fix(agent): prevent stuck loop by adding action history to LLM prompt
The UI agent had no memory of previous actions — each step was a fresh single-shot LLM call. After typing and sending a message, the LLM saw an empty text field and retyped the message in a loop. - Add RECENT_ACTIONS (last 5 actions with text/result) to user prompt - Add chat app completion detection rule to dynamic prompt - Add send-success hints for WhatsApp and Messages apps - Add git convention to CLAUDE.md (no co-author lines)
This commit is contained in:
@@ -63,3 +63,7 @@ Copy `.env.example` to `.env` and configure `LLM_PROVIDER` + the corresponding A
|
||||
## Device Assumptions
|
||||
|
||||
Swipe coordinates in `constants.ts` are hardcoded for 1080px-wide screens (center X=540, center Y=1200). Adjust `SWIPE_COORDS` and `SCREEN_CENTER_*` for different resolutions.
|
||||
|
||||
## Git Conventions
|
||||
|
||||
- Do NOT add `Co-Authored-By: Claude` lines to commit messages.
|
||||
|
||||
Reference in New Issue
Block a user