feat(multiagent): Add __str__ support for MultiAgentResult and NodeResult

[dosvk]

Add __str__ methods to MultiAgentResult and NodeResult for human-readable
string output, consistent with the existing AgentResult.__str__ behavior.

NodeResult.__str__ delegates to its inner result — AgentResult, nested
MultiAgentResult, or Exception.

MultiAgentResult.__str__ follows the same priority order as AgentResult.__str__:

1. Interrupts (if present) → stringified list of interrupt dicts
2. Node results → each node's text output, prefixed with node name

This addresses the review feedback from #1568 regarding matching the priority
order from AgentResult.__str__.

Related Issues

Closes #1561

Type of Change

New feature

Testing

• Added 5 unit tests covering all code paths: AgentResult delegation,
  Exception delegation, node iteration, interrupt priority, and empty results
• 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.

[mkmeral]

/strands review

[github-actions]

Assessment: Approve

Clean implementation that follows the established AgentResult.__str__ pattern. The priority order for interrupts is consistent with the existing behavior and the delegation pattern in NodeResult is simple and effective.

Review Details

• Code Quality: Well-structured with proper type annotations and Google-style docstrings
• API Consistency: Correctly mirrors AgentResult.__str__ priority order (interrupts → content)
• Testing: 5 tests cover the primary code paths; consider adding tests for multiple nodes and nested MultiAgentResult for completeness

---

Suggestion for improved test coverage:

Consider adding tests for:

1. Multiple nodes - tests the for loop and newline joining in MultiAgentResult.__str__
2. Nested MultiAgentResult - tests the recursive case mentioned in the docstring

Example tests:

def test_multi_agent_result_str_multiple_nodes():
    """Test MultiAgentResult.__str__ with multiple nodes."""
    ar1 = AgentResult(
        message={"role": "assistant", "content": [{"text": "Response 1"}]},
        stop_reason="end_turn", state={}, metrics={},
    )
    ar2 = AgentResult(
        message={"role": "assistant", "content": [{"text": "Response 2"}]},
        stop_reason="end_turn", state={}, metrics={},
    )
    result = MultiAgentResult(
        status=Status.COMPLETED,
        results={"node1": NodeResult(result=ar1), "node2": NodeResult(result=ar2)},
    )
    output = str(result)
    assert "node1: Response 1" in output
    assert "node2: Response 2" in output
    assert "\n" in output


def test_node_result_str_with_nested_multiagent():
    """Test NodeResult.__str__ with nested MultiAgentResult."""
    inner_ar = AgentResult(
        message={"role": "assistant", "content": [{"text": "Nested response"}]},
        stop_reason="end_turn", state={}, metrics={},
    )
    inner_mar = MultiAgentResult(
        status=Status.COMPLETED,
        results={"inner_node": NodeResult(result=inner_ar)},
    )
    outer_node = NodeResult(result=inner_mar)
    assert "inner_node: Nested response" in str(outer_node)