Documentation Index
Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1778693861-0079777.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Subscribe: Our changelog includes an RSS feed that can integrate with Slack, email, Discord bots like Readybot or RSS Feeds to Discord Bot, and other subscription tools.
langsmith-0.15.0-rc.9
- Fixed widened ‘Enabled’ column in automations table to prevent header truncation.
- Updated details view header in the frontend.
- Fixed issues with SmithDB zero-row Arrow response in the backend.
- Improved performance by removing dead joins from session stats queries.
- Added support for SmithDB-backed comparison view endpoint.
- Fixed issues with Pollys’ button icon sticking to the cursor and layout in full-page view.
- Enhanced UI sorting by ‘created’ and ‘updated’ in evaluators table.
- Added user-friendly navigation to evaluator source projects.
- Improved feedback consistency by truncating oversized feedback fields before rejection.
- Fixed various issues with tracing projects UI, including column visibility and selector options.
- Added support for agent cost breakdown table and spend limit checking in fleet features.
- Improved Fleet UI component sorting and layout for usage analysis and tool management.
- Fixed polymorphic issues and enhancements surrounding Docker, evaluator loading states, workspace, and agent settings.
- Added mTLS support via clickhouse migrations.
- Enhanced mobile-friendly UI for login and made it installable as a progressive web app (PWA).
- Fixed playground prompt navigation within the hub and playground.
- Improved performance and refactored UI for easier message processing and memory utilization.
- Added UX improvements for dynamic evaluator actions and thread management within evaluator reuse.
- Implemented SSO groups columns support for enhanced authentication and provisioning.
- Included agent monitoring and component feedback to streamline usage and enhance fleet management.
langsmith-0.15.0-rc.9.tgzlangsmith-0.15.0-rc.8
- Added feature to show back button on full-page trace view for better navigation.
- Improved evaluator functionality: added sorting by created and updated timestamps in the evaluators table.
- Enhanced evaluator functionality with feedback key and resource filters, allowing better data management.
- Updated evaluator user interface with click-to-filter options on type, feedback key, and resource cells.
- Integrated a new UX for evaluator template packs and updates to evaluator templates for better UI experience.
- Introduced async agents in the fleet for improved handling of tasks.
- Enabled evaluator details sorting and additional metadata display for enhanced data accessibility.
- Refined keyboard enhancements in the agent builder with cmd/ctrl+s for saving, improving the user experience.
- Added the ability to detach run rules from the resources tab, increasing flexibility in use.
- Implemented a “create agent manually” button in the navigation bar for easier agent creation.
- Enhanced pagination and data retrieval speed in trace and evaluator functionalities.
- Improved evaluator interface with a warning system and associated run rules when deleting evaluators.
- Extended functionalities in evaluator reuse for the side panel and enhanced feedback options in UI.
- Presented evaluator actions as a requirement in issue board creation, increasing data control.
- Added spend limit capabilities with CRUD endpoints in fleet management, optimizing resource monitoring.
- Improved agent builder with spent breakdown visualization enhancements, optimized for user insights.
- Implemented an audit logging feature for sensitive endpoints to enhance security.
- Added support for external OAuth providers with additional GitHub App installation support.
- Engineered mobile-friendly login and PWA for improved access on mobile devices.
- Enhanced split evaluator pages into adaptable components for better user interaction.
- Improved Dinamic tool evaluations, enhancing overall tool usage experience.
- Migrated to robust infrastructure capable of handling ClickHouse integrations with enhanced mTLS support, elevating security features.
- Introduced new API endpoints for enhanced tracing control, including latency logging and evaluation interfaces.
- Enabled SSO login through UI improvements, broadening authentication support.
- Sustained internal improvements in JSON/YAML toggle interactions for trace view.
- Incorporated dark mode enhancements and new theming options for consistent visual experience.
langsmith-0.15.0-rc.8.tgzlangsmith-0.15.0-rc.7
- Fixed header truncation by widening the ‘Enabled’ column in the automations table.
- Improved icon support by adding solid icons and an extra small (xs) variant in the frontend.
- Enhanced model support by adding invoke model bedrock event hooks to the auth proxy injection.
- Updated details view header for better user interface clarity.
- Improved loading performance by removing dead join from session stats queries.
- Made the MCP server filter dropdown scrollable to enhance navigation.
- Added agent cost breakdown and user cost table with agent/user toggle for better cost management.
- Introduced new sorting options for evaluators on their details page.
- Added URL allowlist enforcement to enhance JWT injection security.
- Allowed searching by creator in the evaluators table for more efficient data retrieval.
- Added access control feature with read permission for fleet-admin and related support.
- Enhanced auth interrupt UI by adding an all-scopes auth option.
- Provided a back button on the full-page trace view to improve navigation.
- Added a new menu skeleton for org members, accessed toggling features based on workspace permissions.
- Introduced a filtering feature in the evaluator table for key and resource filters.
- Improved file access by using prefix matching for OAuth provider icons and names.
- Handled non-SSO login more robustly for users with multiple SSO provider records.
- Updated evaluator reuse launching feature with feedback banner.
- Added sorting capability to the evaluators’ table filters dropdown.
- Enhanced security with stricter authentication checks.
- Introduced agent notification mechanism for flagged traces.
- Improved resilience and performance of bulk delete operations.
- Incorporated real-time streaming for CSV exports in experiment comparisons.
- Added localization and tool support for tool call parsing in frontend.
- Enhanced usage insights with agent metadata in the dashboard.
- Improved tool usage rendering and approval UX in the agent builder editor.
- Integrated a design system dialog component to standardize UI design.
- Supported mounting system skills in custom agents for enhanced tool utilization.
- Added audit logging for sensitive data access endpoints to ensure compliance and monitoring.
- Allowed user accounts with self-hosted licenses to update via JWT endpoint.
- Improved performance by synchronizing integrations toggle cache efficiently.
langsmith-0.15.0-rc.7.tgzlangsmith-0.15.0-rc.6
- Updated UI by widening the ‘Enabled’ column in the automations table to prevent header truncation.
