Repository navigation
Fix integrate agent - #19
Merged
Merged
Conversation
-temporary bypass connect to calender
- Implement AgentChatProvider and AgentChatDrawer for managing chat state and UI. - Add streaming capabilities for real-time message handling in the agent chat. - Update LLMProvider to use a new model and adjust JSON schema handling. - Enhance recruiter decision-making process with candidate batching and compacting methods. - Refactor prompts for clarity and consistency in agent interactions. - Introduce rate limiting for agent chat requests.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces significant improvements and refactoring to the recruiter agent pipeline, including schema updates, prompt clarifications, and a new streaming API route. The changes focus on making candidate recommendations more robust and user-friendly, enforcing stricter schema validation, and improving batch processing and output normalization. Additionally, several prompts and environment variables are updated to ensure consistency and clarity across the system.
Core recruiter pipeline and schema improvements:
full_name,candidate_code,display_name) toCandidateContextandCandidateRecommendationmodels, with normalization logic and stricter validation for candidate recommendations. UpdatedRecruiterDecisionOutputto usecandidatesandsummaryinstead of legacy fields, with backward compatibility and new property accessors.RecruiterDecisionNodeto process candidates in small batches, compact candidate/mission/history data for LLM calls, normalize recommendations, and produce a summary of top matches.full_namewhen available.Prompt and instruction updates:
clarification.status, explicit output field requirements, and improved instructions for candidate recommendation and reflection.API and infrastructure enhancements:
/agentsAPI route with proper error handling, context support, and integration with the agent graph, leveraging FastAPI and Groq/HF providers.Configuration updates:
.env.example.