merge: resolve conflict with main — adapt exit-code handling to combined invocation

Keep the combined JFR + tracing agent single JVM invocation from main while
preserving the fix's intent: raise when trace-db was not created, warn when
exit code is non-zero but trace-db exists. Integration tests rewritten to
match the combined-invocation semantics.

Author: mohamedashrraf222

tests/benchmarks/__init__.py .codeflash/benchmarks/__init__.pytests/benchmarks/__init__.py renamed to .codeflash/benchmarks/__init__.py

@@ -2,7 +2,7 @@
 from codeflash.verification.parse_test_output import merge_test_results
 
 
-def generate_test_invocations(count=100):
+def generate_test_invocations(count: int = 100) -> tuple[TestResults, TestResults]:
     """Generate a set number of test invocations for benchmarking."""
     test_results_xml = TestResults()
     test_results_bin = TestResults()
@@ -21,7 +21,7 @@ def generate_test_invocations(count=100):
                     function_getting_tested="sorter",
                     iteration_id=iteration_id,
                 ),
-                file_name="/tmp/tests/unittest/test_bubble_sort__perfinstrumented.py",
+                file_name="/tmp/tests/unittest/test_bubble_sort__perfinstrumented.py",  # noqa: S108
                 did_pass=True,
                 runtime=None if i % 3 == 0 else i * 100,  # Vary runtime values
                 test_framework="unittest",
@@ -42,7 +42,7 @@ def generate_test_invocations(count=100):
                     function_getting_tested="sorter",
                     iteration_id=iteration_id,
                 ),
-                file_name="/tmp/tests/unittest/test_bubble_sort__perfinstrumented.py",
+                file_name="/tmp/tests/unittest/test_bubble_sort__perfinstrumented.py",  # noqa: S108
                 did_pass=True,
                 runtime=500 + i * 20,  # Generate varying runtime values
                 test_framework="unittest",
@@ -56,12 +56,12 @@ def generate_test_invocations(count=100):
     return test_results_xml, test_results_bin
 
 
-def run_merge_benchmark(count=100):
+def run_merge_benchmark(count: int = 100) -> None:
     test_results_xml, test_results_bin = generate_test_invocations(count)
 
     # Perform the merge operation that will be benchmarked
     merge_test_results(xml_test_results=test_results_xml, bin_test_results=test_results_bin, test_framework="unittest")
 
 
-def test_benchmark_merge_test_results(benchmark):
+def test_benchmark_merge_test_results(benchmark) -> None:
     benchmark(run_merge_benchmark, 1000)  # Default to 100 test invocations

…t_benchmark_code_extract_code_context.py …t_benchmark_code_extract_code_context.pytests/benchmarks/test_benchmark_code_extract_code_context.py renamed to .codeflash/benchmarks/test_benchmark_code_extract_code_context.py tests/benchmarks/test_benchmark_code_extract_code_context.py renamed to .codeflash/benchmarks/test_benchmark_code_extract_code_context.py

@@ -95,7 +95,8 @@ jobs:
             'codeflash/languages/java/' 'codeflash/languages/base.py' \
             'codeflash/languages/registry.py' 'codeflash/optimization/' \
             'codeflash/verification/' 'codeflash-java-runtime/' \
-            'code_to_optimize/java/' 'tests/scripts/end_to_end_test_java*'
+            'code_to_optimize/java/' 'tests/scripts/end_to_end_test_java*' \
+            'tests/test_languages/fixtures/java_tracer_e2e/'
         env:
           MERGE_BASE: ${{ steps.merge_base.outputs.sha }}
 
@@ -257,7 +258,7 @@ jobs:
           - name: init-optimization
             script: end_to_end_test_init_optimization.py
             expected_improvement: 10
-    environment: ${{ (github.event_name == 'workflow_dispatch' || (contains(toJSON(github.event.pull_request.files.*.filename), '.github/workflows/') && github.event.pull_request.user.login != 'misrasaurabh1' && github.event.pull_request.user.login != 'KRRT7')) && 'external-trusted-contributors' || '' }}
+    environment: ${{ ((github.event_name == 'workflow_dispatch' && github.actor != 'misrasaurabh1' && github.actor != 'KRRT7') || (contains(toJSON(github.event.pull_request.files.*.filename), '.github/workflows/') && github.event.pull_request.user.login != 'misrasaurabh1' && github.event.pull_request.user.login != 'KRRT7')) && 'external-trusted-contributors' || '' }}
     runs-on: ubuntu-latest
     env:
       CODEFLASH_AIS_SERVER: prod
@@ -344,7 +345,7 @@ jobs:
             script: end_to_end_test_js_ts_class.py
             js_project_dir: code_to_optimize/js/code_to_optimize_ts
             expected_improvement: 30
-    environment: ${{ (github.event_name == 'workflow_dispatch' || (contains(toJSON(github.event.pull_request.files.*.filename), '.github/workflows/') && github.event.pull_request.user.login != 'misrasaurabh1' && github.event.pull_request.user.login != 'KRRT7')) && 'external-trusted-contributors' || '' }}
+    environment: ${{ ((github.event_name == 'workflow_dispatch' && github.actor != 'misrasaurabh1' && github.actor != 'KRRT7') || (contains(toJSON(github.event.pull_request.files.*.filename), '.github/workflows/') && github.event.pull_request.user.login != 'misrasaurabh1' && github.event.pull_request.user.login != 'KRRT7')) && 'external-trusted-contributors' || '' }}
     runs-on: ubuntu-latest
     env:
       CODEFLASH_AIS_SERVER: prod
@@ -424,7 +425,7 @@ jobs:
             script: end_to_end_test_java_void_optimization.py
             expected_improvement: 70
             remove_git: true
-    environment: ${{ (github.event_name == 'workflow_dispatch' || (contains(toJSON(github.event.pull_request.files.*.filename), '.github/workflows/') && github.event.pull_request.user.login != 'misrasaurabh1' && github.event.pull_request.user.login != 'KRRT7')) && 'external-trusted-contributors' || '' }}
+    environment: ${{ ((github.event_name == 'workflow_dispatch' && github.actor != 'misrasaurabh1' && github.actor != 'KRRT7') || (contains(toJSON(github.event.pull_request.files.*.filename), '.github/workflows/') && github.event.pull_request.user.login != 'misrasaurabh1' && github.event.pull_request.user.login != 'KRRT7')) && 'external-trusted-contributors' || '' }}
     runs-on: ubuntu-latest
     env:
       CODEFLASH_AIS_SERVER: prod
@@ -435,6 +436,7 @@ jobs:
       RETRY_DELAY: 5
       EXPECTED_IMPROVEMENT_PCT: ${{ matrix.expected_improvement }}
       CODEFLASH_END_TO_END: 1
+      CODEFLASH_LOOPING_TIME: 5
     steps:
       - uses: actions/checkout@v6
         with:
@@ -468,7 +470,15 @@ jobs:
       - name: Install dependencies
         run: uv sync
 
