Format run queue.position is always null: no queue depth published
The status response has a queue object, but position is null on purpose. Use queue.state and expires_at for waiting UX instead of a fake countdown.
Do not build a 'you are number 4 in line' message for a Format run: queue.position is always null. Sume's Runs and results page documents the field and says a position is not published (read 2026-10-04). What the object does give you is queue.state, which is waiting or runtime_unavailable.
A client that renders position as a number will show nothing, or a bug, so decide the waiting screen from the fields that are real.
What can the UI say instead?
Map the documented fields to copy you can stand behind.
| Signal | Show |
|---|---|
status queued, queue.state waiting | Queued, waiting for a worker to pick it up |
queue.state runtime_unavailable | Delayed; the runtime is not available yet |
status processing | Working; show events from events_url |
expires_at approaching | Latest time the run can end as failed |
How long can it wait?
expires_at is the outer bound. A run is force-finalized as failed 90 minutes after creation, or sooner when it is older than 25 minutes and has been silent for 10. Show that time rather than guessing, and let next_action tell your poller whether to keep going.
What about a progress bar?
Use the events instead. The run's events_url lists what the agent has done, which is a truer sign of progress than a queue number would be, and it needs no estimate that could be wrong.
Sources
Related posts
More in Formats
- Argon 1M output tokens vs Sume Format 120,000-character schema cap
A 1M-token output limit does not lift Sume's output_schema limits. The 120,000 characters bound the schema, and the fallback projection reads 8,000 characters.
- Argon targets long-horizon work; a Sume Format run ends at 90 minutes
Google positions Gemini 4 Argon for long tasks. A Sume Format run is force-finalized as failed 90 minutes after creation, so split long jobs into runs.
- GPT-6.1 Sol errs less, but still pass prices as Format input
OpenAI says GPT-6.1 Sol cut factual errors from 11.4% to 7.7%. For ad video, give the run your prices and claims as input data instead of trusting recall.
- A gift portrait for your store homepage: model product portrait Format
The sume-model-product-portrait Format returns one finished still of a person with your product. Use it for a homepage hero, not for a motion ad.
Written by Sume