Skip to content

fix: respect enableReasoningEffort setting when determining reasoning usage #7049

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+41 −2
Open

fix: respect enableReasoningEffort setting when determining reasoning usage #7049

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d4bc592
fix: respect enableReasoningEffort setting when determining reasoning…
roomote-agent Aug 13, 2025
9af9e46
Update src/shared/api.ts
daniel-lxs Aug 18, 2025
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
31 changes: 30 additions & 1 deletion src/shared/__tests__/api.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -375,12 +375,41 @@ describe("shouldUseReasoningEffort", () => {
reasoningEffort: "medium",
}

// Should return true regardless of settings
// Should return true regardless of settings (unless explicitly disabled)
expect(shouldUseReasoningEffort({ model })).toBe(true)
expect(shouldUseReasoningEffort({ model, settings: {} })).toBe(true)
expect(shouldUseReasoningEffort({ model, settings: { reasoningEffort: undefined } })).toBe(true)
})

test("should return false when enableReasoningEffort is false, even if reasoningEffort is set", () => {
const model: ModelInfo = {
contextWindow: 200_000,
supportsPromptCache: true,
supportsReasoningEffort: true,
}

const settings: ProviderSettings = {
enableReasoningEffort: false,
reasoningEffort: "medium",
}

expect(shouldUseReasoningEffort({ model, settings })).toBe(false)
Copy link
Author

Choose a reason for hiding this comment

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

Good test coverage for the explicit false case! Consider also adding a test for when enableReasoningEffort is explicitly undefined (not just missing) to document that this allows reasoning to proceed - this would make the behavior more explicit.

})

test("should return false when enableReasoningEffort is false, even if model has reasoningEffort property", () => {
const model: ModelInfo = {
contextWindow: 200_000,
supportsPromptCache: true,
reasoningEffort: "medium",
}

const settings: ProviderSettings = {
enableReasoningEffort: false,
}

expect(shouldUseReasoningEffort({ model, settings })).toBe(false)
})

test("should return true when model supports reasoning effort and settings provide reasoning effort", () => {
const model: ModelInfo = {
contextWindow: 200_000,
Expand Down
12 changes: 11 additions & 1 deletion src/shared/api.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,17 @@ export const shouldUseReasoningEffort = ({
}: {
model: ModelInfo
settings?: ProviderSettings
}): boolean => (!!model.supportsReasoningEffort && !!settings?.reasoningEffort) || !!model.reasoningEffort
}): boolean => {
// If enableReasoningEffort is explicitly set to false, reasoning should be disabled
Copy link
Author

Choose a reason for hiding this comment

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

Consider adding a JSDoc comment above the function to document the precedence rules. This would help future developers understand that enableReasoningEffort: false takes absolute precedence over all other settings.

if (settings?.enableReasoningEffort === false) {
return false
Copy link
Author

Choose a reason for hiding this comment

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

Is this intentional? When enableReasoningEffort is undefined (not explicitly set), reasoning can still be enabled if other conditions are met. Should we consider treating undefined the same as false for a more conservative approach, or is the current behavior where only an explicit false disables reasoning the desired one?

}

// Otherwise, use reasoning if:
// 1. Model supports reasoning effort AND settings provide reasoning effort, OR
// 2. Model itself has a reasoningEffort property
return (!!model.supportsReasoningEffort && !!settings?.reasoningEffort) || !!model.reasoningEffort
}

export const DEFAULT_HYBRID_REASONING_MODEL_MAX_TOKENS = 16_384
export const DEFAULT_HYBRID_REASONING_MODEL_THINKING_TOKENS = 8_192
Expand Down
Loading