docs: add chaos testing doc and example script

[ybdarrenwang]

Description

Adds documentation and example for the chaos testing module in Strands Evals.

The example demonstrates:

• How chaos testing would impact GoalSuccessRateEvaluator and how to evaluate agent resilience with 3 new chaos evaluators (FailureCommunicationEvaluator, PartialCompletionEvaluator, RecoveryStrategyEvaluator)
• Defining named effect maps (dict[str, dict[str, list[ChaosEffect]]]) for readable failure conditions (e.g., "search_timeout", "total_chaos")
• Using ChaosCase.expand(cases, effect_maps) to generate the Cartesian product of test cases × failure conditions with optional baseline
• Running a ChaosExperiment with ChaosPlugin for transparent fault injection

The example uses ToolSimulator for reproducible tool responses and covers pre-hook effects (tool call failures), post-hook effects (response corruption), and compound multi-tool chaos.

Related Issues

#114

Type of Change

• New content

Checklist

• I have read the CONTRIBUTING document
• My changes follow the project's documentation style
• I have tested the documentation locally using npm run dev
• Links in the documentation are valid and working

---

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

[strands-agent]

This repository has been merged into the strands-agents/harness-sdk monorepo and will be archived shortly. All new development happens there.

If this PR is still relevant, please recreate it against the monorepo. The code now lives under site/. Full commit history was preserved, so your base should be findable.

Apologies for the disruption, and thank you for contributing!