fix: stop leaking OpenAI base_url into non-OpenAI provider clients

Default config had backend_url='https://api.openai.com/v1' which was
forwarded to every provider client, including Google. ChatGoogleGenerativeAI
constructed requests against that base, producing malformed URLs like
https://api.openai.com/v1/v1beta/models/gemini-2.5-flash:generateContent
that 404 with empty body.

Discovered while running propagate() against Gemini end-to-end. The
structured-output smoke worked because that path constructed the LLM
without going through the factory and without forwarding backend_url;
propagate() goes through TradingAgentsGraph.__init__ which forwards
config['backend_url'] to every provider.

Fix: default to None. Each provider client falls back to its own
endpoint (api.openai.com for OpenAI via _PROVIDER_CONFIG, Gemini's
default for Google, and so on). The CLI flow already sets backend_url
explicitly per provider when the user picks one, so that path is
unchanged.

Verified: full propagate() now passes end-to-end on both
OpenAI gpt-5.4-mini and Gemini gemini-3-flash-preview, with all nine
structure/log/signal checks green for each.

tradingagents/default_config.py

@@ -11,7 +11,12 @@ DEFAULT_CONFIG = {
     "llm_provider": "openai",
     "deep_think_llm": "gpt-5.4",
     "quick_think_llm": "gpt-5.4-mini",
-    "backend_url": "https://api.openai.com/v1",
+    # When None, each provider's client falls back to its own default endpoint
+    # (api.openai.com for OpenAI, generativelanguage.googleapis.com for Gemini, ...).
+    # The CLI overrides this per provider when the user picks one. Keeping a
+    # provider-specific URL here would leak (e.g. OpenAI's /v1 was previously
+    # being forwarded to Gemini, producing malformed request URLs).
+    "backend_url": None,
     # Provider-specific thinking configuration
     "google_thinking_level": None,      # "high", "minimal", etc.
     "openai_reasoning_effort": None,    # "medium", "high", "low"