+      - name: Cache codeflash-runtime JAR
+        id: runtime-jar-cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.m2/repository/io/codeflash
+          key: codeflash-runtime-${{ hashFiles('codeflash-java-runtime/pom.xml', 'codeflash-java-runtime/src/**') }}
+
       - name: Build and install codeflash-runtime JAR
+        if: steps.runtime-jar-cache.outputs.cache-hit != 'true'
         run: |
           cd codeflash-java-runtime
           mvn install -q -DskipTests

…/benchmarks/test_benchmark_comparator.py …/benchmarks/test_benchmark_comparator.pytests/benchmarks/test_benchmark_comparator.py renamed to .codeflash/benchmarks/test_benchmark_comparator.py tests/benchmarks/test_benchmark_comparator.py renamed to .codeflash/benchmarks/test_benchmark_comparator.py

@@ -43,4 +43,4 @@ jobs:
       - name: ⚡️Codeflash Optimization
         id: optimize_code
         run: |
-          uv run codeflash --benchmark --testgen-review
+          uv run codeflash --benchmark --testgen-review --no-pr

…ks/test_benchmark_discover_unit_tests.py …ks/test_benchmark_discover_unit_tests.pytests/benchmarks/test_benchmark_discover_unit_tests.py renamed to .codeflash/benchmarks/test_benchmark_discover_unit_tests.py tests/benchmarks/test_benchmark_discover_unit_tests.py renamed to .codeflash/benchmarks/test_benchmark_discover_unit_tests.py

@@ -0,0 +1,77 @@
+name: Java E2E Tests
+on:
+  workflow_dispatch:
+
+jobs:
+  e2e-java:
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: java-fibonacci-nogit
+            script: end_to_end_test_java_fibonacci.py
+            expected_improvement: 70
+            remove_git: true
+          - name: java-tracer
+            script: end_to_end_test_java_tracer.py
+            expected_improvement: 10
+          - name: java-void-optimization-nogit
+            script: end_to_end_test_java_void_optimization.py
+            expected_improvement: 70
+            remove_git: true
+    runs-on: ubuntu-latest
+    env:
+      CODEFLASH_AIS_SERVER: prod
+      POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
+      CODEFLASH_API_KEY: ${{ secrets.CODEFLASH_API_KEY }}
+      COLUMNS: 110
+      MAX_RETRIES: 3
+      RETRY_DELAY: 5
+      EXPECTED_IMPROVEMENT_PCT: ${{ matrix.expected_improvement }}
+      CODEFLASH_END_TO_END: 1
+      CODEFLASH_LOOPING_TIME: 5
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up JDK 11
+        uses: actions/setup-java@v5
+        with:
+          java-version: '11'
+          distribution: 'temurin'
+          cache: maven
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v8.0.0
+        with:
+          python-version: 3.11.6
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Cache codeflash-runtime JAR
+        id: runtime-jar-cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.m2/repository/io/codeflash
+          key: codeflash-runtime-${{ hashFiles('codeflash-java-runtime/pom.xml', 'codeflash-java-runtime/src/**') }}
+
+      - name: Build and install codeflash-runtime JAR
+        if: steps.runtime-jar-cache.outputs.cache-hit != 'true'
+        run: |
+          cd codeflash-java-runtime
+          mvn install -q -DskipTests
+
+      - name: Remove .git
+        if: matrix.remove_git
+        run: |
+          if [ -d ".git" ]; then
+            sudo rm -rf .git
+            echo ".git directory removed."
+          else
+            echo ".git directory does not exist."
+            exit 1
+          fi
+
+      - name: Run E2E test
+        run: uv run python tests/scripts/${{ matrix.script }}