Skip to content

Conversation

@pgrayy
Copy link
Member

@pgrayy pgrayy commented Oct 2, 2025

Description

Support cancelling tool calls from a BeforeToolCallEvent hook. This feature is meant to compliment interrupts as part of the human-in-the-loop (HIL) process. The idea is that if a customer interrupts a tool for human approval and that human sends back a rejection, the tool call will be cancelled. This however could also be extended to use cases outside of HIL.

Usage

class CancelHook(HookProvider):
    def register_hooks(self, registry) -> None:
        registry.add_callback(BeforeToolCallEvent, self.cancel)

    def cancel(self, event: BeforeToolCallEvent) -> None:
        if event.tool_use["name"] == "delete_tool":
            response = event.interrupt("Tool needs approval")
            if response == "REJECT":
                event.cancel_tool = "tool rejected"

agent = Agent(hooks=[CancelHook()])

If rejected, the tool will not execute and the tool result will look as follows:

{
    "toolUseId": "delete_tool",
    "status": "error",
    "content": [{"text": "tool rejected"}],
}

Note, this cancellation does not stop the agent loop. It strictly prevents the given tool from executing. Any other tools executing in sequence or concurrently will continue to do so. All results (including the cancel result) are sent to the model on the next iteration of the agent loop.

Related Issues

#204

Documentation PR

Will follow up on this after all the HIL changes are merged.

Type of Change

New feature

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

  • I ran hatch run prepare: Wrote new unit tests.
  • hatch test tests_integ/tools/executors/*.py: Wrote new integ tests.

Checklist

  • I have read the CONTRIBUTING document
  • I have added any necessary tests that prove my fix is effective or my feature works
  • I have updated the documentation accordingly
  • I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
  • My changes generate no new warnings
  • Any dependent changes have been merged and published

Follow up

The SequentialToolExecutor will execute all tools in sequence even if one fails. Support for cancellation got me thinking that maybe we want to break out of execution if a tool fails since the SequentialToolExecutor is meant to set an order/dependency between calls.


By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

@pgrayy pgrayy marked this pull request as ready for review October 2, 2025 18:28
@pgrayy pgrayy requested a review from zastrowm October 3, 2025 20:02
@pgrayy pgrayy merged commit bab1270 into strands-agents:main Oct 3, 2025
12 checks passed
JackYPCOnline added a commit that referenced this pull request Oct 10, 2025
* feat: replace kwargs with invocation_state in agent APIs

* fix: handle **kwargs in stream_async.

* feat: add a unit test for the change

* Update src/strands/agent/agent.py

Co-authored-by: Nick Clegg <[email protected]>

* tool - executors - concurrent - remove no-op gather (#954)

* feat(telemetry): updated traces to match OTEL v1.37 semantic conventions (#952)

* event loop - handle model execution (#958)

* feat: implement concurrent message reading for session managers (#897)

Replace sequential message loading with async concurrent reading in both
S3SessionManager and FileSessionManager to improve performance for long
conversations. Uses asyncio.gather() with run_in_executor() to read
multiple messages simultaneously while maintaining proper ordering.

Resolves: #874

Co-authored-by: Vamil Gandhi <[email protected]>

* hooks - before tool call event - cancel tool (#964)

* fix(telemetry): removed double serialization for events (#977)

* fix(litellm): map LiteLLM context-window errors to ContextWindowOverflowException (#994)

* feat: add more tests and adjust invocation_state dic structure

* Apply suggestion from @Unshure

Co-authored-by: Nick Clegg <[email protected]>

* fix: adjust **kwargs in multiagent primitives

---------

Co-authored-by: Nick Clegg <[email protected]>
Co-authored-by: Patrick Gray <[email protected]>
Co-authored-by: poshinchen <[email protected]>
Co-authored-by: Vamil Gandhi <[email protected]>
Co-authored-by: Vamil Gandhi <[email protected]>
Co-authored-by: ratish <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants