Skip to content
Closed
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 0 additions & 5 deletions src/api/transform/reasoning.ts
Original file line number Diff line number Diff line change
Expand Up @@ -54,11 +54,6 @@ export const getRooReasoning = ({
return undefined
}

// If enableReasoningEffort is explicitly false, return enabled: false
if (settings.enableReasoningEffort === false) {
return { enabled: false }
}

// If reasoning effort is provided, return it with enabled: true
Comment on lines -57 to 62
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Removing this check breaks the enableReasoningEffort setting for the Roo provider. When a user explicitly sets enableReasoningEffort: false in their settings, the function should return { enabled: false } to respect their preference, but now it will ignore this setting and potentially enable reasoning anyway if reasoningEffort has a value. This creates inconsistency with other providers (getOpenRouterReasoning, getAnthropicReasoning, getOpenAiReasoning) which all respect enableReasoningEffort: false via shouldUseReasoningEffort(). The existing test at line 774-792 expects this behavior and will fail without this check.

if (reasoningEffort && reasoningEffort !== "minimal") {
return { enabled: true, effort: reasoningEffort }
Expand Down
Loading