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/tests/test_interview_prompts.py

@@ -23,6 +23,7 @@ from app.agents.state_schema import (
     MemoirStateSchema,
     PersonaThread,
     default_slots,
+    prompt_empty_slots_for_current_stage,
 )
 
 
@@ -293,8 +294,9 @@ def test_prompt_empty_slots_excludes_slots_already_covered_by_known_facts():
             )
         ],
     )
-    assert "city" not in state.prompt_empty_slots_for_current_stage()
-    assert "school" in state.prompt_empty_slots_for_current_stage()
+    prompt_empty = prompt_empty_slots_for_current_stage(state)
+    assert "city" not in prompt_empty
+    assert "school" in prompt_empty
 
 
 def test_duplicate_question_guard_downgrades_recent_repeat_question():