v0.3.0

New

• Guided first-run wizard: pick provider type (Anthropic, OpenAI, Gemini), API key or OAuth, model. Lands in a working chat (#6).
• Wizard text fields accept paste (terminal paste and Ctrl+V).
• OpenAI-compatible endpoints (Ollama, OpenRouter, vLLM) ask for a URL in the wizard.
• OAuth providers print the baifo provider auth <name> command to run before start.

Fixes

• Overlay footer shortcuts use ASCII keycaps, readable on Windows consoles (#1).
• r in /session opens the rename editor instead of printing the CLI command (#2).
• Renaming a non-existent session reports an error instead of false success (#4).
• /help and /root use the same palette colours as the rest (#5).

Changes

• First-run scaffold seeds only the root agent. Internal chores use the root model; add an optional utility: true agent to use a cheaper one.

Documentation

• Fixed the utility-agent section and first-run wizard description in docs/CONFIGURATION.md.
• Config guide link shown on every wizard screen.

Contributors

• @Iminwe reported #1, #2, #4, #5 and #6.

v0.2.0

New

• Model detection per provider. baifo now maps each declared provider to its available models offline, and flags custom endpoints instead of guessing their model list.
• Smarter TUI autocomplete. Model suggestions are now scoped to the selected provider, and provider type suggestions are limited to what baifo actually supports.
• Tighter token control in filesystem tools. The search tool now has a configurable output cap, so broad queries no longer flood the context window.

Performance

• Faster model listing and TUI autocomplete thanks to a one-time catalogue index.

Breaking changes

• The openai-compatible and ollama provider types are gone. Declare any OpenAI compatible endpoint (Ollama, OpenRouter, vLLM) as type: openai with a url.
• Invalid auth modes now fail at startup instead of being silently ignored.

Documentation

• New configuration guide at docs/CONFIGURATION.md, plus an updated README.

v0.1.0

Full Changelog: v0.0.1...v0.1.0