LangSmith Fleet changelog

​

Fleet

• Fleet agents can use a built-in configuration-hardening skill to selectively separate trust boundaries, minimize tools, require approval for sensitive actions, and review access.
• Open chat files in an edge-to-edge workspace, then collapse them back to the Files side panel without losing your place.
• Self-hosted Fleet agents can use sandbox-backed computer access without requiring a cloud billing plan tier.
• Files attached to Slack messages are now available under /workspace/uploads for sandbox-backed agents, matching files uploaded from Fleet.
• Clicking + New Agent from Workspace Agents now opens the same New agent dialog used elsewhere in Fleet, instead of the old draft editor.
• Navigating to agent chat with an agent selected no longer crashes while the agent details are still loading. The chat shows a loading state until the agent is ready, then renders normally.
• Sandbox-backed Fleet agents can create or revise downloadable DOCX files without installing an authoring package during the task. A built-in skill guides document authoring and structural validation.
• The Configure panel is now enabled for everyone, so it always shows up beside the chat when you open an agent.
• Fleet now resolves AWS IAM roles only for Bedrock models, so loading OpenAI and other provider secrets no longer waits on AWS STS.
• The new agent creation experience is now enabled for everyone. Asking the assistant for an agent surfaces the Create agent button, and the new agent runs its own setup conversation instead of being built inline.
• A conversation whose stored state grew past the API’s usual single-response size limit now loads in full, up to 32 MiB, instead of failing. The response marks the conversation as oversized, and updates to it still fail until its state shrinks.
• Sandbox-backed Fleet agents can build a new deck, revise an existing one, and answer questions about the contents of a .pptx file without installing presentation tooling first. A built-in skill guides authoring and validates the file before delivery.
• Fleet agents can send workspace files to Slack channels, threads, and direct messages using slack_send_file and slack_send_file_to_user.
• Fleet agents now correctly route sandbox creation and org config requests to the Go platform-backend service on self-hosted deployments where the Go and Python services run on separate addresses, eliminating the need for a reverse-proxy workaround.

​

Fleet

• Reopening or reloading an agent chat thread while a run is still in progress no longer crashes the chat view. The chat shows a loading state until the agent is ready, then resumes streaming the active run.
• The Fleet usage dashboard now shows a meter for orgs with a monthly LangChain Unit (LCU) spend limit, comparing month-to-date consumption against the limit and any overage.
• Arcade MCP gateways configured with Arcade Headers (API-key) authentication can no longer be added to a Fleet workspace, because LangSmith connects to Arcade gateways over OAuth. These gateways now explain how to reconfigure them with Arcade Auth or a User Source instead of failing when you try to connect.
• Fleet now labels the agent card action as Configure, matching the action in the chat view.
• When a Google Docs, Sheets, Drive, or Slides tool can’t open a file (a 403 or 404), the agent now explains it can only access files it created itself with its connected Google account, instead of wrongly saying the file doesn’t exist.
• Fleet now shows a warning (inline above the failing tool call in chat, and as a message in Slack) when a Google Docs, Sheets, Drive, or Slides tool hits a 403 or 404, explaining the agent can only access files it created itself with its connected Google account.
• Fleet’s configure panel now shows the connection format selector so you can choose whether an agent uses shared or per-user accounts.
• Agents connected to Slack can now send a file from their workspace into a Slack channel using the new slack_send_file tool, for example a report, export, or chart the agent has generated. The file is uploaded server-side and the agent never sees the Slack token.
• Fleet agents retain DeltaChannel conversation history when thread state is updated, including when users continue trigger-started conversations in chat.
• Fleet thread APIs can now include the current agent’s ID and name, making thread lists and details easier to display without fetching full agent records.
• Fleet agents with Slack file tools can now send files from thread-scoped and agent-scoped sandbox workspaces.

