litellm

mirror of https://github.com/BerriAI/litellm.git synced 2026-11-14 09:03:16 +00:00

History

mateo 1ac32542b1 feat(proxy): serve the requesting Codex release's own model catalog /v1/models?client_version= fetches openai/codex's models.json and prompt.md at rust-v<client_version> once per release, so a model Codex ships after our vendored catalog (gpt-6.1-terra today) keeps its own entry instead of the degraded fallback. The vendored pair moves to 0.166.0 and stays the fallback for releases without a tag, failed fetches, LITELLM_LOCAL_CODEX_CATALOG=True and offline mode Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-11-03 21:27:38 +00:00
..
homebrew	feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy (#29850 )	2026-06-10 13:52:26 -07:00
litellm-core	feat(proxy): serve the requesting Codex release's own model catalog	2026-11-03 21:27:38 +00:00

mateo 1ac32542b1 feat(proxy): serve the requesting Codex release's own model catalog

/v1/models?client_version= fetches openai/codex's models.json and prompt.md at
rust-v<client_version> once per release, so a model Codex ships after our
vendored catalog (gpt-6.1-terra today) keeps its own entry instead of the
degraded fallback. The vendored pair moves to 0.166.0 and stays the fallback
for releases without a tag, failed fetches, LITELLM_LOCAL_CODEX_CATALOG=True
and offline mode

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

2026-11-03 21:27:38 +00:00

homebrew feat(cli): per-agent lite claude / codex / opencode commands that wrap coding agents through the proxy (#29850 ) 2026-06-10 13:52:26 -07:00

litellm-core feat(proxy): serve the requesting Codex release's own model catalog 2026-11-03 21:27:38 +00:00