Skip to content

fix: Fix the issue of Moonshot's maximum return token count being limited to 1024 #7673

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
merged 4 commits into from
Sep 5, 2025
Merged

fix: Fix the issue of Moonshot's maximum return token count being limited to 1024 #7673

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
dcbfe00
feat: enhance MoonshotHandler to include max_tokens and update OpenAi…
wangxiaolong100 Sep 4, 2025
5d4ed0e
Update src/api/providers/moonshot.ts
wangxiaolong100 Sep 4, 2025
ad4943f
Update src/api/providers/moonshot.ts
wangxiaolong100 Sep 4, 2025
bafc6c1
feat: add tests for addMaxTokensIfNeeded method in MoonshotHandler
wangxiaolong100 Sep 4, 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
14 changes: 13 additions & 1 deletion src/api/providers/moonshot.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import { moonshotModels, moonshotDefaultModelId } from "@roo-code/types"
import OpenAI from "openai"
import { moonshotModels, moonshotDefaultModelId, type ModelInfo } from "@roo-code/types"

import type { ApiHandlerOptions } from "../../shared/api"

Expand Down Expand Up @@ -36,4 +37,15 @@ export class MoonshotHandler extends OpenAiHandler {
cacheReadTokens: usage?.cached_tokens,
}
}

// Override to always include max_completion_tokens for Moonshot
protected override addMaxTokensIfNeeded(
requestOptions:
| OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming
| OpenAI.Chat.Completions.ChatCompletionCreateParamsNonStreaming,
modelInfo: ModelInfo,
): void {
// Moonshot use max_tokens instead of max_completion_tokens
requestOptions.max_tokens = this.options.modelMaxTokens || modelInfo.maxTokens
}
}
2 changes: 1 addition & 1 deletion src/api/providers/openai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -408,7 +408,7 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
* Note: max_tokens is deprecated in favor of max_completion_tokens as per OpenAI documentation
* O3 family models handle max_tokens separately in handleO3FamilyMessage
*/
private addMaxTokensIfNeeded(
protected addMaxTokensIfNeeded(
requestOptions:
| OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming
| OpenAI.Chat.Completions.ChatCompletionCreateParamsNonStreaming,
Expand Down
Loading