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
fix(tests): pin repro smoke server to websockets-sansio backend
Adryan Eka Vandraea0d519677b7
diff --git a/tests/test_scripts/test_repro_codex_replay_smoke.py b/tests/test_scripts/test_repro_codex_replay_smoke.pyindex 2e8f85ffb..745b70c81 100644--- a/tests/test_scripts/test_repro_codex_replay_smoke.py+++ b/tests/test_scripts/test_repro_codex_replay_smoke.py@@ -90,6 +90,7 @@ class _ServerThread:log_level="warning",loop="asyncio",lifespan="on",+ ws="websockets-sansio",)self.server = uvicorn.Server(config)self.port = port