fix: tool-result message for non-vision tools (KeyError on width); polza provider verified end-to-end (vision + mission on first attempt)

testbed/README.md

@@ -64,6 +64,25 @@ 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`.
 
+## Providers
+
+Provider presets resolve endpoint + API key + default model:
+
+```bash
+export POLZA_API_KEY="..."        # from https://polza.ai/dashboard/api-keys
+scripts/run_chat.sh --provider polza            # openai/gpt-5.6-luna, vision ON
+scripts/run_demo.sh --provider polza --agent llm
+scripts/run_demo.sh --provider openai --model gpt-4o-mini
+# local ollama stays the default (no flags needed)
+
+# anything else OpenAI-compatible:
+scripts/run_chat.sh --base-url https://... --model ... --api-key ...
+```
+
+Keys are read from the environment (`POLZA_API_KEY`, `OPENAI_API_KEY`), never
+stored in the repo. Multimodal models (gpt-5.x, gemma, qwen-vl, ...) get real
+camera frames automatically; `--vision`/`--no-vision` override.
+
 ## Interactive chat mode
 
 Talk to the capsule's brain in natural language (any language):

testbed/llm_agent.py

@@ -516,7 +516,7 @@ class LLMController:
                     )
                     self.messages.append(self._frame_message(frame_b64, frame_note))
                     self._trim_frames()
-                else:
+                elif frame_b64 is not None:
                     # Fallback channel: the digest (plus frame metadata) for
                     # text-only models.
                     content = (
@@ -528,6 +528,13 @@ class LLMController:
                     self.messages.append(
                         {"role": "tool", "tool_call_id": tc.id, "content": content}
                     )
+                else:
+                    # Any other tool: plain structured result, prefixed with
+                    # the CURRENT STATE note.
+                    content = (hint + "\n" if hint else "") + json.dumps(outcome.output)
+                    self.messages.append(
+                        {"role": "tool", "tool_call_id": tc.id, "content": content}
+                    )
                 call_result = ToolCallResult(
                     name=name, args=args, ok=True, output=outcome.output, digest=digest
                 )