> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1783460346-e74075c.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LangSmith Cloud changelog

> Weekly updates to LangSmith Cloud

Weekly updates to [LangSmith Cloud](/langsmith/observability) and [LangSmith Fleet](/langsmith/fleet).

<Callout icon="rss" color="#4F46E5" iconType="regular">
  **Subscribe**: This changelog includes an [RSS feed](https://docs.langchain.com/langsmith/product-changelog/rss.xml) that can integrate with [Slack](https://slack.com/help/articles/218688467-Add-RSS-feeds-to-Slack), [email](https://zapier.com/apps/email/integrations/rss/1441/send-new-rss-feed-entries-via-email), Discord bots like [Readybot](https://readybot.io/) or [RSS Feeds to Discord Bot](https://rss.app/en/bots/rssfeeds-discord-bot), and other subscription tools.
</Callout>

<Info>
  If you use self-hosted LangSmith, see the [self-hosted changelog](/langsmith/self-hosted-changelog) for updates.
</Info>

<Tabs>
  <Tab title="LangSmith Cloud">
    <Update label="June 20-28, 2026" rss={{ title: "2026-06-20 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * Adding feedback or reviewer notes from the UI no longer upgrades short-lived traces to extended retention.

      ## Sandboxes

      * [Sandbox registries](/langsmith/sandbox-snapshots#private-registries) now support pulling private container images alongside existing sandbox and snapshot operations.

      ## Admin and billing

      ## Fixes

      * Duplicate run create or update payloads now return clearer 409 Conflict messages that indicate whether the duplicate was a create or an update request when possible.
    </Update>

    <Update label="June 15-19, 2026" rss={{ title: "2026-06-15 - Cloud update" }}>
      ## Observability and evaluations

      ### Automations

      * [Automations](/langsmith/rules) now let you control trace retention per action, so traces matched by a rule can stay at base retention instead of being upgraded.

      ### Engine

      * The [Engine](/langsmith/engine) issue board now shows a Connect GitHub action when GitHub is not connected, so you can set up pull request creation without leaving the board.
      * [Engine](/langsmith/engine) now has a unified enablement screen with access requests, and organization settings consolidate Engine usage and limits in one place.
      * Organization admins now receive [Engine](/langsmith/engine) spend emails when spend crosses each configured threshold, and pausing or disabling Engine now asks for confirmation.

      ### Datasets and experiments

      * [Experiments](/langsmith/analyze-an-experiment) now show live loading progress in the header and the Progress column, so you can track completed and evaluated runs in real time.
      * [Evaluators](/langsmith/evaluators) now include a trace-retention toggle in the advanced options, so scored traces can stay at base retention when that fits your workflow.
      * [Evaluator](/langsmith/evaluators) prompt editing now offers an advanced mode for editing Mustache templates directly with separate variable mappings.
      * You can now apply resource tags when creating a [dataset](/langsmith/manage-datasets), including from scratch, file upload, or a clone.
      * Auto-attached Assertions [evaluators](/langsmith/evaluators) now read assertions from the reference output, so experiment scores reflect actual pass and fail results.

      ### Prompts and playground

      * [OAuth client credentials](/langsmith/model-configurations#oauth-client-credentials) now support per-workspace setup on model configurations, so workspace admins can self-serve OAuth on saved prompts and models.
      * The [Playground](/langsmith/playground-model-providers) now exposes a Reasoning Summary option for OpenAI reasoning models on the Responses API.
      * The model dropdown no longer suggests OpenAI models for an OpenAI Compatible Endpoint, so you can enter your own [custom model name](/langsmith/model-configurations).

      ### Tracing

      * [Trace query syntax](/langsmith/trace-query-syntax) now has a full operator reference, field table, and quick examples, so API filtering is easier to discover.
      * The [OpenTelemetry guide](/langsmith/trace-with-opentelemetry) now explains how to link spans to an existing LangSmith SDK trace and what happens when a parent span never arrives, so cross-process traces are easier to debug.

      ### Monitoring and alerting

      * [Dashboards](/langsmith/dashboards) now include a chart builder with chart templates, a create and edit pane, and brush and series controls on time series charts.
      * You can now send [alerts](/langsmith/alerts) to Slack as a native notification target and connect or disconnect the Slack app from the UI.

