Document the incremental reasoning-delta streaming, live display pricing, and dynamic model fetch in CHANGELOG.md. Add a Pricing section to README.md explaining the MODEL_COSTS overlay and how to update prices.
1.1 KiB
1.1 KiB
Changelog
0.2.0 - 2026-05-27
- Stream
reasoning-deltaevents incrementally instead of buffering the full thinking block untilreasoning-end. Emitsthinking_start,thinking_delta, andthinking_endevents as they arrive so the UI can show reasoning in real time. - Close open text blocks on
reasoning-startandreasoning-deltaso thinking and text never overlap in the output. - Add live display pricing (
MODEL_COSTS) for known Command Code models. Cost falls back to zero for models not yet in the price table until the Provider API exposes pricing directly. - Fetch models from the Command Code Provider API at startup (inherited from upstream 0.1.1) and overlay the static cost table.
0.1.1 - 2026-05-26
- Align Command Code generate requests with CLI
0.27.2headers and payload shape. - Support official Command Code CLI auth files using the
command-codecredential key. - Handle
reasoning-startand ignore streamedtool-resultevents. - Cap generated
max_tokensby the selected model and the Command Code output limit.
0.1.0 - 2026-05-05
- Initial public release.