fix: remove hardcoded Google backend_url that caused 404 errors

The CLI hardcoded https://generativelanguage.googleapis.com/v1 as the
backend_url for the Google provider. When forwarded as base_url to
ChatGoogleGenerativeAI, the google-genai SDK constructs incorrect request
paths resulting in 404 Not Found for all Gemini models.

Fix by setting the Google provider's backend_url to None so the SDK uses
its default endpoint. GoogleClient.get_llm() still forwards base_url when
explicitly provided, preserving proxy/custom endpoint support.

Reproducer:
    ChatGoogleGenerativeAI(
        model="gemini-2.5-flash",
        base_url="https://generativelanguage.googleapis.com/v1",
    ).invoke("Hello")
    # → ChatGoogleGenerativeAIError: 404 Not Found

cli/utils.py

@@ -192,7 +192,7 @@ def select_llm_provider() -> tuple[str, str]:
     # Define OpenAI api options with their corresponding endpoints
     BASE_URLS = [
         ("OpenAI", "https://api.openai.com/v1"),
-        ("Google", "https://generativelanguage.googleapis.com/v1"),
+        ("Google", None),  # google-genai SDK manages its own endpoint internally
         ("Anthropic", "https://api.anthropic.com/"),
         ("xAI", "https://api.x.ai/v1"),
         ("Openrouter", "https://openrouter.ai/api/v1"),

tradingagents/llm_clients/google_client.py

@@ -28,10 +28,8 @@ class GoogleClient(BaseLLMClient):
         self.warn_if_unknown_model()
         llm_kwargs = {"model": self.model}
 
-        # base_url is intentionally NOT passed to ChatGoogleGenerativeAI.
-        # The google-genai SDK manages its own endpoint and API versioning internally.
-        # Passing a base_url (e.g. https://generativelanguage.googleapis.com/v1)
-        # causes 404s because the SDK appends its own paths onto the override URL.
+        if self.base_url:
+            llm_kwargs["base_url"] = self.base_url
 
         for key in ("timeout", "max_retries", "callbacks", "http_client", "http_async_client"):
             if key in self.kwargs: