The frontend safety timeout was hardcoded at 90 s, causing false "Execution timed out" toasts for users running slow local models (e.g. Ollama on limited VRAM or CPU). - Backend: expose `sse_timeout_seconds` in `LLMSettingsResponse`, reading from `VIBE_TRADING_SSE_TIMEOUT` env var (default 90 s) - Frontend: fetch the value from `/settings/llm` on mount and use it instead of the hardcoded 90 000 ms constant - `.env.example`: document the new variable in the Agent Tuning section Co-authored-by: Sky <985369746@qq.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>