ci: add GitHub Actions for tests and auto-formatting

.github/workflows/validate.yml

@@ -0,0 +1,85 @@
+name: Validate
+
+on:
+  pull_request:
+    branches: ["*"]
+
+permissions:
+  contents: write
+
+jobs:
+  format:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run ruff formatting
+        run: uv run ruff format src/ tests/
+
+      - name: Run ruff linting with auto-fix
+        run: uv run ruff check --fix src/ tests/
+
+      - name: Re-run formatting after auto-fix
+        run: uv run ruff format src/ tests/
+
+      - name: Verify all issues are fixed
+        run: |
+          uv run ruff check src/ tests/
+          uv run ruff format --check src/ tests/
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          if [[ -n "$(git status --porcelain)" ]]; then
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit and push formatting changes
+        if: steps.check_changes.outputs.has_changes == 'true'
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add -A
+          git commit -m "style: auto-format code with ruff"
+          git push
+
+  tests:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run tests
+        run: uv run pytest tests/ -v

src/deepwork/__init__.py

@@ -8,6 +8,7 @@
     "__author__",
 ]
 
+
 # Lazy imports to avoid circular dependencies and missing modules during development
 def __getattr__(name: str) -> object:
     """Lazy import for core modules."""
@@ -19,5 +20,6 @@ def __getattr__(name: str) -> object:
             StepInput,
             parse_job_definition,
         )
+
         return locals()[name]
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

src/deepwork/cli/install.py

@@ -20,9 +20,7 @@ class InstallError(Exception):
     pass
 
 
-def _inject_standard_job(
-    job_name: str, jobs_dir: Path, project_path: Path
-) -> None:
+def _inject_standard_job(job_name: str, jobs_dir: Path, project_path: Path) -> None:
     """
     Inject a standard job definition into the project.
 
@@ -54,8 +52,7 @@ def _inject_standard_job(
 
         shutil.copytree(standard_jobs_dir, target_dir)
         console.print(
-            f"  [green]✓[/green] Installed {job_name} "
-            f"({target_dir.relative_to(project_path)})"
+            f"  [green]✓[/green] Installed {job_name} ({target_dir.relative_to(project_path)})"
         )
     except Exception as e:
         raise InstallError(f"Failed to install {job_name}: {e}") from e
@@ -250,9 +247,7 @@ def _install_deepwork(platform_name: str | None, project_path: Path) -> None:
     # Add platform if not already present
     if platform_to_add not in config_data["platforms"]:
         config_data["platforms"].append(platform_to_add)
-        console.print(
-            f"  [green]✓[/green] Added {platform_config.display_name} to platforms"
-        )
+        console.print(f"  [green]✓[/green] Added {platform_config.display_name} to platforms")
     else:
         console.print(f"  [dim]•[/dim] {platform_config.display_name} already configured")
 

src/deepwork/cli/sync.py

@@ -137,9 +137,7 @@ def sync_commands(project_path: Path) -> None:
         if job_hooks_list:
             console.print("  [dim]•[/dim] Syncing hooks...")
             try:
-                hooks_count = sync_hooks_to_platform(
-                    project_path, platform_config, job_hooks_list
-                )
+                hooks_count = sync_hooks_to_platform(project_path, platform_config, job_hooks_list)
                 stats["hooks"] += hooks_count
                 if hooks_count > 0:
                     console.print(f"    [green]✓[/green] Synced {hooks_count} hook(s)")

src/deepwork/core/generator.py

@@ -100,9 +100,7 @@ def _build_step_context(
         instructions_file = job.job_dir / step.instructions_file
         instructions_content = safe_read(instructions_file)
         if instructions_content is None:
-            raise GeneratorError(
-                f"Step instructions file not found: {instructions_file}"
-            )
+            raise GeneratorError(f"Step instructions file not found: {instructions_file}")
 
         # Separate user inputs and file inputs
         user_inputs = [
@@ -142,9 +140,7 @@ def _build_step_context(
                 prompt_file_path = job.job_dir / hook.prompt_file
                 prompt_content = safe_read(prompt_file_path)
                 if prompt_content is None:
-                    raise GeneratorError(
-                        f"Stop hook prompt file not found: {prompt_file_path}"
-                    )
+                    raise GeneratorError(f"Stop hook prompt file not found: {prompt_file_path}")
                 hook_ctx["content"] = prompt_content
             elif hook.is_script():
                 hook_ctx["type"] = "script"
@@ -203,9 +199,7 @@ def generate_step_command(
 
         # Find step index
         try:
-            step_index = next(
-                i for i, s in enumerate(job.steps) if s.id == step.id
-            )
+            step_index = next(i for i, s in enumerate(job.steps) if s.id == step.id)
         except StopIteration as e:
             raise GeneratorError(f"Step '{step.id}' not found in job '{job.name}'") from e
 
@@ -262,4 +256,3 @@ def generate_all_commands(
             command_paths.append(command_path)
 
         return command_paths
-

src/deepwork/core/hooks_syncer.py

@@ -8,7 +8,6 @@
 import yaml
 
 from deepwork.core.detector import PlatformConfig
-from deepwork.utils.yaml_utils import load_yaml
 
 
 class HooksSyncError(Exception):

src/deepwork/core/parser.py

@@ -155,9 +155,7 @@ def validate_dependencies(self) -> None:
         for step in self.steps:
             for dep_id in step.dependencies:
                 if dep_id not in step_ids:
-                    raise ParseError(
-                        f"Step '{step.id}' depends on non-existent step '{dep_id}'"
-                    )
+                    raise ParseError(f"Step '{step.id}' depends on non-existent step '{dep_id}'")
 
