@langchain/google@0.2.1
f017708 Thanks @christian-bromann! - fix: classify provider 429s before retryingFetched June 22, 2026
Added opt-in client-side rate limiting for exception autocapture, using a token bucket algorithm to allow bursts and refill over time. Rate…
PostHog · PostHog PythonPatch Changes - 7452642: fix(provider/google-vertex): avoid recreating Node GoogleAuth clients for repeated requests Create Google auth tok…
Vercel · AI SDKHTTP 429 rate-limit responses from providers are now classified correctly before retry logic is applied.
LangChain · LangChain.jsProvider 429 responses are now classified before retry logic runs. Tool outputs that are arrays of plain objects are JSON-stringified inste…
LangChain · LangChain.js