What models do you use?
Codebuff uses different models for different tasks. The orchestrator coordinates; subagents handle specific jobs.
Orchestrator
The main agent ("Buffy") coordinates everything:
| Mode | Model |
|---|---|
| Default | Opus 4.7 |
| Plan | Opus 4.7 |
| Max | Opus 4.7 |
| Lite | GPT-5.6 Luna |
Subagents
The orchestrator spawns these for specific jobs:
| Task | Models |
|---|---|
| Code editing | Claude Opus 4.7, GPT-5.1 |
| Thinking/reasoning | Claude Opus 4.7, GPT-5.4 |
| Code review | Claude Opus 4.7, GPT-5.4, GPT-5.6 Luna |
| File discovery | Gemini 3.1 Flash Lite, Gemini 2.5 Flash Lite |
| Terminal commands | Gemini 3.1 Flash Lite |
| Web/docs research | Gemini 3.1 Flash Lite |
Max mode runs multiple implementations in parallel and picks the best one. Default mode runs a single implementation pass. Lite mode uses GPT-5.6 Luna and includes code review support.