Mark some tests as slow for quicker feedback

justfile

@@ -20,7 +20,15 @@ install:
 # Testing & Coverage
 # Run tests using pytest.
 test:
-    uv run pytest -n auto {{TESTS_DIR}}
+    uv run pytest {{TESTS_DIR}}
+
+# Run the fast subset of tests (excludes @pytest.mark.slow).
+test-quick:
+    uv run pytest --durations=10 -m "not slow" {{TESTS_DIR}}
+
+# Run only long-running tests marked with @pytest.mark.slow.
+test-slow:
+    uv run pytest -m "slow" {{TESTS_DIR}}
 
 # Run tests and generate coverage data.
 coverage:

pyproject.toml

@@ -129,3 +129,8 @@ exclude = [
   "src/batdetect2/finetune",
   "src/batdetect2/utils",
 ]
+
+[tool.pytest.ini_options]
+markers = [
+  "slow: marks long-running tests that are skipped in quick runs",
+]

tests/test_api_v2/test_api_v2.py

@@ -46,6 +46,7 @@ def test_process_file_returns_recording_level_predictions(
         )
 
 
+@pytest.mark.slow
 def test_process_files_is_batch_size_invariant(
     api_v2: BatDetect2API,
     example_audio_files: list[Path],
@@ -180,6 +181,7 @@ def test_user_can_read_extracted_features_per_detection(
     assert all(vec.size > 0 for vec in feature_vectors)
 
 
+@pytest.mark.slow
 def test_user_can_load_checkpoint_and_finetune(
     tmp_path: Path,
     example_annotations,
@@ -293,6 +295,7 @@ def test_checkpoint_with_same_targets_config_keeps_heads_unchanged(
         )
 
 
+@pytest.mark.slow
 def test_user_can_finetune_only_heads(
     tmp_path: Path,
     example_annotations,
@@ -328,6 +331,7 @@ def test_user_can_finetune_only_heads(
     assert list(finetune_dir.rglob("*.ckpt"))
 
 
+@pytest.mark.slow
 def test_user_can_evaluate_small_dataset_and_get_metrics(
     api_v2: BatDetect2API,
     example_annotations,
@@ -414,6 +418,7 @@ def test_detection_threshold_override_changes_process_file_results(
     )
 
 
+@pytest.mark.slow
 def test_detection_threshold_override_is_ephemeral_in_process_file(
     api_v2: BatDetect2API,
     example_audio_files: list[Path],

tests/test_audio_utils.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pytest
 import torch
 import torch.nn.functional as F
 from hypothesis import given, settings
@@ -10,6 +11,7 @@ from batdetect2.utils import audio_utils, detector_utils
 
 @given(duration=st.floats(min_value=0.1, max_value=1))
 @settings(deadline=None)
+@pytest.mark.slow
 def test_can_compute_correct_spectrogram_width(duration: float):
     samplerate = parameters.TARGET_SAMPLERATE_HZ
     params = parameters.DEFAULT_SPECTROGRAM_PARAMETERS
@@ -89,6 +91,7 @@ def test_pad_audio_without_fixed_size(duration: float):
 
 @given(duration=st.floats(min_value=0.1, max_value=2))
 @settings(deadline=None)
+@pytest.mark.slow
 def test_computed_spectrograms_are_actually_divisible_by_the_spec_divide_factor(
     duration: float,
 ):

tests/test_cli/test_detect.py

@@ -3,11 +3,13 @@
 from pathlib import Path
 
 import pandas as pd
+import pytest
 from click.testing import CliRunner
 
 from batdetect2.cli import cli
 
 
+@pytest.mark.slow
 def test_cli_detect_command_on_test_audio(tmp_path: Path) -> None:
     """User story: run legacy detect on example audio directory."""
 
