Skip to content

fix: pass reasoning_effort="none" when thinking is disabled for OpenAI-compatible providers #1363

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
lin200083 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: pass reasoning_effort="none" when thinking is disabled for OpenAI-compatible providers #1363

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e1e666
fix: pass reasoning_effort='none' when thinking is disabled for OpenA…
lin200083 Jul 4, 2026
4580c3d
Merge branch 'main' into fix/reasoning-effort-off-none
lin200083 Jul 7, 2026
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
2 changes: 1 addition & 1 deletion packages/kosong/src/providers/openai-common.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ export function isFunctionToolCall<T extends { type: string }>(
export function thinkingEffortToReasoningEffort(effort: ThinkingEffort): string | undefined {
switch (effort) {
case 'off':
return undefined;
return 'none';

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 4, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P1 Badge Gate none to models that support reasoning effort

This maps the global off state to a wire value for every OpenAI-compatible request. ConfigState.provider always calls .withThinking(this.thinkingEffort), and non-thinking or unknown aliases resolve to off; then the OpenAI legacy/responses providers send any non-undefined value as reasoning_effort/reasoning.effort. For OpenAI configs using models such as gpt-4.1/gpt-4o, or gateways that do not accept none, the previously valid “thinking off” request now includes reasoning_effort: "none" and is rejected as an unsupported parameter/value. Please emit none only when the selected model/provider declares support for that disable value, otherwise keep omitting the parameter.

Useful? React with 👍 / 👎.

case 'low':
return 'low';
case 'medium':
Expand Down