feat: adding terminate attribute for after-model-call-event hooks

[gaurav71531]

Description

Supporting agent event loop termination via after-model-call-event hooks

Type of Change

Bug fix
[x] New feature
Breaking change
Documentation update
Other (please describe):

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

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

---

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

[mehtarac]

/strands review

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[poshinchen]

I see that there's conflict, could you resolve it?

[pgrayy]

Per discussion, we want to instead try to expand the concept of interrupt to be used in cases like this where the user stops the agent loop from a hook lifecycle event. The new behaviors to support are:

• Stop agent loop without the expectation of resuming.
  • Currently, interrupts stop the agent loop and have a user provide a response. That response is carried back to where the interrupt occurred without taking another turn in the agent loop.
• Set AgentResult stop reason to "interrupt".