Avatar for the langchain-ai user
langchain-ai
langchain
BlogDocsChangelog

Performance History

Latest Results

fix(core): redact streaming callback options (#39179) Credential-bearing model kwargs can be sanitized by an integration's `_get_invocation_params`, but streaming callbacks also received the original kwargs through `options`. This could expose remote MCP credentials to callback handlers and persisted LangSmith traces even when `invocation_params` was redacted. Streaming and v3 streaming-event callbacks now construct `options` from the integration-sanitized invocation parameters while the model invocation continues to receive the original values. Sync and async regression coverage verifies both callback redaction and provider propagation. ## Release note Streaming chat-model callbacks no longer receive unsanitized invocation options when an integration redacts sensitive parameters. This contribution was prepared with AI-agent assistance. Co-authored-by: jkennedyvz <jkennedyvz@users.noreply.github.com>
master
4 hours ago
fix(core): redact streaming callback options
jkennedyvz/core/redact-streaming-mcp-credentials
6 hours ago
fix(langchain): update Anthropic config tests
nh/langchain/fix-anthropic-config-test
12 hours ago
fix(core): type text stream projections
nh/fix-projection-typing
13 hours ago
fix(core): forward kwargs in `RouterRunnable`
ShiroKSH:ShiroKSH/core/forward-router-kwargs
1 day ago

Latest Branches

CodSpeed Performance Gauge
0%
fix(core): redact streaming callback options#39179
6 hours ago
56773d1
jkennedyvz/core/redact-streaming-mcp-credentials
CodSpeed Performance Gauge
0%
12 hours ago
2961305
nh/fix-projection-typing
CodSpeed Performance Gauge
0%
12 hours ago
2021a25
nh/langchain/fix-anthropic-config-test
© 2026 CodSpeed Technology
Home Terms Privacy Docs