- Fixed issue with the MCP server filter dropdown being scrollable.
- Fixed bug where the polly button icon was sticking to the cursor.
- Improved backend to allow async agents.
- Fixed issue preventing file creation from clearing active interrupt state.
- Introduced agent cost breakdown and user cost tables.
- Improved performance by removing unnecessary joins from session stats queries.
- Enhanced ability to sort evaluators table by created and updated at dates.
- Added new capabilities to detach run rules from the resource tab.
- Improved loading performance by making frontend sandbox proxy profiles.
- Added several new backend APIs, including support for metadata comparator operations and session filtering for Go delta stream endpoint.
- Enhanced security by adding URL allowlist enforcement for JWT injection.
- Implemented a feedback key filter with searchable dropdown in evaluators table.
- Improved security by terminating IdP session on OIDC SSO logout.
- Streamlined UI with a new dialog added to the design system.
- Added support for JSON and YAML in input/output displays within trace view.
- Revamped UI styling of evaluator details page and issue board.
- Integrated Claude Opus 4.7 into default model pricing maps.
- Introduced get_current_time tool in the agent-builder.
- Added filtering and sorting in issue boards.
- Added support for multitenancy with short-lived API keys.
- Improved playground loader with prompt navigation enhancements.
- Introduced new endpoint for updating self-hosted customer licenses.
- Efficiently synced integrations toggle cache across front-end and back-end systems.
- Enhanced sandbox observability and request handling.
- Enabled audit logging across remaining backend endpoints.
- Enhanced message processing to include latency metrics and detailed agent information.
- Implemented automatic addition of flagged traces to annotation queues.
- Enhanced evaluator UX, including improved sorting, filtering, and trace detail view.
- Revamped contextual transitions and navigational flows throughout the application UI.
- Added support for run rule logic improvements.
- Optimized message view processing for memory utilization and performance.
- Introduced opt-in onboarding flow for agent templates.
langsmith-0.15.0-rc.6.tgzlangsmith-0.15.0-rc.5
- Fixed the ‘Enabled’ column width in the automations table for better header visibility.
- Improved session stats queries by removing dead joins, enhancing performance.
- Made the MCP server filter dropdown scrollable in the fleet module.
- Added user cost table and agent/user toggle for better cost tracking in fleet.
- Improved trace layout in the full page trace view.
- Fixed various layout and data loading issues in the frontend for better user experience.
- Added URL allowlist enforcement for JWT injection in Polly for enhanced security.
- Fixed an issue with responsive layout in the feedback editor.
- Improved evaluator table functionality with sorting, filtering, and new columns.
- Added async agents support in the fleet for better performance.
- Enhanced evaluator creation with attribution and sorting capabilities.
- Added new rule logs tab in the frontend for better run rules management.
- Fixed file creation issues clearing active interrupt states.
- Enhanced trace detail panel with a source section for evaluators.
- Improved evaluator reuse launch feedback and banner visibility.
- Added multi-repo query support to the context page.
- Implemented navigation improvements for evaluator details pages.
- Improved visibility and rendering of evaluator actions and tools.
- Enhanced run rule selection and UX in the frontend.
- Enhanced run rules with additional statistics and session insights.
- Improved logging and authorization in API operations.
- Introduced SSO login functionality for an improved sign-in experience.
- Enhanced frontend to include cost information next to token counts for better transparency.
- Enabled column sorting on the annotation queues list view for organized data management.
- Added mobile-friendly login and installable PWA features.
- Improved the agent builder chat by displaying provider API key links.
- Enhanced GitHub App frontend components for seamless integrations.
langsmith-0.15.0-rc.5.tgzlangsmith-0.15.0-rc.4
- Fixed layout issues by widening the ‘Enabled’ column in the automations table to prevent header truncation.
- Added solid icons to the frontend icon package and introduced an icon XS variant for better UI representation.
- Enhanced details view header for improved user interface.
- Improved performance by removing unnecessary join operations from session stats queries.
- Made the MCP server filter dropdown scrollable to enhance user navigation.
- Added agent cost breakdown and user cost tables with an agent/user toggle for better financial insights.
- Fixed layout issues in trace layout on full page trace view.
- Enhanced the evaluator’s table with added sorting capabilities based on created and updated timestamps.
- Provided a URL allowlist for JWT injection to improve security in polly.
- Enhanced the frontend with click-to-filter capabilities on type, feedback key, and resource cells in evaluator tables.
- Added a rule logs tab and toggle for backfill runs in the frontend.
- Improved evaluator feedback key and resource filters with searchable dropdowns.
- Implemented an async agent feature to increase fleet efficacy.
- Addressed sandbox issues by stabilizing the local Firecracker e2e flow.
- Incorporated FIPS variants support for various langchain components to enhance security.
- Improved evaluator usability by showing ‘Feedback Key’ in the evaluators column dropdown with new filtering options.
- Enhanced loading speed in the frontend’s DataGrid by loading the next page when scrolled to the bottom.
- Supported tool call parsing from directly wrapped Anthropic clients for a smoother experience.
- Introduced additional API endpoints to track usage and insight metrics effectively.
- Enhanced security by terminating IdP sessions on OIDC SSO logout.
- Added support for SmithDB-backed comparison view endpoints, enabling efficient data comparison.
- Introduced feedback delta stream usage for comparison view on datasets.
- Streamlined frontend interactions by reducing metadata filtering issues in evaluator tables.
- Enhanced agent builder settings with an option for auto-improvement toggle.
- Integrated Redis for enhanced data streaming and performance improvements.
- Optimized memory usage by introducing asynchronous chat data streaming.
- Implemented enhancements in the feedback mechanism by making edit history available for prompt reuse.
- New endpoints introduced for API key management to enhance integration capabilities.
- Upgraded evaluator functionality to allow for evaluators’ fork and trace navigation enhancements.
- Expanded capabilities of tracing APIs to support advanced operational requirements.
- Added composable databases for MCP servers to enhance data management flexibility.
