Re-author with the LLM (paid)
author_opRuns ONE edit op that re-authors with the LLM — the SAME op the human director runs from the chat — and stages its result into the project's conversation draft, which becomes a new version when it is committed. The call waits up to 60 s for the pass (50 of the 58 authoring turns measured finished within that) and answers with the staged edit (outcome: completed_inline); a longer pass keeps running and the answer is its job (outcome: still_running, runId), which the project status reports by run_id. An identical call while the job runs, or within 15 minutes after it succeeded, returns the SAME job, so a retry is not charged twice; request_id names a deliberately repeated request. One authoring turn at a time per project (authoring-in-progress).
Ops:
revestir_como_autor: Re-dress ONE scene's visual as an animated author's scene (a world with an actor where the data lives), keeping the narration word for word; for a still image held too long. LLM. Args: scene_index, brief? (only the VISUAL is re-dressed as an animated author's scene by the piece's director; the narration stays word for word, so the voice is reused; brief orients the world/actor).rewrite_scene: Re-author one scene (script and visual) under a brief. LLM. Args: scene_index, brief (the WHOLE scene is re-authored under the brief).tighten_hook: Strengthen the opening hook (scene 0). LLM. Args: brief? (scene 0). Requires thewritescope. Spends LLM budget (charged like a chat turn).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| op | Yes | ||
| args | Yes | Op arguments (see description). | |
| project_id | Yes | ||
| request_id | No | Optional: a caller-chosen key for this request (up to 64 characters). The same key returns the same job for 24 h; a new key runs it again. Without it, an identical call within 15 minutes is the same request. |