diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index f5a51ba8..aa71c1bf 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -68,8 +68,6 @@ jobs:
         run: uv run python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('Qwen/Qwen3-Embedding-0.6B')"
       - name: Run tests with coverage
         run: uv run pytest -m "not integration" --cov=haiku --cov-report=xml
-        env:
-          HF_HUB_OFFLINE: "1"
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         with:
diff --git a/tests/conftest.py b/tests/conftest.py
index 5362a6cf..3c1fb261 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -17,13 +17,14 @@ embeddings:
     vector_dim: 2560
 """)
 os.environ["HAIKU_RAG_CONFIG_PATH"] = str(_test_config_path)
+os.environ["HF_HUB_OFFLINE"] = "1"
 
 import pydantic_ai.models  # noqa: E402
 import pytest  # noqa: E402
 import yaml  # noqa: E402
-from datasets import Dataset, load_dataset, load_from_disk  # noqa: E402
 
 if TYPE_CHECKING:
+    from datasets import Dataset
     from vcr import VCR
 
 setattr(pydantic_ai.models, "ALLOW_MODEL_REQUESTS", False)
@@ -31,7 +32,9 @@ logging.getLogger("vcr.cassette").setLevel(logging.WARNING)
 
 
 @pytest.fixture(scope="session")
-def qa_corpus() -> Dataset:
+def qa_corpus() -> "Dataset":
+    from datasets import Dataset, load_dataset, load_from_disk
+
     ds_path = Path(__file__).parent / "data" / "dataset"
     ds_path.mkdir(parents=True, exist_ok=True)
     try: