Merge branch 'main' into dont-optimize-repeatedly-gh-actions

Author: Archan Das

.github/workflows/codeflash-optimize.yaml

@@ -1,7 +1,7 @@
 name: CodeFlash
 
 on:
-  pull_request_target:
+  pull_request:
     paths:
       - '**'  # Trigger for all paths
 
@@ -14,8 +14,6 @@ concurrency:
 jobs:
   optimize:
     name: Optimize new Python code
-    # Dynamically determine if environment is needed only when workflow files change and contributor is external
-    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' || '' }}
     if: ${{ github.actor != 'codeflash-ai[bot]' }}
     runs-on: ubuntu-latest
     env:
@@ -28,31 +26,7 @@ jobs:
       - name: 🛎️ Checkout
         uses: actions/checkout@v4
         with:
-          ref: ${{ github.event.pull_request.head.ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
           fetch-depth: 0
-      - name: Validate PR
-        run: |
-          # Check for any workflow changes
-          if git diff --name-only "${{ github.event.pull_request.base.sha }}" "${{ github.event.pull_request.head.sha }}" | grep -q "^.github/workflows/"; then
-            echo "⚠️ Workflow changes detected."
-
-            # Get the PR author
-            AUTHOR="${{ github.event.pull_request.user.login }}"
-            echo "PR Author: $AUTHOR"
-
-            # Allowlist check
-            if [[ "$AUTHOR" == "misrasaurabh1" || "$AUTHOR" == "KRRT7" ]]; then
-              echo "✅ Authorized user ($AUTHOR). Proceeding."
-            elif [[ "${{ github.event.pull_request.state }}" == "open" ]]; then
-              echo "✅ PR is open. Proceeding with appropriate protections."
-            else
-              echo "⛔ Unauthorized user ($AUTHOR) attempting to modify workflows. Exiting."
-              exit 1
-            fi
-          else
-            echo "✅ No workflow file changes detected. Proceeding."
-          fi
 
       - name: 🐍 Set up Python 3.11 for CLI
         uses: astral-sh/setup-uv@v5

.github/workflows/end-to-end-test-init-optim.yaml

@@ -20,7 +20,7 @@ jobs:
       COLUMNS: 110
       MAX_RETRIES: 3
       RETRY_DELAY: 5
-      EXPECTED_IMPROVEMENT_PCT: 300
+      EXPECTED_IMPROVEMENT_PCT: 30
       CODEFLASH_END_TO_END: 1
     steps:
       - name: 🛎️ Checkout

.github/workflows/pre-commit.yaml

@@ -0,0 +1,19 @@
+name: Lint
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    name: Run pre-commit hooks
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+      - uses: pre-commit/[email protected]

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.11.0"
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --config=pyproject.toml]
+      - id: ruff-format

README.md

@@ -11,13 +11,13 @@
   </a>
 </p>
 
-[Codeflash](https://www.codeflash.ai) is a general purpose optimizer for Python that automatically improves the performance of your Python code while maintaining its correctness.
+[Codeflash](https://www.codeflash.ai) is a general purpose optimizer for Python that helps you improve the performance of your Python code while maintaining its correctness.
 It uses advanced LLMs to generate multiple optimization ideas for your code, tests them to be correct and benchmarks them for performance. It then creates merge-ready pull requests containing the best optimization found, which you can review and merge.
 
 How to use Codeflash -
 - Optimize an entire existing codebase by running `codeflash --all`
 - Automate optimizing all __future__ code you will write by installing Codeflash as a GitHub action.
-- Optimize a Python workflow end-to-end by tracing the workflow.
+- Optimize a Python workflow `python myscript.py` end-to-end by running `python -m codeflash.tracer -o benchmark.trace myscript.py`
 
 Codeflash is used by top engineering teams at [Pydantic](https://github.com/pydantic/pydantic/pulls?q=is%3Apr+author%3Amisrasaurabh1+is%3Amerged), [Langflow](https://github.com/langflow-ai/langflow/issues?q=state%3Aclosed%20is%3Apr%20author%3Amisrasaurabh1), [Albumentations](https://github.com/albumentations-team/albumentations/issues?q=state%3Amerged%20is%3Apr%20author%3Akrrt7%20OR%20state%3Amerged%20is%3Apr%20author%3Aaseembits93%20) and many others to ship performant, expert level code.
 