​

Fleet

• In the Agent Builder view, the footer workspace and tenant list is sourced from the Fleet API so you can switch between your Fleet workspaces.
• The Access Profiles dialog in chat now includes a Create an access profile link that opens the sandboxes create flow, so you can add a profile when a workspace has none configured instead of hitting a dead end.
• Fleet agents can now delete files from their memory and skills using the new delete tool, including files in linked workspace skills. Core agent files and read-only system skills remain protected.
• Fleet now completes OAuth for MCP servers whose authorization server requires client-secret authentication at the token endpoint, so connecting these servers no longer fails after the consent step.
• First-time Fleet users now see a streamlined welcome modal with two clear paths (describe an agent to build with AI, starting from a prompt in Chat, or start from a curated template), replacing the previous multi-step setup wizard.
• Creating an agent from a Fleet template now skips the setup wizard and opens the agent editor with the template onboarding card.
• Fleet now sends the MCP protocol version a server negotiates during the handshake, both when loading tools and when the agent calls them, so MCP servers that require a newer version no longer return zero tools or fail tool calls.
• Fleet agents receive the day of week alongside the current date (for example “Monday, June 29th 2026”), so scheduling and date reasoning no longer relies on the model inferring the weekday from the ISO date.
• File edits in Fleet agent chat now render as syntax-highlighted, line-by-line diffs, making changes easier to review.
• Fleet agents can now read files shared with them in Slack. Attach an image, PDF, audio, video, or text file in a mention or DM and the agent ingests it into the conversation.
• On the Agent Builder Integrations page, searching now selects the All tab so results span every category, and switching category tabs clears the search.
• When you connect a custom Slack bot to a Fleet agent, Fleet sends the installer a direct message with quick setup tips, including how to add the bot to channels and mention it with @.
• Fleet agents now have a Slack tool for listing channels the connected bot is a member of, making it easier to discover the right channel before posting or reading messages.
• Fleet OAuth provider and integration responses now include an owner field (workspace or platform) so you can tell your own resources apart from built-in, platform-managed ones. The platform manager organization can now create and modify built-in OAuth providers.
• Setting up a schedule is now clearer: choose a preset (daily, weekly, monthly, or every few minutes) or enter a custom cron expression, with a live human-readable preview and inline validation as you go.
• When registering an integration OAuth provider for headless connections, http:// redirect URIs are now accepted only for the loopback IP literals 127.0.0.1 or [::1]. The localhost hostname is no longer accepted over http; use the loopback IP literal or https.
• The MCP servers settings page now scrolls when the pointer is over the servers list.
• The load previous conversations tool now writes conversation files into the attached Computer sandbox when one is enabled, so agents can inspect the downloaded history with their normal file tools.
• When a Fleet agent’s subagent calls a tool that requires human approval, the approval prompt now appears in the chat instead of the run completing without it.
• The Executive Assistant template can now deliver its daily brief and answer @mentions in Slack after you connect a Slack workspace, and both the Executive Assistant and Software Engineer templates received configuration fixes.
• You can now type and send a message in agent chat while a human-in-the-loop prompt is pending. Sending a new message dismisses the pending request and continues the conversation instead of leaving the composer locked.
• Empty sections in the agent configuration panel (Channels, Connections, Skills, Schedules, Instructions, and Subagents) now explain what each one is for and what you can add before you connect anything.
• Creating a new agent no longer fails with a contentBlocks.push error when the chat stream returns string message content.
• Opening an agent in the chat inbox no longer issues repeated duplicate background requests while choosing which thread to open, reducing flicker.
• Fleet agents now load your workspace’s private skills. Previously, in workspaces with fine-grained access controls, an agent could start with only public skills available.
• Reloading an agent chat page no longer flashes the thread list through loading and loaded states multiple times. The sidebar now waits for agent scope to finish loading before fetching threads, so the list settles once.
• GitHub App installations now sync through the authenticated LangSmith session after installation completes, keeping workspace linking aligned with the active user.
• OAuth providers now accept an optional default redirect URI (default_redirect_uri). When set, headless OAuth flows for that provider return the authorization code to it instead of the LangSmith callback, without passing a redirect on every request. The value is validated against the provider’s allowed redirect URIs.
• Fleet agents now discover tools with find_tools or an /tools listing before opening a tool’s reference doc, so they no longer waste a turn reading guessed tool filenames that do not exist.
• The Fleet Fast model tier (gpt-5.4-mini) now runs at medium reasoning effort instead of low, improving response quality on harder tasks.
• The templates gallery now features the Executive Assistant and Software Engineer templates as large cards with a hero illustration, each showing the agent’s own icon.
• Each tool inside a connection in the agent Configure panel now has a remove action (a trash button revealed on hover, matching the connection remove) instead of an on/off switch. The switch implied a reversible toggle, but turning a tool off actually removed it from the agent, so the control now reflects what it does.
• Sending a chat message while clarifying questions were pending could fail the run and leave the thread stuck. Free-text now correctly dismisses the pending request before continuing.
• In the Agent Builder chat, the Skills block’s “Add skill” menu now opens the browse-workspace, create-skill, and import-from-URL dialogs. Previously choosing an option changed the URL but nothing appeared.
• Opening an agent in Fleet now always starts a new chat instead of jumping into a recent thread. Past conversations remain available in the thread sidebar.
• When an agent created from a template introduces itself, it writes what it learns straight to its own memory instead of pausing for approval on every file. Memory writes in your other threads still ask first.
• Skill descriptions containing quotes, colons, or multiple lines are now parsed and stored correctly, and importing or editing a skill preserves all of its frontmatter instead of dropping fields like license or allowed-tools.
• The Add connection dialog now groups Arcade MCP servers under a dedicated Arcade section, so they are easy to find instead of being listed under Other.
• The Fleet model picker now groups served, LCU-billed models (Fast, Pro, Max) separately from bring-your-own models billed per run, making the pricing model for each option clearer.
• The compact Fast/Pro/Max model picker in Agent Builder now shows the model icon on its closed trigger, matching the full model picker.
• When an organization reaches its monthly Fleet usage limit, the error now directs users to upgrade their plan to continue.

