test and lint

Author: davidlevybooth-dyno

.github/workflows/ci.yml

@@ -0,0 +1,34 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint-and-test:
+    name: Lint, type-check & test
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dev dependencies
+        run: pip install -e ".[dev]"
+
+      - name: ruff format (check)
+        run: ruff format --check src/ tests/
+
+      - name: ruff lint
+        run: ruff check src/ tests/
+
+      - name: mypy
+        run: mypy src/phi/
+
+      - name: pytest
+        run: pytest --tb=short

.pre-commit-config.yaml

@@ -0,0 +1,27 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.6
+    hooks:
+      - id: ruff
+        args: [--fix]
+        types_or: [python, pyi]
+      - id: ruff-format
+        types_or: [python, pyi]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.13.0
+    hooks:
+      - id: mypy
+        args: [src/phi/]
+        pass_filenames: false
+        additional_dependencies: []
+        stages: [pre-push]
+
+  - repo: local
+    hooks:
+      - id: pytest
+        name: pytest
+        entry: pytest --tb=short -q
+        language: system
+        pass_filenames: false
+        stages: [pre-push]

biomodals/modal_af2rank.py

@@ -395,7 +395,7 @@ def print_score(k):
     timeout=int(TIMEOUT),
     secrets=[modal.Secret.from_name("cloudsql-credentials")],
 )
-def run_af2rank(  # type: ignore[no-untyped-def]
+def run_af2rank(
     pdb_str: str,
     pdb_name: str | None = None,
     chains: str = "A",

biomodals/modal_alphafold.py

@@ -654,7 +654,7 @@ def main(
     fasta_str = open(input_fasta).read()
     models_int: list[int] = [int(m) for m in models.split(",")] if models else [1]
 
-    result = alphafold.remote(  # type: ignore[call-arg]
+    result = alphafold.remote(
         fasta_name=Path(input_fasta).name,
         fasta_str=fasta_str,
         models=models_int,

biomodals/modal_bindcraft.py

@@ -83,7 +83,7 @@
     timeout=TIMEOUT * 60,
     secrets=[modal.Secret.from_name("cloudsql-credentials")],
 )
-def bindcraft(  # type: ignore[no-untyped-def]
+def bindcraft(
     design_path,
     binder_name,
     pdb_str,

biomodals/modal_boltz.py

@@ -55,7 +55,7 @@
 DEFAULT_PARAMS = "--use_msa_server --seed 42"
 
 
-def download_model():
+def download_model() -> None:
     """Forces download of the Boltz-1 model by running it once.
 
     Args:
@@ -303,7 +303,7 @@ def boltz(
                         gcs_bucket=gcs_bucket,
                     )
                     return base.create_success_result(
-                        output_files=output_files,  # type: ignore[arg-type]
+                        output_files=output_files,
                         message=f"Boltz completed: {len(output_files)} files uploaded",
                         stdout=result.stdout,
                         num_output_files=len(output_files),
@@ -351,7 +351,7 @@ def boltz(
                             "size_bytes": file_path.stat().st_size,
                             "metadata": {},
                         }
-                        output_files.append(file_dict)  # type: ignore[arg-type]
+                        output_files.append(file_dict)
 
                     return {
                         "exit_code": 0,
@@ -366,7 +366,7 @@ def boltz(
                 # No GCS upload - return local files in dict format
                 if use_base_class:
                     return base.create_success_result(
-                        output_files=output_files_paths,  # type: ignore[arg-type]
+                        output_files=output_files_paths,
                         message=f"Boltz completed: {len(output_files_paths)} files generated",
                         stdout=result.stdout,
                         num_output_files=len(output_files_paths),
@@ -383,7 +383,7 @@ def boltz(
                             "size_bytes": file_path.stat().st_size,
                             "metadata": {},
                         }
-                        output_files.append(file_info)  # type: ignore[arg-type]
+                        output_files.append(file_info)
 
                     return {
                         "exit_code": 0,

biomodals/modal_boltzgen.py

@@ -39,7 +39,7 @@
 TIMEOUT = int(os.environ.get("TIMEOUT", 120))
 
 
-def download_boltzgen_models():
+def download_boltzgen_models() -> None:
     """Download all boltzgen models during image build to avoid runtime timeouts."""
 
     # Download all artifacts to default cache location (~/.cache)
@@ -746,7 +746,7 @@ def boltzgen_run(
 
 
 @app.local_entrypoint()
-def test_merge_only():
+def test_merge_only() -> None:
     """Test merge step only using existing GCS data (for debugging).
 
     IMPORTANT: Get the run_id from the output of test_boltzgen_parallel.py

biomodals/modal_chai1.py

@@ -30,7 +30,7 @@
 TIMEOUT = int(os.environ.get("TIMEOUT", 30))
 
 
-def download_models():
+def download_models() -> None:
     """Downloads Chai-1 models by running a minimal inference.
 
     Args:

biomodals/modal_esm2_predict_masked.py

@@ -23,7 +23,7 @@
 TIMEOUT = int(os.environ.get("TIMEOUT", 15))
 
 
-def download_model():
+def download_model() -> None:
     import esm
 
     _model, _alphabet = esm.pretrained.esm2_t33_650M_UR50D()

biomodals/modal_esmfold.py

@@ -317,7 +317,7 @@ def esmfold(
 
         # Create a Python script that will run in the conda environment
         script_path = Path(tmpdir) / "run_esmfold.py"
-        script_content = f'''
+        script_content = f"""
 import json
 import os
 import sys
@@ -403,7 +403,7 @@ def esmfold(
 summary_path = output_dir / "results.json"
 summary_path.write_text(json.dumps(results, indent=2))
 print(f"Completed {{len(results)}} sequences")
-'''
+"""
 
         script_path.write_text(script_content)