fix: stabilize /model reasoning-effort selection (v0.3.5)
Keep pending model outside the picker map, omit undefined reasoningEffort in selectModel payload, auto-apply single-effort models, and surface RPC errors. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "dsh-telegram-channel",
|
||||
"version": "0.3.4",
|
||||
"version": "0.3.5",
|
||||
"description": "DeepSeek Harness Telegram mobile remote: workspace→session, /last context, /model — dsh-plugin",
|
||||
"keywords": [
|
||||
"telegram",
|
||||
|
||||
Reference in New Issue
Block a user