CI updates for linting, testing & publishing package

.bumpversion.cfg

@@ -0,0 +1,12 @@
+[bumpversion]
+current_version = 0.3.0
+commit = True
+tag = True
+
+[bumpversion:file:setup.py]
+search = version="{current_version}"
+replace = version="{new_version}"
+
+[bumpversion:file:stagehand/__init__.py]
+search = __version__ = "{current_version}"
+replace = __version__ = "{new_version}" 

.github/README_PUBLISHING.md

@@ -0,0 +1,81 @@
+# Publishing stagehand-python to PyPI
+
+This repository is configured with a GitHub Actions workflow to automate the process of publishing new versions to PyPI.
+
+## Prerequisites
+
+Before using the publishing workflow, ensure you have:
+
+1. Set up the following secrets in your GitHub repository settings:
+   - `PYPI_USERNAME`: Your PyPI username
+   - `PYPI_API_TOKEN`: Your PyPI API token (not your password)
+
+## How to Publish a New Version
+
+### Manual Trigger
+
+1. Go to the "Actions" tab in your GitHub repository
+2. Select the "Publish to PyPI" workflow from the list
+3. Click "Run workflow" on the right side
+4. Configure the workflow:
+   - Choose the release type:
+     - `patch` (e.g., 0.3.0 → 0.3.1) for bug fixes
+     - `minor` (e.g., 0.3.0 → 0.4.0) for backward-compatible features
+     - `major` (e.g., 0.3.0 → 1.0.0) for breaking changes
+   - Toggle "Create GitHub Release" if you want to create a GitHub release
+5. Click "Run workflow" to start the process
+
+### What Happens During Publishing
+
+The workflow will:
+
+1. Checkout the repository
+2. Set up Python environment
+3. Install dependencies
+4. **Run Ruff linting checks**:
+   - Checks for code style and quality issues
+   - Verifies formatting according to project standards
+   - Fails the workflow if issues are found
+5. Run tests to ensure everything works
+6. Update the version number using bumpversion
+7. Build the package
+8. Upload to PyPI
+9. Push the version bump commit and tag
+10. Create a GitHub release (if selected)
+
+## Code Quality Standards
+
+This project uses Ruff for linting and formatting. The workflow enforces these standards before publishing:
+
+- Style checks following configured rules in `pyproject.toml`
+- Format verification without making changes
+- All linting issues must be fixed before a successful publish
+
+To run the same checks locally:
+```bash
+# Install Ruff
+pip install ruff
+
+# Run linting
+ruff check .
+
+# Check formatting
+ruff format --check .
+
+# Auto-fix issues where possible
+ruff check --fix .
+ruff format .
+
+# Use Black to format the code
+black .
+```
+
+## Troubleshooting
+
+If the workflow fails, check the following:
+
+1. **Linting errors**: Fix any issues reported by Ruff
+2. Ensure all secrets are properly set
+3. Verify that tests pass locally
+4. Check if you have proper permissions on the repository
+5. Make sure you have a PyPI account with publishing permissions 

.github/workflows/publish.yml

@@ -0,0 +1,82 @@
+name: Publish to PyPI
+
+on:
+  workflow_dispatch:
+    inputs:
+      release_type:
+        description: 'Release type (patch, minor, major)'
+        required: true
+        default: 'patch'
+        type: choice
+        options:
+          - patch
+          - minor
+          - major
+      create_release:
+        description: 'Create GitHub Release'
+        required: true
+        default: true
+        type: boolean
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine wheel setuptools bumpversion ruff
+          pip install -r requirements.txt
+          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
+
+      - name: Run Ruff linting
+        run: |
+          # Run Ruff linter
+          ruff check .
+
+          # Run Ruff formatter check (without modifying files)
+          ruff format --check .
+
+      - name: Run tests
+        run: |
+          pytest
+
+      - name: Update version
+        run: |
+          git config --local user.email "action@github.com"
+          git config --local user.name "GitHub Action"
+          bumpversion ${{ github.event.inputs.release_type }}
+
+      - name: Build package
+        run: |
+          python -m build
+
+      - name: Upload to PyPI
+        env:
+          TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+        run: |
+          twine upload dist/*
+
+      - name: Push version bump
+        run: |
+          git push
+          git push --tags
+
+      - name: Create GitHub Release
+        if: ${{ github.event.inputs.create_release == 'true' }}
+        uses: softprops/action-gh-release@v1
+        with:
+          tag_name: v$(python setup.py --version)
+          name: Release v$(python setup.py --version)
+          generate_release_notes: true 

evals/act/google_jobs.py

@@ -1,6 +1,6 @@
 import asyncio
 import traceback
-from typing import Any, Dict, Optional
+from typing import Any, Optional, dict
 
 from pydantic import BaseModel
 
@@ -10,23 +10,24 @@
 
 class Qualifications(BaseModel):
     degree: Optional[str] = None
-    yearsOfExperience: Optional[float] = None  # Representing the number
+    years_of_experience: Optional[float] = None  # Representing the number
 
 
 class JobDetails(BaseModel):
-    applicationDeadline: Optional[str] = None
-    minimumQualifications: Qualifications
-    preferredQualifications: Qualifications
+    application_deadline: Optional[str] = None
+    minimum_qualifications: Qualifications
+    preferred_qualifications: Qualifications
 
 
-def is_job_details_valid(details: Dict[str, Any]) -> bool:
+def is_job_details_valid(details: dict[str, Any]) -> bool:
     """
     Validates that each top-level field in the extracted job details is not None.
-    For nested dictionary values, each sub-value must be non-null and a string or a number.
+    For nested dictionary values, each sub-value must be non-null and a string
+    or a number.
     """
     if not details:
         return False
-    for key, value in details.items():
+    for _key, value in details.items():
         if value is None:
             return False
         if isinstance(value, dict):
@@ -53,9 +54,9 @@ async def google_jobs(model_name: str, logger, use_text_extract: bool) -> dict:
       4. Extracting job posting details using an AI-driven extraction schema.
 
