llm based pk detector added

.github/workflows/acceptance.yml

@@ -47,18 +47,12 @@ jobs:
         run: make test
 
       # Integration tests are run from within tests/integration folder.
-      # Create .coveragerc with correct relative path to source code.
+      # We need to make sure .coveragerc is there so that code coverage is generated for the right modules.
       - name: Prepare code coverage configuration for integration tests
-        run: |
-          cat > tests/integration/.coveragerc << EOF
-          [run]
-          source = ../../src
-          relative_files = true
-          EOF
+        run: cp .coveragerc tests/integration
 
       # Run tests from `tests/integration` as defined in .codegen.json
       # and generate code coverage for modules defined in .coveragerc
-      # Run 10 tests in parallel: https://github.com/databrickslabs/sandbox/blob/main/acceptance/ecosystem/pytest_run.py
       - name: Run integration tests and generate test coverage report
         uses: databrickslabs/sandbox/acceptance@acceptance/v0.4.4
         with:
@@ -69,14 +63,8 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           ARM_CLIENT_ID: ${{ secrets.ARM_CLIENT_ID }}
           ARM_TENANT_ID: ${{ secrets.ARM_TENANT_ID }}
-          COVERAGE_FILE: ${{ github.workspace }}/.coverage  # make sure the coverage report is preserved
-
-      - name: Merge coverage reports and convert them to XML
-        run: |
-          hatch run combine_coverage
 
-      # Recursively search the entire workspace directory for all coverage reports.
-      # All uploaded test coverage reports will be used even if publish is done multiple time.
+      # collects all coverage reports: coverage.xml from integration tests, coverage-unit.xml from unit tests
       - name: Publish test coverage
         uses: codecov/codecov-action@v5
         with:
@@ -107,16 +95,6 @@ jobs:
       - name: Install hatch
         run: pip install hatch==1.15.0
 
-      # Integration tests are run from within tests/integration folder.
-      # Create .coveragerc with correct relative path to source code.
-      - name: Prepare code coverage configuration for integration tests
-        run: |
-          cat > tests/integration/.coveragerc << EOF
-          [run]
-          source = ../../src
-          relative_files = true
-          EOF
-
       - name: Run integration tests on serverless cluster
         uses: databrickslabs/sandbox/acceptance@acceptance/v0.4.4
         with:
@@ -128,17 +106,6 @@ jobs:
           ARM_CLIENT_ID: ${{ secrets.ARM_CLIENT_ID }}
           ARM_TENANT_ID: ${{ secrets.ARM_TENANT_ID }}
           DATABRICKS_SERVERLESS_COMPUTE_ID: ${{ env.DATABRICKS_SERVERLESS_COMPUTE_ID }}
-          COVERAGE_FILE: ${{ github.workspace }}/.coverage  # make sure the coverage report is preserved
-
-      - name: Merge coverage reports and convert them to XML
-        run: |
-          hatch run combine_coverage
-
-      # collects all coverage reports
-      - name: Publish test coverage
-        uses: codecov/codecov-action@v5
-        with:
-          use_oidc: true
 
   e2e:
     if: github.event_name == 'pull_request' && !github.event.pull_request.draft && !github.event.pull_request.head.repo.fork

.github/workflows/nightly.yml

@@ -37,15 +37,10 @@ jobs:
       - name: Run unit tests and generate test coverage report
         run: make test
 
-      # Integration tests are run from within tests/integration folder.
-      # Create .coveragerc with correct relative path to source code.
-      - name: Prepare code coverage configuration for integration tests
-        run: |
-          cat > tests/integration/.coveragerc << EOF
-          [run]
-          source = ../../src
-          relative_files = true
-          EOF
+      # Acceptance tests are run from within tests/integration folder.
+      # We need to make sure .coveragerc is there so that code coverage is generated for the right modules.
+      - name: Prepare .coveragerc for integration tests
+        run: cp .coveragerc tests/integration
 
       # Run tests from `tests/integration` as defined in .codegen.json
       # and generate code coverage for modules defined in .coveragerc
@@ -60,13 +55,8 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           ARM_CLIENT_ID: ${{ secrets.ARM_CLIENT_ID }}
           ARM_TENANT_ID: ${{ secrets.ARM_TENANT_ID }}
-          COVERAGE_FILE: ${{ github.workspace }}/.coverage  # make sure the coverage report is preserved
-
-      - name: Merge coverage reports and convert them to XML
-        run: |
-          hatch run combine_coverage
 
-      # collects all coverage reports
+      # collects all coverage reports: coverage.xml from integration tests, coverage-unit.xml from unit tests
       - name: Publish test coverage
         uses: codecov/codecov-action@v5
         with:
@@ -93,16 +83,6 @@ jobs:
       - name: Install hatch
         run: pip install hatch==1.15.0
 
-      # Integration tests are run from within tests/integration folder.
-      # Create .coveragerc with correct relative path to source code.
-      - name: Prepare code coverage configuration for integration tests
-        run: |
-          cat > tests/integration/.coveragerc << EOF
-          [run]
-          source = ../../src
-          relative_files = true
-          EOF
-
       - name: Run integration tests on serverless cluster
         uses: databrickslabs/sandbox/acceptance@acceptance/v0.4.4
         with:
@@ -115,17 +95,6 @@ jobs:
           ARM_CLIENT_ID: ${{ secrets.ARM_CLIENT_ID }}
           ARM_TENANT_ID: ${{ secrets.ARM_TENANT_ID }}
           DATABRICKS_SERVERLESS_COMPUTE_ID: ${{ env.DATABRICKS_SERVERLESS_COMPUTE_ID }}
-          COVERAGE_FILE: ${{ github.workspace }}/.coverage  # make sure the coverage report is preserved
-
-      - name: Merge coverage reports and convert them to XML
-        run: |
-          hatch run combine_coverage
-
-      # collects all coverage reports
-      - name: Publish test coverage
-        uses: codecov/codecov-action@v5
-        with:
-          use_oidc: true
 
   e2e:
     environment: tool

.gitignore

@@ -51,7 +51,6 @@ htmlcov/
 nosetests.xml
 coverage.xml
 coverage-unit.xml
-coverage-integration.xml
 *.cover
 *.py,cover
 .hypothesis/

Makefile

@@ -7,6 +7,7 @@ clean: docs-clean
 .venv/bin/python:
 	pip install hatch
 	hatch env create
+	hatch run pip install ".[llm,pii]"
 
 dev: .venv/bin/python
 	@hatch run which python