v0.4.6

New dataset supporting proper tool calling, Add Anthropic "messages" style API support, Add on-disk caching for Llama.cpp backend

v0.4.5

Add support for AI Task entities, Replace custom Ollama API implementation with the official ollama-python package to avoid future compatibility issues, Support multiple LLM APIs at once, Fix issues in tool call handling for various backends

v0.4.4

Fix issue with OpenAI backends appending /v1 to all URLs, and fix an issue with tools being serialized into the system prompt.

v0.4.3

Fix an issue with the integration not creating model configs properly during setup

v0.4.2

Fix the following issues:

• not correctly setting default model settings during initial setup
• non-integers being allowed in numeric config fields
• being too strict with finish_reason requirements
• not letting the user clear the active LLM API

v0.4.1

Fix an issue with using Llama.cpp models downloaded from HuggingFace

v0.4

Rewrite integration to support tool calling models/agentic tool use loop, voice streaming, multiple config sub-entries per backend, and dynamic llama.cpp processor selection

v0.3.11

Bug-fixes and llama.cpp version update

NOTE: This is the last release before v0.4, which will drop support for prompt formats and usage of the raw "completions" remote endpoint.

v0.3.10

Add support for the OpenAI "Responses" API endpoint, Update llama.cpp version, Fix for breaking change in HA version 2025.7.0

v0.3.9

Update llama.cpp version, fix installation bugs, fix conversation history not working