1 Version 0.32.0
════════════════

  • Use success callback when there is partial tool call success, with
    multi-output `:errors' key
  • Always add errors to the prompt after tool calling
  • Add Qwen 3.8, GLM 5.3, GPT 5.6 Sol / Terra / Luna and Gemini 3.7
    Flash (now the default)


2 Version 0.31.4
════════════════

  • Fix missing symbol for Gemini 3.6 Flash
  • Default to Gemini 3.6 Flash for Gemini
  • Added Claude 5 Opus and Sonnet, defaulted Claude to Claude 5 Sonnet


3 Version 0.31.3
════════════════

  • Added Kimi K3.
  • Added Gemini 3.6 Flash and 3.5 Flash Lite, and removed temperature
    settings for these models.
  • Fix some incorrect model identification issues.


4 Version 0.31.2
════════════════

  • Fixed Deepseek streaming tool calling, by [İsa Mert Gürbüz].


[İsa Mert Gürbüz] <https://github.com/isamert>


5 Version 0.31.1
════════════════

  • Fixed Audio API support for Open AI-compatible providers and Ollama
    providers by [Sergey Kostyaev].
  • Added Claude Opus 4.8, StepFun 3.7 Flash, and Claude Fable 5
  • Don't send json format when unsupported; add `json-response' to more
    models that support it.
  • Fix OpenAI compatible names


[Sergey Kostyaev] <https://github.com/s-kostyaev>


6 Version 0.31.0
════════════════

  • Switch Open AI to Responses API, for more functionality
  • Keep reasoning information between turns for improved performance in
    tool calling for Open AI and Claude (Gemini does this already).
  • Fix error with logged tool calls
  • Fix behavior when tool calling has an error; we no longer call the
    success result as well
  • Fix error with Claude tool use requests
  • Fix error with Claude 4.5 Haiku and reasoning support
  • Tweaked Claude name and capabilities to not always support reasoning
  • Added Gemini 3.5, Qwen 3.7


7 Version 0.30.3
════════════════

  • Fix for OpenRouter breakage


8 Version 0.30.2
════════════════

  • Fix json encoding error caused by utf-8 strings for Open AI and
    Ollama
  • Add Claude Opus 4.7, Kimi K2.6, Qwen 3.6, Chat GPT 5.5, Mistral
    Medium 3.5, XiaoMi 2.5, and Deepseek V4.
  • Improved support for Open AI streaming for tool calls, by [Renato
    Ferreira].
  • Add reasoning controls to DeepSeek and OpenAI
  • Fix reasoning for Claude Opus 4.7 and Chat GPT.
  • Changed default Claude model to 4.6 Sonnet
  • Fix text extraction for Claude when using reasoning
  • Return token counts when streaming
  • Return token counts for DeepSeek


[Renato Ferreira] <https://github.com/renatofdds>


9 Version 0.30.1
════════════════

  • Fix lack of reasoning response when doing tool calls
  • Added support for Open AI compatible `reasoning_content' and
    `reasoning' blocks for streaming


10 Version 0.30.0
═════════════════

  • Add `:input-tokens' and `:output-tokens' to multioutput result.
  • Fixed inability of zero-arg tools to be called
  • Added OpenRouter as a top-level model type
  • Add support for Open AI compatible `reasoning_content' and
    `reasoning' blocks
  • Added Qwen 3.5, LFM2 and LFM 2.5 Thinking
  • Added Gemini 3.1 Pro, Gemini 3.1 Flash Lite
  • Added Chat GPT 5.4, with extra context
  • Added StepFun 3.5 Flash
  • Added Gemma 4
  • Added Claude Sonnet 4.6


11 Version 0.29.0
═════════════════

  • Check for tool use mismatches and define new errors for them
  • Normalize false values in tool args or tool call results
  • Add Claude Opus 4.6
  • Fix bug running two async calls in parallel
  • Set Gemini default to 3.0 pro
  • Added Kimi k2.5, GLM-5, and Qwen 3 Coder Next
  • Increased the default context length for unknown models to be more
    up to date
  • Allow Ollama authed keys to be functions


12 Version 0.28.5
═════════════════

  • Improved the tool calling docs
  • Fix for running tools in the original buffer with streaming


13 Version 0.28.4
═════════════════

  • Removed bad interactions made in Ollama tool calls
  • Fixed Ollama tool calling requests
  • Fixed Ollama reasoning, whose API has changed
  • Added gpt-oss, supported low/medium/high reasoning with Ollama
  • Run tools in the original buffer


14 Version 0.28.3
═════════════════

  • Fixed breakage in Ollama streaming tool calling
  • Fixed incorrect Ollama streaming tool use capability reporting
  • Add Gemini 3 Flash


15 Version 0.28.2
═════════════════

  • Add Chat GPT post 5.0 series models, such as 5.1 and 5.2


16 Version 0.28.1
═════════════════

  • Fix error on empty Claude responses


17 Version 0.28.0
═════════════════

  • Add tool calling options, for forbidding or forcing tool choice.
  • Fix bug (or perhaps breaking change) in Ollama tool use.
  …  …
