Thank you! 🙂 I have added a class to our lisette LLM library now to make this easy to use too.
@jeremyphoward
-
Opus Models Excel at HTMX with Contextual Information
By
–
The latest Opus models are good at HTMX nowadays, at least when they have something useful in context to work from.
-
Codex App Server limitations with dynamic tools support
By
–
Dunno if we need an official "OK" or not?…
Currently we're using Codex App Server but it's pretty limited compared to what we need – particularly the experimental dynamic tools support doesn't support adding tools during a session. -
Integrating Technology into Open Source Harness Project
By
–
Oh very cool! @thsottiaux I'd love to use it in our open source harness too:
-
OpenAI Codex API Endpoint Support and Reverse Engineering
By
–
Anyone know whether OpenAI officially supports the use of the `/backend-api/codex/responses` endpoint that Pi and Opencode (IIUC) uses? It doesn't seem to be documented, and was reverse engineered by @simonw – but is now used by some popular harnesses.
-
Claude Code limitations and harness-specific issues discussed
By
–
I don't use Claude Code much any more – I think some of the issues are harness-specific.
-
Maximizing AI Reasoning: Setting Effort Parameters
By
–
Have you tried setting reasoning effort to 'max'?
-
Pi Uses Codex App Server OpenAI Completions Endpoint
By
–
Pi uses Codex App Server, I believe. By "regular" I mean the OpenAI completions REST endpoint.
-
Codex App Server limitations: server-side processing constraints
By
–
Codex App Server is super limited, unfortunately, since it does everything server-side.