github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-07-01 14:47:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(openai): clarify expected strict schema error (#38338)

Browse Source 
This clarifies that the strict Responses API schema in
`test_parsed_strict` is intentionally made invalid before asserting
OpenAI raises `BadRequestError`.

The scheduled integration traces for this test can otherwise look like
real product regressions because OpenAI reports that `punchline` is
missing from `required`. The comment now makes the test intent explicit
for future readers and issue triage tooling.
This commit is contained in:
Mason Daugherty
2026-06-20 19:57:11 -04:00
committed by GitHub
parent 7d1a38379d
commit cc6b125f02
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
libs/partners/openai/tests/integration_tests/chat_models/test_responses_api.py
View File

@@ -511,7 +511,9 @@ def test_parsed_strict() -> None:
schema = _convert_to_openai_response_format(Joke)
invalid_schema = cast(dict, _convert_to_openai_response_format(Joke, strict=True))
invalid_schema["json_schema"]["schema"]["required"] = ["setup"] # make invalid
# Intentionally make the strict schema invalid. OpenAI requires every property
# to appear in `required`; omitting `punchline` should produce a BadRequestError.
invalid_schema["json_schema"]["schema"]["required"] = ["setup"]
# Test not strict
response = llm.invoke("Tell me a joke", response_format=schema)