         # Check for circular dependencies using topological sort
         visited = set()

src/deepwork/hooks/evaluate_policies.py

@@ -63,7 +63,7 @@ def format_policy_message(policies: list) -> str:
     lines = ["## DeepWork Policies Triggered", ""]
     lines.append(
         "Comply with the following policies. "
-        "To mark a policy as addressed, include `<promise policy=\"Policy Name\">addressed</promise>` "
+        'To mark a policy as addressed, include `<promise policy="Policy Name">addressed</promise>` '
         "in your response."
     )
     lines.append("")

src/deepwork/utils/fs.py

@@ -54,9 +54,7 @@ def safe_read(path: Path | str) -> str | None:
     return path_obj.read_text(encoding="utf-8")
 
 
-def copy_dir(
-    src: Path | str, dst: Path | str, ignore_patterns: list[str] | None = None
-) -> None:
+def copy_dir(src: Path | str, dst: Path | str, ignore_patterns: list[str] | None = None) -> None:
     """
     Recursively copy directory, optionally ignoring patterns.
 

tests/integration/test_full_workflow.py

@@ -10,9 +10,7 @@
 class TestJobWorkflow:
     """Integration tests for complete job workflow."""
 
-    def test_parse_and_generate_workflow(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_parse_and_generate_workflow(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test complete workflow: parse job → generate commands."""
         # Step 1: Parse job definition
         job_dir = fixtures_dir / "jobs" / "complex_job"
@@ -40,7 +38,7 @@ def test_parse_and_generate_workflow(
             assert f"# {job.name}.{job.steps[i].id}" in content
 
             # Check step numbers
-            assert f"Step {i+1} of 4" in content
+            assert f"Step {i + 1} of 4" in content
 
     def test_simple_job_workflow(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test workflow with simple single-step job."""
@@ -68,9 +66,7 @@ def test_simple_job_workflow(self, fixtures_dir: Path, temp_dir: Path) -> None:
         assert "input_param" in content
         assert "Command Complete" in content  # Standalone completion message
 
-    def test_command_generation_with_dependencies(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_command_generation_with_dependencies(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test that generated commands properly handle dependencies."""
         job_dir = fixtures_dir / "jobs" / "complex_job"
         job = parse_job_definition(job_dir)
@@ -99,9 +95,7 @@ def test_command_generation_with_dependencies(
         assert "## Workflow Complete" in step4_content
         assert "## Next Step" not in step4_content
 
-    def test_command_generation_with_file_inputs(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_command_generation_with_file_inputs(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test that generated commands properly handle file inputs."""
         job_dir = fixtures_dir / "jobs" / "complex_job"
         job = parse_job_definition(job_dir)
@@ -125,9 +119,7 @@ def test_command_generation_with_file_inputs(
         assert "primary_research.md" in step4_content
         assert "secondary_research.md" in step4_content
 
-    def test_command_generation_with_user_inputs(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_command_generation_with_user_inputs(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test that generated commands properly handle user parameter inputs."""
         job_dir = fixtures_dir / "jobs" / "complex_job"
         job = parse_job_definition(job_dir)

tests/integration/test_install_flow.py

@@ -16,8 +16,9 @@ def test_install_with_claude(self, mock_claude_project: Path) -> None:
         runner = CliRunner()
 
         result = runner.invoke(
-            cli, ["install", "--platform", "claude", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli,
+            ["install", "--platform", "claude", "--path", str(mock_claude_project)],
+            catch_exceptions=False,
         )
 
         assert result.exit_code == 0
@@ -54,8 +55,7 @@ def test_install_with_auto_detect(self, mock_claude_project: Path) -> None:
         runner = CliRunner()
 
         result = runner.invoke(
-            cli, ["install", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli, ["install", "--path", str(mock_claude_project)], catch_exceptions=False
         )
 
         assert result.exit_code == 0
@@ -101,9 +101,7 @@ def test_install_fails_with_multiple_platforms(self, temp_dir: Path) -> None:
         assert result.exit_code != 0
         assert "Multiple AI platforms detected" in result.output
 
-    def test_install_with_specified_platform_when_missing(
-        self, mock_git_repo: Path
-    ) -> None:
+    def test_install_with_specified_platform_when_missing(self, mock_git_repo: Path) -> None:
         """Test that install fails when specified platform is not present."""
         runner = CliRunner()
 
@@ -121,15 +119,17 @@ def test_install_is_idempotent(self, mock_claude_project: Path) -> None:
 
         # First install
         result1 = runner.invoke(
-            cli, ["install", "--platform", "claude", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli,
+            ["install", "--platform", "claude", "--path", str(mock_claude_project)],
+            catch_exceptions=False,
         )
         assert result1.exit_code == 0
 
         # Second install
         result2 = runner.invoke(
-            cli, ["install", "--platform", "claude", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli,
+            ["install", "--platform", "claude", "--path", str(mock_claude_project)],
+            catch_exceptions=False,
         )
         assert result2.exit_code == 0
 

tests/unit/test_evaluate_policies.py

@@ -1,9 +1,7 @@
 """Tests for the hooks evaluate_policies module."""
 
-import pytest
-
-from deepwork.hooks.evaluate_policies import extract_promise_tags, format_policy_message
 from deepwork.core.policy_parser import Policy
+from deepwork.hooks.evaluate_policies import extract_promise_tags, format_policy_message
 
 
 class TestExtractPromiseTags:
@@ -45,11 +43,11 @@ def test_returns_empty_set_for_no_promises(self) -> None:
 
     def test_multiline_promise_content(self) -> None:
         """Test promise tag with multiline content."""
-        text = '''<promise policy="Complex Policy">
+        text = """<promise policy="Complex Policy">
         I have addressed this by:
         1. Updating the docs
         2. Running tests
-        </promise>'''
+        </promise>"""
         result = extract_promise_tags(text)
         assert result == {"Complex Policy"}