diff --git a/ols/utils/token_handler.py b/ols/utils/token_handler.py
index a9f06f0d..3b14fcb5 100644
--- a/ols/utils/token_handler.py
+++ b/ols/utils/token_handler.py
@@ -181,10 +181,11 @@ def limit_conversation_history(
     ) -> tuple[list[str], bool]:
         """Limit conversation history to specified number of tokens."""
         total_length = 0
+        formatted_history: list[str] = []
 
-        for index, message in enumerate(reversed(history)):
+        for original_message in reversed(history):
             # Restructure messages as per model
-            message = restructure_history(message, model)
+            message = restructure_history(original_message, model)
 
             message_length = TokenHandler._get_token_count(self.text_to_tokens(message))
             total_length += message_length
@@ -194,6 +195,7 @@ def limit_conversation_history(
                 logger.debug(
                     "History truncated, it exceeds available %d tokens.", limit
                 )
-                return history[len(history) - index :], True
+                return formatted_history[::-1], True
+            formatted_history.append(message)
 
-        return history, False
+        return formatted_history[::-1], False
diff --git a/pyproject.toml b/pyproject.toml
index c92b16a8..f685f511 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,7 +1,7 @@
 [tool.ruff]
 
 # description of all rules are available on https://docs.astral.sh/ruff/rules/
-lint.select = ["D", "E", "F", "W", "C", "S", "I", "TCH", "SLOT", "RUF", "C90", "N", "YTT", "ASYNC", "A", "C4", "T10", "PGH", "FURB", "PERF", "AIR", "NPY", "FLY"]
+lint.select = ["D", "E", "F", "W", "C", "S", "I", "TCH", "SLOT", "RUF", "C90", "N", "YTT", "ASYNC", "A", "C4", "T10", "PGH", "FURB", "PERF", "AIR", "NPY", "FLY", "PLW2901"]
 
 # we need to check 'mood' of all docstrings, this needs to be enabled explicitly
 lint.extend-select = ["D401"]