feat(llm): add a configurable output-token cap

- some model/gateway combinations emit unbounded reasoning/output and hang or
  trip an idle timeout (e.g. some deepseek-v4-flash deployments)
- add an opt-in max_tokens config knob + TRADINGAGENTS_MAX_TOKENS, forwarded to
  every provider when set (Gemini takes it as max_output_tokens); int-coerced,
  rejects non-positive/boolean values #1204

tradingagents/llm_clients/openai_client.py

@@ -164,7 +164,7 @@ class MinimaxChatOpenAI(NormalizedChatOpenAI):
 
 # Kwargs forwarded from user config to ChatOpenAI
 _PASSTHROUGH_KWARGS = (
-    "timeout", "max_retries", "reasoning_effort", "temperature",
+    "timeout", "max_retries", "reasoning_effort", "temperature", "max_tokens",
     "api_key", "callbacks", "http_client", "http_async_client",
 )