Add model-output chaos end-to-end example

[venkatkrish543re]

Description

Adds an end-to-end example for the model output chaos plugin (strands-agents/evals#284), mirroring chaos_testing.py: pre hook effects (FullRefusal, EmptyResponse) cancel the model call via BeforeModelCallEvent; post hook effects (MalformedJson, Confabulation, SuccessFraming) corrupt output via MessageAddedEvent. Includes an EventProbe plugin asserting both hook events fire in the real agent loop

Also extends the chaos testing docs page with a Model Output Effects section (kept on the existing page since the ChaosPlugin/ChaosCase machinery sections are shared )

Verification

Real Agent(plugins=[chaos_plugin]), Bedrock default model, 5 cases (baseline + 4 effect maps):

Related Issues

strands-agents/evals#284

Documentation PR

Type of Change

Documentation update

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce new warnings.

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have reviewed and understand every line of code in this PR, including any generated by AI tools, and I can explain why it works
• My change is focused and reasonably small; I have split unrelated work into separate PRs
• 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.

[ybdarrenwang]

Can we rename the script chaos_model_testing.py, and the existing chaos_testing.py -> chaos_tool_testing.py?