chore(release): publish 0.5.1 (#44)
This commit is contained in:
@@ -2,9 +2,15 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
## 0.5.1 - 2026-08-11
|
||||
|
||||
- Add model-specific image input capabilities from the `command-code@1.15.1` catalog and forward user and tool-result images using the current Command Code wire format.
|
||||
- Update the Command Code client version header to `1.15.1`.
|
||||
|
||||
### Contributors
|
||||
|
||||
- @DiyarD — reported missing vision support for GPT-5.6 Luna, Muse Spark 1.2, and other vision-capable models.
|
||||
|
||||
## 0.5.0 - 2026-08-07
|
||||
|
||||
- Stop replaying completed assistant reasoning traces to Command Code while preserving visible text and completed tool calls in follow-up request history.
|
||||
|
||||
Reference in New Issue
Block a user