PMFlow/docs/architecture/DATAFLOW.md

DATAFLOW

Signal Planner Flow (Post-Commit Async)

1. AIPMOKernelService creates signal (signal.create) in transaction.
2. Transaction commits.
3. Background task triggers SignalPlannerService.analyze(signal_id, tenant_id, ...).
4. Planner service opens isolated AsyncSessionLocal and loads context:
   • signal content/project context
   • project members (user_projects -> users -> user_workloads -> user_skill_bindings -> skill_tags)
5. Planner calls llm_service.generate_structured_object(function_name="signal_planner_analyze") with hard wait timeout (25s).
6. Structured success:
   • SignalStrategicAnalysisService.merge_and_save(...)
   • update signals.planner_status=completed
   • write planner payload into strategic_analysis.ai_planner
7. Structured invalid / timeout fallback:
   • build degraded planner payload (fallback_mode=true)
   • still merge_and_save(...) and mark signals.planner_status=completed
8. Hard failure (DB write / unexpected exception):
   • SignalStrategicAnalysisService.mark_failed(...)
   • update signals.planner_status=failed
   • try enqueue compensate reply via FeishuOutboxService.enqueue(...)

Model Routing Flow

1. Frontend ModelRoutingConfigPage reads current mapping via /model-routing/functions/{function_name}.
2. Manager updates mapping via PUT API.
3. Backend persists override into integrations(type='model_routing').
4. LLMService resolves function-level override at runtime before default control-plane rules.

Task Brief Flow

1. Frontend chooses template / trigger generate.
2. Backend task_brief_service stores template and run records in integrations(type='task_briefs').
3. Generation run writes summary + artifact path.
4. /task-briefs/center aggregates latest generated cards for sidebar center.