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/features/memory/llm_schemas.py

@@ -31,6 +31,13 @@ class FactsExtractionPayload(BaseModel):
     facts: list[ExtractedFactItem] = Field(default_factory=list)
 
 
+class EnrichmentPayload(BaseModel):
+    """单轮记忆富化：会话摘要 + 结构化事实（ingest 后一次 LLM 调用）。"""
+
+    summary: str = ""
+    facts: list[ExtractedFactItem] = Field(default_factory=list)
+
+
 class SessionSummaryPayload(BaseModel):
     summary: str = ""
 
@@ -85,6 +92,11 @@ def facts_payload_to_dicts(payload: FactsExtractionPayload) -> list[dict]:
     return out
 
 
+def enrichment_payload_to_fact_dicts(payload: EnrichmentPayload) -> list[dict]:
+    """将 EnrichmentPayload.facts 转为与 extract_facts 一致的字典列表。"""
+    return facts_payload_to_dicts(FactsExtractionPayload(facts=list(payload.facts)))
+
+
 def timeline_payload_to_dicts(payload: TimelineEventsPayload) -> list[dict]:
     out: list[dict] = []
     for ev in payload.events: