Legacy endpoints deprecated; sandbox streaming added

Observability and evaluations

Datasets and experiments

• LangSmith exposes annotation queue item endpoints for adding, listing, updating, deleting, counting, positioning, and reviewing run or thread queue items through the public API and SDK generation flow.
• Uploading a .csv or .jsonl dataset now works regardless of the Content-Type the browser reports. Windows browsers label .csv files as an Excel type, which previously caused valid uploads to fail. Uppercase filenames such as DATASET.CSV are also accepted.
• Evaluator lists on a dataset or tracing project now show an evaluator's current name instead of the name it had when it was attached.
• Metadata columns in the experiment comparison grid now render their values instead of staying empty.
• LangSmith marks every legacy endpoint replaced by the SmithDB SDK migration guide as deprecated with Deprecation: true, a Sunset date of January 31, 2027, and a Link header pointing at the migration guide.
• Dataset experiment tables can sort by feedback score when SmithDB queries are enabled and ClickHouse queries are disabled.
• Annotation queue item APIs use project_id for the tracing project. Request bodies also accept session_id as an alias.
• Dataset example views restore clear spacing between the example details and tab navigation.
• Pairwise annotation queue runs again include the tracing project id needed to create feedback when ClickHouse query support is disabled.
• Correcting an evaluator score from the experiment results grid now updates the cell and its popover right away.
• The Configure Evaluator pane's header and templates navigation again paint the same background as the pane itself in dark mode.
• Dataset and run attachments now resolve relative signed download URLs before previewing, opening, or downloading them in self-hosted deployments.

Monitoring and alerting

• Adds a reusable ChartCard component to the LangSmith design system.

Engine

• A resolved issue on an Engine Issue Board now returns to Open as soon as Engine links a new matching trace to it. Dismissed issues stay dismissed.
• The issue detail header now renders category and tag badges on the same line as the title.
• The "Engine failed to complete a run" trigger is no longer offered when configuring a Slack channel or webhook destination on an issue board.
• Engine run webhooks and sandbox links now resolve the externally reachable API base from LANGSMITH_PUBLIC_API_ENDPOINT, falling back to LANGCHAIN_PLATFORM_ENDPOINT and then LANGCHAIN_ENDPOINT.

Tracing

• Trace detail panes once again use an elevated background that matches their section headers.
• Bulk exports accept a new opt-in feedbacks column that carries each run's individual feedback entries as a JSON array.
• Delete an entire trace from the run details actions menu after confirming the destructive action.
• Negative feedback-key filters now return matching traces correctly when ClickHouse uses optimized runs tables.
• When a project configures a custom output renderer, the trace Output section now offers it as a Custom option alongside Markdown, Plain, JSON, and YAML.
• Tracing project activity and sorting stay up to date for self-hosted deployments using Redis versions before 6.2.
• POST /api/v1/runs/stats now returns a 404 when the requested tracing project does not exist.
• Self-hosted deployments now catch up missing tracing project last-run timestamps.
• Run filters now support total, prompt, and completion token counts and costs consistently across routed query backends.
• Token Count / Cost filters now default to total tokens / cost instead of input tokens.
• On a tracing project, resetting a view now moves the Threads/Traces/Runs switcher back in step with the rows being shown.

Feedback

• The annotation queue item endpoints are now documented at their served path under /api/v1/platform.
• PDFs and other documents attached to a message now render in a full-width preview frame.

Prompts and playground

• When a model provider rejects a playground run, the playground now shows the provider's own error message.
• Playground batch and invoke endpoints now sanitize buffered run trees into JSON-safe payloads before responding.

Automations

• Forking an evaluator attaches the copy to the project or dataset named in the fork dialog.

Deployment

• The Create New Deployment form now shows a clear, per-field message when a submitted value fails validation.
• Deleting a tracing project whose LangGraph deployment is still within its post-deletion retention window now schedules the project to be removed along with the deployment.
• The delete confirmation for a LangGraph deployment now says that cleanup of the underlying database runs after you confirm.

Sandboxes

• Sandboxes accept a new streaming execute request that returns stdout and stderr as Server-Sent Events.
• Sandboxes now ship with the langsmith CLI on PATH.
• Sandbox and snapshot rows now use single-column layouts with actions in context menus.
• Engine sandbox commands in self-hosted deployments now authenticate over WebSocket with the deployment service key.
• The langsmith CLI in sandboxes is updated to v0.2.44.

Administration

• The LangSmith home page now provides quick access to copy the current organization and workspace IDs.
• On self-hosted installations authenticating with OAuth/SSO, the Remote MCP authorization endpoint now works correctly.
• Self-hosted deployments with an online license key now see the monthly organization usage graph automatically.
• Switching workspaces or organizations keeps you on the same page when the route has no workspace-specific resource IDs.
• LangSmith now refreshes expired browser sessions and retries interrupted API requests before asking you to log in again.

LLM Gateway

• Gateway policies with a blank or whitespace-only name now fall back to showing the policy ID.
• The Gateway usage spend chart now shows the top 12 individual spenders per bucket.
• The home page onboarding flow now includes a step for choosing how your agent reaches a model: bring your own provider API key, or use Gateway Credits.
• The custom X-Gateway-* header condition on LLM Gateway spend-cap and rate-limit policies now works with organization-, workspace-, and user-scoped policies.
• Default spend cap and rate limit policies in LLM Gateway now expand to show the per-user, per-workspace, and per-API-key policies materialized underneath them.
• The Gateway Credits purchase dialog now shows the credit balance your purchase will land you on.
• Enterprise organizations without Data Protection now see the tab in the LLM Gateway, greyed out with a link to request access.
• The connect card now appears above the Gateway Credits balance on the LLM Gateway Home page.
• Generating an API key from the LLM Gateway Home connect card now shows the standard one-time key reveal dialog.
• The "Purchase Credits" button on LLM Gateway Home now opens the credit purchase dialog.
• The Cost Controls and Model Fallbacks shortcuts on LLM Gateway Home now read "View cost controls"/"View model fallbacks" for members who can't manage the org.
• Gateway Home code samples now use the gateway hostname constructed for each LangSmith region and default to the Responses API where supported.
• LLM Gateway policy tabs now clarify that policies apply across the organization.
• The home onboarding step now states your Gateway Credits balance in US dollars.
• The prompt you copy into your coding agent during onboarding now states how the agent should reach a model.
• Homepage spacing and surface tinting now match design review feedback.
• LLM Gateway Home again includes Google Gemini and generates valid model identifiers for Gemini and Baseten connect samples.
• LLM Gateway Home now highlights the selected model and lets you switch connect samples between Chat Completions, Messages, and Responses formats.
• The LLM Gateway Usage tab now explains when usage queries aren't available for a deployment.
• When you select Gateway Credits during onboarding, the prompt copied into your coding agent now includes the correct Gateway URL for your deployment.
• Gateway Credits checkout now remains on the active purchase step while a free workspace upgrades to the Developer plan.
• Requests that set prompt_cache_options now enable Anthropic prompt caching when the LLM Gateway translates an OpenAI Chat Completions or Responses request to a Claude model.
• Tooltips on disabled LLM Gateway policy controls now read "You need organization admin access to create policies".
• The Gateway Usage tab no longer shows an in-page workspace dropdown.