feat: migrate to LangChain v1 packages with enhanced HITL and context management #2
Conversation
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
- Refactor context schemas for agents, introducing `BaseAgentContext` and specialized contexts for data analysis and search capabilities. - Update `SupervisorContext` and `DeepAgentContext` to extend from the new base context, improving configuration management. - Implement `BaseMiddleware` for structured logging and debug capabilities, enhancing middleware components. - Remove deprecated middleware and streamline imports to align with the latest LangChain v1 structure. - Update tests to reflect new context and middleware structures, ensuring comprehensive coverage and functionality. This commit significantly improves the organization and maintainability of the LangGraph agent system, enhancing both context management and middleware capabilities.
- Update README to include detailed instructions for unit and integration testing, emphasizing the new human-in-the-loop (HITL) testing capabilities. - Implement comprehensive HITL integration tests to verify interrupt functionality with real LLM calls, ensuring robust decision-making processes. - Refactor `make_graph` to accept `interrupt_on` and `subagent_interrupts` configurations, allowing for more granular control over interrupt behavior. - Add a new context configuration for HITL, ensuring that interrupt settings are clearly defined and managed. - Introduce a structured prompt for handling tool rejections, guiding the agent's response strategy after user feedback. This commit significantly enhances the sample deep agent's HITL capabilities, improving its responsiveness and adaptability to user interactions.
webup
changed the title
webup
changed the title
webup
changed the title
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.
Overview
This PR migrates the codebase to LangChain v1 ecosystem and introduces enhanced Human-in-the-Loop (HITL) functionality with improved context management.
Key Changes
🔄 LangChain v1 Migration
modify_model_requestwithwrap_model_call/awrap_model_call✨ Enhanced HITL Functionality
interrupt_onandsubagent_interruptsparameters inmake_graph♻️ Context Management Refactor
BaseAgentContextas foundationSupervisorContextandDeepAgentContextto extend baseBaseMiddlewarefor logging and debugging🔧 Infrastructure Updates
create_deep_agentsignatureBreaking Changes