​

New features

• You can now add any agent to Slack in one click. After you authenticate with Slack once, Fleet automatically creates a Slack app configured with the agent’s name, description, and icon, and maps each agent to a single Slack app.
• When an agent is first added to a Slack workspace, it sends the creator a direct message with tips for inviting it to channels and mentioning it.
• Agents now raise tool approvals directly in Slack, with Approve and Deny buttons in the thread, so you no longer need to switch to the Fleet UI to respond.
• When an agent encounters an error during a run, it now replies in the Slack thread instead of going silent. Authentication errors and some other error types include more detail.
• Agents can now read file attachments in Slack messages.
• The agent editor is now a sidebar built into the agent chat page, which organizes configuration into Channels, Connections, Knowledge, Schedule, and Advanced settings drawers.
• The agent creation experience now starts from a blank-slate agent that configures itself and pauses at key points to bring you into the process.

​

Fleet

• In the Agent Builder view, the footer workspace and tenant list is sourced from the Fleet API so you can switch between your Fleet workspaces.
• The Access Profiles dialog in chat now includes a Create an access profile link that opens the sandboxes create flow, so you can add a profile when a workspace has none configured instead of hitting a dead end.
• Fleet agents can now delete files from their memory and skills using the new delete tool, including files in linked workspace skills. Core agent files and read-only system skills remain protected.
• Fleet now completes OAuth for MCP servers whose authorization server requires client-secret authentication at the token endpoint, so connecting these servers no longer fails after the consent step.
• First-time Fleet users now see a streamlined welcome modal with two clear paths (describe an agent to build with AI, starting from a prompt in Chat, or start from a curated template), replacing the previous multi-step setup wizard.
• Creating an agent from a Fleet template now skips the setup wizard and opens the agent editor with the template onboarding card.
• Fleet now sends the MCP protocol version a server negotiates during the handshake, both when loading tools and when the agent calls them, so MCP servers that require a newer version no longer return zero tools or fail tool calls.
• Fleet agents receive the day of week alongside the current date (for example “Monday, June 29th 2026”), so scheduling and date reasoning no longer relies on the model inferring the weekday from the ISO date.
• File edits in Fleet agent chat now render as syntax-highlighted, line-by-line diffs, making changes easier to review.
• Fleet agents can now read files shared with them in Slack. Attach an image, PDF, audio, video, or text file in a mention or DM and the agent ingests it into the conversation.
• On the Agent Builder Integrations page, searching now selects the All tab so results span every category, and switching category tabs clears the search.
• When you connect a custom Slack bot to a Fleet agent, Fleet sends the installer a direct message with quick setup tips, including how to add the bot to channels and mention it with @.
• Fleet agents now have a Slack tool for listing channels the connected bot is a member of, making it easier to discover the right channel before posting or reading messages.
• Fleet OAuth provider and integration responses now include an owner field (workspace or platform) so you can tell your own resources apart from built-in, platform-managed ones. The platform manager organization can now create and modify built-in OAuth providers.
• Setting up a schedule is now clearer: choose a preset (daily, weekly, monthly, or every few minutes) or enter a custom cron expression, with a live human-readable preview and inline validation as you go.
• When registering an integration OAuth provider for headless connections, http:// redirect URIs are now accepted only for the loopback IP literals 127.0.0.1 or [::1]. The localhost hostname is no longer accepted over http; use the loopback IP literal or https.
• The MCP servers settings page now scrolls when the pointer is over the servers list.
• When a Fleet agent’s subagent calls a tool that requires human approval, the approval prompt now appears in the chat instead of the run completing without it.
• The Executive Assistant template can now deliver its daily brief and answer @mentions in Slack after you connect a Slack workspace, and both the Executive Assistant and Software Engineer templates received configuration fixes.
• You can now type and send a message in agent chat while a human-in-the-loop prompt is pending. Sending a new message dismisses the pending request and continues the conversation instead of leaving the composer locked.
• Empty sections in the agent configuration panel (Channels, Connections, Skills, Schedules, Instructions, and Subagents) now explain what each one is for and what you can add before you connect anything.
• Opening an agent in the chat inbox no longer issues repeated duplicate background requests while choosing which thread to open, reducing flicker.
• Fleet agents now load your workspace’s private skills. Previously, in workspaces with fine-grained access controls, an agent could start with only public skills available.
• GitHub App installations now sync through the authenticated LangSmith session after installation completes, keeping workspace linking aligned with the active user.
• OAuth providers now accept an optional default redirect URI (default_redirect_uri). When set, headless OAuth flows for that provider return the authorization code to it instead of the LangSmith callback, without passing a redirect on every request. The value is validated against the provider’s allowed redirect URIs.

