fix: Add request_timeout to OpenRouter provider to prevent indefinite hangs

When using OpenRouter as the LLM provider, deep research mode can hang
indefinitely if any LLM call takes too long. This adds a 180-second timeout
to ensure requests either complete or fail gracefully instead of hanging forever.

Author: Ubuntu

gpt_researcher/llm_provider/generic/base.py

@@ -220,6 +220,7 @@ def from_provider(cls, provider: str, chat_log: str | None = None, verbose: bool
             )
 
             llm = ChatOpenAI(openai_api_base='https://openrouter.ai/api/v1',
+                     request_timeout=180,
                      openai_api_key=os.environ["OPENROUTER_API_KEY"],
                      rate_limiter=rate_limiter,
                      **kwargs