langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

[PR #6532] feat(langgraph): add input schema validation for interrupt resume values #5106

New Issue
Closed
opened 2026-02-20 17:51:14 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:51:14 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langchain-ai/langgraph/pull/6532

State: closed
Merged: No

Description:

This PR adds support for validating resume values against a schema when using interrupt(). Users can now specify an input_schema parameter that enforces the format of resume values, enabling type-safe human-in-the-loop workflows.

Key Changes:

  • Added input_schema parameter to Interrupt class and interrupt() function
  • Implemented _validate_resume_value() helper for schema validation
  • Support for multiple schema types:
    • Pydantic BaseModel classes
    • Python dataclasses
    • Dict schemas (JSON schema format)
  • When a resume value doesn't match the provided schema, the interrupt is re-raised for proper error handling
  • Comprehensive unit tests covering all schema types and edge cases
  • Applied formatting and linting fixes

Behavior:

  • If a resume map is provided and the response format does not match InputSchema, re-raise the interrupt
  • If a null resume is provided and there is one pending interrupt, and the response format does not match, re-raise the interrupt
  • If the response format does match InputSchema, resume the interrupt
  • Backward compatible - works without schema parameter (existing behavior)

Thanks to @kushalgarg101 for proposing this feature and providing valuable feedback on the implementation approach.

Issue: Closes #6531

Dependencies: None

Twitter handle: 0xaaryan

**Original Pull Request:** https://github.com/langchain-ai/langgraph/pull/6532 **State:** closed **Merged:** No --- **Description:** This PR adds support for validating resume values against a schema when using `interrupt()`. Users can now specify an `input_schema` parameter that enforces the format of resume values, enabling type-safe human-in-the-loop workflows. **Key Changes:** - Added `input_schema` parameter to `Interrupt` class and `interrupt()` function - Implemented `_validate_resume_value()` helper for schema validation - Support for multiple schema types: - Pydantic BaseModel classes - Python dataclasses - Dict schemas (JSON schema format) - When a resume value doesn't match the provided schema, the interrupt is re-raised for proper error handling - Comprehensive unit tests covering all schema types and edge cases - Applied formatting and linting fixes **Behavior:** - If a resume map is provided and the response format does not match InputSchema, re-raise the interrupt - If a null resume is provided and there is one pending interrupt, and the response format does not match, re-raise the interrupt - If the response format does match InputSchema, resume the interrupt - Backward compatible - works without schema parameter (existing behavior) Thanks to @kushalgarg101 for proposing this feature and providing valuable feedback on the implementation approach. **Issue:** Closes #6531 **Dependencies:** None **Twitter handle:** 0xaaryan
yindo added the pull-request label 2026-02-20 17:51:14 -05:00
yindo closed this issue 2026-02-20 17:51:14 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#5106
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?