LangChain OSS(@LangChain_OSS):What's new in LangChain? 🚀 🧯 Standard exceptions: chat models now raise standard exception types across providers, so you can distinguish retryable errors (timeouts, rate limits, etc.) in a consistent way. Fully backward compatible. 🧩 Agent middleware: custom token_counter in ContextEditingMiddleware, plus non-retryable exceptions now skip retries in ModelRetryMiddleware (https://t.co/DJoIL2aqAK, https://t.co/0nMJg3BvFW) 🔥 Fireworks document reranking: a new reranker integration (https://t.co/xPRNjfKbrm) 📊 Token & usage accounting: bug fixes for xAI and DeepSeek (https://t.co/TbudILb6Fy, https://t.co/PG0KisZyUl) ⚡ Portability & perf: lazy transformers import, and tighter grep scope for Anthropic (https://t.co/yVKPPsrSUL, https://t.co/K1I5fgt6yk) This is your harness! Thanks to everyone who made it better. 🙏

2026.08.20 19:32

What's new in LangChain? 🚀 🧯 Standard exceptions: chat models now raise standard exception types across providers, so you can distinguish retryable errors (timeouts, rate limits, etc.) in a consistent way. Fully backward compatible. 🧩 Agent middleware: custom token_counter in ContextEditingMiddleware, plus non-retryable exceptions now skip retries in ModelRetryMiddleware ( 🔥 Fireworks document reranking: a new reranker integration ( 📊 Token & usage accounting: bug fixes for xAI and DeepSeek ( ⚡ Portability & perf: lazy transformers import, and tighter grep scope for Anthropic ( This is your harness! Thanks to everyone who made it better. 🙏