Skip to content Skip to footer

GitHub Release Monitoring — September 8, 2026

Findings

  1. [1] 2026-09-09 v0.34.0

    Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction, and makes images work…

  2. [2] 2026-09-08 v0.34.0-rc2

    openai: finalize responses at the web search limit (#18328)

  3. [3] 2026-09-08 langchain-openai==1.6.1

    Changes since langchain-openai==1.6.0 fix(openai): bump max_completion_tokens in cache breakpoint integration test (#40284) release(openai): 1.6.1 (#40268) chore(model-profiles): refresh model profile data (#40217) fix(openai): support Azure AD auth with OpenAI 3.8 (#40190) feat(openai): support async tools (#40208) feat(openai): support configuration_update (#40201) chore(model-profiles): refresh model profile data (#40171) fix(openai): route gpt-5.6-sol to responses API (#40133) chore(openai): fix tests (#39972) fix(openai): correct reasoning_effort_levels for…

  4. [4] 2026-09-08 1.63.1.dev20260907

    Streamlit nightly 1.63.1.dev20260907

Where Kimbodo Comes In

Kimbodo builds and operates this in production for businesses — see our AI Application Development practice, or Estimate My AI Application.

Sources

  1. [1] v0.34.0
  2. [2] v0.34.0-rc2
  3. [3] langchain-openai==1.6.1
  4. [4] 1.63.1.dev20260907

Leave a comment

0.0/5