mark_retryable
Flag a stuck running trial as retryable for infrastructure failures, not scientific ones, so terminal trials are recorded without counting as evidence.
Instructions
Mark a running trial as retryable (infrastructure failure).
This is for trials that are stuck in 'running' due to infrastructure issues (server restart, executor state lost, timeout) — NOT for scientific failures. A retryable trial is terminal and does not count as evidence.
It does NOT unlock re-capture or re-run: a terminal trial's record is finished. To retry the work, design_experiment a new trial and capture_bundle on it (file-path or code://).
Enforcement: commitment 1 — the loop is the unit (orphan check).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"programme_id": "<programme_id>",
"trial_id": "<trial_id>",
"reason": "<reason>"
},
"name": "mark_retryable"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | Why the trial is marked retryable — becomes part of the record. | |
| trial_id | Yes | ID of the target trial. | |
| programme_id | Yes | ID of the target research programme. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | ||
| status | No | ||
| trial_id | No |