Releasesby IbisLangSmith SDK 0.14.7
UpdateyesterdayUnverifiedAdded Oct 10, 2026
- fix: normalize sandbox API endpoint prefixes release(py): 0.14.7
Topics: Developer tools
More LangSmith releases
Every LangSmith releaseLangSmith SDK 0.14.6
- release(js): 0.10.9 ci: freeze js/ now that the JS SDK moved ci: point frozen-folder PRs to the right repo fix(wrappers): don't require completions resource in wrap_anthropic release(py): 0.14.6
LangSmith SDK 0.14.5
- release(js): 0.10.8 chore(deps): bump the actions-minor-and-patch group with 3 updates chore(deps-dev): bump types-psutil from 7.2.2.20260827 to 7.2.2.20260906 in /python chore(deps): bump the actions-major group with 2 updates chore(deps): bump the py-minor-and-patch group in /python with 8 updates fix(tests): prevent background uploads from restoring...
LangSmith SDK 0.14.4
- release(js): 0.10.7 ci: request Open SWE investigation of nightly SDK failures refactor: take addresses as strings (Python and JS) fix(py,js): correctly resolve the full OTLP traces endpoint release(py): 0.14.4
LangSmith SDK 0.14.3
- feat(js): add address() handle for agent addressing chore(js): patch vulnerable development dependencies fix(sandbox): retry transient WebSocket failures before command start chore(deps): bump urllib3 from 2.7.0 to 2.8.0 in /python chore(deps): bump pyjwt from 2.13.0 to 2.15.0 in /python chore(deps): bump undici from 7.29.0 to 7.29.1 in...
LangSmith SDK 0.14.2
- fix(js): missing OTel exports for tool name, call_id and definitions chore: increase Python and JS dependency delay to seven days feat(python): add ls.address handle for agent addressing fix(py): preserve response on wrapped HTTP errors fix(js): stub OpenAI transport in completions test fix(py,js): only the primary write replica keeps the original run ids...
LangSmith SDK 0.14.1
- release(js): 0.10.5 ci: mirror merges to the staging repos ci: drop the push-based mirror workflow, staging pulls instead test(py): select s3_urls so list_runs and list_threads return attachments fix(py): fix missing OTel exports for tool_call_id and tool_definitions fix(py): trace ClaudeSDKClient.receive_messages() feat(sandbox): verify service URL user...
LangSmith SDK 0.14.0
- fix(deps): patch soupsieve ReDoS vulnerabilities by John Kennedy (@jkennedyvz) in #3560 feat(sandbox): grant sandboxes delegated LangSmith access on create by Ramon Nogueira (@ramon-langchain) in #3563 feat(sandbox): LangSmith-login service URLs, and service URLs for JS by Ramon Nogueira (@ramon-langchain) in #3564 fix(py): correct broken migration-guide...
LangSmith SDK 0.13.0
- feat(evaluate): add disable_evaluator_tracing toggle to evaluate() and aevaluate() by Sineha Manivannan (@sineha-mani) in #3547 ci(openwiki): open the update PR with gh instead of a third-party action by Thibaut Lehmann (@thibautlehmann) in #3545 refactor(sandbox): deprecate no_proxy in proxy config helpers by Ramon Nogueira (@ramon-langchain) in #3512...
Also shipped on Oct 9, 2026
LangChain in October 2026Google Workspace connector is available in Beta
The managed Google Workspace connector is now available in Beta in Databricks Lakeflow Connect. Use the connector to ingest audit activity from Google Workspace applications and services into Databricks. The connector uses OAuth user authorization and supports incremental ingestion.
Agentic Marketplace Discovery (Public preview)
Agentic Marketplace Discovery is now available in public preview. On the public Snowflake Marketplace Discover page in Snowsight, you can switch between Agentic discovery and Marketplace search . Describe what you need to CoCo to find and compare matching listings, or search for providers and listings directly.
All AI Gateway models with prepaid credits, backend features with your coding agent, and new ways to send feedback release - Oct 09, 2026
All AI Gateway models now available with prepaid credits. You don't need to request access to frontier models in the Neon AI Gateway anymore. If you're on a pai...
Use request tags in Unity Gateway service policies (Beta)
Custom service policies in Unity Gateway can now check caller-supplied request tags, such as requiring a tag before a model request or MCP tool call proceeds. See Request tags .
Use OpenJev as the evaluator for LLM-as-a-judge service policies (Beta)
You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM-as-a-judge service policy. OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator. See Use OpenJev as the evaluator .
Code execution in Genie One (Public Preview)
Genie One can now run code in a secure, isolated sandbox to take on work that goes beyond SQL, such as more advanced analyses. Code runs on your behalf using your existing permissions, so Unity Catalog governance and data access controls continue to apply. See Code execution in Genie One .