Kaeso 0.5.3 widens what the gateway accepts from Codex and Claude Code. Codex requests now reach Groq, Moonshot and Cohere models, and Claude Code requests reach OpenAI models, with the fields a provider refuses left out or adapted and named in response headers. Fresh installs start with KPMR's model data as of 2 November 2026, which removes openai/gpt-5.2-chat from OpenRouter, and running installs get the same data from KPMR on their own. There are no breaking changes in this release.
Contributors: @dvnold
Full changes: v0.5.2...v0.5.3 (öffnet in einem neuen Tab)
Geändert
Gateway
- A fresh install starts with KPMR's model data as of 2 November 2026, 09:30 UTC: OpenRouter no longer lists
openai/gpt-5.2-chat, and five of its prices and three of its limits changed. Running installs get the same data from KPMR on their own. (#587 (öffnet in einem neuen Tab))
Behoben
- Codex requests reach Groq models. Groq refuses
prompt_cache_key, which Codex sends on every request, so Kaeso leaves a Responses app's key out for Groq and names it in thekaeso-left-outheader; a Chat app's own key is refused before sending, as Groq would refuse it. (#584 (öffnet in einem neuen Tab)) - Claude Code reaches OpenAI models. Its
metadata.user_idis 150 characters long, and OpenAI takes at most 128 insafety_identifier, so an Anthropic app's longer id reaches OpenAI as its SHA-256 hash, the same for the same id, and thekaeso-adaptedheader names it. Ids that fit, and every other provider, are unchanged. (#585 (öffnet in einem neuen Tab)) - Codex requests reach Moonshot and Cohere models. Their profiles refuse
parallel_tool_calls, which Codex sends astrueon every request;trueonly allows parallel calls, so Kaeso leaves it out and names it in thekaeso-left-outheader, whilefalseis still refused. (#586 (öffnet in einem neuen Tab))