langchain-ai/langchainjs @langchain/core@1.3.0

on GitHub

Minor Changes

• #11986 2caf64d Thanks @richardscarrott! - feat: stream tool-call args as tool-call-delta slices

  Tool-call and server-tool-call args now stream as tool-call-delta events, which carry only the new slice of the args, instead of block-delta snapshots of the args so far. A large tool call now costs about the same bytes on the wire as the same length of text.

  • This covers the compat bridge (any model that only implements _streamResponseChunks), the OpenAI-compatible converter (OpenAI Completions, Groq, Mistral, IBM, OpenRouter, Perplexity, DeepSeek, Fireworks, Together AI and xAI Completions), OpenAI and xAI Responses, Anthropic (client and server tool calls) and Bedrock Converse. Google and Ollama still send one complete snapshot per call.
  • A tool call's id, name and index go on content-block-start, which carries no args. An id or name that arrives later reaches consumers on content-block-finish.
  • If you read raw events and their block-delta fields.args mid-stream, or write agent stream transformers that do, read tool-call-delta instead. await stream, .toolCalls and the assembled message are unchanged.
  • Upgrade your clients first. Older clients mishandle tool-call-delta. You need @langchain/langgraph-sdk 1.12.6 or later; @langchain/react, @langchain/vue, @langchain/svelte or @langchain/angular 1.2.6 or later; and langchain-core 1.6.13 or later for Python clients.
  • To hold back, pin @langchain/core below 1.3.0. That also keeps you on @langchain/openai, @langchain/anthropic, @langchain/aws and @langchain/xai versions that send snapshots.