[BlueRaddish]

Motivation & Context

Copying either the ChatResponse.to_updates() or AgentResponse.to_updates() example into a clean interpreter uses an undefined updates variable. Each example should demonstrate its response-to-stream round trip without requiring values from a different example.

Description & Review Guide

• What are the major changes? Import Message and construct a text response in each example before the existing round-trip assertion.
• What is the impact of these changes? Documentation only; the implementation and public APIs are unchanged.
• What do you want reviewers to focus on? Whether each short example is self-contained and still demonstrates to_updates()/from_updates() correctly.

Validation on a standard Ubuntu 24.04 runner with uv 0.12.23:

• Executed each actual method docstring against the unchanged base: both fail with NameError because updates is undefined. Normal public response round trips pass on the same base.
• Executed both corrected snippets through the public exports: both round trips pass.
• uv run --frozen --no-sync pytest packages/core/tests/core/test_types.py -m "not integration" -q: 436 passed, no failures or skips.
• The normal scoped prek hooks pass, and an ordinary Git commit invokes the installed pre-commit hook successfully. The full patch, source/configuration, and tracked dependency lock remain unchanged through validation.

No integration/model/service tests or local SDK tests were executed for this scope.

Related Issue

N/A - trivial change. This replaces the same undefined variable in the two examples with complete text responses and changes no runtime behavior.

AI Assistance

• No material AI assistance was used.
• This is an AI-assisted contribution. I reviewed, understood, and verified all submitted content and accept responsibility for it.

AI assistance details: Codex assisted with diagnosis, the documentation correction, verification recipes, and this description.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR links to an agreed issue with no competing open PR, or the Related Issue section documents a trivial-change or repository-automation exception.
• This is not a breaking change.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[Eduard van Valkenburg (eavanvalkenburg)]

/review

[github-actions]

MAF Automated Review — Iteration 1

Result: No findings
Scope: full PR (1 commit(s)): 324f2942a572
Model: gpt-5.6-sol

Overview

This documentation-only change makes both response-to-update examples self-contained by constructing a response from a public Message before round-tripping it. The package exports, constructor contract, conversion implementation, existing round-trip tests, and direct execution of both snippets support the examples as written. No Critical, High, or Medium residual risk was established.

Reviewed the supplied pull-request change set across correctness, security/reliability, architecture, and failure behavior.
No publishable findings remained after source verification for this scope.