providers: presets for polza/openai/ollama (--provider), keys from env, gpt-5.6-luna default for polza, multimodal heuristic for cloud ids

testbed/llm_agent.py

@@ -67,6 +67,97 @@ NUDGE = (
     "then call a tool (turn or move, or interact if within 1.6 m)."
 )
 
+# ---------------------------------------------------------------------------
+# Provider presets (OpenAI-compatible endpoints)
+# ---------------------------------------------------------------------------
+
+PROVIDERS: dict[str, dict[str, str | None]] = {
+    "polza": {
+        "base_url": "https://polza.ai/api/v1",
+        "env_key": "POLZA_API_KEY",
+        "default_model": "openai/gpt-5.6-luna",
+    },
+    "openai": {
+        "base_url": "https://api.openai.com/v1",
+        "env_key": "OPENAI_API_KEY",
+        "default_model": "gpt-4o-mini",
+    },
+    "ollama": {
+        "base_url": "http://localhost:11434/v1",
+        "env_key": None,
+        "default_model": "gemma4:e2b",
+    },
+}
+
+# Best-effort multimodal detection for non-ollama providers (no way to
+# introspect remotely): ids carrying these markers usually accept images.
+_MULTIMODAL_HINTS = (
+    "gpt-4o",
+    "gpt-4.1",
+    "gpt-5",
+    "gemma",
+    "gemini",
+    "claude",
+    "vl-",
+    "vision",
+    "luna",
+)
+
+
+def resolve_provider(
+    *,
+    provider: str | None,
+    base_url: str | None,
+    api_key: str | None,
+    model: str | None,
+) -> tuple[str, str, str]:
+    """Resolve endpoint + key + model from a provider preset (or explicit args).
+
+    Keys come from the environment (POLZA_API_KEY / OPENAI_API_KEY) so nothing
+    secret lives in the repo or on the command line.
+    """
+    import os
+
+    if provider:
+        preset = PROVIDERS.get(provider)
+        if preset is None:
+            raise ValueError(
+                f"unknown provider {provider!r}; available: {', '.join(PROVIDERS)}"
+            )
+        base_url = preset["base_url"]
+        if model is None:
+            model = preset["default_model"]
+        env_key = preset["env_key"]
+        if api_key is None and env_key:
+            api_key = os.environ.get(env_key)
+        if api_key is None:
+            raise ValueError(
+                f"provider {provider!r} needs an API key: set ${env_key} "
+                "(see https://polza.ai/dashboard/api-keys)"
+            )
+    else:
+        base_url = base_url or str(PROVIDERS["ollama"]["base_url"])
+        model = model or str(PROVIDERS["ollama"]["default_model"])
+        if api_key is None:
+            host = base_url.replace("http://", "").replace("https://", "").split("/")[0]
+            if "polza" in host:
+                api_key = os.environ.get("POLZA_API_KEY")
+                if not api_key:
+                    raise ValueError("set $POLZA_API_KEY (polza.ai/dashboard/api-keys)")
+            elif "openai" in host:
+                api_key = os.environ.get("OPENAI_API_KEY")
+                if not api_key:
+                    raise ValueError("set $OPENAI_API_KEY")
+            else:
+                api_key = "ollama"  # local ollama ignores the key
+    return base_url, api_key, model
+
+
+def looks_multimodal(model: str) -> bool:
+    low = model.lower()
+    return any(h in low for h in _MULTIMODAL_HINTS)
+
+
 COLOR_NAMES = [
     ("beacon_cyan", (120, 210, 235)),
     ("beacon_yellow", (255, 190, 90)),
@@ -236,7 +327,7 @@ class LLMController:
         self.client = client
         self.model = model
         if multimodal is None:
-            multimodal = detect_multimodal(base_url, model)
+            multimodal = looks_multimodal(model) or detect_multimodal(base_url, model)
         self.multimodal = multimodal
         # The color-grid digest is the fallback channel for text-only models.
         # For multimodal models it is off unless explicitly requested.