     The extraction schema requires:
-      - applicationDeadline: The opening date until which applications are accepted.
-      - minimumQualifications: An object with degree and yearsOfExperience.
-      - preferredQualifications: An object with degree and yearsOfExperience.
+      - application_deadline: The opening date until which applications are accepted.
+      - minimum_qualifications: An object with degree and years_of_experience.
+      - preferred_qualifications: An object with degree and years_of_experience.
 
     Returns a dictionary containing:
       - _success (bool): Whether valid job details were extracted.
@@ -90,8 +91,9 @@ async def google_jobs(model_name: str, logger, use_text_extract: bool) -> dict:
         job_details = await stagehand.page.extract(
             ExtractOptions(
                 instruction=(
-                    "Extract the following details from the job posting: application deadline, "
-                    "minimum qualifications (degree and years of experience), and preferred qualifications "
+                    "Extract the following details from the job posting: "
+                    "application deadline, minimum qualifications "
+                    "(degree and years of experience), and preferred qualifications "
                     "(degree and years of experience)"
                 ),
                 schemaDefinition=JobDetails.model_json_schema(),

evals/extract/extract_press_releases.py

@@ -19,7 +19,8 @@ class PressReleases(BaseModel):
 
 async def extract_press_releases(model_name: str, logger, use_text_extract: bool):
     """
-    Extract press releases from the dummy press releases page using the Stagehand client.
+    Extract press releases from the dummy press releases page using the Stagehand
+    client.
 
     Args:
         model_name (str): Name of the AI model to use.
@@ -56,7 +57,10 @@ async def extract_press_releases(model_name: str, logger, use_text_extract: bool
         # TODO - FAILING - extract is likely timing out
         raw_result = await stagehand.page.extract(
             ExtractOptions(
-                instruction="extract the title and corresponding publish date of EACH AND EVERY press releases on this page. DO NOT MISS ANY PRESS RELEASES.",
+                instruction=(
+                    "extract the title and corresponding publish date of EACH AND EVERY "
+                    "press releases on this page. DO NOT MISS ANY PRESS RELEASES."
+                ),
                 schemaDefinition=PressReleases.model_json_schema(),
                 useTextExtract=use_text_extract,
             )

evals/init_stagehand.py

@@ -6,10 +6,12 @@
 
 async def init_stagehand(model_name: str, logger, dom_settle_timeout_ms: int = 3000):
     """
-    Initialize a Stagehand client with the given model name, logger, and DOM settle timeout.
+    Initialize a Stagehand client with the given model name, logger, and DOM settle
+    timeout.
 
-    This function creates a configuration from environment variables, initializes the Stagehand client,
-    and returns a tuple of (stagehand, init_response). The init_response contains debug and session URLs.
+    This function creates a configuration from environment variables, initializes
+    the Stagehand client, and returns a tuple of (stagehand, init_response).
+    The init_response contains debug and session URLs.
 
     Args:
         model_name (str): The name of the AI model to use.
@@ -37,7 +39,8 @@ async def init_stagehand(model_name: str, logger, dom_settle_timeout_ms: int = 3
         model_client_options={"apiKey": os.getenv("MODEL_API_KEY")},
     )
 
-    # Create a Stagehand client with the configuration; server_url is taken from environment variables.
+    # Create a Stagehand client with the configuration; server_url is taken from
+    # environment variables.
     stagehand = Stagehand(
         config=config, server_url=os.getenv("STAGEHAND_SERVER_URL"), verbose=2
     )

examples/example.py

@@ -87,7 +87,10 @@ async def main():
     if len(observed) > 0:
         element = observed[0]
         console.print("✅ [success]Found element:[/] News button")
+        console.print("\n▶️ [highlight] Performing action on observed element")
         await page.act(element)
+        console.print("✅ [success]Performing Action:[/] Action completed successfully")
+
     else:
         console.print("❌ [error]No element found[/]")
 

examples/example_sync.py

@@ -6,8 +6,8 @@
 from rich.panel import Panel
 from rich.theme import Theme
 
-from stagehand.sync import Stagehand
 from stagehand.config import StagehandConfig
+from stagehand.sync import Stagehand
 
 # Create a custom theme for consistent styling
 custom_theme = Theme(
@@ -60,6 +60,7 @@ def main():
     )
 
     import time
+
     time.sleep(2)
 
     console.print("\n▶️ [highlight] Navigating[/] to Google")
@@ -112,4 +113,4 @@ def main():
             padding=(1, 10),
         ),
     )
-    main() 
+    main()

format.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+# Define source directories (adjust as needed)
+SOURCE_DIRS="evals stagehand"
+
+# Apply Black formatting only to source directories
+echo "Applying Black formatting..."
+black $SOURCE_DIRS
+
+# Fix import sorting (addresses I001 errors)
+echo "Sorting imports..."
+isort $SOURCE_DIRS
+
+# Apply Ruff with autofix for remaining issues
+echo "Applying Ruff autofixes..."
+ruff check --fix $SOURCE_DIRS
+
+echo "Checking for remaining issues..."
+ruff check $SOURCE_DIRS
+
+echo "Done! Code has been formatted and linted."