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
Add global httpx.ReadTimeout handler for memory tests
chopratejas4ea173388aeb
diff --git a/tests/test_memory/conftest.py b/tests/test_memory/conftest.pyindex 2ae939a95..3dfe47bda 100644--- a/tests/test_memory/conftest.py+++ b/tests/test_memory/conftest.py@@ -6,3 +6,30 @@ from __future__ import annotationsimport osos.environ["TOKENIZERS_PARALLELISM"] = "false"++import pytest++# Import httpx for type checking (will be available since it's a dependency)+try:+ import httpx++ HTTPX_AVAILABLE = True+except ImportError:+ HTTPX_AVAILABLE = False++[email protected](hookwrapper=True)+def pytest_runtest_call(item):+ """Wrap test execution to catch httpx.ReadTimeout and skip instead of fail.++ This handles flaky network timeouts that occur when:+ - HuggingFace Hub is slow during model downloads (sentence-transformers)+ - External embedding APIs timeout+ - Network connectivity issues in CI+ """+ outcome = yield++ if HTTPX_AVAILABLE and outcome.excinfo is not None:+ exc_type, exc_value, exc_tb = outcome.excinfo+ if isinstance(exc_value, httpx.ReadTimeout):+ pytest.skip("Skipped due to network timeout (flaky CI)")