Rerun AI Triage
POST/api/support/agent/tickets/:ticket/ai/rerun
Re-runs the AI triage and drafted reply for a ticket from the current thread. Each call starts a new pass and does not overwrite earlier runs; the response is the latest completed run of each kind (triage, draft) that is not withheld. A run can finish as done, skipped (a prompt-injection screen matched the ticket text and it was left for a human), failed, or superseded (a draft replaced by the regenerated one after a release) — only done runs are returned. Nothing here reaches the customer; a drafted reply is only sent if an agent sends it.
support:writeGrant this scope to your token under Settings → Developer → Personal Access Tokens.
Run fields: kind, status, model, output (triage: classification — one of NEEDS_INFO, BUG_SUSPECTED, HOW_TO, FEATURE_REQUEST, BILLING, SPAM_OR_NOISE — plus type, priority, area, summary, questions[], bug_confirmed and docs[] of {title, url, snippet, score}; draft: body, classification), withheld / withheld_reason (a draft for a confirmed bug that has not shipped is held with reason awaiting_deploy until Record Support Release clears it, and is left out of this response while held), accepted (null until an agent records feedback), created_at. When the ticket has no type yet, a completed triage sets it.
Authentication: Bearer token with the support:write scope, or an authenticated session, from a caller with an active support role that can work tickets.
Request
Responses
- 200
- 401
- 403
- 404
- 422
- 429
OK
Response Headers
Unauthorized
Response Headers
Forbidden
Response Headers
Not Found
Response Headers
Validation failed — the body is a field → messages map (Laravel shape) or the platform envelope with a stable machine-readable code. Fix the payload and resubmit.
Rate limited — platform limit is 1,000 requests/min; individual tokens may carry lower limits. Honor the Retry-After header before retrying. See the Rate Limits guide.