_citations(citations)
+                    answer_citations = _answer_citations(citations, content)
                     db.add(ChatMessage(conversation_id=conversation_id, role="assistant", content=content,
                                        citations=answer_citations, tool_calls=used))
                     run.status, run.finished_at = "completed", now()