34 lines
1.6 KiB
Markdown
34 lines
1.6 KiB
Markdown
# TODO
|
|
|
|
## Project: Clickthrough v1
|
|
|
|
## Current Status
|
|
- [x] Draft implementation plan approved
|
|
- [x] Build FastAPI server with screenshot + grid + zoom + actions
|
|
- [x] Add auth + safety guardrails (token, dry-run, bounds)
|
|
- [x] Add AgentSkill docs for operating the API reliably
|
|
- [x] Add Gitea CI workflow for Python syntax safety
|
|
- [x] Add usage docs + quickstart
|
|
- [x] Run local syntax validation
|
|
|
|
## Notes
|
|
- API responses now include request IDs, timestamps, and coordinate metadata
|
|
- Local syntax checks passed (`py_compile`, `compileall`)
|
|
- CI workflow runs syntax checks on push + PR
|
|
|
|
## Next
|
|
- [x] Add `POST /exec` endpoint (PowerShell/Bash/CMD) with timeout + stdout/stderr
|
|
- [x] Add exec configuration via env (`CLICKTHROUGH_EXEC_*`)
|
|
- [x] Document exec API + config
|
|
- [x] Create backlog issues for OCR/find/window/input/session-state improvements
|
|
- [x] Open PR for exec feature branch and review/merge
|
|
- [x] Require configured exec secret + per-request exec secret header
|
|
- [x] Upgrade skill with verify-before-click rules, confidence thresholds, two-phase risky actions, and Spotify playbook
|
|
- [x] Add top-level skill section for instance setup + mini API docs
|
|
- [x] Clarify user-owned setup responsibilities vs agent responsibilities in skill docs
|
|
|
|
## Deferred Backlog
|
|
- [ ] Higher-level task macros composed from `see` + `interact` + `interact/verify` primitives
|
|
- [ ] Additional verify primitives beyond `ocr_text_near_point` (image-diff region, window title/process state, color/pixel checks)
|
|
- [ ] Broader API simplification pass to reduce payload overlap and consolidate shared OCR options
|