Launch Study Run
launch_study_runLaunch a new model fit for a frozen revision within study attempt and concurrency budgets. Never opens existing results; verify eligibility first and reuse submission key for retries.
Instructions
Launch a NEW fit of a frozen revision within study attempt/concurrency budgets; it never opens existing results. Call get_launch_eligibility first: a refusal here carries the same code, message and next_action. Requires an active study, an executable revision frozen on the current engine, and an active same-study policy (choose it deliberately; the newest is not always the intended one). Budget/state conflicts require inspection, not a new attempt key. Reuse the same submission_key after an ambiguous response; never invent another key for a retry. engine_changed means re-freeze (refreeze_recipe_revision) and launch the new revision.
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": {
"study_id": "<study_id>",
"revision_id": "<revision_id>",
"policy_id": "<policy_id>",
"submission_key": "<submission_key>"
},
"name": "launch_study_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| study_id | Yes | ||
| policy_id | Yes | ||
| revision_id | Yes | ||
| submission_key | Yes | Caller-generated 8-128 character identity for one intentional attempt. Reuse identical key and inputs after a lost response; a new key may consume another attempt. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||