- Implemented enhancements and upgrades across security management to include new authentication endpoints.
langsmith-0.15.0-rc.4.tgzlangsmith-0.14.5
- Internal improvements and maintenance updates
langsmith-0.14.5.tgzlangsmith-0.15.0-rc.3
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.3.tgzlangsmith-0.14.3
- Internal improvements and maintenance updates
langsmith-0.14.3.tgzlangsmith-0.15.0-rc.2
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.2.tgzlangsmith-0.15.0-rc.1
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.1.tgzlangsmith-0.14.2
- Internal improvements and maintenance updates
langsmith-0.14.2.tgzlangsmith-0.14.1
- Internal improvements and maintenance updates
langsmith-0.14.1.tgzlangsmith-0.14.0
- Internal improvements and maintenance updates
langsmith-0.14.0.tgzlangsmith-0.13.43
- Internal improvements and maintenance updates
langsmith-0.13.43.tgzlangsmith-auth-proxy-0.0.10
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.10.tgzlangsmith-0.13.42
- Internal improvements and maintenance updates
langsmith-0.13.42.tgzlangsmith-0.13.41
- Internal improvements and maintenance updates
langsmith-0.13.41.tgzlangsmith-0.13.40
- Internal improvements and maintenance updates
langsmith-0.13.40.tgzlangsmith-0.13.39
- Internal improvements and maintenance updates
langsmith-0.13.39.tgzlangsmith-0.13.38
- Internal improvements and maintenance updates
langsmith-0.13.38.tgzlangsmith-0.13.37
- Internal improvements and maintenance updates
langsmith-0.13.37.tgzlangsmith-0.13.36
- Internal improvements and maintenance updates
langsmith-0.13.36.tgzlangsmith-0.13.35
- Internal improvements and maintenance updates
langsmith-0.13.35.tgzlangsmith-0.13.34
- Internal improvements and maintenance updates
langsmith-0.13.34.tgzlangsmith-0.13.33
- Internal improvements and maintenance updates
langsmith-0.13.33.tgzlangsmith-0.13.32
- Internal improvements and maintenance updates
langsmith-0.13.32.tgzlangsmith-auth-proxy-0.0.9
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.9.tgzlangsmith-0.13.31
- Internal improvements and maintenance updates
langsmith-0.13.31.tgzlangsmith-0.13.30
- Internal improvements and maintenance updates
langsmith-0.13.30.tgzlangsmith-0.13.29
- Internal improvements and maintenance updates
langsmith-0.13.29.tgzlangsmith-0.13.28
- Internal improvements and maintenance updates
langsmith-0.13.28.tgzlangsmith-auth-proxy-0.0.8
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.8.tgzlangsmith-auth-proxy-0.0.7
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.7.tgzlangsmith-0.13.27
- Internal improvements and maintenance updates
langsmith-0.13.27.tgzlangsmith-auth-proxy-0.0.6
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.6.tgzlangsmith-auth-proxy-0.0.5
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.5.tgzlangsmith-auth-proxy-0.0.4
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.4.tgzlangsmith-0.13.26
- Internal improvements and maintenance updates
langsmith-0.13.26.tgzlangsmith-0.13.25
- Internal improvements and maintenance updates
langsmith-0.13.25.tgzlangsmith-auth-proxy-0.0.3
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.3.tgzlangsmith-0.13.24
- Internal improvements and maintenance updates
langsmith-0.13.24.tgzlangsmith-observability-0.2.0
- Internal improvements and maintenance updates
langsmith-observability-0.2.0.tgzlangsmith-auth-proxy-0.0.2
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.2.tgzlangsmith-0.13.23
- Internal improvements and maintenance updates
langsmith-0.13.23.tgzlangsmith-0.13.21
- Internal improvements and maintenance updates
langsmith-0.13.21.tgzlangsmith-0.13.20
- Internal improvements and maintenance updates
langsmith-0.13.20.tgzlangsmith-0.13.19
- Internal improvements and maintenance updates
langsmith-0.13.19.tgzlangsmith-0.13.18
- Internal improvements and maintenance updates
langsmith-0.13.18.tgzlangsmith-0.13.17
- Internal improvements and maintenance updates
langsmith-0.13.17.tgzlangsmith-0.13.16
- Internal improvements and maintenance updates
langsmith-0.13.16.tgzlangsmith-0.13.15
- Internal improvements and maintenance updates
langsmith-0.13.15.tgzlangsmith-0.13.14
- Internal improvements and maintenance updates
langsmith-0.13.14.tgzlangsmith-auth-proxy-0.0.1
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.1.tgzlangsmith-0.13.13
- Internal improvements and maintenance updates
langsmith-0.13.13.tgzlangsmith-0.13.12
- Internal improvements and maintenance updates
langsmith-0.13.12.tgzlangsmith-0.13.11
- Internal improvements and maintenance updates
langsmith-0.13.11.tgzlangsmith-0.13.10
- Internal improvements and maintenance updates
langsmith-0.13.10.tgzlangsmith-0.13.9
- Internal improvements and maintenance updates
langsmith-0.13.9.tgzlangsmith-0.13.7
- Internal improvements and maintenance updates
langsmith-0.13.7.tgzlangsmith-0.13.6
- Internal improvements and maintenance updates
langsmith-0.13.6.tgzlangsmith-0.13.5
- Internal improvements and maintenance updates
langsmith-0.13.5.tgzlangsmith-0.13.4
- Internal improvements and maintenance updates
langsmith-0.13.4.tgzlangsmith-0.13.3
- Internal improvements and maintenance updates
langsmith-0.13.3.tgzlangsmith-0.13.2
- Internal improvements and maintenance updates
langsmith-0.13.2.tgzlangsmith-0.13.1
- Internal improvements and maintenance updates
langsmith-0.13.1.tgzlangsmith-0.13.0
- Internal improvements and maintenance updates
langsmith-0.13.0.tgzlangsmith-0.12.37
- Internal improvements and maintenance updates
langsmith-0.12.37.tgzlangsmith-0.12.36
- Internal improvements and maintenance updates
langsmith-0.12.36.tgzlangsmith-0.12.35
- Internal improvements and maintenance updates
langsmith-0.12.35.tgzlangsmith-0.12.34
- Internal improvements and maintenance updates
langsmith-0.12.34.tgzlangsmith-0.12.33
- Internal improvements and maintenance updates
langsmith-0.12.33.tgzlangsmith-0.12.32
- Internal improvements and maintenance updates
langsmith-0.12.32.tgzlangsmith-0.12.31
- Internal improvements and maintenance updates
langsmith-0.12.31.tgzlangsmith-0.12.30
- Internal improvements and maintenance updates
langsmith-0.12.30.tgzlangsmith-0.12.29
- Internal improvements and maintenance updates
langsmith-0.12.29.tgzlangsmith-0.12.28
- Internal improvements and maintenance updates
langsmith-0.12.28.tgzlangsmith-0.12.27
- Internal improvements and maintenance updates
langsmith-0.12.27.tgzlangsmith-0.8.30
- Internal improvements and maintenance updates
langsmith-0.8.30.tgzlangsmith-0.12.25
- Internal improvements and maintenance updates
langsmith-0.12.25.tgzlangsmith-0.12.24
- Internal improvements and maintenance updates
langsmith-0.12.24.tgzlangsmith-0.12.23
- Internal improvements and maintenance updates
langsmith-0.12.23.tgzlangsmith-0.12.22
- Internal improvements and maintenance updates
langsmith-0.12.22.tgzlangsmith-0.12.21
- Internal improvements and maintenance updates
langsmith-0.12.21.tgzlangsmith-0.12.20
- Internal improvements and maintenance updates
langsmith-0.12.20.tgzlangsmith-0.15.0-rc.8
- Fixed the ‘Enabled’ column in the automations table to prevent header truncation.