@@ -29,6 +31,7 @@ def test_cli_detect_command_on_test_audio(tmp_path: Path) -> None:
     assert len(list(results_dir.glob("*.json"))) == 3
 
 
+@pytest.mark.slow
 def test_cli_detect_command_with_non_trivial_time_expansion(
     tmp_path: Path,
 ) -> None:
@@ -52,6 +55,7 @@ def test_cli_detect_command_with_non_trivial_time_expansion(
     assert "Time Expansion Factor: 10" in result.stdout
 
 
+@pytest.mark.slow
 def test_cli_detect_command_with_spec_feature_flag(tmp_path: Path) -> None:
     """User story: request extra spectral features in output CSV."""
 

tests/test_cli/test_predict.py

@@ -20,6 +20,7 @@ def test_cli_predict_help() -> None:
     assert "dataset" in result.output
 
 
+@pytest.mark.slow
 def test_cli_predict_directory_runs_on_real_audio(
     tmp_path: Path,
     tiny_checkpoint_path: Path,

tests/test_cli/test_train.py

@@ -2,6 +2,7 @@
 
 from pathlib import Path
 
+import pytest
 from click.testing import CliRunner
 
 from batdetect2.cli import cli
@@ -19,6 +20,7 @@ def test_cli_train_help() -> None:
     assert "--model" in result.output
 
 
+@pytest.mark.slow
 def test_cli_train_from_checkpoint_runs_on_small_dataset(
     tmp_path: Path,
     tiny_checkpoint_path: Path,

tests/test_contrib.py

@@ -2,11 +2,13 @@
 
 from pathlib import Path
 
+import pytest
 from click.testing import CliRunner
 
 from batdetect2.cli import cli
 
 runner = CliRunner()
+pytestmark = pytest.mark.slow
 
 
 def test_can_process_jeff37_files(

tests/test_detections.py

@@ -2,11 +2,14 @@
 
 import os
 
+import pytest
+
 from batdetect2 import api
 
 DATA_DIR = os.path.join(os.path.dirname(__file__), "data")
 
 
+@pytest.mark.slow
 def test_no_detections_above_nyquist():
     """Test that no detections are made above the nyquist frequency."""
     # Recording donated by @@kdarras

tests/test_model.py

@@ -4,6 +4,7 @@ from pathlib import Path
 from typing import List
 
 import numpy as np
+import pytest
 from hypothesis import given, settings
 from hypothesis import strategies as st
 
@@ -13,6 +14,7 @@ from batdetect2.detector import parameters
 
 @settings(deadline=None, max_examples=5)
 @given(duration=st.floats(min_value=0.1, max_value=2))
+@pytest.mark.slow
 def test_can_import_model_without_pickle(duration: float):
     # NOTE: remove this test once no other issues are found This is a temporary
     # test to check that change in model loading did not impact model behaviour
@@ -42,6 +44,7 @@ def test_can_import_model_without_pickle(duration: float):
     assert predictions_without_pickle == predictions_with_pickle
 
 
+@pytest.mark.slow
 def test_can_import_model_without_pickle_on_test_data(
     example_audio_files: List[Path],
 ):

tests/test_train/test_checkpoints.py

@@ -1,10 +1,13 @@
 from pathlib import Path
 
+import pytest
 from soundevent import data
 
 from batdetect2.config import BatDetect2Config
 from batdetect2.train import run_train
 
+pytestmark = pytest.mark.slow
+
 
 def _build_fast_train_config() -> BatDetect2Config:
     config = BatDetect2Config()

tests/test_train/test_lightning.py

@@ -37,6 +37,7 @@ def test_can_initialize_default_module():
     assert isinstance(module, L.LightningModule)
 
 
+@pytest.mark.slow
 def test_can_save_checkpoint(
     tmp_path: Path,
     clip: data.Clip,
@@ -182,6 +183,7 @@ def test_api_from_checkpoint_reconstructs_model_config(tmp_path: Path):
     assert api.audio_config.samplerate == module.model_config.samplerate
 
 
+@pytest.mark.slow
 def test_train_smoke_produces_loadable_checkpoint(
     tmp_path: Path,
     example_annotations: list[data.ClipAnnotation],