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/tests/test_story_route_oral_invariant.py

@@ -90,13 +90,18 @@ def test_single_segment_decide_receives_only_combined_text_not_evidence() -> Non
         patch(
             "app.features.memoir.story_pipeline_sync.MemoirImageSettings",
         ) as mis,
+        patch(
+            "app.tasks.story_title_tasks.generate_story_title_after_create.delay",
+        ),
+        patch(
+            "app.features.memoir.story_pipeline_sync.refresh_chapter_evidence_snapshot_with_retry_sync",
+        ),
     ):
         route_agent_mock.plan_batch.return_value = None
         route_agent_mock.decide.side_effect = decide_capture
 
         na = MagicMock()
         nac.return_value = na
-        na.generate_title.return_value = "章节标题"
         na.generate_narrative.return_value = '{"paragraphs": [{"content": "叙事正文段落足够长用于测试合并逻辑避免触发过短回退"}]}'
 
         mock_story = MagicMock()
@@ -200,13 +205,18 @@ def test_decide_receives_only_same_stage_story_candidates() -> None:
         patch(
             "app.features.memoir.story_pipeline_sync.MemoirImageSettings",
         ) as mis,
+        patch(
+            "app.tasks.story_title_tasks.generate_story_title_after_create.delay",
+        ),
+        patch(
+            "app.features.memoir.story_pipeline_sync.refresh_chapter_evidence_snapshot_with_retry_sync",
+        ),
     ):
         route_agent_mock.plan_batch.return_value = None
         route_agent_mock.decide.side_effect = decide_capture
 
         na = MagicMock()
         nac.return_value = na
-        na.generate_title.return_value = "章节标题"
         na.generate_narrative.return_value = '{"paragraphs": [{"content": "叙事正文段落足够长用于测试合并逻辑避免触发过短回退"}]}'
 
         mock_story = MagicMock()