Simplify AI memory pipeline

api/tests/test_story_route_oral_invariant.py

@@ -4,7 +4,6 @@
 from types import SimpleNamespace
 from unittest.mock import MagicMock, patch
 
-from app.agents.memoir.prompts import format_evidence_chunks_for_prompt
 from app.agents.memoir.story_route_agent import StoryRouteDecision
 from app.agents.state_schema import MemoirStateSchema
 from app.features.asset import models as _asset_models  # noqa: F401
@@ -15,6 +14,7 @@ from app.features.memoir.story_pipeline_sync import (
     run_story_pipeline_for_category_batch,
 )
 from app.features.memory import models as _memory_models  # noqa: F401
+from app.features.memory.evidence_format import format_evidence_chunks_for_prompt
 from app.features.payment import models as _payment_models  # noqa: F401
 from app.features.story import models as _story_models  # noqa: F401
 from app.features.user import models as _user_models  # noqa: F401
@@ -47,7 +47,6 @@ def test_single_segment_decide_receives_only_combined_text_not_evidence() -> Non
             }
         ],
         "relevant_facts": [{"subject": "X", "predicate": "y", "object_json": {}}],
-        "timeline_hints": [],
         "relevant_stories": [],
     }
     evidence_formatted = format_evidence_chunks_for_prompt(evidence_payload)
@@ -236,7 +235,6 @@ def test_decide_receives_only_same_stage_story_candidates() -> None:
                 "relevant_chunks": [],
                 "relevant_summaries": [],
                 "relevant_facts": [],
-                "timeline_hints": [],
                 "relevant_stories": [],
             },
         )