feat(evaluation): session catalog, user export import, and eval web UI

- Extend evaluation API: schemas, router, repo, admin and execution services
- Improve user export markdown importer; add fixtures and importer tests
- Session catalog repo/service updates; internal app wiring and docs
- Add internal-eval.sh helper; refresh app-eval-web (App, styles, Vite)

api/app/features/evaluation/execution_service.py

@@ -23,6 +23,17 @@ from app.features.evaluation.models import EvalCase, EvalRun, EvalVersion
 
 logger = get_logger(__name__)
 
+_MAX_JUDGE_MARKDOWN_CHARS = 20_000
+_MAX_EVAL_CHAPTERS = 30
+_MAX_EVAL_STORIES = 40
+
+
+def _clip_md_for_judge(text: str, max_chars: int = _MAX_JUDGE_MARKDOWN_CHARS) -> str:
+    s = (text or "").strip()
+    if len(s) <= max_chars:
+        return s
+    return f"{s[:max_chars]}\n\n…（已截断供评审）"
+
 
 def _composite(
     conv: float | None, mem: float | None, weights: dict[str, Any] | None
@@ -149,7 +160,66 @@ async def execute_eval_run(
 
     memoir_md = simple_memoir_from_transcript(utterances, replies)
     mem_out = await judge.judge_memoir(memoir_markdown=memoir_md)
-    mem_total = mem_out.total_score if mem_out else None
+
+    chapter_entries: list[dict[str, Any]] = []
+    story_entries: list[dict[str, Any]] = []
+    uid = (case.source_user_id or "").strip()
+    if uid:
+        from app.features.memoir.repo import get_chapters_for_memoir_list
+        from app.features.story.repo import get_stories_for_user
+
+        try:
+            chapters = await get_chapters_for_memoir_list(
+                uid, db, active_only=True, is_new_only=None
+            )
+            for ch in chapters[:_MAX_EVAL_CHAPTERS]:
+                body = (ch.canonical_markdown or "").strip()
+                if not body:
+                    continue
+                md = f"# 章节：{ch.title}\n\n{_clip_md_for_judge(body)}"
+                cj = await judge.judge_memoir(memoir_markdown=md)
+                chapter_entries.append(
+                    {
+                        "id": ch.id,
+                        "title": ch.title,
+                        "order_index": ch.order_index,
+                        "judge": cj.model_dump() if cj else None,
+                    }
+                )
+        except Exception as e:
+            logger.warning("eval chapter judges skipped: {}", e)
+
+        try:
+            stories = await get_stories_for_user(db, uid, status="active")
+            for st in stories[:_MAX_EVAL_STORIES]:
+                body = (st.canonical_markdown or "").strip()
+                if not body:
+                    continue
+                md = f"# 故事：{st.title}\n\n{_clip_md_for_judge(body)}"
+                sj = await judge.judge_memoir(memoir_markdown=md)
+                story_entries.append(
+                    {
+                        "id": st.id,
+                        "title": st.title,
+                        "stage": st.stage,
+                        "judge": sj.model_dump() if sj else None,
+                    }
+                )
+        except Exception as e:
+            logger.warning("eval story judges skipped: {}", e)
+
+    mem_parts: list[float] = []
+    if mem_out is not None:
+        mem_parts.append(float(mem_out.total_score))
+    for row in chapter_entries:
+        j = row.get("judge")
+        if isinstance(j, dict) and j.get("total_score") is not None:
+            mem_parts.append(float(j["total_score"]))
+    for row in story_entries:
+        j = row.get("judge")
+        if isinstance(j, dict) and j.get("total_score") is not None:
+            mem_parts.append(float(j["total_score"]))
+    mem_total = sum(mem_parts) / len(mem_parts) if mem_parts else None
 
     exp = await eval_repo.get_experiment(db, run.experiment_id)
     weights = exp.composite_weights_json if exp else None
@@ -158,6 +228,8 @@ async def execute_eval_run(
     bundle: dict[str, Any] = {
         "conversation_judge": conv_out.model_dump() if conv_out else None,
         "memoir_judge": mem_out.model_dump() if mem_out else None,
+        "chapters": chapter_entries,
+        "stories": story_entries,
     }
     await eval_repo.update_run(
         db,