LangSmith SDK

OTLP traces can now be sent to an Agent environment, and sandbox run() no longer waits 100ms for the server's TCP close. Also fixed Python comparative evaluator scores when randomizing concurrent runs.

Sandbox S3 mounts now support customer-managed KMS keys in the Python SDK, and the sandbox accepts any JOSE asymmetric algorithm chosen by the JWKS key. Also fixed sending session_id on RunTree.patch and made the /runs/multipart 404 fallback to /runs/batch reachable.

Fixed normalization of sandbox API endpoint prefixes.

wrap_anthropic no longer requires the completions resource. Release bundles the Python 0.14.6 and JS 0.10.9 versions, plus CI updates freezing the JS folder.

Adds AgentAddress, ExperimentAddress, and EvaluatorAddress types, exposes client.sessions in the JS SDK to resolve an address, and reads LANGSMITH_REVISION_ID for run revision_id. License key and API key salt assignments are now redacted in both the Python and JS SDKs.

Fixed the full OTLP traces endpoint resolving incorrectly across the Python and JavaScript SDKs. Also refactored address handling to use strings.

Adds an address() handle and typed address object for agent addressing, and ends traced runs when a returned ReadableStream errors. Also retries transient WebSocket failures before sandbox command start and exports OTel prompt/completion as JSON strings.

Python gains an ls.address handle for agent addressing, and only the primary write replica now keeps the original run IDs. Also fixed missing OTel exports for tool name, call_id and definitions, preserved responses on wrapped HTTP errors, and resolved relative example attachment URLs.

Restored missing OpenTelemetry exports for tool_call_id and tool_definitions, and fixed tracing of ClaudeSDKClient.receive_messages(). Sandbox now verifies service URL user tokens and proxy callbacks.

Sandboxes are now granted delegated LangSmith access on create, with LangSmith-login service URLs and JS service URL support. Also captured Claude SDK run stop_reason plus tool and response IDs, added agent-scoped addressing for runs and feedback parts in Python, and patched soupsieve ReDoS vulnerabilities.

evaluate() and aevaluate() now accept a disable_evaluator_tracing toggle, and sandbox helpers support AWS IAM roles in Python and JavaScript. Sandbox also gains run_config, stdin EOF handling, native file search and range operations, and an SSE exec-api command streaming option behind a feature flag.

Fixed the LiveKit integration dropping system instructions when history is supplied. Release also includes a JS SDK 0.10.4 release and docs for OpenWiki with a weekly refresh workflow.

Runs now report the configured tracing sample rate in both Python and JS. Also fixed sandbox run() waiting about a second on the server's TCP close after exit, and patched vulnerable Vitest, Hono, js-yaml, and sharp test dependencies.

LiveKit telemetry now supports agents 1.7 and 1.8.

New LangSmithSecret class redacts sensitive function parameters, and update_sandbox now supports proxy_config in both Python and JS. Also fixed multipart body replay across retry layers and reduced ThreadPoolExecutor churn in hybrid tracing.

Python client now supports snapshot tags in the sandbox, and rate-limited sandbox WebSocket connections are retried in both Python and JS. Plus dependency and advisory patches.

Fixed the anonymizer walk queue to drain in O(1) time, resolving a performance issue in the SDK.

Trace sampling is now deterministic, and per-function anonymization fails closed when the callable errors. Switched to httpx2 with httpx as a fallback, and serializes identical replicas once into a single frame.

Run metadata now excludes password and email environment variables, preventing credential leaks. Handles 64-bit+ integers without precision loss and closes an argument-shape bypass in Anthropic MCP redaction, plus several other fixes.

Python and JS clients now offer generate_download_url for sandbox files, and retry transient WebSocket upgrades. Also fixed inaccurate pytest suite reporting.