* fix: configurable timeout for AI requests
Add AI_REQUEST_TIMEOUT_SECONDS environment variable (default 3600s)
to fix timeout issues with slow AI models like self-hosted Ollama.
Previously hardcoded at 300 seconds, causing legitimate long-running
requests to fail.
Fixes#6497
* docs(ai): add critical NGINX configuration warning
Add comprehensive documentation about reverse proxy timeout requirements.
Without proper NGINX/proxy configuration, connections will still timeout
at the proxy layer regardless of backend timeout settings.
Enhanced documentation includes:
- CRITICAL warning about proxy configuration requirement
- Example NGINX configuration snippet
- Explanation of proxy vs backend timeout interaction
This addresses the root cause in issue #6497 where logs showed
"upstream prematurely closed connection" indicating proxy-level timeout.
Part of #6497
5cfc186377