Skip to content

Fix maxOutputTokens compression bug. #8026

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

Merged
scidomino merged 1 commit into from
Sep 8, 2025
Merged

Fix maxOutputTokens compression bug. #8026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
28 changes: 0 additions & 28 deletions packages/core/src/core/client.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -652,34 +652,6 @@ describe('Gemini Client (client.ts)', () => {
});
});

it('attempts to compress with a maxOutputTokens set to the original token count', async () => {
vi.mocked(tokenLimit).mockReturnValue(1000);
vi.mocked(mockContentGenerator.countTokens).mockResolvedValue({
totalTokens: 999,
});

mockGetHistory.mockReturnValue([
{ role: 'user', parts: [{ text: '...history...' }] },
]);

// Mock the summary response from the chat
mockSendMessage.mockResolvedValue({
role: 'model',
parts: [{ text: 'This is a summary.' }],
});

await client.tryCompressChat('prompt-id-2', true);

expect(mockSendMessage).toHaveBeenCalledWith(
expect.objectContaining({
config: expect.objectContaining({
maxOutputTokens: 999,
}),
}),
'prompt-id-2',
);
});

it('should not trigger summarization if token count is below threshold', async () => {
const MOCKED_TOKEN_LIMIT = 1000;
vi.mocked(tokenLimit).mockReturnValue(MOCKED_TOKEN_LIMIT);
Expand Down
1 change: 0 additions & 1 deletion packages/core/src/core/client.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -845,7 +845,6 @@ export class GeminiClient {
},
config: {
systemInstruction: { text: getCompressionPrompt() },
maxOutputTokens: originalTokenCount,
},
},
prompt_id,
Expand Down
Loading