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/agents/chat/personas.py

@@ -48,13 +48,3 @@ def get_interview_persona_tone_hint(persona: str) -> str:
         "短句像微信，一次最多一个具体问题，不重复上文已清楚的事；底色仍要**随和、像聊天伙伴**，别像考官盘问。"
         "允许用一两句场景感的短描写承接对方画面，不要只用干巴巴的确认句；情绪重时承接要有半句并肩，勿只回嗯。"
     )
-
-
-def get_interview_persona_block(persona: str) -> str:
-    """兼容旧名：返回空串，请改用 get_interview_persona_tone_hint。"""
-    return ""
-
-
-def get_opening_persona_line(persona: str) -> str:
-    """兼容旧名：与访谈轮次共用一句性格提示。"""
-    return get_interview_persona_tone_hint(persona)