- Improved the evaluator details view header in the frontend.
- Enhanced performance by removing dead join from session stats queries.
- Made MCP server filter dropdown scrollable in the fleet UI.
- Added a cost breakdown table for agents and users.
- Added new sorting options in the evaluators table for created and updated timestamps.
- Improved trace layout in full page views.
- Fixed file creation interrupt state clear issue in the fleet.
- Added an “Always approve memory updates” option to interrupt UI.
- Added support for GLM5 and Minimax 2.5 models.
- Implemented async agent capabilities in the fleet.
- Enhanced OAuth provider icons and names matching.
- Updated evaluator template packs in the frontend.
- Added scroll functionality for human messages in fleet chat.
- Added integration support for AWS and BYOC in sign-up pages.
- Improved UI for evaluator reuse in the frontend.
- Enabled audit logging for Go write endpoints.
- Enhanced GitHub OAuth flow with user authentication sync.
- Improved frontend layout performance by refactoring playground UI.
- Improved UI and usability for tracing projects.
- Supported PostgreSQL TLS migrations using system root certificates.
- Added new API endpoints for sessions and usage insights.
- Added AWS marketplace tables for usage tracking.
- Enhanced performance metrics for ClickHouse ingestion and SmithDB dual-write.
- Enabled per-trace summaries in issue boards.
- Fixed evaluator feedback creation for threads in Tracing projects.
- Improved UI for evaluator CRUD operations in the frontend.
- Augmented agent builder settings with auto-improve toggle.
- Enhanced model support with language models configuration updates.
- Improved performance for experiments syncing.
- Fixed sandbox snapshot handling for local environments.
- Improved evaluator details page with metadata enhancements and better filtering options.
- Added provider API key links in the agent builder chat.
- Added presentation-builder as a core system skill in the fleet.
- Supported multi-repo queries in context table and frontend display.
- Fixed feedback truncate issue to improve evaluator ingestion.
- Implemented async OOB retries and error handling for SmithDB operations.
- Improved usage dashboard with detailed spend limits and tracing project insights.
- Added multi-platform API key support for agent usage in tracing projects.
- Added network marketplace registration and CRUD updates.
- Introduced audit and latency logging for sensitive data sessions.
- Supported issue and annotation queue handling with enhanced UI in frontend.
- Migrated toast notifications to toast management system in UI.
- Enabled enhanced filtering and sorting in tracing projects for better data organization.
langsmith-0.15.0-rc.8.tgzlangsmith-0.15.0-rc.7
- Fixed a UI bug that widened the ‘Enabled’ column in the automations table to prevent header truncation.
- Improved performance by removing dead joins from session stats queries, enhancing query efficiency.
- Added Fleet feature to make MCP server filter dropdown scrollable.
- Fixed issue where layout was incorrect for full page trace view.
- Enhanced the evaluator by adding search functionality for created by field and sorting options.
- Updated icon package to include solid icons and new size variants for improved UI.
- Added all-scopes authentication option to the auth interrupt UI.
- Improved fleet system with agent cost breakdown tables and additional dashboard insights.
- Introduced feature flags for skill library, spend limits, and permissions management within Fleet.
- Implemented async ingestion and storage to improve data processing performance.
- Improved evaluator details with new columns and options for sorting and filtering.
- Added new API endpoints for managing agent templates, integrations, and usage tracking in Fleet.
- Introduced audit logging on various Go write endpoints to improve monitoring and security.
- Implemented specific fixes to address language models like Anthropic and Claude for tool call parsing.
- Enabled updating and inviting users to organizations via enhanced API endpoint.
- Updated UI with new components for dialog design and suggestion tools in fleet and evaluation workflows.
- Enhanced OAuth and SSO integrations with safety checks and UI enhancements.
- Improved the logging and exception handling mechanisms for better traceability and debugging.
- Introduced new endpoint to update online self-hosted licenses.
- Enhanced support for SmithDB shadow with improved filtering and querying capabilities for dataset views.
langsmith-0.15.0-rc.7.tgzlangsmith-0.15.0-rc.6
- Improved the UI by widening the ‘Enabled’ column in the automations table to prevent header truncation.
- Added solid icons and an icon xs variant to the frontend for better visual representation.
- Updated the details view header in the frontend for enhanced navigation.
