Scheduled runs are pre-approved: they carry out their brief instead of drafting for confirmation. A run that can't do its brief calls report_run_failed and is retried 5 and 10 minutes later; only then does the user get one "failed after N tries" message, and the routine keeps why in last_error. Every reply and task now gets ActionCheckNote: look for an existing record before creating one, and verify an action took effect before saying it's done. Memory and instructions saves are read back, and create_bot, create_schedule, start_task and delegate_task refuse duplicates. Co-Authored-By: Claude Opus 5.5 <[email protected]>
11 lines
330 B
TypeScript
11 lines
330 B
TypeScript
/**
|
|
* Thrown by a task runner when a scheduled run reported that it failed
|
|
* (`report_run_failed`). Unlike `BotJobFatalError`, the queue retries it.
|
|
*/
|
|
export default class ScheduledRunFailedError extends Error {
|
|
constructor(message: string) {
|
|
super(message);
|
|
this.name = "ScheduledRunFailedError";
|
|
}
|
|
}
|