Check Python packages and CUDA readiness for local GPU image generation.

Compatibility tool for WebUI or Diffusers image generation; not for ComfyUI routes and never a bypass for the confirmed high-level run workflow.

Plan or execute bounded local model discovery without loading model weights.

Inspect one local ComfyUI API workflow and infer a safe ordinary txt2img binding without writing state.

Recheck and immutably register one exact previously inspected ComfyUI workflow proposal.

Inspect, approve, or revoke one exact current local model identity. A trust mutation requires the exact confirmation previously returned for the same mutation boundary, displayed to the user, and repeated in a later user message.

Recommend one exact confirmed-capability route and at most two alternatives. preferred_model_id must be an exact catalog ID. Display the selected route and start_run_boundary, then wait for later user confirmation before local_gpu_start_run.

List registered visual-asset profiles and current local backend capabilities.

Create a visual-asset run only after later user confirmation; copy start_run_boundary exactly from the previously displayed recommendation and add the remaining run fields.

Get the current persisted state of a visual-asset run.

Create an immutable child revision run from one reviewed parent round.

Prepare an unconfirmed child-run inpaint mask and return its JPEG overlay.

Confirm an unchanged prepared mask after explicit overlay approval.

Generate one root or immutable revision round and return an optional bounded JPEG preview.

Record human or model review evidence for one generated round.

Publish the selected reviewed round as the run's final PNG.

Remove run intermediates or a fully confirmed run directory.