-
Notifications
You must be signed in to change notification settings - Fork 0
DBP-128: reduce AI cost #34
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.
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
The head ref may contain hidden characters: "pan93412/dbp-128-\u964D\u4F4E-ai-\u6210\u672C"
Conversation
pan93412
commented
Oct 29, 2025
- fix(chat): increase timeout to 300s
- fix(chat): switch to Haiku 4.5
- refactor(chat): prune context
- chore: update schema
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR introduces a new Point creation mutation to the GraphQL API, updates comment translations from Chinese to English for question statistics, and optimizes the AI chat API by implementing message pruning and switching to a more cost-effective model.
- Added
createPointmutation with corresponding input type for creating user point records - Translated Chinese comments to English in
QuestionStatisticstype - Optimized chat API with message pruning and reduced AI model token budget
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| schema.graphql | Added CreatePointInput type and createPoint mutation; translated QuestionStatistics comments to English |
| gql/graphql.ts | Generated TypeScript types corresponding to schema changes |
| app/api/chat/route.ts | Added message pruning, switched from claude-sonnet-4-5 to claude-haiku-4-5, reduced thinking token budget, removed maxDuration export |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.