You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Remove /think command and session-level thinking toggle
Thinking is now solely driven by the model's thinking_budget config.
If a model has thinking_budget set or requires thinking (e.g. o-series),
it uses thinking. There is no longer a per-session toggle.
Removed:
- /think slash command from TUI
- Session.Thinking field and WithThinking option
- options.WithThinking model option and applyOverrides
- Thinking toggle from sidebar, server API, session state
- ThinkingConfigured from agent and teamloader
- All related handlers, messages, and tests
Assisted-By: docker-agent
Copy file name to clipboardExpand all lines: agent-schema.json
+8-11Lines changed: 8 additions & 11 deletions
Original file line number
Diff line number
Diff line change
@@ -554,20 +554,12 @@
554
554
"description": "Whether to track usage"
555
555
},
556
556
"thinking_budget": {
557
-
"description": "Controls reasoning effort/budget. Use 'none' or 0 to disable thinking. OpenAI: string levels ('minimal','low','medium','high'). Anthropic: integer token budget (1024-32768), 'adaptive' (lets the model decide), or effort levels ('low','medium','high','max') which use adaptive thinking with the given effort. Amazon Bedrock (Claude): integer token budget or effort levels ('low','medium','high') mapped to token budgets. Google Gemini 2.5: integer token budget (-1 for dynamic, 0 to disable, 24576 max). Google Gemini 3: string levels ('minimal' Flash only,'low','medium','high'). Thinking is only enabled when explicitly configured.",
557
+
"description": "Controls reasoning effort/budget. Use 'none' or 0 to disable thinking. OpenAI: string levels ('minimal','low','medium','high','xhigh'). Anthropic: integer token budget (1024-32768), 'adaptive' (adaptive thinking with high effort by default), 'adaptive/<effort>' where effort is low/medium/high/max (adaptive thinking with specified effort), or effort levels ('low','medium','high','max') which use adaptive thinking with the given effort. Amazon Bedrock (Claude): integer token budget or effort levels ('low','medium','high') mapped to token budgets. Google Gemini 2.5: integer token budget (-1 for dynamic, 0 to disable, 24576 max). Google Gemini 3: string levels ('minimal' Flash only,'low','medium','high'). Thinking is only enabled when explicitly configured.",
558
558
"oneOf": [
559
559
{
560
560
"type": "string",
561
-
"enum": [
562
-
"none",
563
-
"minimal",
564
-
"low",
565
-
"medium",
566
-
"high",
567
-
"max",
568
-
"adaptive"
569
-
],
570
-
"description": "Reasoning effort level. 'adaptive'/'max' are Anthropic-specific. Use 'none' to disable thinking."
"description": "Reasoning effort level. 'adaptive' uses adaptive thinking with high effort (default). 'adaptive/<effort>' specifies the effort level (low/medium/high/max). Use 'none' to disable thinking."
0 commit comments