examples: validate Responses function tool output

[jbeckwith-oai]

Summary

• inspect mixed Responses output items before reading parsed function arguments
• print only parsed GetWeather function calls
• fail clearly when the response has no valid parsed tool call
• add offline regression coverage for mixed, empty, and invalid parsed outputs

Scope and compatibility

The change is limited to a handwritten example and its test. It does not modify generated code, runtime SDK behavior, public APIs, type signatures, transport, authentication, serialization, dependencies, or supported Ruby versions.

Generator ownership: examples/ and this regression test are handwritten repository artifacts, so no regeneration is required.

Validation

• focused example regression: 3 runs, 17 assertions, 0 failures
• Responses model tests: 8 runs, 8 assertions, 0 failures
• example E2E harness tests: 15 runs, 187 assertions, 0 failures
• offline example inventory: 30 examples classified
• repository lint, rubyfmt, RuboCop, Sorbet, RBS, and directive validation: passed
• non-Bedrock suite excluding one sandbox-incompatible realtime proxy socket test: 1089 runs, 9805 assertions, 0 failures
• complete non-Bedrock attempt: 1090 runs, 9805 assertions, 0 failures, 1 unrelated local proxy socket error
• thermo-nuclear code-quality review: no findings
• git diff --check: passed

[github-actions]

Castiron custom code

✅ No new custom-code files detected.

48 mixed files remain; 0 existing customizations changed.

Compared 851f53438f5a → c2c1e7b9bf91. Generated baselines verified.

48 existing customizations unchanged

• lib/openai.rb
• lib/openai/client.rb
• lib/openai/models/chat/chat_completion_message.rb
• lib/openai/models/chat/chat_completion_message_function_tool_call.rb
• lib/openai/models/chat/completion_create_params.rb
• lib/openai/models/response_format_json_schema.rb
• lib/openai/models/responses/function_tool.rb
• lib/openai/models/responses/response.rb
• lib/openai/models/responses/response_create_params.rb
• lib/openai/models/responses/response_format_text_config.rb
• lib/openai/models/responses/response_format_text_json_schema_config.rb
• lib/openai/models/responses/response_function_tool_call.rb
• lib/openai/models/responses/response_function_web_search.rb
• lib/openai/models/responses/response_output_text.rb
• lib/openai/models/responses/tool.rb
• lib/openai/resources/beta/responses.rb
• lib/openai/resources/beta/threads.rb
• lib/openai/resources/chat/completions.rb
• lib/openai/resources/files.rb
• lib/openai/resources/responses.rb
• lib/openai/resources/vector_stores/file_batches.rb
• lib/openai/resources/vector_stores/files.rb
• lib/openai/resources/webhooks.rb
• rbi/openai/client.rbi
• rbi/openai/models/chat/chat_completion_message.rbi
• rbi/openai/models/chat/chat_completion_message_function_tool_call.rbi
• rbi/openai/models/chat/completion_create_params.rbi
• rbi/openai/models/response_format_json_schema.rbi
• rbi/openai/models/responses/response.rbi
• rbi/openai/models/responses/response_create_params.rbi
• rbi/openai/models/responses/response_function_tool_call.rbi
• rbi/openai/models/responses/response_function_web_search.rbi
• rbi/openai/models/responses/response_output_text.rbi
• rbi/openai/resources/chat/completions.rbi
• rbi/openai/resources/files.rbi
• rbi/openai/resources/responses.rbi
• rbi/openai/resources/vector_stores/file_batches.rbi
• rbi/openai/resources/vector_stores/files.rbi
• scripts/castiron/README.md
• scripts/castiron/custom_code_report.py

8 more in the full report.

A changed generated baseline means this report cannot reliably identify which handwritten lines changed.

Inspect the custom-code diff

Download the exact patch produced by this run (requires repository access):

gh run download 32446845547 --repo openai/openai-ruby \
  --name castiron-custom-code-32446845547-1 --dir /tmp/castiron-custom-code-32446845547-1
git apply --stat /tmp/castiron-custom-code-32446845547-1/custom-code.patch
cat /tmp/castiron-custom-code-32446845547-1/custom-code.patch

Or reproduce it from an SDK checkout containing the vendored reporter:

git fetch --no-tags origin 851f53438f5afc7f32e3ccbe866fd03bbade576a c2c1e7b9bf91ff7ae5ad63d6f236ad551922fa49
python3 scripts/castiron/custom_code_report.py report \
  --base 851f53438f5afc7f32e3ccbe866fd03bbade576a \
  --head c2c1e7b9bf91ff7ae5ad63d6f236ad551922fa49 --fetch --require-head-hash --public \
  --out /tmp/castiron-custom-code-c2c1e7b9bf91
cat /tmp/castiron-custom-code-c2c1e7b9bf91/custom-code.patch

This is the current full custom patch for mixed files, not an attribution of only the handwritten lines changed by this PR.

