vision: real-time perception — auto frame attach every N turns (--look-every) and on collision, frame context cap (6), digest fallback for text models

testbed/README.md

@@ -101,6 +101,18 @@ works: `python -m testbed.chat --base-url https://api.openai.com/v1
 --model gpt-4o-mini --api-key $OPENAI_API_KEY`. `--auto-steps N` controls how
 many tool steps the model may chain per request (0 = one action per turn).
 
+### Real-time perception
+
+The model sees continuously, not only when it asks:
+
+- `--look-every N` attaches a fresh camera frame every N steps/turns (default 3,
+  `0` disables). Frames go in as images for multimodal models, as digests for
+  text-only ones, and old frames are trimmed (max 6) to keep the context
+  bounded.
+- On a collision the current frame is attached immediately, so the model sees
+  what it bumped into.
+- The live viewer (http://127.0.0.1:8000) shows the same frames in the browser.
+
 ### Real vision
 
 Vision is the **primary channel**: when the model is multimodal, `vision`