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
test: Update LLMLingua default model test to match new default
Prakersh Maheshwari658dc6c06c48
diff --git a/tests/test_transforms/test_llmlingua_compressor.py b/tests/test_transforms/test_llmlingua_compressor.pyindex 1b432e8a3..5581bf676 100644--- a/tests/test_transforms/test_llmlingua_compressor.py+++ b/tests/test_transforms/test_llmlingua_compressor.py@@ -141,7 +141,7 @@ class TestLLMLinguaConfig:"""Default config values are sensible."""config = LLMLinguaConfig()- assert config.model_name == "microsoft/llmlingua-2-xlm-roberta-large-meetingbank"+ assert config.model_name == "microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank"assert config.device == "auto"assert config.target_compression_rate == 0.3assert config.min_tokens_for_compression == 100