vision: real camera frames to the model (image_url), auto-detected for multimodal ollama models; --vision/--no-vision flags; verified gemma4:12b sees frames and completed the beacon mission

testbed/demo.py

@@ -139,6 +139,7 @@ async def run_llm_agent(
     model: str,
     max_steps: int,
     recorder: FrameRecorder | None = None,
+    vision: bool | None = None,
 ) -> dict[str, Any]:
     """Autonomous LLM run: controller + nudge/correct loop (see llm_agent)."""
     from testbed.llm_agent import LLMController, run_llm_agent_loop
@@ -150,6 +151,7 @@ async def run_llm_agent(
         api_key=api_key,
         model=model,
         log=lambda role, msg: print(f"[{role}] {msg}"),
+        multimodal=vision,
     )
     try:
         return await run_llm_agent_loop(
@@ -307,6 +309,7 @@ async def run_demo(args: argparse.Namespace) -> dict[str, Any]:
                 model=args.model,
                 max_steps=args.max_steps,
                 recorder=recorder,
+                vision=args.vision,
             )
         elif args.agent == "scripted":
             summary = await run_scripted_agent(
@@ -327,6 +330,7 @@ async def run_demo(args: argparse.Namespace) -> dict[str, Any]:
                     model=args.model,
                     max_steps=llm_steps,
                     recorder=recorder,
+                    vision=args.vision,
                 )
                 if summary.get("interacted"):
                     return summary
@@ -388,6 +392,12 @@ def main() -> int:
     )
     parser.add_argument("--api-key", default="ollama", help="API key for the endpoint")
     parser.add_argument("--max-steps", type=int, default=60, help="max agent steps")
+    parser.add_argument(
+        "--vision",
+        action=argparse.BooleanOptionalAction,
+        default=None,
+        help="pass real camera frames to the model as images (auto-detected for local ollama)",
+    )
     parser.add_argument(
         "--frame",
         default="demo_final_frame.png",