feat(agent): add generic type parameters for structured output type i… #1139
+607
−12
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
…nference
Add generic type parameters to Agent, AgentResult, and AgentResultEvent
to enable proper type inference for structured output fields. This allows
type checkers and IDEs to validate field access on specific Pydantic model
types without requiring explicit type casting.
Changes:
- Add Generic[T] base class to AgentResult with T bound to BaseModel
- Add Generic[T] base class to Agent with structured_output_model: Type[T]
- Update Agent invocation methods to return AgentResult[T]
- Add Generic[T] base class to AgentResultEvent for type consistency
- Add comprehensive docstrings with type parameter documentation
- Add test suite for type inference validation (9 new tests)
- Add reproduction test demonstrating the issue (6 tests)
- Update existing tests to work with generic types
Benefits:
- Type-safe field access on structured_output without explicit casting
- IDE autocomplete works correctly on structured output fields
- mypy can validate field access at development time
- Backward compatible - existing code without annotations continues to work
- No runtime overhead - purely type system enhancement
Type inference flow:
agent: Agent[UserProfile] = Agent(
model=model,
structured_output_model=UserProfile
)
result = agent('prompt') # AgentResult[UserProfile]
if result.structured_output is not None:
name: str = result.structured_output.name # Type-safe access
Tested across Python 3.10, 3.11, 3.12, 3.13 - all 1489 tests pass.
anwschne
requested a deployment
to
manual-approval
GitHub Actions
Waiting
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
Hi @anwschne thanks for creating this PR! We are not inclined to make the agent class generic right now to maintain backwards compatibly. Thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Fix type inference for
AgentResult.structured_output" --body "
Summary
AgentandAgentResultfor proper type inference ofstructured_outputAgentResult.structured_outputreturnsBaseModel | Noneinstead of the specific model typeChanges
Agentclass to accept generic type parameterTStructuredOutputAgentResultto use generic type parameter forstructured_outputfieldAgent[TestOutputModel]toagent_response.structured_outputRelated Issues
#1114
Type of Change
Bug fix
Testing
How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli
hatch run prepareChecklist
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.