      ## Deployment

      * Preview [deployments](/langsmith/deployment) now build the image for the preview commit instead of reusing the parent deployment's image.

      ## Sandboxes

      * [Sandbox auth proxy](/langsmith/sandbox-auth-proxy) now documents GCP rules and service-account handling, so Google API access through the proxy is clearer.
      * [Sandboxes](/langsmith/sandboxes) now marks AWS US SaaS availability as generally available, so the region table reflects the current rollout.
      * [Sandboxes](/langsmith/sandboxes) now support Git mounts and Google Cloud Storage bucket mounts.

      ## Admin and billing

      ### Administration

      * [Organization settings](/langsmith/administration-overview) now clarify that SSO/SCIM group names can omit spaces, so enterprise IdPs that disallow spaces still work cleanly.
      * The Vanta MCP integration is now generally available to all workspaces.
      * Applying tags when creating datasets, prompts, and projects is now governed by dedicated [tag-on-create permissions](/langsmith/administration-overview).

      ### LLM Gateway

      * The [LLM gateway](/langsmith/llm-gateway) now supports native Gemini routes for Vertex AI and the OpenAI embeddings endpoint.
      * [Gateway guard](/langsmith/llm-gateway) policies now accept a granular PII configuration and a configurable timeout action.

      ### Usage and billing

      * [Granular billable usage](/langsmith/granular-usage) now clarifies org scoping, so you can interpret usage totals more accurately.
    </Update>

    <Update label="June 8-12, 2026" rss={{ title: "2026-06-08 - Cloud update" }}>
      ## Observability and evaluations

      ### Engine

      * [Engine](/langsmith/engine) now shows only project-level spend in project view, so org-wide spend stays in the org settings surface.
      * [Engine](/langsmith/engine) now keeps the Slack issue-alert deck pinned above the scrolling issues list, so the callout stays visible as you browse.

      ### Datasets and experiments

      The experiments table now displays loading progress bars showing the number of runs completed and evaluated, and experiments that predate this feature show a placeholder progress bar.

      * [Dashboards](/langsmith/dashboards) now support time series bar and line charts backed by the v2 chart API, so monitored metrics can use the newer chart type.
      * Categorical feedback now shows derived percentages in experiment tables, so pass/fail metrics are easier to scan.

      ### Prompts and playground

      * [Playground](/langsmith/playground-model-providers) now mints OAuth bearers end to end for OAuth-enabled presets, so long-running batches and streams keep working.

      ## Sandboxes

      * [Sandbox auth proxy](/langsmith/sandbox-auth-proxy) now supports GCP auth flows, so sandbox workloads can reach Google APIs through the proxy.

      ## Fixes

      * The Engine trial modal no longer shows the rough-math LCU bullet, so the pricing copy is less misleading.
    </Update>

    <Update label="June 1-5, 2026" rss={{ title: "2026-06-01 - LangSmith Cloud update" }}>
      ## Observability and evaluations

      ### Automations

      * [Run rule](/langsmith/rules) webhook payloads now include a trace deep link for each run, so downstream systems can jump straight back to the trace.

      ### Engine

      * Per-workspace [Engine](/langsmith/engine) spend is now generally available: you can view LCU and USD spend directly on the Engine settings page, including session-level spend.
      * The Engine settings page now surfaces additional Engine details in one place.
      * You can rotate [Engine issue-board webhook](/langsmith/engine-webhooks) signing secrets from both the API and the webhook settings UI.
      * The Engine issues list adds a sort option by trace count.

      ### Datasets and experiments

      * A new out-of-the-box [Assertions evaluator](/langsmith/assertions) scores outputs against an explicit list of criteria specified in the reference output, and an Assertions rule is auto-attached when you add assertion-style examples to a dataset.
      * Evaluator metrics are improved in the experiment detail, [comparison](/langsmith/compare-experiment-results), and global experiments tables.

      ### Prompts and playground

      * The [Playground](/langsmith/playground-model-providers) supports Amazon Bedrock API key authentication, letting you authenticate with a bearer token instead of AWS credentials.

