Schedule run history
List a schedule's past batch runs (its run history), every batch that cron job fired, newest first, each with its status (running / complete / error), progress (completed/total), failed and errored counts, and start/finish times. Pass the cron job id from list_cron_jobs. Use this to answer "how has this schedule been doing?" or to find a batch to re-score. A pure read, it does not fire the schedule.
Authorization
bearerAuth A personal access token from Settings > API tokens.
In: header
Header Parameters
A key you choose, such as a UUID, that makes this POST safe to retry. Within 24 hours the same key and request answers with the first successful answer and runs nothing, the same key with a different request answers 422 idempotency_key_reused, and a key whose request is still running answers 409 idempotency_key_in_use. A failed request keeps nothing, so the same key runs it again.
1 <= length <= 255Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
curl -X POST "https://example.com/operations/list_cron_batch_history" \ -H "Content-Type: application/json" \ -d '{ "cronJobId": "string", "agent": "string" }'{}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}List connector tools POST
List the actions/tools a connected app exposes, so you can choose which to enable on an agent with set_agent_connection's `allowedTools`. Returns `tools`, each `{ slug, name, description }`, plus `nextCursor` for paging and `totalItems`. `toolkit` is the toolkit slug (from list_available_connectors or list_agent_connections). Pass `search` (min 3 chars) to filter by keyword. By default this returns the app's FULL tool catalogue; pass `important: true` for only the provider's curated high-signal subset, but note some large toolkits (e.g. HighLevel, 200+ tools) have zero 'important' tools, so the default full list is usually what you want. This is the discovery half of set_agent_connection: call it to get valid tool slugs before scoping an agent's allowed tools.
List schedules POST
List the scheduled eval runs (cron jobs) for the agent you're editing, each with its name, cron expression, a human-readable schedule, timezone, whether it's enabled, and its last-run status. A cron job runs this agent's eval suite automatically on a recurring schedule. Call this FIRST to see what's already scheduled before create_cron_job so you don't duplicate a schedule.