Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
Update test_proxy_savings_history.py
Garmbb5b60f6e64a
diff --git a/tests/test_proxy_savings_history.py b/tests/test_proxy_savings_history.pyindex 6cdb04f2e..060a2decd 100644--- a/tests/test_proxy_savings_history.py+++ b/tests/test_proxy_savings_history.py@@ -11,9 +11,9 @@ import pytestpytest.importorskip("fastapi")-import headroom.proxy.savings_tracker as savings_tracker_modulefrom fastapi.testclient import TestClient+import headroom.proxy.savings_tracker as savings_tracker_modulefrom headroom.proxy.savings_tracker import HEADROOM_SAVINGS_PATH_ENV_VAR, SavingsTrackerfrom headroom.proxy.server import ProxyConfig, create_app