Add test case for multi-command cancellation behavior #1026
+125
−1
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Outdated suggestions cannot be applied.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.
Description
This PR adds a new test case to verify the Agent's cancellation behavior when processing multiple commands in sequence. Currently, the test suite covers cancellation behavior for single commands, but lacks coverage for scenarios where multiple commands are queued.
The new test case ensures that:
Motivation and Context
Ensuring proper cancellation behavior is critical for the agent's reliability. When a user cancels an agent operation, we need to guarantee that:
This test strengthens our confidence in the cancellation mechanism by testing a more complex scenario with multiple sequential commands.
Implementation Details
The test creates a custom FakeStream implementation that yields multiple function_call items in sequence, simulating an agent that wants to run multiple shell commands. It then:
How Has This Been Tested?
The test has been verified to pass locally and correctly fail when the cancellation behavior is broken.
Types of changes
Checklist: