Add pytesseract OCR, click_text interact action, and interact verify endpoint

2026-05-03 20:57:34 +02:00
parent 1c03cab457
commit 9e816e0417
8 changed files with 559 additions and 11 deletions
--- a/TODO.md
+++ b/TODO.md
@@ -26,3 +26,8 @@
 - [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