fix: route bedrock/ model ids via LiteLLM Bedrock adapter (#89)

_resolve_llm_params treated any non-anthropic/openai prefix as an HF
router model and wrapped it as 'openai/<id>' pointed at
router.huggingface.co. 'bedrock/...' therefore fell through to HF
router which rejected it with 'model does not exist'. Add a dedicated
bedrock/ branch that passes the model id as-is so LiteLLM's Converse
adapter picks it up with the standard AWS env creds.

agent/core/llm_params.py

@@ -154,6 +154,14 @@ def _resolve_llm_params(
                 params["output_config"] = {"effort": level}
         return params
 
+    if model_name.startswith("bedrock/"):
+        # LiteLLM routes ``bedrock/...`` through the Converse adapter, which
+        # picks up AWS credentials from the standard env vars
+        # (``AWS_ACCESS_KEY_ID`` / ``AWS_SECRET_ACCESS_KEY`` / ``AWS_REGION``).
+        # The Anthropic thinking/effort shape is not forwarded through Converse
+        # the same way, so we leave it off for now.
+        return {"model": model_name}
+
     if model_name.startswith("openai/"):
         params = {"model": model_name}
         if reasoning_effort: