ARAI ROUTERinai-router.hashnode.dev·1d ago · 9 min readNo Tokens Yet Does Not Mean a Rust LLM Stream Is Safe to RetryYour LLM request returned HTTP 200. The stream produced no text. Then the connection reset. Is it safe to retry the whole request? Not necessarily. “No text reached the UI” answers only one narrow que00
ARAI ROUTERinai-router.hashnode.dev·1d ago · 7 min readTest openai-python Retries with HTTPX MockTransportTo measure how many requests openai-python really sends, inject an httpx.Client backed by MockTransport, count handler calls, and return a synthetic 429. With openai==2.49.0, the default max_retries=200
ARAI ROUTERinai-router.hashnode.dev·Jul 5 · 5 min readConfiguring an OpenAI-compatible base URL in Python and Node.jsMany AI applications start with the official OpenAI SDK pattern: create a client, pass an API key, send a chat completion request, and read the response. That pattern is useful because a lot of compat00