Save a task (YAML, see get task format) to the user's OpenMark account and run it on the given models with real API calls. Returns a job id and the expected cost; poll get results. Spends the user's credits; pass max credits to only start within a budget. Optional run settings match the app's Configure & Run panel (preset, stability runs, max tokens, temperature discovery, temp preference, timeout profile, custom timeout, fail fast).
Показать схему аргументов
{
"type": "object",
"required": [
"task_yaml",
"models"
],
"properties": {
"models": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"minItems": 1,
"description": "Model ids from list_models"
},
"preset": {
"enum": [
"standard",
"thorough"
],
"type": "string",
"description": "Like the app's presets: standard = 2 passes + snappy timeouts (the default), thorough = 3 passes + patient timeouts. Explicit stability_runs / timeout_profile override it"
},
"fail_fast": {
"type": "boolean",
"default": true,
"description": "Stop a model after repeated errors to save credits. Set false to let every model finish, e.g. to diagnose failures"
},
"task_yaml": {
"type": "string",
"description": "The full task YAML (a JSON object with the same fields also works)"
},
"max_tokens": {
"type": "integer",
"default": 500,
"maximum": 16000,
"minimum": 0,
"description": "Output token limit per answer, 16 to 16000; 0 = no limit. Keep the default unless results show it was too low: a higher limit raises the credits needed to start. get_results flags models whose answers came back empty or near the limit; re-run those with a higher value"
},
"upload_uid": {
"type": "string",
"description": "From prepare_attachments, when tests use attachments"
},
"max_credits": {
"type": "integer",
"minimum": 1,
"description": "Budget: if the expected cost is higher, nothing runs and you get the quote instead"
},
"custom_timeout": {
"type": "integer",
"maximum": 600,
"minimum": 120,
"description": "Seconds per answer, with timeout_profile custom"
},
"stability_runs": {
"type": "integer",
"default": 2,
"maximum": 5,
"minimum": 1,
"description": "Passes per model; 2+ shows which models are consistent"
},
"temp_preference": {
"enum": [
"low",
"high"
],
"type": "string",
"default": "low",
"description": "With temperature_discovery: which temperature wins a tie"
},
"timeout_profile": {
"enum": [
"snappy",
"patient",
"custom"
],
"type": "string",
"default": "snappy",
"description": "How long to wait per answer: snappy 45s, patient 90s, custom = custom_timeout"
},
"temperature_discovery": {
"type": "boolean",
"default": false,
"description": "Find each model's best temperature for this task. Costs about 6x as much"
}
}
}