asgi-replay. As part of submitting LLM to Homebrew core I needed an automated test that demonstrated that the tool was working—but I couldn’t test against the live OpenAI API because I didn’t want to have to reveal my API token as part of the test. I solved this by creating a dummy HTTP endpoint that simulates a hit to the OpenAI API, then configuring the Homebrew test to hit that instead. As part of THAT I ended up building this tiny tool which uses my asgi-proxy-lib package to intercept and log the details of hits made to a service, then provides a mechanism to replay that traffic.
Recent articles
- 2025: The year in LLMs - 31st December 2025
- How Rob Pike got spammed with an AI slop "act of kindness" - 26th December 2025
- A new way to extract detailed transcripts from Claude Code - 25th December 2025