​

New features

• The Access Profiles dialog in chat now includes a Create an access profile link that opens the sandboxes create flow, so you can add a profile when a workspace has none configured instead of hitting a dead end.
• Fleet agents can now delete files from their memory and skills using the new delete tool, including files in linked workspace skills. Core agent files and read-only system skills remain protected.
• Fleet now completes OAuth for MCP servers whose authorization server requires client-secret authentication at the token endpoint, so connecting these servers no longer fails after the consent step.
• First-time Fleet users now see a streamlined welcome modal with two clear paths (describe an agent to build with AI, starting from a prompt in Chat, or start from a curated template), replacing the previous multi-step setup wizard.
• Creating an agent from a Fleet template now skips the setup wizard and opens the agent editor with the template onboarding card.
• Fleet now sends the MCP protocol version a server negotiates during the handshake, both when loading tools and when the agent calls them, so MCP servers that require a newer version no longer return zero tools or fail tool calls.
• Fleet agents receive the day of week alongside the current date (for example “Monday, June 29th 2026”), so scheduling and date reasoning no longer relies on the model inferring the weekday from the ISO date.
• File edits in Fleet agent chat now render as syntax-highlighted, line-by-line diffs, making changes easier to review.
• When you connect a custom Slack bot to a Fleet agent, Fleet sends the installer a direct message with quick setup tips, including how to add the bot to channels and mention it with @.
• Fleet agents now have a Slack tool for listing channels the connected bot is a member of, making it easier to discover the right channel before posting or reading messages.
• Fleet OAuth provider and integration responses now include an owner field (workspace or platform) so you can tell your own resources apart from built-in, platform-managed ones. The platform manager organization can now create and modify built-in OAuth providers.
• Setting up a schedule is now clearer: choose a preset (daily, weekly, monthly, or every few minutes) or enter a custom cron expression, with a live human-readable preview and inline validation as you go.
• When registering an integration OAuth provider for headless connections, http:// redirect URIs are now accepted only for the loopback IP literals 127.0.0.1 or [::1]. The localhost hostname is no longer accepted over http; use the loopback IP literal or https.

​

Fixes

• On the Agent Builder Integrations page, searching now selects the All tab so results span every category, and switching category tabs clears the search.
• When a Fleet agent’s subagent calls a tool that requires human approval, the approval prompt now appears in the chat instead of the run completing without it.

​

New features

• 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, 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 list now degrades gracefully when one skill fails to load, so the remaining skills still appear.

​

New features

• 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.

​

New features

• 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 entry.
• The remote MCP authorization screen now shows the connecting application’s name, logo, and homepage, terms, and privacy links instead of its raw client ID.
• Slack integration available in AWS and APAC regions.

​

Fixes

• Scheduled (cron) execution 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 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.

​

New features

• Agent Builder is now 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.

​

New features

• A central Chat agent connects to all of your workspace 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, manage authentication, and control access across the organization.

​

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.