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(cache): make purge insertion eligible after setup (#3790)
JD Davise64b9f58a209
diff --git a/tests/test_ccr_sqlite_backend.py b/tests/test_ccr_sqlite_backend.pyindex d7f6384d9..7accad392 100644--- a/tests/test_ccr_sqlite_backend.py+++ b/tests/test_ccr_sqlite_backend.py@@ -213,6 +213,10 @@ class TestSQLiteBackend:assert expired is not Noneexpired.created_at = time.time() - 11backend.set(expired_hash, expired)+ # The setup stores above intentionally exercised the periodic purge and+ # advanced its 60-second throttle. Make the insertion under test eligible+ # to purge the row we only just backdated.+ backend._last_purge = 0.0monkeypatch.setattr(backend,