      ### Tracing

      * The [trace view](/langsmith/view-traces) now shows an unread indicator on a run's actions menu when the run has reviewer notes you have not seen yet.
      * The waterfall view is now full-height with sticky turn headers, so you keep your place while scrolling through long traces.
      * Global search now includes context and sandboxes

      ## Deployment

      * You can now trigger a LangSmith Deployment from the [Studio](/langsmith/studio) page.
      * LangSmith Deployment now supports [deploying Google Agent Development Kit (ADK) agents](/langsmith/deploy-google-adk).

      ## Sandboxes

      * [Sandbox proxy rules](/langsmith/sandbox-auth-proxy) now support configuring AWS authentication, so sandboxes can reach AWS services through the proxy with signed requests.
      * Sandboxes can create [snapshots](/langsmith/sandbox-snapshots) from a Dockerfile build source.

      ## Admin and billing

      ### Administration

      * Organization admins can now disable personal access token creation from the [organization settings](/langsmith/administration-overview) page.

      ### Usage and billing

      * [Granular billable usage](/langsmith/granular-usage) now supports filtering and grouping by retention tier, separating long-lived from short-lived traces.
      * The Granular Billable Usage page now surfaces LangSmith Deployment usage, including nodes executed, agent runs, and agent uptime, alongside trace usage.

      ## Fixes

      * Performance improvements for the loading of large traces.
      * Filter values for metadata are now preserved when you reopen a filter dropdown to edit it.
      * Dataset creation now uses a multi-select dropdown for choosing CSV fields.
    </Update>

    <Update label="February 16-20, 2026" rss={{ title: "2026-02-16 - Cloud update" }}>
      ## Observability and evaluations

      ### Insights

      * The [Insights Agent](/langsmith/insights) now supports scheduled reports on daily, weekly, or custom cron intervals, so report generation runs without manual triggering. Time ranges compute dynamically, so a "last 24 hours" report always reflects the most recent window when it runs, not when you configured it.

      ### Datasets and experiments

      * You can now pin any experiment as a baseline. The pinned experiment stays at the top of the [Experiments](/langsmith/compare-experiment-results) view and serves as the automatic comparison point for later runs, surfacing performance deltas across every column so improvements and regressions are immediately clear.
    </Update>

    <Update label="February 2-6, 2026" rss={{ title: "2026-02-02 - Cloud update" }}>
      ## Observability and evaluations

      ### Cost tracking

      * [Cost tracking](/langsmith/cost-tracking) now extends beyond LLM calls. Submit custom cost metadata for any run, such as an expensive tool call, a third-party API, or a retrieval step, to monitor, debug, and optimize spend across your entire agent stack from a single dashboard.

      ### Tracing

      * You can now [configure which parts of a trace's inputs and outputs](/langsmith/configure-input-output-preview) appear in the tracing table, so teams working with custom trace formats can surface the most relevant fields, reduce clutter, and identify traces that need a closer look faster.
    </Update>

    <Update label="December 15-19, 2025" rss={{ title: "2025-12-15 - Cloud update" }}>
      ## Observability and evaluations

      ### Annotation and human feedback

      * New pairwise [annotation queues](/langsmith/annotation-queues) let reviewers compare two runs side by side and choose whether option A is better, option B is better, or the two are equal across rubric items. LangSmith automatically pairs runs between two experiments and manages queues, reviewer assignments, and trace access, so you can run A/B evaluations across agents, prompts, and models, including for subjective dimensions like tone, correctness, usefulness, or style.
    </Update>

    <Update label="December 8-12, 2025" rss={{ title: "2025-12-08 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * LangSmith Fetch, a new command-line tool, brings LangSmith traces directly into your terminal, coding environment, or IDE. Install it with `pip install langsmith-fetch`, then retrieve traces with filters such as `--limit`, `--after`, and `--last-n-minutes`, or bulk-export traces and threads to files for analysis, scripting, or dataset creation.
    </Update>

    <Update label="December 1-5, 2025" rss={{ title: "2025-12-01 - Cloud update" }}>
      ## Observability and evaluations

