gpu_status
Check GPU-Bridge job status and retrieve results using the job ID from gpu_run. Monitor AI compute tasks across multiple backends.
Instructions
Check the status of a GPU-Bridge job and retrieve results.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | The job ID returned by gpu_run |
Implementation Reference
- index.js:161-188 (handler)The handler for the 'gpu_status' tool, which fetches job status from the API and returns the result or current progress to the user.
case "gpu_status": { const { job_id } = args; const status = await apiCall(`/status/${job_id}`, "GET"); let text = `Job ${status.id}: ${status.status}`; if (status.progress) { text += ` Progress: ${status.progress.phase} (${status.progress.percent_estimate}%, ${status.progress.elapsed_seconds}s elapsed)`; } if (status.output) { const o = status.output; if (o.text) text += ` Output: ${o.text}`; else if (o.url) text += ` Output: ${o.url}`; else if (o.audio_url) text += ` Output: ${o.audio_url}`; else text += ` Output: ${JSON.stringify(o)}`; } if (status.error) { text += ` Error: ${status.error}`; if (status.refunded) text += ` (refunded $${status.refund_amount_usd})`; } if (status.output_notice) text += ` Note: ${status.output_notice}`; return { content: [{ type: "text", text }] }; } - index.js:46-55 (schema)Registration of the 'gpu_status' tool, including its description and input schema (requiring 'job_id').
name: "gpu_status", description: "Check the status of a GPU-Bridge job and retrieve results.", inputSchema: { type: "object", properties: { job_id: { type: "string", description: "The job ID returned by gpu_run" } }, required: ["job_id"] } },