This project is still evolving.
Disappointed with Gemma 4 performance I decided to see if adding reasoning with Ollama would help (after all, I had “great success” with it here: > clai: your useful command line helper! - #4 by merefield )
Unfortunately it didn’t much
gpt-5.4-mini with medium reasoning still shows off the capabilities of this coding agent well, however, and it’s very cost effective. The OpenAI models are just so awesome for this stuff, even mini
master ← add_reasoning_to_context
opened 07:46AM - 04 Jul 26 UTC
- Added provider split:
- openai uses OpenAI API-key auth with the Responses … API.
- openai-compat keeps Chat Completions-compatible API-key behavior.
- openai-chatgpt uses ChatGPT OAuth with the ChatGPT/Codex Responses backend.
- ollama remains the local Ollama provider.
- Added reasoning support:
- Sends reasoning.effort for Responses providers.
- Sends reasoning_effort for openai-compat.
- Sends Ollama think: true when reasoning_level is set and not none.
- Added include_reasoning_in_context config:
- When enabled, returned OpenAI reasoning summaries or Ollama message.thinking are shown as an assistant message before the final
answer.
- The reasoning message is saved into session history and included in future context.
- Updated Ollama support:
- Uses the correct Ollama request key: think.
- Parses Ollama response message.thinking.
- Documented Ollama config with gemma4:latest and reasoning enabled.
- Renamed provider/auth naming:
- Replaced openai-codex with openai-chatgpt.
- Added openai-chatgpt:default as the ChatGPT OAuth profile default.
- Added app version metadata:
- Introduced version 0.5.0.
- Displays version in the TUI header.
- Documents current version in README.
- Updated README:
- Added provider table.
- Clarified Responses vs Chat Completions behavior.
- Documented reasoning context behavior.
- Removed stale .env.example reference.
- Added .codegollm/ to .gitignore to avoid committing runtime session history.
- Expanded tests for:
- OpenAI Responses provider behavior.
- OpenAI-compatible Chat Completions behavior.
- ChatGPT OAuth Responses behavior.
- Ollama think request behavior and message.thinking parsing.
- Reasoning insertion into UI/session/context.
I’ve since updated the system prompt slightly though I’ve not properly evaluated that yet, but it definitely still works!
This was almost one-shotted apart from the tinted glass:
, but this is still useful for any Ollama models and might work well with larger models.