      ### Cost tracking

      * [Cost tracking](/langsmith/cost-tracking) now automatically records token usage and derived costs for major model providers, and you can submit custom cost data for tools, retrieval steps, and other operations. Costs appear across trace trees, project stats, and dashboards, with an editable price map for non-standard pricing.
    </Update>

    <Update label="November 17-21, 2025" rss={{ title: "2025-11-17 - Cloud update" }}>
      ## Admin and billing

      ### Administration

      * LangSmith is now on the Okta Integration Network, so enterprise teams can provision and deprovision users with SCIM and configure SSO through Okta's guided setup. See the [administration overview](/langsmith/administration-overview) for access control options.
    </Update>

    <Update label="October 20-24, 2025" rss={{ title: "2025-10-20 - Cloud update" }}>
      ## Observability and evaluations

      ### Insights

      * The [Insights Agent](/langsmith/insights) is now generally available for Plus and Enterprise plans. It analyzes production traces to surface usage patterns, agent behaviors, and failure modes, with usage-pattern clustering, poor-interaction analysis, and custom grouping and filtering.

      ### Datasets and experiments

      * [Multi-turn evals](/langsmith/online-evaluations-multi-turn) measure end-to-end agent conversations across multiple exchanges, scoring semantic intent, semantic outcomes, and agent trajectory, including tool calls and decisions.
    </Update>

    <Update label="October 13-17, 2025" rss={{ title: "2025-10-13 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * [Dataset creation](/langsmith/manage-datasets) now infers schema automatically from uploaded CSV and JSONL files, supports adding metadata fields during upload, supports column mapping and renaming, and supports bulk additions to existing datasets from new uploads.

      ## Deployment

      * LangGraph Platform is now [LangSmith Deployment](/langsmith/deployment) and LangGraph Studio is now [LangSmith Studio](/langsmith/studio). LangSmith now spans three services: Observability, Evaluation, and Deployment. Existing deployments, APIs, workflows, pricing, and contracts are unchanged, and no action is required.
    </Update>

    <Update label="October 6-10, 2025" rss={{ title: "2025-10-06 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * You can now write custom code [evaluators](/langsmith/evaluators) in JavaScript in addition to Python, so TypeScript teams can stay in their ecosystem end to end.
    </Update>

    <Update label="September 22-26, 2025" rss={{ title: "2025-09-22 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * [Composite evaluators](/langsmith/online-evaluations-composite) combine multiple evaluator scores into a single metric using a weighted average or weighted sum, with customizable weights.
    </Update>

    <Update label="September 8-12, 2025" rss={{ title: "2025-09-08 - Cloud update" }}>
      ## Admin and billing

      ### Administration

      * You can now create service keys at the [organization level](/langsmith/administration-overview), scoped to multiple workspaces or the entire organization, and assign roles, including custom roles, for granular permissions.
    </Update>

    <Update label="August 25-29, 2025" rss={{ title: "2025-08-25 - Cloud update" }}>
      ## Deployment

      * [LangSmith Deployment](/langsmith/deployment) now queues revisions automatically, processing each new revision only after the current one finishes to prevent overlapping deployments and conflicts.
    </Update>

    <Update label="August 11-15, 2025" rss={{ title: "2025-08-11 - Cloud update" }}>
      ## Deployment

      * [Studio](/langsmith/studio) now includes Trace Mode, which shows your LangSmith traces directly in Studio and supports annotating runs and adding them to datasets for evaluation.
    </Update>

    <Update label="July 28 - August 1, 2025" rss={{ title: "2025-07-28 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * Align Evals provides a playground-like interface for iterating on [evaluator](/langsmith/evaluators) prompts and comparing human-graded scores side by side with LLM-generated scores to surface misaligned cases.

      ## Deployment

      * LangSmith now links traces to the server logs in [LangSmith Deployment](/langsmith/deployment), so you can open user and system logs directly from a trace.
    </Update>

    <Update label="July 21-25, 2025" rss={{ title: "2025-07-21 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * [Data export](/langsmith/data-export) now supports scheduled exports of traces, so external systems such as data warehouses, monitoring platforms, and dashboards stay in sync without custom infrastructure.
    </Update>

    <Update label="July 7-11, 2025" rss={{ title: "2025-07-07 - Cloud update" }}>
      ## Deployment

      * A new Monitoring tab shows [deployment](/langsmith/deployment) metrics, including CPU and memory usage, API request latency, and active run counts, over a customizable time range.
    </Update>

    <Update label="June 30 - July 4, 2025" rss={{ title: "2025-06-30 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * You can now create custom views of [evaluation results](/langsmith/analyze-an-experiment) by breaking fields from inputs, outputs, and reference outputs into their own columns, hiding or reordering columns, and adjusting decimal precision on feedback scores.

