Pass caller LLM runtime options

agent_builder/builder.py

@@ -30,6 +30,9 @@ class BuilderContext:
     llm_base_url: str | None = None
     llm_api_key: str | None = None
     llm_model: str | None = None
+    llm_temperature_mode: str | None = None
+    llm_temperature: float | None = None
+    llm_extra_body: dict[str, Any] | None = None
 
 
 SYSTEM_PROMPT = """\
@@ -219,12 +222,19 @@ def build_agent_builder(ctx: BuilderContext) -> Any:
     tools = build_tools(ToolContext(
         bucket=ctx.bucket, settings=settings, cp_jwt=ctx.cp_jwt,
     ))
-    model = ChatOpenAI(
-        model=ctx.llm_model or settings.litellm_model,
-        base_url=ctx.llm_base_url or (settings.litellm_url + "/v1"),
-        api_key=ctx.llm_api_key or settings.litellm_key,
-        temperature=0.0,
-    )
+    model_kwargs: dict[str, Any] = {
+        "model": ctx.llm_model or settings.litellm_model,
+        "base_url": ctx.llm_base_url or (settings.litellm_url + "/v1"),
+        "api_key": ctx.llm_api_key or settings.litellm_key,
+        "stream_usage": True,
+    }
+    if ctx.llm_temperature_mode != "omit":
+        model_kwargs["temperature"] = (
+            ctx.llm_temperature if ctx.llm_temperature is not None else 0.0
+        )
+    if ctx.llm_extra_body:
+        model_kwargs["extra_body"] = dict(ctx.llm_extra_body)
+    model = ChatOpenAI(**model_kwargs)
     kwargs: dict[str, Any] = {
         "model": model,
         "tools": tools,