code_to_optimize/code_directories/simple_tracer_e2e/workload.py

@@ -2,6 +2,7 @@
 
 
 def funcA(number):
+    number = number if number < 1000 else 1000
     k = 0
     for i in range(number * 100):
         k += i

codeflash/api/aiservice.py

@@ -3,6 +3,7 @@
 import json
 import os
 import platform
+import time
 from typing import TYPE_CHECKING, Any
 
 import requests
@@ -72,7 +73,7 @@ def make_ai_service_request(
         # response.raise_for_status()  # Will raise an HTTPError if the HTTP request returned an unsuccessful status code
         return response
 
-    def optimize_python_code(
+    def optimize_python_code(  # noqa: D417
         self,
         source_code: str,
         dependency_code: str,
@@ -95,6 +96,7 @@ def optimize_python_code(
         - List[OptimizationCandidate]: A list of Optimization Candidates.
 
         """
+        start_time = time.perf_counter()
         payload = {
             "source_code": source_code,
             "dependency_code": dependency_code,
@@ -118,6 +120,8 @@ def optimize_python_code(
             optimizations_json = response.json()["optimizations"]
             logger.info(f"Generated {len(optimizations_json)} candidates.")
             console.rule()
+            end_time = time.perf_counter()
+            logger.debug(f"Generating optimizations took {end_time - start_time:.2f} seconds.")
             return [
                 OptimizedCandidate(
                     source_code=opt["source_code"],
@@ -135,7 +139,7 @@ def optimize_python_code(
         console.rule()
         return []
 
-    def optimize_python_code_line_profiler(
+    def optimize_python_code_line_profiler(  # noqa: D417
         self,
         source_code: str,
         dependency_code: str,
@@ -172,7 +176,7 @@ def optimize_python_code_line_profiler(
 
         logger.info("Generating optimized candidates…")
         console.rule()
-        if line_profiler_results=="":
+        if line_profiler_results == "":
             logger.info("No LineProfiler results were provided, Skipping optimization.")
             console.rule()
             return []
@@ -204,8 +208,7 @@ def optimize_python_code_line_profiler(
         console.rule()
         return []
 
-
-    def log_results(
+    def log_results(  # noqa: D417
         self,
         function_trace_id: str,
         speedup_ratio: dict[str, float | None] | None,
@@ -237,7 +240,7 @@ def log_results(
         except requests.exceptions.RequestException as e:
             logger.exception(f"Error logging features: {e}")
 
-    def generate_regression_tests(
+    def generate_regression_tests(  # noqa: D417
         self,
         source_code_being_tested: str,
         function_to_optimize: FunctionToOptimize,
@@ -304,7 +307,7 @@ def generate_regression_tests(
             error = response.json()["error"]
             logger.error(f"Error generating tests: {response.status_code} - {error}")
             ph("cli-testgen-error-response", {"response_status_code": response.status_code, "error": error})
-            return None
+            return None  # noqa: TRY300
         except Exception:
             logger.error(f"Error generating tests: {response.status_code} - {response.text}")
             ph("cli-testgen-error-response", {"response_status_code": response.status_code, "error": response.text})

codeflash/api/cfapi.py

@@ -117,7 +117,7 @@ def suggest_changes(
         "existingTests": existing_tests,
         "generatedTests": generated_tests,
         "traceId": trace_id,
-        "coverage": coverage_message,
+        "coverage_message": coverage_message,
     }
     return make_cfapi_request(endpoint="/suggest-pr-changes", method="POST", payload=payload)
 
@@ -153,7 +153,7 @@ def create_pr(
         "existingTests": existing_tests,
         "generatedTests": generated_tests,
         "traceId": trace_id,
-        "coverage": coverage_message,
+        "coverage_message": coverage_message,
     }
     return make_cfapi_request(endpoint="/create-pr", method="POST", payload=payload)
 
@@ -181,19 +181,10 @@ def get_blocklisted_functions() -> dict[str, set[str]] | dict[str, Any]:
     if pr_number is None:
         return {}
 
