chat: interactive mode (natural language -> tool calls), shared LLM driver refactor, run_chat.sh; verified with gemma4:e2b and gemma4:12b

testbed/README.md

@@ -22,6 +22,8 @@ over the protocol, no engine hooks.
 | `server.py` entry       | `python -m testbed.bridge` — WebSocket server.               |
 | `conformance.py`        | Runs the 9 core conformance scenarios against this bridge.   |
 | `live.py`               | Real-time browser viewer (itself an AICC client).            |
+| `chat.py`               | Interactive chat: natural language -> tool calls.            |
+| `llm_agent.py`          | Shared LLM driver (controller + autonomous loop).            |
 | `demo.py`               | Agent demo: LLM driver (OpenAI-compatible) or scripted.      |
 | `tests/`                | pytest suite (world, renderer, bridge, protocol).            |
 
@@ -62,6 +64,33 @@ taken); stop the old one with `fuser -k 8765/tcp` or Ctrl-C in its terminal.
 The demo prints a full transcript of tool calls/results to stdout and saves the
 capsule's final first-person frame to `demo_final_frame.png`.
 
+## Interactive chat mode
+
+Talk to the capsule's brain in natural language (any language):
+
+```bash
+scripts/run_chat.sh --model gemma4:e2b    # small + fast
+scripts/run_chat.sh --model gemma4:12b    # bigger gemma, slower (~20 s/turn)
+```
+
+It starts the bridge, the live viewer and a chat REPL — open
+[http://127.0.0.1:8000](http://127.0.0.1:8000) to watch the capsule while you
+type. The model translates your words into tool calls:
+
+```
+you> иди к маяку            → look_at + move step by step (auto-continue)
+you> повернись налево       → turn(-90)
+you> осмотрись              → vision + description
+you> активируй маяк         → interact (when close)
+you> /state  /look  /map  /models  /model gemma4:12b  /steps N  /help  /exit
+```
+
+Each turn's transcript is printed; the current frame lands in `chat_frame.png`
+and the sensor-built map in `chat_map.png`. Any OpenAI-compatible endpoint
+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 mode
 
 Watch the capsule drive live in your browser: