Add instrumentation for chat.completions.parse() (structured outputs)

[Nik-Reddy]

Closes #12

Background

Originally tracked in opentelemetry-python-contrib#3449 with a previous implementation in opentelemetry-python-contrib#4416, which was approved by @lmolkova and @lzchen. That PR was closed when the GenAI instrumentations moved to this repository. This PR ports the same approach to the new repo, aligned with its current structure.

Changes

Adds telemetry coverage for OpenAI's chat.completions.parse() method, which powers structured outputs. The parse() method was introduced in openai SDK 1.40.0 and returns a ParsedChatCompletion that extends ChatCompletion with a typed .parsed field on each choice message.

Instrumentation (__init__.py)

• Added _is_parse_supported() version guard that checks for hasattr(Completions, "parse"). On openai < 1.40.0 the wrapping is skipped entirely (the repo pins openai >= 1.26.0).
• Completions.parse and AsyncCompletions.parse are wrapped with the same telemetry functions used for create(). Since ParsedChatCompletion inherits from ChatCompletion, the existing wrapper logic (span attributes, metrics, content capture) handles it without changes.
• Corresponding unwrap() calls added to _uninstrument().

response_format type handling (utils.py)

When parse() is called with response_format=SomePydanticModel, the SDK sends a bare Python type rather than a dict or string. Both attribute extraction paths now handle this:

• Legacy path (get_llm_request_attributes): isinstance(response_format, type) branch sets gen_ai.openai.request.response_format = "json_schema" via the GenAiOpenaiRequestResponseFormatValues.JSON_SCHEMA semconv constant.
• Experimental path (create_chat_invocation): same check sets gen_ai.output.type = "json" via the GenAiOutputTypeValues.JSON semconv constant.

Tests

• test_structured_outputs.py / test_async_structured_outputs.py: sync and async tests covering both content-capture and no-content modes.
• Tests verify the wrapper preserves response.choices[0].message.parsed (the structured output field).
• Tests assert the correct gen_ai.output.type / gen_ai.openai.request.response_format attribute based on semconv mode.
• All tests use VCR cassettes and are skipped on openai < 1.40.0 via pytestmark.

CHANGELOG

Adds an entry under ## Unreleased referencing this PR.

Acceptance criteria (from #12)

• Sync and async parse calls produce spans with the same attributes as create() calls
• gen_ai.output.type is set to json when response_format is a Pydantic model class
• No telemetry regression for existing create() calls
• Tests pass on both old and new semconv paths

What's not changed

• No changes to the stream wrappers, metrics, or util layer. Structured outputs via parse() are non-streaming only.
• No changes to the Responses API path.

[Copilot]

Pull request overview

Adds OpenAI structured outputs telemetry coverage by wrapping chat.completions.parse() and handling Pydantic model response_format values in request attribute extraction.

Changes:

• Adds parse wrapping/unwrapping for sync and async chat completions when supported.
• Maps Python type response formats to JSON/JSON schema telemetry attributes.
• Adds sync/async structured-output tests and VCR cassettes for content/no-content modes.

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
instrumentation/opentelemetry-instrumentation-openai-v2/src/opentelemetry/instrumentation/openai_v2/__init__.py	Adds parse support detection and wrappers.
instrumentation/opentelemetry-instrumentation-openai-v2/src/opentelemetry/instrumentation/openai_v2/utils.py	Handles type-based response_format values.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/test_structured_outputs.py	Adds sync structured-output tests.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/test_async_structured_outputs.py	Adds async structured-output tests.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/structured_outputs_utils.py	Adds shared structured-output test model and prompts.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/cassettes/test_structured_output_with_content.yaml	Adds sync content-mode cassette.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/cassettes/test_structured_output_no_content.yaml	Adds sync no-content cassette.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/cassettes/test_async_structured_output_with_content.yaml	Adds async content-mode cassette.
instrumentation/opentelemetry-instrumentation-openai-v2/tests/cassettes/test_async_structured_output_no_content.yaml	Adds async no-content cassette.