Vision-driven browser automation using Midscene Bridge mode. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with...
**Adds strict result reporting requirements and updates model guidance.** - Now mandates a clear summary of results after every automation task, including data found, actions completed, screenshots taken, and relevant findings. - Updates environment variable examples and recommended models (adds Qwen 3.5, Doubao Seed 2.0 Lite, and related provider instructions). - Clarifies workflow: do not disconnect from Bridge mode unless the user's entire task is fully complete; keep sessions available for continued use. - Revises best practices and workflow pattern for improved clarity and efficiency.