Bug Report
Summary
openai SDK 2.7.1 with pydantic 2.12.4 raises intermittent PydanticUserError ("Pydantic models should inherit from BaseModel, BaseModel cannot be instantiated directly") when deserializing chat completion responses in multiprocess forkserver worker processes.
Environment
openai==2.7.1pydantic==2.12.4pydantic-core==2.41.5- Python 3.12
- Using
multiprocess (dill-based fork of multiprocessing) with forkserver start method
- Backend: vLLM serving
client.chat.completions.create() responses
Reproduction
The error occurs when construct() calls _get_extra_fields_type(cls) which accesses cls.__pydantic_core_schema__["type"]. This triggers MockCoreSchema._get_built() → _attempt_rebuild() → model_rebuild(raise_errors=False, _parent_namespace_depth=5).
The hardcoded _parent_namespace_depth=5 walks 5 frames up the call stack to resolve forward references. When the call stack at that depth doesn't contain the openai types module namespace, model_rebuild silently fails and pydantic raises the error.
In a forkserver setup with ~700 workers processing millions of requests:
- With
DEFER_PYDANTIC_BUILD=true (default): ~0.6% error rate, growing over time. The lazy rebuild retries on each request, mostly succeeding.
- With
DEFER_PYDANTIC_BUILD=false: ~9.5% error rate. Eager build fails at import time for ~9.5% of forkserver workers, and since the failure is cached, ALL requests for those workers fail.
Traceback
openai/_models.py:231 construct()
→ openai/_models.py:405 _construct_field()
→ openai/_models.py:570 construct_type() (iterating choices list)
→ openai/_models.py:561 construct_type() → type_.construct(**value)
→ openai/_models.py:236 construct() → _get_extra_fields_type()
→ openai/_models.py:414 _get_extra_fields_type() → schema["type"] == "model"
→ pydantic/_internal/_mock_val_ser.py:41 __getitem__() → _get_built()
→ pydantic/_internal/_mock_val_ser.py:58 _get_built() → raises PydanticUserError
Related Issues
Suggested Fix
Explicitly calling ChatCompletion.model_rebuild() (and related response types) before creating forkserver workers resolves the issue, since the correctly-built schema is then inherited by all worker processes. The SDK could do this internally — either eagerly at import time regardless of defer_build, or by catching the PydanticUserError in _get_extra_fields_type and calling model_rebuild() as a fallback.
Bug Report
Summary
openaiSDK 2.7.1 withpydantic2.12.4 raises intermittentPydanticUserError("Pydantic models should inherit from BaseModel, BaseModel cannot be instantiated directly") when deserializing chat completion responses inmultiprocessforkserver worker processes.Environment
openai==2.7.1pydantic==2.12.4pydantic-core==2.41.5multiprocess(dill-based fork ofmultiprocessing) withforkserverstart methodclient.chat.completions.create()responsesReproduction
The error occurs when
construct()calls_get_extra_fields_type(cls)which accessescls.__pydantic_core_schema__["type"]. This triggersMockCoreSchema._get_built()→_attempt_rebuild()→model_rebuild(raise_errors=False, _parent_namespace_depth=5).The hardcoded
_parent_namespace_depth=5walks 5 frames up the call stack to resolve forward references. When the call stack at that depth doesn't contain the openai types module namespace,model_rebuildsilently fails and pydantic raises the error.In a forkserver setup with ~700 workers processing millions of requests:
DEFER_PYDANTIC_BUILD=true(default): ~0.6% error rate, growing over time. The lazy rebuild retries on each request, mostly succeeding.DEFER_PYDANTIC_BUILD=false: ~9.5% error rate. Eager build fails at import time for ~9.5% of forkserver workers, and since the failure is cached, ALL requests for those workers fail.Traceback
Related Issues
DEFER_PYDANTIC_BUILDcauses issues)Suggested Fix
Explicitly calling
ChatCompletion.model_rebuild()(and related response types) before creating forkserver workers resolves the issue, since the correctly-built schema is then inherited by all worker processes. The SDK could do this internally — either eagerly at import time regardless ofdefer_build, or by catching thePydanticUserErrorin_get_extra_fields_typeand callingmodel_rebuild()as a fallback.