      ## Admin and billing

      ### Administration

      * LangSmith [API keys](/langsmith/administration-overview) now support expiration dates, so you can scope access for temporary tasks or team members.
    </Update>

    <Update label="June 16-20, 2025" rss={{ title: "2025-06-16 - Cloud update" }}>
      ## Observability and evaluations

      ### Prompts and playground

      * The [Playground](/langsmith/playground-model-providers) now supports calling built-in tools from OpenAI and Anthropic, such as web search and MCP, so you can verify tool selection and argument passing.

      ## Deployment

      * [Studio](/langsmith/studio) now lets you run agent evaluations in the UI without code, comparing against reference outputs and grading responses with custom criteria.
    </Update>

    <Update label="June 2-6, 2025" rss={{ title: "2025-06-02 - Cloud update" }}>
      ## Observability and evaluations

      ### Cost tracking

      * [Cost tracking](/langsmith/cost-tracking) now accounts for cached tokens, multiple token modalities such as text and image, and reasoning tokens, and supports tracking costs for arbitrary token types.
    </Update>

    <Update label="May 26-30, 2025" rss={{ title: "2025-05-26 - Cloud update" }}>
      ## Observability and evaluations

      ### Prompts and playground

      * [Prompts](/langsmith/prompt-engineering) now support webhook triggers that sync a prompt to external systems such as GitHub, databases, or CI/CD pipelines when it is updated.
    </Update>

    <Update label="May 19-23, 2025" rss={{ title: "2025-05-19 - Cloud update" }}>
      ## Deployment

      * Every agent deployed on [LangSmith](/langsmith/deployment) now exposes its own Model Context Protocol (MCP) endpoint, so the agent can be used as a tool in any client that supports streamable HTTP for MCP, with no custom code or infrastructure.

      ## Admin and billing

      ### Usage and billing

      * SaaS customers can now view monthly [usage charts](/langsmith/granular-usage) that track all billable metrics in one place.
    </Update>

    <Update label="May 12-16, 2025" rss={{ title: "2025-05-12 - Cloud update" }}>
      ## Observability and evaluations

      ### Monitoring and alerting

      * [Agent observability](/langsmith/observability) surfaces tool calls and run stats, including the most-used tools and runs, their latency, and which generate the most errors.

      ## Deployment

      * LangGraph Platform, now [LangSmith Deployment](/langsmith/deployment), reached general availability for deploying and managing long-running, stateful agents at scale, with one-click GitHub-to-production deployment, integrated memory and persistence, scalable APIs, and an agent registry across cloud, hybrid, self-hosted, and developer deployment options.
      * [Studio](/langsmith/studio) v2 runs locally without the desktop app, supports editing prompts and configuration in the UI, integrates with the Playground, and lets you download production traces to debug them locally.
    </Update>

    <Update label="May 5-9, 2025" rss={{ title: "2025-05-05 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * LangSmith now supports [multimodal content](/langsmith/log-multimodal-traces) for images, PDFs, and audio across the playground, annotation queues, and datasets, including attaching files to dataset examples without base64 encoding and visualizing the content in the app.
    </Update>

    <Update label="April 21-25, 2025" rss={{ title: "2025-04-21 - Cloud update" }}>
      ## Observability and evaluations

      ### Monitoring and alerting

      * [Alerts](/langsmith/alerts) send real-time notifications on error rates, run latency, and feedback scores, so you can catch production failures proactively.
    </Update>

    <Update label="March 31 - April 4, 2025" rss={{ title: "2025-03-31 - Cloud update" }}>
      ## Observability and evaluations

      ### Prompts and playground

      * The [Playground](/langsmith/playground-model-providers) now lets you create datasets inline and add examples to existing datasets without leaving the Playground.
    </Update>

    <Update label="March 24-28, 2025" rss={{ title: "2025-03-24 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * LangSmith now has end-to-end native [OpenTelemetry support](/langsmith/trace-with-opentelemetry) for LangChain and LangGraph applications, including distributed tracing across microservices.

