vision: images are the primary channel for multimodal models (digest off by default); digest is the text-only fallback; --digest/--no-digest to override

testbed/demo.py

@@ -140,6 +140,7 @@ async def run_llm_agent(
     max_steps: int,
     recorder: FrameRecorder | None = None,
     vision: bool | None = None,
+    digest: 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
@@ -152,6 +153,7 @@ async def run_llm_agent(
         model=model,
         log=lambda role, msg: print(f"[{role}] {msg}"),
         multimodal=vision,
+        digest=digest,
     )
     try:
         return await run_llm_agent_loop(
@@ -310,6 +312,7 @@ async def run_demo(args: argparse.Namespace) -> dict[str, Any]:
                 max_steps=args.max_steps,
                 recorder=recorder,
                 vision=args.vision,
+                digest=args.digest,
             )
         elif args.agent == "scripted":
             summary = await run_scripted_agent(
@@ -331,6 +334,7 @@ async def run_demo(args: argparse.Namespace) -> dict[str, Any]:
                     max_steps=llm_steps,
                     recorder=recorder,
                     vision=args.vision,
+                    digest=args.digest,
                 )
                 if summary.get("interacted"):
                     return summary
@@ -398,6 +402,12 @@ def main() -> int:
         default=None,
         help="pass real camera frames to the model as images (auto-detected for local ollama)",
     )
+    parser.add_argument(
+        "--digest",
+        action=argparse.BooleanOptionalAction,
+        default=None,
+        help="always include the color-grid digest alongside images (off by default for multimodal models)",
+    )
     parser.add_argument(
         "--frame",
         default="demo_final_frame.png",