Merge branch 'fix/performance-regression' into dev

Author: sidmohan0

.github/workflows/beta-release.yml

@@ -62,7 +62,7 @@ jobs:
         with:
           fetch-depth: 0
           ref: dev
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ secrets.GH_PAT }}
 
       - name: Set up Python
         uses: actions/setup-python@v5
@@ -86,21 +86,34 @@ jobs:
         id: version
         run: |
           set -e
+          
+          # Fetch all tags to ensure we have the complete tag history
+          git fetch --tags
+          
           CURRENT_VERSION=$(python -c "from datafog.__about__ import __version__; print(__version__)")
           echo "Current version: $CURRENT_VERSION"
 
+          # Extract base version (remove any alpha/beta suffix)
           if [[ $CURRENT_VERSION == *"b"* ]]; then
             BASE_VERSION=$(echo $CURRENT_VERSION | cut -d'b' -f1)
-            BETA_NUM=$(echo $CURRENT_VERSION | cut -d'b' -f2)
-            BETA_VERSION="${BASE_VERSION}b$((BETA_NUM + 1))"
           elif [[ $CURRENT_VERSION == *"a"* ]]; then
             BASE_VERSION=$(echo $CURRENT_VERSION | cut -d'a' -f1)
-            BETA_VERSION="${BASE_VERSION}b1"
           else
-            BASE_VERSION=$(python3 -c "import sys; version='$CURRENT_VERSION'; parts=version.split('.'); parts[1]=str(int(parts[1])+1); parts[2]='0'; print('.'.join(parts))")
-            BETA_VERSION="${BASE_VERSION}b1"
+            BASE_VERSION=$CURRENT_VERSION
           fi
 
+          echo "Base version: $BASE_VERSION"
+
+          # Find the next available beta version by checking existing tags
+          BETA_NUM=1
+          while git tag -l "v${BASE_VERSION}b${BETA_NUM}" | grep -q "v${BASE_VERSION}b${BETA_NUM}"; do
+            echo "Tag v${BASE_VERSION}b${BETA_NUM} already exists"
+            BETA_NUM=$((BETA_NUM + 1))
+          done
+
+          BETA_VERSION="${BASE_VERSION}b${BETA_NUM}"
+          echo "Next available beta version: $BETA_VERSION"
+
           echo "beta_version=$BETA_VERSION" >> $GITHUB_OUTPUT
           sed -i "s/__version__ = \".*\"/__version__ = \"$BETA_VERSION\"/" datafog/__about__.py
           sed -i "s/version=\".*\"/version=\"$BETA_VERSION\"/" setup.py
@@ -126,9 +139,9 @@ jobs:
           echo "Running integration tests..."
           python run_tests.py -m integration --no-header
           
-          # Run benchmark tests with optimal performance (no memory debugging)
-          echo "Running benchmark tests with performance optimizations..."
-          OMP_NUM_THREADS=4 MKL_NUM_THREADS=4 OPENBLAS_NUM_THREADS=4 python -m pytest tests/benchmark_text_service.py -v --no-header --benchmark-skip
+          # Run simple performance validation (no pytest-benchmark dependency)
+          echo "Running simple performance validation..."
+          OMP_NUM_THREADS=4 MKL_NUM_THREADS=4 OPENBLAS_NUM_THREADS=4 python tests/simple_performance_test.py
 
       - name: Build package
         run: |
@@ -137,7 +150,7 @@ jobs:
 
       - name: Create GitHub release
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GH_PAT }}
         run: |
           BETA_VERSION="${{ steps.version.outputs.beta_version }}"
           git add datafog/__about__.py setup.py
@@ -169,7 +182,7 @@ jobs:
 
       - name: Cleanup old betas
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GH_PAT }}
         run: |
           BETA_RELEASES=$(gh release list --limit 30 | grep b | tail -n +6 | cut -f3)
 