      ### Datasets and experiments

      * You can now define [evaluators](/langsmith/evaluators) for datasets and tracing projects directly in the UI with no code, including LLM-as-a-judge evaluators with prebuilt templates, customizable prompts, variable mapping, scoring, and few-shot support.
    </Update>

    <Update label="March 17-21, 2025" rss={{ title: "2025-03-17 - Cloud update" }}>
      ## Deployment

      * [Studio](/langsmith/studio) now lets you view and edit node logic in the UI by tagging configuration fields with `langgraph_nodes`, edit prompts without code changes, and sync Playground experiments back to the graph.
    </Update>

    <Update label="March 10-14, 2025" rss={{ title: "2025-03-10 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * LangSmith now supports tracing [OpenAI Agents SDK](/langsmith/trace-with-openai-agents-sdk) applications with two lines of code, for step-by-step observability of agent execution and reasoning.

      ### Datasets and experiments

      * You can now rename an [experiment](/langsmith/analyze-an-experiment) in the UI, either from the Playground table header after a run or with the pencil icon in the Experiments view.
    </Update>

    <Update label="February 24-28, 2025" rss={{ title: "2025-02-24 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * You can now group [experiment results](/langsmith/analyze-an-experiment) by metadata to analyze evaluation performance across segments such as user groups or subject areas.

      ## Fixes

      * A new ingest-backend service separates trace ingestion from frontend request handling, improving average request processing and high-traffic response times.
    </Update>

    <Update label="February 17-21, 2025" rss={{ title: "2025-02-17 - Cloud update" }}>
      ## Observability and evaluations

      ### Prompts and playground

      * The [Playground](/langsmith/playground-model-providers) can now use workspace secrets saved in LangSmith, for consistent credential management across environments.
    </Update>

    <Update label="February 3-7, 2025" rss={{ title: "2025-02-03 - Cloud update" }}>
      ## Observability and evaluations

      ### Datasets and experiments

      * A new [experiment view](/langsmith/analyze-an-experiment) gives each feedback key its own column and adds filtering, sorting, and a heat map to spot patterns and performance areas.

      ## Deployment

      * You can now open LLM runs from [Studio](/langsmith/studio) in the LangSmith Playground for debugging, visualization, and prompt experimentation within threads.
    </Update>

    <Update label="January 27-31, 2025" rss={{ title: "2025-01-27 - Cloud update" }}>
      ## Observability and evaluations

      ### Tracing

      * [Traces](/langsmith/view-traces) now include a waterfall graph that highlights latency bottlenecks and shows which components run in parallel versus sequentially.
    </Update>

    <Update label="January 20-24, 2025" rss={{ title: "2025-01-20 - Cloud update" }}>
      ## Observability and evaluations

      ### Prompts and playground

      * The [Playground](/langsmith/playground-model-providers) adds a streamlined prompt settings UI, a default model configuration, an enhanced tool management modal, and improved side-by-side comparison.

      ### Datasets and experiments

      * New [Pytest and Vitest integrations](/langsmith/pytest) let you run evaluations using familiar testing frameworks, with debugging, metrics tracking, and built-in evaluation functions.
    </Update>
  </Tab>

  <Tab title="LangSmith Fleet">
    <Update label="June 20-28, 2026" rss={{ title: "2026-06-20 - Fleet product update" }}>
      ## New features

      * Fleet chat now lets you create an [access profile](/langsmith/fleet/computer-use) directly from the dialog, so you can open the sandboxes create flow when a workspace has none configured.
      * Fleet now completes OAuth for [MCP servers](/langsmith/fleet/remote-mcp-servers) whose authorization server requires client-secret authentication at the token endpoint, so the consent flow finishes cleanly.
    </Update>

    <Update label="June 15-19, 2026" rss={{ title: "2026-06-15 - Fleet product update" }}>
      ## New features

