From 5f3756aa134b5618d366c882ec65bb30def8e57f Mon Sep 17 00:00:00 2001
From: seonghobae <8172694+seonghobae@users.noreply.github.com>
Date: Sun, 21 Jun 2026 17:09:48 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=20Bolt:=20Optimize=20JSON=20decoding?=
 =?UTF-8?q?=20in=20normalize=20script?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace O(N^2) string slicing and character-by-character iteration
with `str.find` and index-based `json.JSONDecoder().raw_decode`.
This prevents severe memory copying overhead when incrementally
parsing large OpenCode JSON output files.
---
 .jules/bolt.md                                 |  3 +++
 scripts/ci/opencode_review_normalize_output.py | 18 ++++++++++++------
 2 files changed, 15 insertions(+), 6 deletions(-)
 create mode 100644 .jules/bolt.md

diff --git a/.jules/bolt.md b/.jules/bolt.md
new file mode 100644
index 000000000..36414642e
--- /dev/null
+++ b/.jules/bolt.md
@@ -0,0 +1,3 @@
+## 2024-06-21 - Python JSON Decoding Optimization
+**Learning:** In Python, string slicing `text[index:]` inside a loop can cause O(N^2) complexity and severe memory copying overhead. When decoding JSON incrementally from a large text blob, `json.JSONDecoder().raw_decode(text, index)` can parse from a given index without slicing. Combining this with `text.find("{", index)` to skip irrelevant characters is significantly faster than `enumerate(text)`.
+**Action:** Always prefer `raw_decode(text, index)` and `string.find()` over string slicing and character-by-character iteration when scanning large files for JSON objects.
diff --git a/scripts/ci/opencode_review_normalize_output.py b/scripts/ci/opencode_review_normalize_output.py
index 711fd1ef3..d972ad63d 100755
--- a/scripts/ci/opencode_review_normalize_output.py
+++ b/scripts/ci/opencode_review_normalize_output.py
@@ -83,14 +83,20 @@ def iter_json_objects(text: str) -> list[Any]:
         # OpenCode exports may contain prose around the JSON control object.
         pass
 
-    for index, character in enumerate(text):
-        if character != "{":
-            continue
+    # Bolt: Use text.find and pass index directly to raw_decode to skip
+    # non-brace chars efficiently and prevent O(N^2) string copying.
+    index = 0
+    length = len(text)
+    while index < length:
+        index = text.find("{", index)
+        if index == -1:
+            break
         try:
-            value, _ = decoder.raw_decode(text[index:])
+            value, _ = decoder.raw_decode(text, index)
+            values.append(value)
         except json.JSONDecodeError:
-            continue
-        values.append(value)
+            pass
+        index += 1
 
     return values