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: ruff format tests/test_transforms_search_compressor.py
chopratejas1de32b14374d
diff --git a/tests/test_transforms_search_compressor.py b/tests/test_transforms_search_compressor.pyindex 743b5dc7e..5fd057deb 100644--- a/tests/test_transforms_search_compressor.py+++ b/tests/test_transforms_search_compressor.py@@ -110,10 +110,9 @@ def test_search_compressor_persist_to_python_ccr(monkeypatch: pytest.MonkeyPatch"headroom.cache.compression_store",SimpleNamespace(get_compression_store=lambda: SimpleNamespace(- store=lambda original, compressed, original_item_count=0: seen.setdefault(- "call", (original, compressed)+ store=lambda original, compressed, original_item_count=0: (+ seen.setdefault("call", (original, compressed)) or "stored-key")- or "stored-key")),)