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/memoir/models.py

@@ -35,8 +35,6 @@ class Chapter(Base):
     is_new = Column(Boolean, default=True)
     is_active = Column(Boolean, default=True)
     source_segments = Column(JSON, nullable=True)
-    # 物化当前 canonical 对应的证据闭包（segment / story / memory ids），供评测与审计；见 memoir/chapter_evidence_snapshot
-    evidence_bundle_json = Column(JSON, nullable=True)
     # Phase C：指向当前生效的 chapter_evidence_snapshots 行（版本链可审计）
     current_evidence_snapshot_id = Column(
         String,
@@ -295,6 +293,9 @@ class MemoirState(Base):
     current_stage = Column(String, default="childhood")
     covered_stages = Column(JSON, default=list)
     slots = Column(JSON, nullable=False)
+    known_facts_json = Column(JSON, nullable=True)
+    persona_threads_json = Column(JSON, nullable=True)
+    recent_questions_json = Column(JSON, nullable=True)
     updated_at = Column(DateTime(timezone=True), default=utc_now, onupdate=utc_now)
 
     user = relationship("User", back_populates="memoir_state")