feat(eval): memoir A/B chapter judging and eval-web parity with dialogue

- Judge baseline excerpt and library chapter separately; build_memoir_compare_summary for gate, nine-dim and leaf deltas.

- Memoir SSE chapter payload: baseline_judge, compare_summary, baseline_judge_error.

- MemoirJudgeOutput: loose score coercion and post-validate clamp; memoir judge prompt caps from settings.

- app-eval-web: two-column MemoirScoreCard layout, MemoirCompareSummary, chapter blocks and CSS.

- Add memoir_compare_summary, log_events, celery_log_context, memoir_pipeline_progress; tests and migration 0014.

- Misc: memory/evidence and enrichment paths, task/orchestrator updates, internal-eval docs, env examples.

api/app/agents/chat/orchestrator.py

@@ -216,7 +216,7 @@ class ChatOrchestrator:
                             messages=responses, skip_tts=False, memory_retrieval_trace=None
                         )
                     except Exception as e:
-                        logger.error(f"资料收集处理失败: {e}", exc_info=True)
+                        logger.exception("资料收集处理失败: {}", e)
                         return AgentChatTurn(
                             messages=["不好意思刚才没接住，你再说一遍好吗？"],
                             skip_tts=False,

api/app/agents/memoir/batch_phase1_prep.py

@@ -6,7 +6,7 @@ from __future__ import annotations
 
 import math
 from dataclasses import dataclass
-from typing import Any, Dict, List
+from typing import Any, Callable, Dict, List
 
 from app.agents.memoir.prompts import get_batch_memoir_phase1_prep_prompt
 from app.agents.memoir.schemas import BatchPhase1LLMOutput
@@ -135,7 +135,7 @@ def _run_batch_phase1_prep_chunk_with_bisect(
         if merged.keys() != expected:
             raise ValueError(
                 "batch phase1 chunked bisect merge: segment ids do not match input"
-            )
+            ) from None
         return merged
 
 
@@ -145,6 +145,7 @@ def run_batch_phase1_prep_chunked(
     llm: Any,
     *,
     chunk_size: int,
+    on_chunk: Callable[[int, int], None] | None = None,
 ) -> Dict[str, BatchPhase1SegmentRow]:
     """
     将 segments 按 chunk_size 切片多次调用 Phase1 批处理 LLM，合并 by_id。
@@ -161,13 +162,16 @@ def run_batch_phase1_prep_chunked(
         chunk_idx = i // chunk_size + 1
         sub = segments[i : i + chunk_size]
         logger.info(
-            "event=batch_phase1_chunk chunk_idx={}/{} segment_count={} batch_path=chunked",
+            "event=batch_phase1_chunk chunk_idx={}/{} segment_count={} batch_path=chunked "
+            "msg=Phase1 批处理分块调用",
             chunk_idx,
             total_chunks,
             len(sub),
         )
         part = _run_batch_phase1_prep_chunk_with_bisect(sub, state, llm)
         merged.update(part)
+        if on_chunk is not None:
+            on_chunk(chunk_idx, total_chunks)
     expected = {str(s.id) for s in segments}
     if merged.keys() != expected:
         missing = expected - merged.keys()

api/app/agents/memoir/orchestrator.py

@@ -8,7 +8,7 @@ from __future__ import annotations
 
 import time
 from dataclasses import dataclass
-from typing import Any, Callable, Dict, List, Set, Tuple
+from typing import Any, Callable, Dict, List, Optional, Set, Tuple
 
 from app.agents.memoir.batch_phase1_prep import (
     STAGE_ALLOWED_SLOTS,
@@ -63,6 +63,7 @@ class MemoirOrchestrator:
         get_or_create_state: Callable[[], MemoirStateSchema],
         update_slot: Callable[[str, str, str, List[str]], MemoirStateSchema],
         llm_fast: Any | None = None,
+        on_phase1_chunk: Optional[Callable[[int, int], None]] = None,
     ) -> PreparedMemoirBatches:
         """
         遍历 segments：Extraction → slot 更新 → Classification → 按 category 分桶。
@@ -89,15 +90,19 @@ class MemoirOrchestrator:
                     state=state,
                     classify_extract_llm=classify_extract_llm,
                     update_slot=update_slot,
+                    on_phase1_chunk=on_phase1_chunk,
                 )
                 logger.info(
-                    "event=phase1_batch_path_used segment_count={}",
+                    "event=phase1_batch_path_used segment_count={} "
+                    "msg=Phase1 批处理 LLM 路径已使用",
                     len(segments),
                 )
                 return result
             except Exception as e:
                 logger.warning(
-                    "MemoirOrchestrator.prepare_batches batch LLM 失败，回退逐段: {}",
+                    "event=phase1_batch_path_fallback segment_count={} exc={} "
+                    "msg=Phase1 批处理失败，回退逐段",
+                    len(segments),
                     e,
                 )
 
@@ -172,6 +177,7 @@ class MemoirOrchestrator:
         state: MemoirStateSchema,
         classify_extract_llm: Any,
         update_slot: Callable[[str, str, str, List[str]], MemoirStateSchema],
+        on_phase1_chunk: Optional[Callable[[int, int], None]] = None,
     ) -> PreparedMemoirBatches:
         category_to_segments: Dict[str, List[Segment]] = {}
         segment_skip_story_ids: Set[str] = set()
@@ -182,6 +188,7 @@ class MemoirOrchestrator:
             state,
             classify_extract_llm,
             chunk_size=int(settings.memoir_phase1_batch_llm_chunk_size),
+            on_chunk=on_phase1_chunk,
         )
 
         for segment in segments:
@@ -294,6 +301,7 @@ class MemoirOrchestrator:
             llm_fast=llm_fast,
             get_or_create_state=get_or_create_state,
             update_slot=update_slot,
+            on_phase1_chunk=None,
         )
         state = prepared.state
         chapters_to_enqueue: Set[str] = set()