feat(gen-ai): handle model limits COMPASS-10129

[mabaasit]

Description

Checklist

• New tests and/or benchmarks are included
• Documentation is changed or added
• If this change updates the UI, screenshots/videos are added and a design review is requested
• If this change could impact the load on the MongoDB cluster, please describe the expected and worst case impact
• I have signed the MongoDB Contributor License Agreement (https://www.mongodb.com/legal/contributor-agreement)

Motivation and Context

• Bugfix
• New feature
• Dependency update
• Misc

Open Questions

Dependents

Types of changes

• Backport Needed
• Patch (non-breaking change which fixes an issue)
• Minor (non-breaking change which adds functionality)
• Major (fix or feature that would cause existing functionality to change)

[Copilot]

Pull request overview

This PR updates the AI chatbot prompt size handling by adjusting the maximum prompt length limit from 512,000 to 250,000 characters to align with the chatbot slim model's capacity. It also introduces a dedicated error class for handling cases where prompts exceed this limit.

• Reduced MAX_TOTAL_PROMPT_LENGTH constant to match chatbot slim model capabilities
• Introduced AiChatbotPromptTooLargeError to replace generic error handling
• Updated test cases to reflect the new prompt size limits

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
packages/compass-generative-ai/src/utils/gen-ai-prompt.ts	Updated max prompt length constant and replaced generic Error with specific AiChatbotPromptTooLargeError
packages/compass-generative-ai/src/utils/gen-ai-prompt.spec.ts	Updated test cases to use new prompt length limits and verify the new error type
packages/compass-generative-ai/src/chatbot-errors.ts	Added new AiChatbotPromptTooLargeError class extending AtlasServiceError