LangGraph 1.2.6 fixes nested subgraph checkpointing and streaming
LangGraph version 1.2.6 addresses two critical regressions, restoring correct checkpointing for nested subgraphs and ensuring running subgraphs are canceled when streaming aborts. These fixes are important for stable and predictable execution of complex graph workflows. The update targets developers using LangGraph for multi-step agentic processes or complex state machines.
- →Fix nested subgraph checkpoint inheritance
- →Cancel running subgraphs on stream abort
- →Standardize package README structure
- →Update Tornado dependency
Fixes (2) ›
- Fix nested subgraph checkpoint inheritance
Restores correct checkpoint namespace inheritance for nested subgraphs, fixing a regression introduced in version 1.2.3.
- Cancel running subgraphs on stream abort
Ensures that any currently running subgraphs are properly canceled when a streaming operation is aborted, resolving an issue where subgraphs might continue to run unexpectedly.
Maintenance (2) ›
- Standardize package README structure
The documentation for packages has been updated to use a standardized README file structure.
- Update Tornado dependency
The Tornado dependency within the langgraph library has been updated from version 6.5.5 to 6.5.6.
https://github.com/langchain-ai/langgraph/releases/tag/1.2.6
Related releases
- Pydantic-AI v2.9.0: Security fix, GPT-5.6 models, usage command Pydantic AI Releases ·
- LangGraph 1.2.7: Fixes for delta overwrites and UUID generation LangGraph Releases ·
- pydantic-ai v2.1.0: Anthropic web tools, serialization, and bug fixes Pydantic AI Releases ·
- pydantic-ai v2.5.1: Bug Fixes and Model Compatibility Pydantic AI Releases ·
- crewAI 1.15.0: Conversational Flow Tracking and Declarative Flow Loading CrewAI Releases ·
- OpenAI Agents Python Library v0.17.8: Enhancements and Fixes OpenAI Agents SDK (Python) Releases ·