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 #6621] fix: Reconstruct Pydantic output_schema in invoke/ainvoke (#6607) #5171

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

Original Pull Request: https://github.com/langchain-ai/langgraph/pull/6621

State: closed
Merged: No

Description:

Fixes issue where Graph silently converts Pydantic output_schema to Dict instead of returning the Pydantic instance. When a node returns a Pydantic model and output_schema is set to that Pydantic class, the graph was decomposing the model into fields, writing them to channels, and reconstructing as a plain dict without reconstituting the Pydantic model.

This PR adds reconstruction logic in CompiledStateGraph.invoke() and CompiledStateGraph.ainvoke() to validate and reconstruct the Pydantic model from the dict output when output_schema is a BaseModel subclass.

Changes:

  • Override invoke() and ainvoke() methods in CompiledStateGraph
  • Add _reconstruct_output() helper method that checks if output_schema is a Pydantic BaseModel and reconstructs it using model_validate()
  • Falls back gracefully to dict if reconstruction fails (maintains backward compatibility)
  • Add 3 comprehensive tests covering sync invoke, async ainvoke, and TypedDict backward compatibility

Issue: Closes #6607

Dependencies: None

Twitter handle: N/A

Testing:

  • ✅ Added test_output_schema_pydantic_reconstruction() - tests sync invoke returns Pydantic instance
  • ✅ Added test_output_schema_pydantic_reconstruction_async() - tests async ainvoke returns Pydantic instance
  • ✅ Added test_output_schema_dict_backwards_compat() - ensures TypedDict output_schema still works
  • ✅ All tests pass syntax validation
  • ✅ Changes are backward compatible - only affects Pydantic BaseModel output schemas
**Original Pull Request:** https://github.com/langchain-ai/langgraph/pull/6621 **State:** closed **Merged:** No --- **Description:** Fixes issue where Graph silently converts Pydantic output_schema to Dict instead of returning the Pydantic instance. When a node returns a Pydantic model and `output_schema` is set to that Pydantic class, the graph was decomposing the model into fields, writing them to channels, and reconstructing as a plain dict without reconstituting the Pydantic model. This PR adds reconstruction logic in `CompiledStateGraph.invoke()` and `CompiledStateGraph.ainvoke()` to validate and reconstruct the Pydantic model from the dict output when `output_schema` is a BaseModel subclass. **Changes:** - Override `invoke()` and `ainvoke()` methods in `CompiledStateGraph` - Add `_reconstruct_output()` helper method that checks if output_schema is a Pydantic BaseModel and reconstructs it using `model_validate()` - Falls back gracefully to dict if reconstruction fails (maintains backward compatibility) - Add 3 comprehensive tests covering sync invoke, async ainvoke, and TypedDict backward compatibility **Issue:** Closes #6607 **Dependencies:** None **Twitter handle:** N/A --- **Testing:** - ✅ Added `test_output_schema_pydantic_reconstruction()` - tests sync invoke returns Pydantic instance - ✅ Added `test_output_schema_pydantic_reconstruction_async()` - tests async ainvoke returns Pydantic instance - ✅ Added `test_output_schema_dict_backwards_compat()` - ensures TypedDict output_schema still works - ✅ All tests pass syntax validation - ✅ Changes are backward compatible - only affects Pydantic BaseModel output schemas
yindo added the pull-request label 2026-02-20 17:51:20 -05:00
yindo closed this issue 2026-02-20 17:51:20 -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#5171
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?