Redo one scene of a Shorts episode without redoing the episode
Continue the same Format thread with previous_run_id and a new instruction to redo a single scene. Sume treats it as one more turn of the same conversation.

Create a new Format run with previous_run_id set to the episode's run and an instruction that names the scene. Sume treats it as one more turn of the same conversation instead of a fresh start, so the agent still has the earlier turns.
The docs say a single-scene retry on the same thread costs a fraction of the original run's spend, which is the whole point.
The request
previous_run_id is one of the fields a run item can name, alongside instruction, input and attachments. An unknown or foreign id returns 404 previous_run_not_found. The Continue a run section of the runs page covers the thread rules.
Write the instruction as a delta: the scene number, what was wrong and what to keep. A vague 'make it better' re-opens the whole episode.
| Field | Value | Reason |
|---|---|---|
| previous_run_id | The episode run id | Same thread, same context |
| instruction | Scene 4 only, with the fix | Limits the work |
| generation_spend_cap_usd | A small number | Caps a runaway retry |
| Idempotency-Key | New per retry | A spent key replays the old run |
Fit with batches
In a bulk queue an item may carry previous_run_id, so a season's reshoots can be queued the same way as its first pass: one item per scene that failed review. See the bulk post for limits.
Deadlines apply to each run separately, so a scene run does not inherit the 90-minute clock of the original.
- Review the episode, list failing scenes, queue only those.
- Keep the original receipt for the artifacts of scenes that passed.
- Do not reuse an idempotency key for a different instruction.
What a good redo instruction looks like
Name the scene by its number and the problem by what a viewer sees. 'Scene 4: the lamp is on in the first shot and off in the second; keep the dialogue and the camera, fix the lamp' is a good redo. 'Fix scene 4' invites a rewrite of everything the agent remembers.
List what must not change. The agent holds the earlier turns of the thread, so the more you say about the parts that passed, the less it touches them. If an artifact from the first run passed review, say so by name.
Cap the spend on the redo. A small generation_spend_cap_usd turns a runaway redo into a clean failure that you can inspect, and it keeps the cost of a single-scene fix visible in the receipt as usage.billable_amount_usd_micros. The spend-cap post lists the values the API accepts.
Checks after the redo
Compare the redone scene with the one before and after it. A fix that is right in isolation can still break the cut, so watch the three scenes in sequence at full speed.
If the redo fails twice, stop. Start a fresh run for that scene with a rewritten instruction, or move the scene to the video model's reference mode as in the continuity post.
Sources
Related posts
More in Formats
- Render a Short and wait for it in one request? Timeline sync mode
Timeline 1.0 can answer a Short render in one request when mode is sync and the job finishes within 30 seconds. Otherwise it returns 202 and you poll.
- Restyle your own footage with the Sume restyle Format
sume-restyle keeps the motion, timing and cuts of a clip you attach, rewrites its look chunk by chunk, and reassembles it with your original audio.
- Run 300 ad variants as three bulk queues on Sume
One Sume bulk queue holds 1 to 100 Format runs, so 300 variants means three queues with their own idempotency keys, caps and failure checks. The limits to plan.
- Season outline as nested input: one key, 64-key limit, 2 MiB
Put a whole season outline under one key of a Format run's input. Only top-level keys count toward 64, and the body can be up to 2 MiB, so 40 episodes fit.
Written by Sume