BETA_CHANGELOG.md

@@ -0,0 +1,102 @@
+# Beta Release Notes
+
+_Beta Release: 2025-05-30_
+
+⚠️ **This is a beta release for testing purposes.**
+
+## 🚀 New Features
+
+- fix(ci): add diagnostics and plugin verification for benchmark tests
+- fix(ci): add diagnostics and plugin verification for benchmark tests
+- Merge pull request #104 from DataFog/feature/sample-notebooks
+- Merge branch 'dev' into feature/sample-notebooks
+- Fix segmentation fault in beta-release workflow and add sample notebook
+- Merge pull request #103 from DataFog/feature/sample-notebooks
+- Fix segmentation fault in beta-release workflow and add sample notebook
+- Merge pull request #102 from DataFog/feature/gliner-integration-v420
+- Merge branch 'dev' into feature/gliner-integration-v420
+- Merge branch 'feature/gliner-integration-v420' of github.com:DataFog/datafog-python into feature/gliner-integration-v420
+- Merge pull request #101 from DataFog/feature/gliner-integration-v420
+- Merge branch 'dev' into feature/gliner-integration-v420
+- Merge pull request #100 from DataFog/feature/gliner-integration-v420
+- docs: add release guidelines to Claude.md
+- feat(nlp): add GLiNER integration with smart cascading engine
+- fix(deps): add pydantic-settings to cli and all extras
+- Merge pull request #92 from DataFog/feature/automated-release-pipeline
+- feat(ci): configure release workflows for 4.2.0 minor version bump
+- feat(ci): add comprehensive alpha→beta→stable release cycle
+- feat(ci): add nightly alpha builds for Monday-Thursday
+- Merge pull request #91 from DataFog/feature/implement-weekly-release-plan
+- feat(release): implement weekly release plan infrastructure
+
+## 🐛 Bug Fixes
+
+- fix(ci): improve beta versioning logic and use GH_PAT token
+- fix(ci): replace invalid --benchmark-skip flag with simple performance test
+- Merge branch 'dev' into fix/performance-regression
+- Merge pull request #105 from DataFog/fix/performance-regression
+- fix(ci): reset benchmark baseline to resolve false regression alerts
+- fix(performance): eliminate memory debugging overhead from benchmarks
+- fix(performance): eliminate redundant regex calls in structured output mode
+- fix(performance): eliminate redundant regex calls in structured output mode
+- fix(ci): handle segfault gracefully while preserving test validation
+- fix(tests): make spaCy address detection test more robust
+- fix(ci): improve GLiNER validation to confirm PyTorch exclusion
+- fix(ci): exclude PyTorch dependencies entirely to prevent segfault
+- fix(ci): eliminate PyTorch segfaults and enhance README with GLiNER examples
+- fix(ci): workaround for PyTorch segfault in CI environments
+- fix(ci): split test execution to prevent memory segfault
+- fix(ci): reduce coverage reporting to prevent segmentation fault
+- fix(tests): resolve final GLiNER test failures
+- fix(tests): update GLiNER test mocking for proper import paths
+- fix(tests): resolve GLiNER dependency mocking for CI environments
+- Merge pull request #99 from DataFog/fix/github-actions-workflow-fixes
+- Merge branch 'dev' into fix/github-actions-workflow-fixes
+- fix(deps): move pydantic-settings to core dependencies
+- fix(ci): install all extras and configure pytest-asyncio in workflows
+- Merge pull request #98 from DataFog/fix/github-actions-workflow-fixes
+- fix(ci): resolve YAML syntax errors in GitHub Actions workflows
+- Merge pull request #96 from DataFog/codex/fix-failing-github-actions-in-workflows
+- fix release workflows
+- Merge pull request #95 from DataFog/hotfix/readme-fix
+- Merge branch 'dev' into hotfix/readme-fix
+- fix(ci): remove indentation from Python code in workflow commands
+- fix(text): resolve missing Span import for structured output
+- fix(ci): resolve YAML syntax issues in workflow files
+- fix(ci): resolve prettier pre-commit hook configuration
+- fix(ci): resolve YAML syntax issues in release workflows
+- fix(lint): resolve flake8 string formatting warnings
+- fix(ci): restore expected job names and consolidate workflows
+- fix(imports): resolve flake8 E402 import order issues
+
+## 📚 Documentation
+
+- docs: streamline Claude.md development guide for v4.2.0
+- fixed readme
+
+## 🔧 Other Changes
+
+- chore: set version to 4.2.0b1 for beta testing of unreleased 4.2.0
+- resolve: merge conflicts with enhanced segfault detection
+- release: prepare v4.2.0 with GLiNER integration
+- updated workflows
+- Merge pull request #94 from DataFog/hotfix/beta-workflow-yaml-syntax
+- Merge branch 'dev' into hotfix/beta-workflow-yaml-syntax
+- Merge pull request #93 from DataFog/hotfix/beta-workflow-yaml-syntax
+
+## 📥 Installation
+
+```bash
+# Core package (lightweight)
+pip install datafog
+
+# With all features
+pip install datafog[all]
+```
+
+## 📊 Metrics
+
+- Package size: ~2MB (core)
+- Install time: ~10 seconds
+- Tests passing: ✅
+- Commits this week: 68

datafog/__about__.py

@@ -1 +1 @@
-__version__ = "4.2.0"
+__version__ = "4.2.0b1"

scripts/generate_changelog.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 """Generate changelog for weekly releases."""
 
+import argparse
 import re
 import subprocess
 from datetime import datetime
@@ -60,7 +61,7 @@ def categorize_commits(commits):
     return categories
 
 
-def generate_changelog():
+def generate_changelog(beta=False):
     """Generate changelog content."""
     latest_tag = get_latest_tag()
     commits = get_commits_since_tag(latest_tag)
@@ -70,8 +71,13 @@ def generate_changelog():
 
     categories = categorize_commits(commits)
 
-    changelog = "# What's New\n\n"
-    changelog += f"*Released: {datetime.now().strftime('%Y-%m-%d')}*\n\n"
+    if beta:
+        changelog = "# Beta Release Notes\n\n"
+        changelog += f"*Beta Release: {datetime.now().strftime('%Y-%m-%d')}*\n\n"
+        changelog += "⚠️ **This is a beta release for testing purposes.**\n\n"
+    else:
+        changelog = "# What's New\n\n"
+        changelog += f"*Released: {datetime.now().strftime('%Y-%m-%d')}*\n\n"
 
     if categories["features"]:
         changelog += "## 🚀 New Features\n"
@@ -121,13 +127,23 @@ def generate_changelog():
 
 
 if __name__ == "__main__":
-    changelog_content = generate_changelog()
+    parser = argparse.ArgumentParser(description="Generate changelog for releases")
+    parser.add_argument(
+        "--beta", action="store_true", help="Generate beta release changelog"
+    )
+    parser.add_argument(
+        "--output", help="Output file name", default="CHANGELOG_LATEST.md"
+    )
+
+    args = parser.parse_args()
+
+    changelog_content = generate_changelog(beta=args.beta)
 
     # Write to file for GitHub release
-    with open("CHANGELOG_LATEST.md", "w") as f:
+    with open(args.output, "w") as f:
         f.write(changelog_content)
 
-    print("✅ Changelog generated: CHANGELOG_LATEST.md")
+    print(f"✅ Changelog generated: {args.output}")
     print("\nPreview:")
     print("=" * 50)
     print(changelog_content)