Reliability fixes, merged upstream.
The clearest proof that we read agent frameworks closely is the fixes we have landed in them. Two of the merged pull requests below removed runtime failures in the AI frameworks teams build on. Each links to the public PR.
Fixed thinking + tools crash in ChatAnthropic.bind_tools()
Anthropic’s API rejects tool_choice when extended thinking is enabled. LangChain’s bind_tools() was force-setting it on every call, returning 400 for any agent combining Claude thinking with tool use. Ported the guard the structured-output path already had.
Fixed ChatHistoryTruncationReducer silently deleting system prompts
The truncation reducer was calling extract_range, a summarization helper that filters out system and developer messages. System prompts were being dropped with no warning. Ported Microsoft’s own .NET fix to the Python SDK.
26 merged contributions total. Beyond the two fixes above, 24 more across PyTorch Ignite, Optuna, React Router (56k ★), Nuxt (60k ★), MobX (20k ★), Cloudflare Workers SDK (6k ★), Sentry, ngrx, TSDoc, and others (maintenance and typing modernization). Full list on GitHub.
Back to the open-source catalog.