36 lines
1.4 KiB
Markdown
36 lines
1.4 KiB
Markdown
---
|
|
name: clickthrough-http-control
|
|
description: Control a local computer through the Clickthrough HTTP server using screenshot grids, zoomed grids, and pointer/keyboard actions. Use when an agent must operate GUI apps by repeatedly capturing the screen, refining target coordinates, and executing precise interactions (click/right-click/double-click/scroll/type/hotkey) with verification.
|
|
---
|
|
|
|
# Clickthrough HTTP Control
|
|
|
|
Use a strict observe-decide-act-verify loop.
|
|
|
|
## Workflow
|
|
|
|
1. Call `GET /screen` with coarse grid (e.g., 12x12).
|
|
2. Identify likely cell/region for the target UI element.
|
|
3. If confidence is low, call `POST /zoom` centered on the candidate and use denser grid (e.g., 20x20).
|
|
4. Execute one minimal action via `POST /action`.
|
|
5. Re-capture with `GET /screen` and verify the expected state change.
|
|
6. Repeat until objective is complete.
|
|
|
|
## Precision rules
|
|
|
|
- Prefer grid targets first, then use `dx/dy` for subcell precision.
|
|
- Keep `dx/dy` in `[-1,1]`; start at `0,0` and only offset when needed.
|
|
- Use zoom before guessing offsets.
|
|
|
|
## Safety rules
|
|
|
|
- Respect `dry_run` and `allowed_region` restrictions from `/health`.
|
|
- Avoid destructive shortcuts unless explicitly requested.
|
|
- Send one action at a time unless deterministic; then use `/batch`.
|
|
|
|
## Reliability rules
|
|
|
|
- After every meaningful action, verify with a fresh screenshot.
|
|
- On mismatch, do not spam clicks: zoom, re-localize, and retry once.
|
|
- Prefer short, reversible actions over long macros.
|