governance-lifecyclelisted

# Agent Lifecycle **Last Updated:** 2026-08-17 ## Primary Workflow Names The core lifecycle should use primary task-verb tools. Each is implemented by a raw tool with the same identity rules and returns a **normalized envelope** with the operationally useful fields first (`next_action`, `state_summary`, `risk_summary`, `memory_suggestions`, `recovery_hint`). State-changing aliases preserve the full payload under `raw_governance`; read aliases default compact and explain how to request the full canonical payload. | Task | Primary workflow tool | Raw implementation tool | |------|---------------|----------------| | Start a fresh process identity | `start_session(force_new=true, ...)` | `onboard` | | Check in after meaningful work | `sync_state(response_text=..., complexity=...)` | `process_agent_update` | | Check your working state | `check_working_state()` | `get_governance_metrics` | | Avoid duplicate work | `search_shared_memory(query=...)` | `knowledge(action="search")` | | Record what actually happened | `record_result(...)` | `outcome_event` | | Ask for a structured review | `request_review(issue_description=...)` | `dialectic(action="request")` | | Store a durable finding | `store_finding(summary=..., discovery_type=...)` | `knowledge(action="store")` | | Update a durable finding | `update_finding(discovery_id=..., ...)` | `knowledge(action="update")` | Use the primary workflow tools by default. Use raw implementation names only for older servers, compatibility code