Update AI model version to gpt-5 and increase maxDepth to 10 in use cases #1530
Conversation
There was a problem hiding this comment.
Pull request overview
This PR updates the AI model identifier from 'gpt-4o' to 'gpt-5' in the OpenAI provider and increases the maximum recursion depth (maxDepth) from 5 to 10 in AI use case implementations v5 and v6.
Changes:
- Updated defaultModelId and responsesApiModel from 'gpt-4o' to 'gpt-5' in LangchainOpenAIProvider
- Increased maxDepth from 5 to 10 in RequestInfoFromTableWithAIUseCaseV5
- Increased maxDepth from 5 to 10 in RequestInfoFromTableWithAIUseCaseV6
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| backend/src/ai-core/providers/langchain-openai.provider.ts | Updates AI model identifiers to 'gpt-5' |
| backend/src/entities/ai/use-cases/request-info-from-table-with-ai-v5.use.case.ts | Doubles the maximum tool-calling loop depth from 5 to 10 |
| backend/src/entities/ai/use-cases/request-info-from-table-with-ai-v6.use.case.ts | Doubles the maximum tool-calling loop depth from 5 to 10 |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| implements IRequestInfoFromTableV2 | ||
| { | ||
| private readonly maxDepth: number = 5; | ||
| private readonly maxDepth: number = 10; |
There was a problem hiding this comment.
Doubling maxDepth from 5 to 10 iterations could significantly increase API costs and response times. Each iteration involves an AI model call and potentially multiple database queries through tool execution. Consider the following:
- This doubles the maximum number of AI API calls per request (from 5 to 10)
- Each AI call incurs cost and latency
- Complex queries could now run up to 10 database operations in sequence
If this change is intentional to handle more complex queries, consider adding monitoring or logging to track how often the increased depth limit is actually needed in production. This would help validate whether the cost/performance tradeoff is justified.
| private readonly maxDepth: number = 10; | |
| private readonly maxDepth: number = 5; |
| implements IRequestInfoFromTableV2 | ||
| { | ||
| private readonly maxDepth: number = 5; | ||
| private readonly maxDepth: number = 10; |
There was a problem hiding this comment.
Doubling maxDepth from 5 to 10 iterations could significantly increase API costs and response times. Each iteration involves an AI model call and potentially multiple database queries through tool execution. Consider the following:
- This doubles the maximum number of AI API calls per request (from 5 to 10)
- Each AI call incurs cost and latency
- Complex queries could now run up to 10 database operations in sequence
If this change is intentional to handle more complex queries, consider adding monitoring or logging to track how often the increased depth limit is actually needed in production. This would help validate whether the cost/performance tradeoff is justified.
No description provided.