From 9f3aecaf0226fa13c77eab2bcd55ff81abff5511 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Thu, 28 May 2026 22:07:55 +0000
Subject: [PATCH] perf: optimize list deduplication in config merge

Co-authored-by: SatoryKono <13055362+SatoryKono@users.noreply.github.com>
---
 src/bioetl/infrastructure/config_merge.py | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/src/bioetl/infrastructure/config_merge.py b/src/bioetl/infrastructure/config_merge.py
index 5bbffbaab6..5ca5e2336c 100644
--- a/src/bioetl/infrastructure/config_merge.py
+++ b/src/bioetl/infrastructure/config_merge.py
@@ -35,14 +35,9 @@ def _default_concat_list_merger(
     if all(isinstance(item, str) for item in base) and all(
         isinstance(item, str) for item in override
     ):
-        seen: set[str] = set()
-        merged: list[Any] = []  # Any: YAML config values are heterogeneous
-        for item in base + override:
-            item_str = str(item)
-            if item_str not in seen:
-                seen.add(item_str)
-                merged.append(item)
-        return merged
+        # OPTIMIZATION: dict.fromkeys() leverages fast C-level iteration and
+        # insertion-order preservation, outperforming pure-Python seen=set() loops
+        return list(dict.fromkeys(base + override))
 
     return [*base, *override]