# TODO
- [x] add examples of 'fixing' a failed tool call to the dataset
- [x] add proper 'refusals' to the dataset (i.e. tool/device not available or device is already in the desired state)
- [ ] new model based on qwen3 0.6b, 1.7b and 4b  
- [x] new model based on gemma3 270m  
- [x] support AI task API  
- [x] vision support for remote backends  
- [ ] vision support for local backend (llama.cpp + llava)  
- [ ] move llamacpp to a separate process because of all the crashing  
- [ ] optional sampling parameters in options panel (don't pass to backend if not set)  
- [x] update dataset so new models will work with the Assist API  
- [ ] make ICL examples into conversation turns  
- [ ] translate ICL examples + make better ones  
- [ ] figure out DPO to improve response quality  
- [x] proper tool calling support  
- [x] fix old GGUFs to support tool calling  
- [x] home assistant component text streaming support  
- [x] move llama-cpp build to forked repo + add support for multi backend builds (no more -noavx)  
- [x] support new LLM APIs  
    - rewrite how services are called  
    - handle no API selected  
    - rewrite prompts + service block formats  
    - implement new LLM API that has `HassCallService` so old models can still work  
- [x] areas/room support  
- [x] convert requests to aiohttp  
- [x] detection/mitigation of too many entities being exposed & blowing out the context length  
- [x] setup github actions to build wheels that  are optimized for RPIs
- [x] mixtral + prompting (no fine tuning)  
    - add in context learning variables to sys prompt template
    - add new options to setup process for setting prompt style + picking fine-tuned/ICL  
- [x] prime kv cache with current "state" so that requests are faster  
- [x] ChatML format (actually need to add special tokens)  
- [x] Vicuna dataset merge (yahma/alpaca-cleaned)  
- [x] Phi-2 fine tuning  
- [x] Quantize /w llama.cpp  
- [x] Make custom component use llama.cpp + ChatML  
- [x] Continued synthetic dataset improvements (there are a bunch of TODOs in there)  
- [x] Licenses + Attributions  
- [x] Finish Readme/docs for initial release  
- [x] Function calling as JSON  
- [x] Fine tune Phi-1.5 version  
- [x] make llama-cpp-python wheels for "llama-cpp-python>=0.2.24"  
- [x] make a proper evaluation framework to run. not just loss. should test accuracy on the function calling  
- [x] add more remote backends  
    - LocalAI (openai compatible)  
    - Ollama  
    - support chat completions API (might fix Ollama + adds support for text-gen-ui characters)
- [x] more config options for prompt template (allow other than chatml)  
- [x] publish snapshot of dataset on HF  
- [x] use varied system prompts to add behaviors  


## v0.4 TODO for release:
- [x] re-order the settings on the options config flow page. the order is very confusing  
- [x] split out entity functionality so we can support conversation + ai tasks  
- [x] fix icl examples to match new tool calling syntax config  
- [x] set up docker-compose for running all of the various backends  
- [x] config sub-entry implementation
    - [x] base work  
    - [x] generic openai backend  
    - [x] llamacpp backend  
    - [x] ollama backend  
    - [x] tailored_openai backend  
    - [x] generic openai responses backend  
- [x] fix and re-upload all compatible old models (+ upload all original safetensors)  
- [x] config entry migration function  
- [x] re-write setup guide