- Improved performance by removing redundant joins in session stats queries.
- Made MCP server filter dropdown scrollable for better fleet management.
- Showed a back button on the full-page trace view to improve trace navigation.
- Implemented sorting functionality for ‘created’ and ‘updated’ at fields in evaluators.
- Added URL allowlist enforcement for JWT injection to enhance security.
- Enabled scrollability for selectors in the DataGrid component to ensure ease of navigation when reaching the bottom.
- Optimized the response processing for SmithDB zero-row responses.
- Enhanced feedback table with search, filters, and associated feature improvements in evaluators.
- Introduced new Go CRUD endpoints for managing spend limits in the fleet.
- Improved evaluator reuse UI with trace search and sorting enhancements.
- Added support for new model integrations, including GLM5 and minimax 2.5.
- Enhanced the playground with error handling for missing variables.
- Introduced audit logging for all Go write endpoints.
- Introduced BYOC OAuth tools for Twitter integration.
- Added agent cost breakdown and user cost table toggle to fleet management.
- Enhanced evaluator functionality with organization-based filters and metadata support.
- Improved analytics by enabling evaluator details analytics tracking.
- Enabled column sorting on annotation queues list view for better management.
- Improved performance by enhancing message memory utilization in message view.
- Added functionality for oauth service and user authentication flow integrations.
- Enhanced security by adding mTLS support for ClickHouse migrations.
- Enabled async agents for improved fleet interaction.
- Introduced spend limit enforcement and queries for better cost management.
- Improved skill rendering in chat UI for user feedback.
- Enhanced evaluator inputs with clickable filters and sorting options.
- Introduced support for public shared datasets and exports.
- Improved agent builder navigation and UI with added functionality.
- Introduced metrics API in smith-go for detailed performance analytics.
- Enhanced tracing performance via message view improvements.
- Integrated issue board UI with detailed column enhancements for better usability.
- Enhanced the agent builder with an option for auto-improve settings.
- Added support for new GitHub OAuth flows and integration synchronization.
- Added mobile-friendly login support for enhanced user accessibility.
langsmith-0.15.0-rc.6.tgzlangsmith-0.15.0-rc.5
- Improved the UI by widening the ‘Enabled’ column in the automations table to prevent header truncation.
- Fixed an issue with the ‘Polly’ button icon that stuck to the cursor on click near the bounding box.
- Updated the frontend to remove implicit ‘any’ types and address potential issues.
- Added URL allowlist enforcement for JWT injection for enhanced security.
- Enabled sorting by ‘created’ and ‘updated’ at in the evaluators table for better data management.
- Introduced a new option “invite to org” in workspace settings for admins.
- Improved playground rendering by gating it on feature config loading state.
- Enhanced evaluator table filters with a searchable dropdown for feedback key attributes.
- Allowed detaching run rules from the resources tab to streamline user management.
- Enhanced authentication with a new SSO login button on the login page.
- Comprehensive addition of API endpoints to handle user feedback batch operations.
- Integrated a carousel of suggested evaluators in the evaluator tab to guide users.
- Updated session endpoints to proxy list to Go endpoint under specific flags.
- Released a new feature toggle to manage tracing projects from fleet usage dashboards.
- Performance improvements in syncing idle sessions and experiments.
- Enabled enhanced error handling and tracing for ingest operations.
langsmith-0.15.0-rc.5.tgzlangsmith-0.15.0-rc.4
- Fixed header truncation in the automations table by widening the ‘Enabled’ column.
- Added solid icons and extra-small icon variants to the frontend.
- Improved details view header for better user experience.
- Removed unnecessary join from session stats queries to improve performance.
- Added back button on full-page trace view for easier navigation.
- Updated trace layout in full-page view to enhance user experience.
- Made the MCP server filter dropdown scrollable in fleet management.
- Implemented async agents in fleet features for more efficient operation.
- Integrated X (Twitter) OAuth tools for enhanced social media interaction in fleet.
- Enabled Go CRUD endpoints for spend limits, providing more detailed financial control.
- Enhanced evaluator table with sorting and filtering features for improved data management.
- Updated support for OAuth provider icons and names with prefix matching for better identity resolution.
- Refined UI elements, including scrolling and feedback editor layout for improved usability.
- Improved playground feature by loading feature config state before rendering.
- Enabled scroll-to-top feature for chat in fleet, enhancing user interaction.
- Implemented tracing project name adjustments in the usage dashboard.
- Added support for OAuth2 authentication through database migration.
- Introduced more robust evaluator handling, including warning dialogs and improved UI for reuse workflows.
- Enhanced issue board features with better UI polish, including timestamps and layout adjustments.
- Improved sandbox proxy handling to secure HTTPS requests.
- Added support for Salesforce tool integration in fleet management.
- Enabled error protection for annotator elements to preserve session integrity.
- Implemented configurable retry delays for submission operations, enhancing reliability.
- Fixed unnecessary unauthorized requests in fleet systems, boosting performance and security.
- Added new API endpoints for session management and tracing, broadening integration capabilities.
- Introduced mobile-friendly login features and a progressive web app for mobile devices.
- Streamlined fleet handling workflows, including template efficiencies in agent creation.