      * [Fleet tools](/langsmith/fleet/tools) now include Salesforce OAuth provider setup for self-hosted users, so you can configure the provider end to end.
      * Agent sharing is redesigned around two choices, who can use and who can edit an agent, plus a Publish as template option that lets others fork their own editable copy.
      * Fleet agents now post a notification to the originating thread, such as Slack, when they pause at a human-in-the-loop interrupt, with a link back to the agent chat.
      * You can now complete Fleet integration OAuth through your own callback URL, so headless setups can finish authentication without the LangSmith UI.
      * Agent cards now show the agent owner.
      * New first-party [templates](/langsmith/fleet/templates), Brand Copywriter and Applicant Screening, are available in the gallery.

      ## Fixes

      * Switching threads in the agent chat now clears the previous thread immediately and shows a loading state instead of stale messages.
      * The [skills](/langsmith/fleet/skills) list now degrades gracefully when one skill fails to load, so the remaining skills still appear.
    </Update>

    <Update label="June 8-12, 2026" rss={{ title: "2026-06-08 - Fleet product update" }}>
      ## New features

      * [Templates](/langsmith/fleet/templates) now show “by Fleet” with the Fleet logo, so curated templates match Fleet branding.

      ## Fixes

      * The Fleet list-threads endpoint now returns `items` instead of `threads`, so the response shape matches the rest of the API.
      * Fleet thread requests now return a clearer error when a large response would have triggered a 5xx, so long lists fail gracefully.
    </Update>

    <Update label="June 1-5, 2026" rss={{ title: "2026-06-01 - LangSmith Fleet update" }}>
      ## New features

      * [Skills](/langsmith/fleet/skills) load faster: the skills list fetches lightweight metadata first and loads file contents only when you open a skill.
      * The agent creation menu adds a [Templates](/langsmith/fleet/templates) entry.
      * The [remote MCP](/langsmith/fleet/remote-mcp-servers) authorization screen now shows the connecting application's name, logo, and homepage, terms, and privacy links instead of its raw client ID.
      * [Slack integration](/langsmith/fleet/slack-app) available in AWS and APAC regions.

      ## Fixes

      * [Scheduled (cron) execution](/langsmith/fleet/schedules) is restored for enterprise Fleet agents.
      * Long-running agent runs and agent-builder generations are no longer cut off after 60 seconds.
      * The Gmail read-emails [tool](/langsmith/fleet/tools) now returns results when you search sent mail with an `in:sent` query.
      * Scrolling is improved for long toolbox, skill, and sub-agent lists in the agent editor, and webhook dialogs now scroll within the viewport.
    </Update>

    <Update label="March 16-20, 2026" rss={{ title: "2026-03-16 - Fleet product update" }}>
      ## New features

      * Agent Builder is now [LangSmith Fleet](/langsmith/fleet). The new name reflects Fleet's focus on building and managing agents for your whole team: creating them, sharing them, managing their tasks, and controlling agent access and identity. All existing agents, configurations, integrations, plans, and contracts continue to work unchanged, with no action required on your end.
    </Update>

    <Update label="February 16-20, 2026" rss={{ title: "2026-02-16 - Fleet product update" }}>
      ## New features

      * A central Chat agent connects to all of your workspace [tools](/langsmith/fleet/tools), including Slack, Gmail, Linear, and MCP servers, so you can ask questions and take actions without setting up a dedicated agent first.
      * Turn a useful conversation into a recurring agent with one click, with no prompt engineering or conditional logic required.
      * Upload files directly into chat, including CSVs, images, documents, and style guides, for the agent to act on immediately.
      * A central tool registry lets workspace admins connect [tools](/langsmith/fleet/tools), manage authentication, and control access across the organization.
    </Update>

    <Update label="October 27-31, 2025" rss={{ title: "2025-10-27 - Fleet product update" }}>
      ## New features

      * LangSmith Agent Builder launched in private preview as a no-code way for non-developers to build agents, with conversational setup, built-in memory, MCP integrations, automated triggers, and subagent support. Agent Builder later became [LangSmith Fleet](/langsmith/fleet).
    </Update>
  </Tab>
</Tabs>

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/changelog.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>