generated tests as multiple markdown blocks instead of a single block

codeflash/api/aiservice.py

@@ -308,6 +308,7 @@ def get_new_explanation(  # noqa: D417
         original_throughput: str | None = None,
         optimized_throughput: str | None = None,
         throughput_improvement: str | None = None,
+        codeflash_version: str = codeflash_version,
     ) -> str:
         """Optimize the given python code for performance by making a request to the Django endpoint.
 
@@ -327,6 +328,7 @@ def get_new_explanation(  # noqa: D417
         - original_throughput: str | None - throughput for the baseline code (operations per second)
         - optimized_throughput: str | None - throughput for the optimized code (operations per second)
         - throughput_improvement: str | None - throughput improvement percentage
+        - current codeflash version
 
         Returns
         -------
@@ -349,6 +351,7 @@ def get_new_explanation(  # noqa: D417
             "original_throughput": original_throughput,
             "optimized_throughput": optimized_throughput,
             "throughput_improvement": throughput_improvement,
+            "codeflash_version": codeflash_version,
         }
         logger.info("loading|Generating explanation")
         console.rule()
@@ -591,6 +594,7 @@ def get_optimization_impact(
             "benchmark_details": explanation.benchmark_details if explanation.benchmark_details else None,
             "optimized_runtime": humanize_runtime(explanation.best_runtime_ns),
             "original_runtime": humanize_runtime(explanation.original_runtime_ns),
+            "codeflash_version": codeflash_version,
         }
         console.rule()
         try:

codeflash/optimization/function_optimizer.py

@@ -101,6 +101,7 @@
 from codeflash.verification.test_runner import run_behavioral_tests, run_benchmarking_tests, run_line_profile_tests
 from codeflash.verification.verification_utils import get_test_file_path
 from codeflash.verification.verifier import generate_tests
+from codeflash.version import __version__
 
 if TYPE_CHECKING:
     from argparse import Namespace
@@ -1379,11 +1380,13 @@ def process_review(
             generated_tests, original_runtime_by_test, optimized_runtime_by_test
         )
 
-        generated_tests_str = "\n#------------------------------------------------\n".join(
-            [test.generated_original_test_source for test in generated_tests.generated_tests]
-        )
+        generated_tests_str = ""
+        for test in generated_tests.generated_tests:
+            generated_tests_str += f"```python\n{test.generated_original_test_source}\n```"
+            generated_tests_str += "\n\n"
+
         if concolic_test_str:
-            generated_tests_str += "\n#------------------------------------------------\n" + concolic_test_str
+            generated_tests_str += f"```python\n{concolic_test_str}\n```\n\n"
 
         existing_tests, replay_tests, concolic_tests = existing_tests_source_for(
             self.function_to_optimize.qualified_name_with_modules_from_root(self.project_root),