Merge pull request #1394 from codeflash-ai/fix/detect-java-compilation-failures

fix: detect and log Java compilation failures explicitly

codeflash/languages/java/test_runner.py

@@ -1146,10 +1146,39 @@ def _run_maven_tests(
     logger.debug("Running Maven command: %s in %s", " ".join(cmd), project_root)
 
     try:
-        return subprocess.run(
+        result = subprocess.run(
             cmd, check=False, cwd=project_root, env=env, capture_output=True, text=True, timeout=timeout
         )
 
+        # Check if Maven failed due to compilation errors (not just test failures)
+        if result.returncode != 0:
+            # Maven compilation errors contain specific markers in output
+            compilation_error_indicators = [
+                "[ERROR] COMPILATION ERROR",
+                "[ERROR] Failed to execute goal org.apache.maven.plugins:maven-compiler-plugin",
+                "compilation failure",
+                "cannot find symbol",
+                "package .* does not exist",
+            ]
+
+            combined_output = (result.stdout or "") + (result.stderr or "")
+            has_compilation_error = any(
+                indicator.lower() in combined_output.lower() for indicator in compilation_error_indicators
+            )
+
+            if has_compilation_error:
+                logger.error(
+                    f"Maven compilation failed for {mode} tests. "
+                    f"Check that generated test code is syntactically valid Java. "
+                    f"Return code: {result.returncode}"
+                )
+                # Log first 50 lines of output to help diagnose compilation errors
+                output_lines = combined_output.split("\n")
+                error_context = "\n".join(output_lines[:50]) if len(output_lines) > 50 else combined_output
+                logger.error(f"Maven compilation error output:\n{error_context}")
+
+        return result
+
     except subprocess.TimeoutExpired:
         logger.exception("Maven test execution timed out after %d seconds", timeout)
         return subprocess.CompletedProcess(

codeflash/verification/parse_test_output.py

@@ -1243,8 +1243,14 @@ def parse_test_xml(
                         )
 
     if not test_results:
+        # Show actual test file paths being used (behavior or original), not just original_file_path
+        # For AI-generated tests, original_file_path is None, so show instrumented_behavior_file_path instead
+        test_paths_display = [
+            str(test_file.instrumented_behavior_file_path or test_file.original_file_path)
+            for test_file in test_files.test_files
+        ]
         logger.info(
-            f"Tests '{[test_file.original_file_path for test_file in test_files.test_files]}' failed to run, skipping"
+            f"Tests {test_paths_display} failed to run, skipping"
         )
         if run_result is not None:
             stdout, stderr = "", ""