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/interview_state_hints.py

@@ -5,13 +5,18 @@ from __future__ import annotations
 import re
 from collections.abc import Iterable
 
-# 与 `apply_duplicate_question_guard` 中整段替换句一致；用于判定是否需触发二次生成。
-DUPLICATE_QUESTION_GUARD_FALLBACK_ZH = "这一段我记住了。"
-
-from langchain_core.messages import AIMessage, BaseMessage, HumanMessage
+from langchain_core.messages import AIMessage, BaseMessage
 
 from app.agents.stage_constants import STAGE_DISPLAY_ZH, STAGE_SLOT_KEYS
-from app.agents.state_schema import KnownFact, MemoirStateSchema, PersonaThread
+from app.agents.state_schema import (
+    KnownFact,
+    MemoirStateSchema,
+    PersonaThread,
+    narrative_coverage_state,
+)
+
+# 与 `apply_duplicate_question_guard` 中整段替换句一致；用于判定是否需触发二次生成。
+DUPLICATE_QUESTION_GUARD_FALLBACK_ZH = "这一段我记住了。"
 
 _QUESTION_SPLIT_RE = re.compile(r"[?？]+")
 _SENTENCE_SPLIT_RE = re.compile(r"(?<=[。！？!?])")
@@ -220,10 +225,11 @@ def build_runtime_interview_state(
         )
 
     persona_additions: list[PersonaThread] = []
+    narrative_state = narrative_coverage_state(state)
     haystack = " ".join(
         [msg]
         + [fact.value for fact in state.known_facts[-8:]]
-        + list(state.filled_slots_for_stage(active_stage).values())[:4]
+        + list(narrative_state.filled_slots_for_stage(active_stage).values())[:4]
     )
     for trait, markers in _TRAIT_HINTS:
         for marker in markers: