Register a compose critic
Required permission: projects:write
API key auth. Prefix cf_live_ for production orgs, cf_test_ for sandbox.
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Register a custom compose critic.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl -X POST "https://example.com/v1/critics" \ -H "Content-Type: application/json" \ -d '{ "criticId": "string", "label": "string", "tier": "rules" }'{ "id": "string", "criticId": "string", "tier": "rules", "secret": "string"}{ "error": { "code": "string", "message": "string", "details": { "property1": null, "property2": null } }}{ "error": { "code": "string", "message": "string", "details": { "property1": null, "property2": null } }}{ "error": { "code": "string", "message": "string", "details": { "property1": null, "property2": null } }}{ "error": { "code": "string", "message": "string", "details": { "property1": null, "property2": null } }}{ "error": { "code": "string", "message": "string", "details": { "property1": null, "property2": null } }}{ "error": { "code": "string", "message": "string", "details": { "property1": null, "property2": null } }}Ask the multi-agent Director for editing advice (never writes) POST
Ask the Director for editing advice on the project's current composition — it NEVER saves; you stay the decider. Async: poll the returned job for the advisory envelope. Modes: 'advise' = the planner agent (fast, ~30s-2min) returns a PLAN (framing/cuts/captions/graphics intents) as guidance you re-author from — no grounded scores; 'amend' = the full author→judge→refine loop (minutes) returns a GRADED assessment + an adoptable fix candidate (adopt via POST /compose/jobs/:jobId/select with its candidateIndex). ('explore' — a ranked slate of directions — is coming soon.)
Delete a registered critic DELETE
Required permission: projects:write