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(openclaw): match inherited PATH shell check (#2821)
JD Davis01161fe01913
diff --git a/plugins/openclaw/test/proxy-manager.test.ts b/plugins/openclaw/test/proxy-manager.test.tsindex 600ce268c..02f7302bc 100644--- a/plugins/openclaw/test/proxy-manager.test.ts+++ b/plugins/openclaw/test/proxy-manager.test.ts@@ -364,7 +364,7 @@ describe("ProxyManager launch internals", () => {expect(pathSpec.checkUseShell).toBe(false);} else {expect(pathSpec.checkCommand).toBe("sh");- expect(pathSpec.checkArgs).toEqual(["-lc", "command -v headroom >/dev/null 2>&1"]);+ expect(pathSpec.checkArgs).toEqual(["-c", "command -v headroom >/dev/null 2>&1"]);}});