-    not_found = 404
-    internal_server_error = 500
-
     owner, repo = get_repo_owner_and_name()
     information = {"pr_number": pr_number, "repo_owner": owner, "repo_name": repo}
     try:
         req = make_cfapi_request(endpoint="/verify-existing-optimizations", method="POST", payload=information)
-        if req.status_code == not_found:
-            logger.debug(req.json()["message"])
-            return {}
-        if req.status_code == internal_server_error:
-            logger.error(req.json()["message"])
-            return {}
         req.raise_for_status()
         content: dict[str, list[str]] = req.json()
     except Exception as e:

codeflash/benchmarking/codeflash_trace.py

@@ -4,7 +4,7 @@
 import sqlite3
 import threading
 import time
-from typing import Callable
+from typing import Any, Callable
 
 from codeflash.picklepatch.pickle_patcher import PicklePatcher
 
@@ -69,7 +69,7 @@ def write_function_timings(self) -> None:
                 "(function_name, class_name, module_name, file_path, benchmark_function_name, "
                 "benchmark_module_path, benchmark_line_number, function_time_ns, overhead_time_ns, args, kwargs) "
                 "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
-                self.function_calls_data
+                self.function_calls_data,
             )
             self._connection.commit()
             self.function_calls_data = []
@@ -100,9 +100,10 @@ def __call__(self, func: Callable) -> Callable:
             The wrapped function
 
         """
-        func_id = (func.__module__,func.__name__)
+        func_id = (func.__module__, func.__name__)
+
         @functools.wraps(func)
-        def wrapper(*args, **kwargs):
+        def wrapper(*args, **kwargs) -> Any:  # noqa: ANN002, ANN003, ANN401
             # Initialize thread-local active functions set if it doesn't exist
             if not hasattr(self._thread_local, "active_functions"):
                 self._thread_local.active_functions = set()
@@ -139,9 +140,19 @@ def wrapper(*args, **kwargs):
                 self._thread_local.active_functions.remove(func_id)
                 overhead_time = time.thread_time_ns() - end_time
                 self.function_calls_data.append(
-                    (func.__name__, class_name, func.__module__, func.__code__.co_filename,
-                     benchmark_function_name, benchmark_module_path, benchmark_line_number, execution_time,
-                     overhead_time, None, None)
+                    (
+                        func.__name__,
+                        class_name,
+                        func.__module__,
+                        func.__code__.co_filename,
+                        benchmark_function_name,
+                        benchmark_module_path,
+                        benchmark_line_number,
+                        execution_time,
+                        overhead_time,
+                        None,
+                        None,
+                    )
                 )
                 return result
 
@@ -155,9 +166,19 @@ def wrapper(*args, **kwargs):
                 self._thread_local.active_functions.remove(func_id)
                 overhead_time = time.thread_time_ns() - end_time
                 self.function_calls_data.append(
-                    (func.__name__, class_name, func.__module__, func.__code__.co_filename,
-                     benchmark_function_name, benchmark_module_path, benchmark_line_number, execution_time,
-                     overhead_time, None, None)
+                    (
+                        func.__name__,
+                        class_name,
+                        func.__module__,
+                        func.__code__.co_filename,
+                        benchmark_function_name,
+                        benchmark_module_path,
+                        benchmark_line_number,
+                        execution_time,
+                        overhead_time,
+                        None,
+                        None,
+                    )
                 )
                 return result
             # Flush to database every 100 calls
@@ -168,12 +189,24 @@ def wrapper(*args, **kwargs):
             self._thread_local.active_functions.remove(func_id)
             overhead_time = time.thread_time_ns() - end_time
             self.function_calls_data.append(
-                (func.__name__, class_name, func.__module__, func.__code__.co_filename,
-                 benchmark_function_name, benchmark_module_path, benchmark_line_number, execution_time,
-                 overhead_time, pickled_args, pickled_kwargs)
+                (
+                    func.__name__,
+                    class_name,
+                    func.__module__,
+                    func.__code__.co_filename,
+                    benchmark_function_name,
+                    benchmark_module_path,
+                    benchmark_line_number,
+                    execution_time,
+                    overhead_time,
+                    pickled_args,
+                    pickled_kwargs,
+                )
             )
             return result
+
         return wrapper
 
+
 # Create a singleton instance
 codeflash_trace = CodeflashTrace()