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
style: format test_proxy_savings_history.py for CI
Garma858a0fd4b2d
diff --git a/tests/test_proxy_savings_history.py b/tests/test_proxy_savings_history.pyindex 81927c465..c7387136e 100644--- a/tests/test_proxy_savings_history.py+++ b/tests/test_proxy_savings_history.py@@ -484,7 +484,10 @@ def test_savings_tracker_rollups_preserve_spend_and_input_history(tmp_path, monk"monthly",]-def test_stats_history_defaults_to_compact_history_but_can_return_full_history(tmp_path, monkeypatch):++def test_stats_history_defaults_to_compact_history_but_can_return_full_history(+ tmp_path, monkeypatch+):path = tmp_path / "proxy_savings.json"tracker = SavingsTracker(path=str(path),