- Implemented mTLS support for ClickHouse migrations, reinforcing security for self-hosting.
langsmith-0.15.0-rc.4.tgzlangsmith-0.14.5
- Internal improvements and maintenance updates
langsmith-0.14.5.tgzlangsmith-0.15.0-rc.3
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.3.tgzlangsmith-0.14.3
- Internal improvements and maintenance updates
langsmith-0.14.3.tgzlangsmith-0.15.0-rc.2
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.2.tgzlangsmith-0.15.0-rc.1
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.1.tgzlangsmith-0.14.2
- Internal improvements and maintenance updates
langsmith-0.14.2.tgzlangsmith-0.14.1
- Internal improvements and maintenance updates
langsmith-0.14.1.tgzlangsmith-0.14.0
- Internal improvements and maintenance updates
langsmith-0.14.0.tgzlangsmith-0.13.43
- Internal improvements and maintenance updates
langsmith-0.13.43.tgzlangsmith-auth-proxy-0.0.10
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.10.tgzlangsmith-0.13.42
- Internal improvements and maintenance updates
langsmith-0.13.42.tgzlangsmith-0.13.41
- Internal improvements and maintenance updates
langsmith-0.13.41.tgzlangsmith-0.13.40
- Internal improvements and maintenance updates
langsmith-0.13.40.tgzlangsmith-0.13.39
- Internal improvements and maintenance updates
langsmith-0.13.39.tgzlangsmith-0.13.38
- Internal improvements and maintenance updates
langsmith-0.13.38.tgzlangsmith-0.13.37
- Internal improvements and maintenance updates
langsmith-0.13.37.tgzlangsmith-0.13.36
- Internal improvements and maintenance updates
langsmith-0.13.36.tgzlangsmith-0.13.35
- Internal improvements and maintenance updates
langsmith-0.13.35.tgzlangsmith-0.13.34
- Internal improvements and maintenance updates
langsmith-0.13.34.tgzlangsmith-0.13.33
- Internal improvements and maintenance updates
langsmith-0.13.33.tgzlangsmith-0.13.32
- Internal improvements and maintenance updates
langsmith-0.13.32.tgzlangsmith-auth-proxy-0.0.9
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.9.tgzlangsmith-0.13.31
- Internal improvements and maintenance updates
langsmith-0.13.31.tgzlangsmith-0.13.30
- Internal improvements and maintenance updates
langsmith-0.13.30.tgzlangsmith-0.13.29
- Internal improvements and maintenance updates
langsmith-0.13.29.tgzlangsmith-0.13.28
- Internal improvements and maintenance updates
langsmith-0.13.28.tgzlangsmith-auth-proxy-0.0.8
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.8.tgzlangsmith-auth-proxy-0.0.7
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.7.tgzlangsmith-0.13.27
- Internal improvements and maintenance updates
langsmith-0.13.27.tgzlangsmith-auth-proxy-0.0.6
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.6.tgzlangsmith-auth-proxy-0.0.5
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.5.tgzlangsmith-auth-proxy-0.0.4
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.4.tgzlangsmith-0.13.26
- Internal improvements and maintenance updates
langsmith-0.13.26.tgzlangsmith-0.13.25
- Internal improvements and maintenance updates
langsmith-0.13.25.tgzlangsmith-auth-proxy-0.0.3
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.3.tgzlangsmith-0.13.24
- Internal improvements and maintenance updates
langsmith-0.13.24.tgzlangsmith-observability-0.2.0
- Internal improvements and maintenance updates
langsmith-observability-0.2.0.tgzlangsmith-auth-proxy-0.0.2
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.2.tgzlangsmith-0.13.23
- Internal improvements and maintenance updates
langsmith-0.13.23.tgzlangsmith-0.13.21
- Internal improvements and maintenance updates
langsmith-0.13.21.tgzlangsmith-0.13.20
- Internal improvements and maintenance updates
langsmith-0.13.20.tgzlangsmith-0.13.19
- Internal improvements and maintenance updates
langsmith-0.13.19.tgzlangsmith-0.13.18
- Internal improvements and maintenance updates
langsmith-0.13.18.tgzlangsmith-0.13.17
- Internal improvements and maintenance updates
langsmith-0.13.17.tgzlangsmith-0.13.16
- Internal improvements and maintenance updates
langsmith-0.13.16.tgzlangsmith-0.13.15
- Internal improvements and maintenance updates
langsmith-0.13.15.tgzlangsmith-0.13.14
- Internal improvements and maintenance updates
langsmith-0.13.14.tgzlangsmith-auth-proxy-0.0.1
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.1.tgzlangsmith-0.13.13
- Internal improvements and maintenance updates
langsmith-0.13.13.tgzlangsmith-0.13.12
- Internal improvements and maintenance updates
langsmith-0.13.12.tgzlangsmith-0.13.11
- Internal improvements and maintenance updates
langsmith-0.13.11.tgzlangsmith-0.13.10
- Internal improvements and maintenance updates
langsmith-0.13.10.tgzlangsmith-0.13.9
- Internal improvements and maintenance updates
langsmith-0.13.9.tgzlangsmith-0.13.7
- Internal improvements and maintenance updates
langsmith-0.13.7.tgzlangsmith-0.13.6
- Internal improvements and maintenance updates
langsmith-0.13.6.tgzlangsmith-0.13.5
- Internal improvements and maintenance updates
langsmith-0.13.5.tgzlangsmith-0.13.4
- Internal improvements and maintenance updates
langsmith-0.13.4.tgzlangsmith-0.13.3
- Internal improvements and maintenance updates
langsmith-0.13.3.tgzlangsmith-0.13.2
- Internal improvements and maintenance updates
langsmith-0.13.2.tgzlangsmith-0.13.1
- Internal improvements and maintenance updates
langsmith-0.13.1.tgzlangsmith-0.13.0
- Internal improvements and maintenance updates
langsmith-0.13.0.tgzlangsmith-0.12.37
- Internal improvements and maintenance updates
langsmith-0.12.37.tgzlangsmith-0.12.36
- Internal improvements and maintenance updates
langsmith-0.12.36.tgzlangsmith-0.12.35
- Internal improvements and maintenance updates
langsmith-0.12.35.tgzlangsmith-0.12.34
- Internal improvements and maintenance updates
langsmith-0.12.34.tgzlangsmith-0.12.33
- Internal improvements and maintenance updates
langsmith-0.12.33.tgzlangsmith-0.12.32
- Internal improvements and maintenance updates
langsmith-0.12.32.tgzlangsmith-0.12.31
- Internal improvements and maintenance updates
langsmith-0.12.31.tgzlangsmith-0.12.30
- Internal improvements and maintenance updates
langsmith-0.12.30.tgzlangsmith-0.12.29
- Internal improvements and maintenance updates
langsmith-0.12.29.tgzlangsmith-0.12.28
- Internal improvements and maintenance updates
langsmith-0.12.28.tgzlangsmith-0.12.27
- Internal improvements and maintenance updates
langsmith-0.12.27.tgzlangsmith-0.8.30
- Internal improvements and maintenance updates
langsmith-0.8.30.tgzlangsmith-0.12.25
- Internal improvements and maintenance updates
langsmith-0.12.25.tgzlangsmith-0.12.24
- Internal improvements and maintenance updates
langsmith-0.12.24.tgzlangsmith-0.12.23
- Internal improvements and maintenance updates
langsmith-0.12.23.tgzlangsmith-0.12.22
- Internal improvements and maintenance updates
langsmith-0.12.22.tgzlangsmith-0.12.21
- Internal improvements and maintenance updates
langsmith-0.12.21.tgzlangsmith-0.12.20
- Internal improvements and maintenance updates
langsmith-0.12.20.tgzlangsmith-0.12.19
- Internal improvements and maintenance updates
langsmith-0.12.19.tgzlangsmith-0.15.0-rc.7
- Fixed the ‘Enabled’ column in the automations table to prevent header truncation.
