mirror of
https://github.com/NVIDIA-NeMo/DataDesigner
synced 2026-05-24 09:48:29 +00:00
1356408c6e
* adjust plan * feat: remove litellm dependency and bridge path (PR-7) - Delete litellm_bridge.py adapter, litellm_overrides.py, and their tests - Remove LiteLLM fallback branch and DATA_DESIGNER_MODEL_BACKEND env var from clients/factory.py; unknown provider_type now raises ValueError - Remove apply_litellm_patches() call from models/factory.py - Remove LiteLLM exception match arms and DownstreamLLMExceptionMessageParser from models/errors.py; port context window detail extraction to _extract_context_window_detail for native ProviderError path - Remove litellm from lazy_heavy_imports.py and pyproject.toml runtime deps - Remove flatten_extra_body parameter from TransportKwargs.from_request - Clean up LiteLLM references in docstrings, comments, and AGENTS.md - Add full ProviderErrorKind test coverage to test_model_errors.py - Update benchmark script to patch OpenAICompatibleClient instead of CustomRouter Made-with: Cursor * fix: forward tools to _fake_response in benchmark patch The old CustomRouter patch forwarded **kwargs (including tools) to _fake_response, but the new OpenAICompatibleClient patch only passed model and messages — silently disabling tool-call simulation in benchmark scenarios that exercise allow_tools. Made-with: Cursor * fix: address PR-7 review feedback - Return ChatCompletionResponse from benchmark fakes instead of FakeResponse to match the native client contract (facade expects .message, not .choices[0].message) - Add ids= to parametrize block in test_model_errors.py for readability - Remove unnecessary try/except from _extract_context_window_detail; the `if marker in` guard is sufficient - Make context window marker match case-insensitive - Replace stale httpx.AsyncClient callout in async_concurrency.py docstring with generic "async-stateful resources" Made-with: Cursor
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Shared mock helpers for native HTTP adapter tests
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def mock_httpx_response(json_data: dict[str, Any], status_code: int = 200) -> MagicMock:
|
|
resp = MagicMock()
|
|
resp.status_code = status_code
|
|
resp.json.return_value = json_data
|
|
resp.text = json.dumps(json_data)
|
|
resp.headers = {}
|
|
return resp
|
|
|
|
|
|
def make_mock_sync_client(response_json: dict[str, Any], status_code: int = 200) -> MagicMock:
|
|
mock = MagicMock()
|
|
mock.post = MagicMock(return_value=mock_httpx_response(response_json, status_code))
|
|
return mock
|
|
|
|
|
|
def make_mock_async_client(response_json: dict[str, Any], status_code: int = 200) -> MagicMock:
|
|
mock = MagicMock()
|
|
mock.post = AsyncMock(return_value=mock_httpx_response(response_json, status_code))
|
|
return mock
|