scriptoriumadmin/strix
1
0
Fork 0
mirror of https://github.com/usestrix/strix.git synced 2026-09-11 22:51:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor(llm): rename _get_message_tokens to public API name

Browse source
This commit is contained in:
0xhis 2026-03-21 01:28:19 -07:00
parent 4f852e662f
commit 63035db042
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
strix/llm/llm.py
View file

@ -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)

4
strix/llm/memory_compressor.py
View file

@ -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: