diff --git a/strix/llm/llm.py b/strix/llm/llm.py
index 969710e1..9e96f73c 100644
--- a/strix/llm/llm.py
+++ b/strix/llm/llm.py
@@ -10,7 +10,7 @@ from litellm.utils import supports_prompt_caching, supports_vision
 
 from strix.config import Config
 from strix.llm.config import LLMConfig
-from strix.llm.memory_compressor import MemoryCompressor, _get_message_tokens
+from strix.llm.memory_compressor import MemoryCompressor, get_message_tokens
 from strix.llm.utils import (
     _truncate_to_first_function,
     fix_incomplete_tool_call,
@@ -211,7 +211,7 @@ class LLM:
             )
 
         reserved_tokens = sum(
-            _get_message_tokens(msg, self.config.litellm_model) for msg in messages
+            get_message_tokens(msg, self.config.litellm_model) for msg in messages
         )
         compressed = list(
             self.memory_compressor.compress_history(conversation_history, reserved_tokens)
diff --git a/strix/llm/memory_compressor.py b/strix/llm/memory_compressor.py
index 728831b1..aea086c1 100644
--- a/strix/llm/memory_compressor.py
+++ b/strix/llm/memory_compressor.py
@@ -52,7 +52,7 @@ def _count_tokens(text: str, model: str) -> int:
         return len(text) // 4  # Rough estimate
 
 
-def _get_message_tokens(msg: dict[str, Any], model: str) -> int:
+def get_message_tokens(msg: dict[str, Any], model: str) -> int:
     content = msg.get("content", "")
     if isinstance(content, str):
         return _count_tokens(content, model)
@@ -209,7 +209,7 @@ class MemoryCompressor:
         model_name: str = self.model_name  # type: ignore[assignment]
 
         total_tokens = reserved_tokens + sum(
-            _get_message_tokens(msg, model_name) for msg in system_msgs + regular_msgs
+            get_message_tokens(msg, model_name) for msg in system_msgs + regular_msgs
         )
 
         if total_tokens <= MAX_TOTAL_TOKENS * 0.9: