v0.8.1

[0.8.1] - 2025-12-18

This release adds image editing support with OpenRouter. You should send editing instructions after attaching all source images.

Added

• Image editing support (#31)

v0.8.0

[0.8.0] - 2025-12-06

This release adds support for PDF & image attachments and image generation. Image generation is only supported with OpenRouter API.

Added

• cli: Allow opening saved files with xdg-open (#29)
• Allow passing custom JSON params in request (#28)
• Image generation and editing support (OpenRouter) (#27)
• Image & file attachments support (#26)
• Sanitize links (#24)

Changed

• Use API provided token usage info for context size calculation (#25)

v0.7.0

[0.7.0] - 2025-10-29

This release allows a tokenizer to be shared across chat instances. This reduces a memory footprint by approximately 50 MB per chat instance. Additionally, the API is extended to support response streaming.

Added

• Response streaming (#20)

Changed

• Bump dependencies to the latest versions (#22)
• Allow sharing tokenizer across chat instances (#21)
• Allow reusing generic reqwest::Client & expose HTTP timeout setting (#19)

v0.6.0

[0.6.0] - 2025-09-09

This release adds support for getting reasoning summaries and setting reasoning_budget when using OpenRouter API.

Added

• Option to show reasoning summary (only OpenRouter API) (#17)
• Support reasoning_budget with OpenRouter API (#16)

v0.5.0

[0.5.0] - 2025-09-06

This relase adds support for OpenRouter API, exposes options for reasonning_effort and response verbosity, extends token usage reporting, and adds token usage display to the CLI client.

Added

• Allow disabling system message via CLI (#12)
• Support OpenRouter API (#11)
• Allow setting reasoning_effort & verbosity and return detailed token usage (#10)

Changed

• Increase HTTP timeout from 2 min to 5 min (#14)
• Bump dependencies (#13)

Fixed

• Fix error on null system_fingerprint with gpt-4.5-preview (commit)

v0.4.0

[0.4.0] - 2024-11-30

This release adds min_history_tokens context window rolling strategy. It can be handy to keep the last big response in the context. Additionally, the API now provides token usage info.

Added

• Extend API to report tokens used (#8)
• Add min_history_tokens rolling context window strategy (#7)

Fixed

• Fix loading config file passed as CLI option (commit)
• Remove impossible Error::NoTokenizer and update docs (commit)

v0.3.1

[0.3.1] - 2024-09-24

This is a bugfix release fixing compilation of the library with default-features = false.

Changed

• Fix compilation of library with default-features = false (commit)

v0.3.0

[0.3.0] - 2024-09-24

This release introduces several new features and improvements. Key updates are:

• Execution is now async, based on custom OpenAI API client implementation with proper error handling.
• Added the possibility to discard old messages in the context to keep it below allowed max token limit.
• Added support for Azure endpoints.
• The binary dependencies made optional in the library. Use default-features = false when depending on the library.
• CLI can now copy every response to clipboard via xclip on X11.

Added

• Support Azure endpoints (#4)
• Implement rolling context window (#3)
• cli: Support copying every response to clipboard with xclip (commit)

Changed

• Replace openai_api_rust with custom async OpenAI API client (#2)
• cli: Print xclip stderr on invocation failure (commit)
• Make bin dependencies optional for lib (commit)

v0.2.0

[0.2.0] - 2024-09-19

Initial release under name jutella.