- Improved the evaluator detail page with enhanced UX.
- Updated evaluator template packs for better template management.
- Fixed trace layout issues in full-page view.
- Added new metrics API in smith-go for improved dashboarding and agentic usage.
- Fixed SSRF protection in the remote config and custom model endpoints.
- Added run rule columns to the frontend, enhancing traceability.
- Enhanced load balancing and performance in asynq for ingestion tasks.
- Implemented new API endpoint for updating online self-hosted licenses.
- Supported mTLS for ClickHouse migrations.
- Improved tracing project naming to fleet for better identification in usage dashboards.
- Fixed frontend issues for better evaluator UX, including trace-detail navigation and style updates.
- Added evaluator actions requirement when creating issue board issues.
- Various frontend tweaks and optimizations for better user experience, such as improved header layouts, breadcrumbs, and styling adjustments.
langsmith-0.15.0-rc.7.tgzlangsmith-0.15.0-rc.6
- Fixed the “Enabled” column in the automations table to prevent header truncation, improving UI readability.
- Improved the frontend by bumping the icon package to include solid icons and adding an icon xs variant.
- Updated details view header for better UI clarity.
- Removed a dead join from session stats queries, boosting performance.
- Made MCP server filter dropdown scrollable for easier navigation.
- Fixed the Polly button icon sticking to the cursor issue, enhancing user interaction.
- Added created and updated sorting capabilities to evaluator features.
- Fixed trace layout in full-page view, providing better trace visualization.
- Added URL allowlist enforcement for JWT injection for enhanced security.
- Improved the evaluator filter table with “created_by” user attribution.
- Added fleet-admin:read permission with migration for better permissions control.
- Introduced an all-scopes auth option to auth interrupt UI for flexible access management.
- Showed a back button on full-page trace view for improved navigation.
- Fixed layout and scrolling issues in the frontend evaluator reuse feature.
- Enabled sorting by “created by” field in evaluators table for easier data management.
- Added evaluator feedback key and resource filters for more precise data handling.
- Implemented async agents in fleet for improved efficiency.
- Added dialog support to the frontend design system for better UX.
- Improved evaluator reuse functionalities in playground UI.
- Introduced issue event table backend support for managing issue actions.
- Added spend limit check capabilities to agent-builder-graphs.
- Added X (Twitter) BYO OAuth tools for more flexible OAuth integrations.
- Made sandbox proxy profiles available for enhanced security and configuration.
- Fixed playground feature gating based on configuration state.
- Improved frontend UI for feedback delta stream process.
- Created a public SharedComparisonView endpoint for shared datasets for better data accessibility.
- Added parallel tool call rendering in Messages View for more efficient message processing.
- Enabled carousel of suggested evaluators within the evaluator tab for better UX.
- Fixed playground rendering performance by reducing per-keystroke re-renders.
- Introduced new API endpoints for updating self-hosted licenses.
- Added new run rules logic to improve trace filtering and management.
- Enabled parallel ClickHouse and SmithDB writes to improve ingestion latency.
- Improved agent builder sandbox mode and OAuth integration caching for improved stability.
- Enhanced evaluator design in the UI for clearer visualization and interaction.
- Integrated dark mode improvements, ensuring better visual compliance.
- Streamlined navigation between runs and threads with new filter and trace view features.
langsmith-0.15.0-rc.6.tgzlangsmith-0.15.0-rc.5
- Fixed layout issues in the ‘Enabled’ column of the automations table to prevent header truncation.
- Improved evaluator template packs and updated the details view header.
- Improved performance by removing unnecessary database joins from session stats queries.
- Fixed a bug causing the Polly button’s icon to stick to the cursor on click.
- Enhanced user experience by adding a back button on the full-page trace view.
- Added sorting capabilities for ‘updated’ and ‘created at’ fields in evaluators.
- Added a new API endpoint for feedback-filtered run rules.
- Improved file creation interrupt handling.
- Added Fleet Spend Limit feature with new CRUD endpoints.
- Enhanced Playground tool by adding SSRF protection to remote config and custom model endpoints.
- Introduced evaluator feedback filters with resource filtering.
- Fixed layout issues in evaluator tables.
- Improved UX for evaluator application tags and sorting.
- Added analytics tracking for templates/cards selection.
- Enhanced tracing view with grouped tabs animation.
- Improved mobile-friendly login and installable PWA.
- Fixed run data validation after feedback edit.
- Added support for filtering runs by metadata fields.
- Added support for “always approve memory updates” setting.
- Included GitHub OAuth integration and App installation sync.
- Improved tracing projects by integrating Project/Dataset navigator buttons.
- Released new UI component for presenting spend limits in usage dashboards.
- Added authentication improvements with support for issuing API keys.
langsmith-0.15.0-rc.5.tgzlangsmith-0.15.0-rc.4
- Fixed truncation issue in the ‘Enabled’ column of the automations table to improve usability.
- Added solid icons and icon size variants to enhance the UI experience.