Full report and patch

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-08-21T04:25:35.010544Z	c2c1e7b	Draft marked ready
🔒 Security Review	✅ Completed 2026-08-21T04:25:49.874349Z	c2c1e7b	Draft marked ready

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[openai-sdks]

OkTest Summary

✅ 237/237 SDK tests passed in 9.22s for Ruby SDK PR #505.

Test results — 42 files

Test	Result	Time
tests/chat-completions-complex-body.test.ts	✅ Passed	147ms
tests/chat-completions-create.test.ts	✅ Passed	188ms
tests/chat-completions-stream.test.ts	✅ Passed	116ms
tests/files-content-binary.test.ts	✅ Passed	172ms
tests/files-create-multipart.test.ts	✅ Passed	275ms
tests/files-list-pagination.test.ts	✅ Passed	128ms
tests/initialize-config.test.ts	✅ Passed	244ms
tests/instance-isolation.test.ts	✅ Passed	162ms
tests/models-list.test.ts	✅ Passed	266ms
tests/responses-background-lifecycle.test.ts	✅ Passed	135ms
tests/responses-body-method-errors.test.ts	✅ Passed	376ms
tests/responses-cancel-timeout.test.ts	✅ Passed	175ms
tests/responses-cancel.test.ts	✅ Passed	186ms
tests/responses-compact-retries.test.ts	✅ Passed	219ms
tests/responses-compact.test.ts	✅ Passed	237ms
tests/responses-create-advanced-stream.test.ts	✅ Passed	140ms
tests/responses-create-advanced.test.ts	✅ Passed	141ms
tests/responses-create-disconnect.test.ts	✅ Passed	1.063s
tests/responses-create-errors.test.ts	✅ Passed	385ms
tests/responses-create-malformed-api-responses.test.ts	✅ Passed	149ms
tests/responses-create-retries.test.ts	✅ Passed	244ms
tests/responses-create-stream-failures.test.ts	✅ Passed	125ms
tests/responses-create-stream-timeout.test.ts	✅ Passed	193ms
tests/responses-create-stream-wire.test.ts	✅ Passed	2.359s
tests/responses-create-stream.test.ts	✅ Passed	73ms
tests/responses-create-terminal-states.test.ts	✅ Passed	295ms
tests/responses-create-timeout.test.ts	✅ Passed	174ms
tests/responses-create.test.ts	✅ Passed	220ms
tests/responses-delete.test.ts	✅ Passed	245ms
tests/responses-input-items-errors.test.ts	✅ Passed	144ms
tests/responses-input-items-list.test.ts	✅ Passed	151ms
tests/responses-input-items-options.test.ts	✅ Passed	147ms
tests/responses-input-tokens-count-timeout.test.ts	✅ Passed	213ms
tests/responses-input-tokens-count.test.ts	✅ Passed	201ms
tests/responses-malformed-inputs.test.ts	✅ Passed	2.027s
tests/responses-not-found-errors.test.ts	✅ Passed	275ms
tests/responses-parse.test.ts	✅ Passed	164ms
tests/responses-retrieve-retries.test.ts	✅ Passed	273ms
tests/responses-retrieve.test.ts	✅ Passed	177ms
tests/responses-stored-method-errors.test.ts	✅ Passed	607ms
tests/retry-behavior.test.ts	✅ Passed	3.027s
tests/sdk-error-shape.test.ts	✅ Passed	366ms

View OkTest run #32446847158

_{SDK merge (7fe8b4b34904) · head (c2c1e7b9bf91) · base (851f53438f5a) · OkTest (2b1bdfd25e98)}

[apcha-oai]

[sdk codex review] Approved after two independent reviews of c2c1e7b. Verified mixed-output discrimination, typed GetWeather parsing, multiple valid calls, clear empty/invalid-output failure, and serial-test isolation without SDK API changes. Independent checks passed: 13 focused/helper tests with 53 assertions, five separate real-parser/example scenarios, syntax, and offline inventory. The local test run used a fallback mock dependency rather than the exact locked bundle; no live API tests were run. All current required checks pass. Latest main's tooling-only changes were reviewed, and head/base/author/draft/mergeability and feedback were rechecked before submission.