local_gpu_start_run
Initiate a visual-asset generation run only after user confirmation, using the start_run_boundary from the earlier recommendation and adding the remaining required run fields.
Instructions
Create a visual-asset run only after later user confirmation; copy start_run_boundary exactly from the previously displayed recommendation and add the remaining run fields.
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": {
"intent": "<intent>",
"profile": "<profile>",
"subtype": "<subtype>",
"style": "<style>",
"constraints": "<constraints>",
"model_choice": "<model_choice>",
"backend": "<backend>",
"authorization_scope": "<authorization_scope>",
"route_token": "<route_token>",
"max_rounds": "<max_rounds>",
"upscale_policy": "<upscale_policy>"
},
"name": "local_gpu_start_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| style | Yes | ||
| intent | Yes | ||
| backend | Yes | ||
| profile | Yes | ||
| subtype | Yes | ||
| max_rounds | Yes | ||
| constraints | Yes | ||
| route_token | Yes | ||
| model_choice | Yes | ||
| upscale_policy | Yes | ||
| authorization_scope | Yes | ||
| initial_regional_conditioning | No | ||
| initial_two_stage_conditioning | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||