From 5f166066816285155d7c62f9ccb84bbd7a0dcf49 Mon Sep 17 00:00:00 2001
From: "codeflash-ai[bot]"
 <148906541+codeflash-ai[bot]@users.noreply.github.com>
Date: Fri, 6 Mar 2026 16:27:31 +0000
Subject: [PATCH 1/2] Optimize JavaScriptSupport.normalize_code

The optimization moves the `normalize_js_code` import from inside the method to module-level and wraps it with a 128-entry LRU cache (`functools.lru_cache`), achieving a 114% speedup by eliminating repeated parsing and normalization of duplicate code snippets. Line profiler shows the original spent 96.9% of wall time calling `normalize_js_code` (which internally spends ~74% on `normalize_tree` and AST traversal); caching this result avoids re-parsing identical source strings, common during deduplication workflows. The smaller cache size (128 vs. 1024) balances memory usage with hit-rate for typical workloads where a modest number of distinct snippets are repeatedly normalized.
---
 codeflash/languages/javascript/support.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/codeflash/languages/javascript/support.py b/codeflash/languages/javascript/support.py
index f1a570740..69503508f 100644
--- a/codeflash/languages/javascript/support.py
+++ b/codeflash/languages/javascript/support.py
@@ -17,6 +17,8 @@
 from codeflash.languages.javascript.treesitter import TreeSitterAnalyzer, TreeSitterLanguage, get_analyzer_for_file
 from codeflash.languages.registry import register_language
 from codeflash.models.models import FunctionParent
+from codeflash.languages.javascript.normalizer import normalize_js_code
+from functools import lru_cache
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
@@ -26,6 +28,8 @@
     from codeflash.models.models import GeneratedTestsList, InvocationId, ValidCode
     from codeflash.verification.verification_utils import TestConfig
 
+_cached_normalize_js_code = lru_cache(maxsize=128)(normalize_js_code)
+
 logger = logging.getLogger(__name__)
 
 
@@ -1704,11 +1708,9 @@ def validate_syntax(self, source: str) -> bool:
 
     def normalize_code(self, source: str) -> str:
         """Normalize JavaScript code for deduplication using tree-sitter."""
-        from codeflash.languages.javascript.normalizer import normalize_js_code
-
         try:
             is_ts = self.treesitter_language == TreeSitterLanguage.TYPESCRIPT
-            return normalize_js_code(source, typescript=is_ts)
+            return _cached_normalize_js_code(source, typescript=is_ts)
         except Exception:
             return source
 

From 347b0b7fd636084dc4251e4bf1ee475fbac2f630 Mon Sep 17 00:00:00 2001
From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com>
Date: Fri, 6 Mar 2026 16:30:50 +0000
Subject: [PATCH 2/2] style: fix import sort order in javascript/support.py

---
 codeflash/languages/javascript/support.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/codeflash/languages/javascript/support.py b/codeflash/languages/javascript/support.py
index 69503508f..1d41b3ae8 100644
--- a/codeflash/languages/javascript/support.py
+++ b/codeflash/languages/javascript/support.py
@@ -9,16 +9,16 @@
 import logging
 import subprocess
 import xml.etree.ElementTree as ET
+from functools import lru_cache
 from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
 from codeflash.discovery.functions_to_optimize import FunctionToOptimize
 from codeflash.languages.base import CodeContext, FunctionFilterCriteria, HelperFunction, Language, TestInfo, TestResult
+from codeflash.languages.javascript.normalizer import normalize_js_code
 from codeflash.languages.javascript.treesitter import TreeSitterAnalyzer, TreeSitterLanguage, get_analyzer_for_file
 from codeflash.languages.registry import register_language
 from codeflash.models.models import FunctionParent
-from codeflash.languages.javascript.normalizer import normalize_js_code
-from functools import lru_cache
 
 if TYPE_CHECKING:
     from collections.abc import Sequence