wyrm_run

Category

Fleet & Presence

Use to manage a fleet run lifecycle from the orchestrator: action=start mints a ULID run_id and registers the orchestrator, join registers each subagent (agent_id, role), status reports agents, run-quarantined failure counts, and quest claims, debrief fans each agent's learnings through the LOCAL extractor (never a cloud LLM) into a run-scoped review queue for wyrm_review, and end writes the run summary, promotes or expires quarantined failures, and releases claims.

Signature

Argument	Type	Required	Description
action	'start' | 'join' | 'status' | 'debrief' | 'end'	✓
run_id	string		start mints if omitted
agent_id	string		default: ambient envelope
role	string		join
orchestrator	string		start
parent_run_id	string		start: nested fleets
project_path	string		debrief/end
learnings	object[]		debrief: [{agent_id?, text}]
status	'completed' | 'failed' | 'abandoned'		end (default completed)

Hand-written prose for this tool will appear here. Edit between the markers above and below; the rest of this page regenerates on every docs build.