feat(api)!: memory single chain — async MemoryService, strict eval closure

Route all memory ingest/retrieve/enrichment/compaction through async MemoryService.
Remove legacy sync memory implementations (ingest/retrieve/compaction); Celery and
memoir Phase2 call asyncio.run into MemoryService-backed helpers.

Memoir Phase1 batch ingest uses MemoryService.ingest_transcripts_batch; drop chapters.
evidence_bundle_json mirror (Alembic 0015). Evaluation uses snapshot/link-only bundles;
raise EvidenceClosureMissing instead of partial/fallback lineage tiers.

Split memoir state into NarrativeCoverageState and InterviewControlState; delete the
_interview_meta_store adapter layer. Remove rolling-query and recent-fact fallback
settings from config and evidence assembly.

Update judges, docs, tests, and PlaygroundPage alignment.

Made-with: Cursor

api/app/features/evaluation/judge_manual_service.py

@@ -688,7 +688,6 @@ class EvalJudgeManualService:
         trace_svc = EvalTraceService(self._db)
 
         def _chapter_evidence_notes(
-            lineage_tier: str,
             evidence_summary: str,
             truncated: bool,
             dropped: list[str],
@@ -696,7 +695,7 @@ class EvalJudgeManualService:
             drops = ",".join(dropped[:12]) if dropped else ""
             return (
                 "严格按文档打分；真实性、事实覆盖率、可追溯性以本章节绑定的证据闭包为准。"
-                f" lineage_tier={lineage_tier}；evidence_summary={evidence_summary}；"
+                f" evidence_summary={evidence_summary}；"
                 f" prompt_truncated={truncated}；dropped_sections={drops or 'none'}"
             )
 
@@ -792,7 +791,6 @@ class EvalJudgeManualService:
                         structured_evidence=formatted.structured_evidence,
                         reference_memoir_markdown=baseline_excerpt,
                         evidence_notes=_chapter_evidence_notes(
-                            cb2.lineage_tier,
                             formatted.evidence_summary,
                             fm.truncated,
                             fm.dropped_sections,
@@ -819,7 +817,6 @@ class EvalJudgeManualService:
                     "title": ch.title,
                     "order_index": ch.order_index,
                     "baseline_title": bl.title if bl else None,
-                    "lineage_tier": cb2.lineage_tier,
                     "evidence_summary": formatted.evidence_summary,
                     "evidence_trace": cb2.model_dump(),
                     "format_meta": fm.model_dump(),
@@ -917,7 +914,6 @@ class EvalJudgeManualService:
         trace_svc = EvalTraceService(self._db)
 
         def _chapter_evidence_notes(
-            lineage_tier: str,
             evidence_summary: str,
             truncated: bool,
             dropped: list[str],
@@ -925,7 +921,7 @@ class EvalJudgeManualService:
             drops = ",".join(dropped[:12]) if dropped else ""
             return (
                 "严格按文档打分；真实性、事实覆盖率、可追溯性以本章节绑定的证据闭包为准。"
-                f" lineage_tier={lineage_tier}；evidence_summary={evidence_summary}；"
+                f" evidence_summary={evidence_summary}；"
                 f" prompt_truncated={truncated}；dropped_sections={drops or 'none'}"
             )
 
@@ -1017,7 +1013,6 @@ class EvalJudgeManualService:
                 md = payload["md"]
                 bl = payload["bl"]
                 ev_notes = _chapter_evidence_notes(
-                    cb2.lineage_tier,
                     formatted.evidence_summary,
                     fm.truncated,
                     fm.dropped_sections,
@@ -1084,7 +1079,6 @@ class EvalJudgeManualService:
                     "title": ch.title,
                     "order_index": ch.order_index,
                     "baseline_title": bl.title if bl else None,
-                    "lineage_tier": cb2.lineage_tier,
                     "evidence_summary": formatted.evidence_summary,
                     "evidence_trace": cb2.model_dump(),
                     "format_meta": fm.model_dump(),