cat-shark/pi-commandcode-provider
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #65 from ThomasByr/main

Browse Source 
feat(models): add GLM5.3-Flash and Qwen3.8-Flash

# Conflicts:
#	CHANGELOG.md
This commit is contained in:
Patrick Wozniak
2026-09-01 23:27:37 +02:00
parent 711b342ddd 9945a67bae
commit 090d5e5310
8 changed files with 86 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+3
View File
@@ -3,6 +3,9 @@
## Unreleased
- Stop silently dropping `role: "developer"` messages (for example OMP advisor steering notes, reminders, and nudges). `/alpha/generate` only accepts `user`, `assistant`, and `tool` roles, so developer messages are now forwarded as `user` messages with identical content in the same chronological position instead of disappearing from the request.
- Add `Qwen/Qwen3.8-Flash` and `z-ai/glm-5.3-flash` with their verified reasoning efforts (`low, medium, xhigh` and `low, high, max`) and display pricing.
- Refresh static model capabilities from `command-code@1.36.0`, adding the free `minimax/minimax-m3-free` model and the `z-ai/glm-5.3-flash` output limit while dropping the retired `stealth/ox-alpha`.
- Refresh display pricing for the current 62-model catalog, adding the free `minimax/minimax-m3-free` and `minimax/minimax-m2.7-free` promotional variants (free through September 5, 2026) and `tencent/hy4-preview`, and removing the retired `stealth/ox-alpha`.
## 0.6.0 - 2026-08-25