DataDesigner/packages/data-designer-engine/tests/engine/models
Nabin Mulepati d6b8433e25
fix: preserve extra_body for LiteLLM to avoid UnsupportedParamsError (#409) (#412)
* fix: preserve extra_body for LiteLLM to avoid UnsupportedParamsError (#409)

TransportKwargs.from_request() flattened extra_body keys into top-level
kwargs, causing LiteLLM to reject provider-specific params like
reasoning_effort via its per-provider allowlist validation.

Add a flatten_extra_body flag (default True for backward compat) so the
LiteLLM bridge can opt out and preserve extra_body as a distinct kwarg
that LiteLLM forwards without validation.

Made-with: Cursor

* fix: address PR #412 review comments

Update stale docstrings in TransportKwargs and facade.py to reflect the
new flatten_extra_body flag, and add an edge-case test for empty
extra_body with flatten disabled.
2026-03-13 13:35:32 -06:00
..
clients fix: preserve extra_body for LiteLLM to avoid UnsupportedParamsError (#409) (#412) 2026-03-13 13:35:32 -06:00
parsers chore: add publish script and update license headers (#253) 2026-01-28 08:47:34 -05:00
recipes chore: add publish script and update license headers (#253) 2026-01-28 08:47:34 -05:00
conftest.py refactor: Decouple ModelFacade from LiteLLM via ModelClient adapter (#373) 2026-03-11 14:30:40 -06:00
stub_secrets.json refactor: slim package refactor into three subpackages (#240) 2026-01-27 13:53:20 -05:00
test_async_engine_switch.py feat(engine): env-var switch for async-first models experiment (#280) 2026-02-13 17:28:35 -05:00
test_facade.py refactor: Decouple ModelFacade from LiteLLM via ModelClient adapter (#373) 2026-03-11 14:30:40 -06:00
test_litellm_overrides.py fix: patch litellm ImageURLListItem to make index field optional (#384) (#385) 2026-03-09 14:09:26 -06:00
test_model_errors.py chore: add publish script and update license headers (#253) 2026-01-28 08:47:34 -05:00
test_model_registry.py feat(engine): env-var switch for async-first models experiment (#280) 2026-02-13 17:28:35 -05:00
test_model_utils.py feat: add message trace support for LLM generation (#272) 2026-01-30 17:03:07 -05:00
test_usage.py feat: add image generation support with multi-modal context (#317) 2026-02-12 14:00:28 -07:00