thegrif tried to seat OpenAI at Mike's model table

A bid to give Mike a third AI brain to choose from, built to full parity with the ones already there - though it never made it in.

integrationinfrastructure

Mike already lets you run its legal-AI work on two engines, Anthropic's Claude and Google's Gemini. thegrif proposed adding a third, OpenAI, and did it the thorough way: instead of a token bolt-on, the work followed the same wiring the other two use, so an OpenAI-backed conversation would behave like a first-class option rather than a limping fallback. It offered two OpenAI models to pick from.

The change reached across the whole app in one pass:

Pick your provider and model from the interface, then bring your own API key rather than relying on a shared one.
Hold full conversations - including the app's tool-using steps, not just plain replies - on the OpenAI engine.
Store each provider's settings so your choice sticks between sessions.

The pull request was closed in May without merging, so none of it landed in Mike itself.

So what Worth a look for anyone weighing whether to give users a choice of AI vendor - and a reminder that even a clean, complete build can stall at the door.

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from thegrif/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA	Subject	Author	Date
`860e6ff5`	Add OpenAI as third LLM provider (GPT-5.5, GPT-5.4 Nano)	Tom Griffin	2026-05-01	↗ GitHub
commit body Adds full OpenAI support across backend and frontend, following the existing Claude/Gemini provider pattern: streaming chat with tool use, text completion, model selection UI, API key management, and DB schema. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

SHA

Subject

Author

Date

860e6ff5

Add OpenAI as third LLM provider (GPT-5.5, GPT-5.4 Nano)

Tom Griffin

2026-05-01

↗ GitHub

commit body

Adds full OpenAI support across backend and frontend, following the
existing Claude/Gemini provider pattern: streaming chat with tool use,
text completion, model selection UI, API key management, and DB schema.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-803.md from inside the repo you want the changes in.