What this test proves
Inside the shared colima testbed, a real agent executes prompt AT11 and observes only public ATM CLI JSON. Task events expose queued, ready, reminder, and started for the prompted task but queued only for later tasks; disabling reminders removes the reminder event and produces the documented doctor finding.
Evidence layout
This procedure is one step of a colima integration run. The agent's unedited prompt-report-1 JSON is retained beside step.json; scripts/integration/render_colima.py renders the panel and aggregate. Historical payloads remain byte-identical and render through the same path.
Changes
The revision sections below list every runner revision that produced committed evidence, newest first. A run whose source revision is not an ancestor of any listed revision links to the revision in effect on its run date and is marked inferred.
Flow
Steps
| step | action | observable | evidence |
|---|---|---|---|
| 1 | `task_events_shows_ready_reminders_and_started_for_prompted_task_only`: assign three tasks, wait for reminders, start and close the prompted one | task events and the prompt_handoffs table agree row for row, for the prompted task only; recorded PASS or FAIL at revision `a2491a6c` | `step.json` cases |
| 2 | `disabled_task_reminder_override_yields_no_handoff_and_doctor_finding`: disable the task reminder and assign | no handoff row is written and `atm doctor` reports the finding; recorded PASS or FAIL at revision `a2491a6c` | `step.json` cases |