LangChain shipped LangSmith Python SDK 0.14.1 on 2026-09-25 (rolling in 0.14.0): address runs and feedback by agent rather than only by project; sandboxes can receive delegated LangSmith access and login service URLs (JS too); ClaudeSDKClient.receive_messages() is traced with stop_reason plus tool/response IDs; OTel exports add tool_call_id, tool_definitions, and finish_reasons. JS package moves to 0.10.5.
Key Takeaways
- ✓Shipped: Python 0.14.1 / JS 0.10.5 — pip install -U langsmith
- ✓Address runs and feedback by agent, not only by project
- ✓Sandboxes get delegated LangSmith access + login/service URLs
- ✓ClaudeSDKClient.receive_messages() traced with stop_reason and tool/response IDs
- ✓OTel exports tool_call_id, tool_definitions, finish_reasons; list_runs can return s3_urls attachments
Finished reading? Explore benchmark rankings & pricing
Real-world SWE-bench scores & $20/mo vs API cost break-even calculator
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Core Background & Industry Pain Points
Multi-agent pipelines span sub-agents, tools, and sandboxes. Project-only addressing is awkward; Claude SDK streams and OTel fields were incomplete; sandboxes lacked safe delegated LangSmith login.
Architecture Highlights & Internals
Python 0.14.0→0.14.1 (JS 0.10.5) addresses runs/feedback by agent, grants delegated LangSmith access plus login/service URLs on sandbox create, traces ClaudeSDKClient.receive_messages() with stop_reason and tool/response IDs, and enriches OTel with tool_call_id, tool_definitions, and finish_reasons. list_runs/list_threads can return s3_urls attachments.
Authoritative Benchmarks & Measured Scores
No published latency/overhead figures—validate agent filters, sandbox login, and OTel field presence on your stack.
Developer Hands-on Guide
pip install -U langsmith. Configure tracing via docs.smith.langchain.com. See v0.14.1 and v0.14.0.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.