Run model fit
run_model_fitRun a released model parameter fit with exact parameters and destination. Validates internally, then queues one job. Requires authorization and compute entitlements. Retain the UUID for retries; inspect request_status after uncertainty.
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": {
"parameters": "<parameters>",
"destination_project_id": "<destination_project_id>",
"idempotency_key": "<idempotency_key>"
},
"name": "run_model_fit"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| inputs | No | ||
| limits | No | Optional maximum cost and resources; missing estimates block execution. 1000 cpu_millis = 1 vCPU. | |
| parameters | Yes | ||
| agent_run_id | No | ||
| idempotency_key | Yes | One UUID retained for this logical mutation and its retries. | |
| capability_version | No | ||
| destination_project_id | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||