v1.3.0

New feature: voice input using external recording programs (arecord and sox) and openai whisper1.

Use -v to try! Only tested on linux, welcoming feedback.

v1.3.0-rc.0

New feature: voice input using external recording programs and openai whisper1.

v1.2.2

Doc updates and minor code improvements.

v1.2.1

Better onboarding, error handling and doc.

v1.2.0

Add support for local ollama and set it as the default model for new installs.

v1.1.0

Add Groq support

v1.0.0

BREAKING CHANGES

• remove -i and -p, now infer automatically if you are referring to a template or writing input
• rename most arguments
• remove after_input and system_message config options (were not used)
• add support for multiple context patterns
• add char limit to prevent high cost mistakes (ask for user input)

CODE IMPROVEMENTS

• friendlier UX
• removed a lot of useless stuff
• better separation of concerns
• fixed a bunch of bugs

v0.7.4

Use a near 0 instead of 0 temperature.

Fix logging. (now RUSTLOG=debug sc will have the desired effect)

v0.7.3

Fix anthropic when overriding apis.

v0.7.2

Fixed config location be hardcoded at build time thanks @xlambein