- Improved session stats queries by removing dead code for better performance.
- Made dropdowns and tables scrollable and sortable for large datasets to improve data visibility and interaction.
- Enhanced trace layout and filtering options in full page views for better navigation and user experience.
- Fixed click responsiveness of icons and buttons in various UI sections to ensure a smoother user interface.
- Added permission-based access for fleet-admin roles to enhance security and permissions management.
- Implemented new endpoints and migration support for spend limits and other fleet features.
- Corrected file permission checks and cache handling in the Fleet API for improved user roles and data security.
- Introduced toggles for evaluator and feedback features, improving customization and user feedback handling.
- Integrated SSO support with new authentication options to enhance security configurations.
- Enabled new evaluator features and improved sorting/filtering to strengthen data handling capabilities.
- Added feedback key filters and new evaluator options for refined user feedback and evaluation processes.
- Implemented audit logging capabilities across various backend endpoints to improve security and accountability.
- Optimized database read/write operations to enhance overall system performance.
- Improved tool parsing and integration with Anthropic clients for streamlined operations in the user interface.
- Updated GitHub App syncing and token service processes to improve authentication and integration services.
- Introduced new API endpoints and resolved configuration options for OAuth and SSO, enhancing infrastructure support.
- Enabled mobile-friendly UI and PWA support for better accessibility across platforms.
- Integrated new operational metrics and debug endpoints to streamline troubleshooting and diagnostics.
langsmith-0.15.0-rc.4.tgzlangsmith-0.14.5
- Internal improvements and maintenance updates
langsmith-0.14.5.tgzlangsmith-0.15.0-rc.3
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.3.tgzlangsmith-0.14.3
- Internal improvements and maintenance updates
langsmith-0.14.3.tgzlangsmith-0.15.0-rc.2
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.2.tgzlangsmith-0.15.0-rc.1
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.1.tgzlangsmith-0.14.2
- Internal improvements and maintenance updates
langsmith-0.14.2.tgzlangsmith-0.14.1
- Internal improvements and maintenance updates
langsmith-0.14.1.tgzlangsmith-0.14.0
- Internal improvements and maintenance updates
langsmith-0.14.0.tgzlangsmith-0.13.43
- Internal improvements and maintenance updates
langsmith-0.13.43.tgzlangsmith-auth-proxy-0.0.10
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.10.tgzlangsmith-0.13.42
- Internal improvements and maintenance updates
langsmith-0.13.42.tgzlangsmith-0.13.41
- Internal improvements and maintenance updates
langsmith-0.13.41.tgzlangsmith-0.13.40
- Internal improvements and maintenance updates
langsmith-0.13.40.tgzlangsmith-0.13.39
- Internal improvements and maintenance updates
langsmith-0.13.39.tgzlangsmith-0.13.38
- Internal improvements and maintenance updates
langsmith-0.13.38.tgzlangsmith-0.13.37
- Internal improvements and maintenance updates
langsmith-0.13.37.tgzlangsmith-0.13.36
- Internal improvements and maintenance updates
langsmith-0.13.36.tgzlangsmith-0.13.35
- Internal improvements and maintenance updates
langsmith-0.13.35.tgzlangsmith-0.13.34
- Internal improvements and maintenance updates
langsmith-0.13.34.tgzlangsmith-0.13.33
- Internal improvements and maintenance updates
langsmith-0.13.33.tgzlangsmith-0.13.32
- Internal improvements and maintenance updates
langsmith-0.13.32.tgzlangsmith-auth-proxy-0.0.9
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.9.tgzlangsmith-0.13.31
- Internal improvements and maintenance updates
langsmith-0.13.31.tgzlangsmith-0.13.30
- Internal improvements and maintenance updates
langsmith-0.13.30.tgzlangsmith-0.13.29
- Internal improvements and maintenance updates
langsmith-0.13.29.tgzlangsmith-0.13.28
- Internal improvements and maintenance updates
langsmith-0.13.28.tgzlangsmith-auth-proxy-0.0.8
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.8.tgzlangsmith-auth-proxy-0.0.7
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.7.tgzlangsmith-0.13.27
- Internal improvements and maintenance updates
langsmith-0.13.27.tgzlangsmith-auth-proxy-0.0.6
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.6.tgzlangsmith-auth-proxy-0.0.5
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.5.tgzlangsmith-auth-proxy-0.0.4
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.4.tgzlangsmith-0.13.26
- Internal improvements and maintenance updates
langsmith-0.13.26.tgzlangsmith-0.13.25
- Internal improvements and maintenance updates
langsmith-0.13.25.tgzlangsmith-auth-proxy-0.0.3
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.3.tgzlangsmith-0.13.24
- Internal improvements and maintenance updates
langsmith-0.13.24.tgzlangsmith-observability-0.2.0
- Internal improvements and maintenance updates
langsmith-observability-0.2.0.tgzlangsmith-auth-proxy-0.0.2
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.2.tgzlangsmith-0.13.23
- Internal improvements and maintenance updates
langsmith-0.13.23.tgzlangsmith-0.13.21
- Internal improvements and maintenance updates
langsmith-0.13.21.tgzlangsmith-0.13.20
- Internal improvements and maintenance updates
langsmith-0.13.20.tgzlangsmith-0.13.19
- Internal improvements and maintenance updates
langsmith-0.13.19.tgzlangsmith-0.13.18
- Internal improvements and maintenance updates
langsmith-0.13.18.tgzlangsmith-0.13.17
- Internal improvements and maintenance updates
langsmith-0.13.17.tgzlangsmith-0.13.16
- Internal improvements and maintenance updates
langsmith-0.13.16.tgzlangsmith-0.13.15
- Internal improvements and maintenance updates
langsmith-0.13.15.tgzlangsmith-0.13.14
- Internal improvements and maintenance updates
langsmith-0.13.14.tgzlangsmith-auth-proxy-0.0.1
- Internal improvements and maintenance updates
langsmith-auth-proxy-0.0.1.tgzlangsmith-0.13.13
- Internal improvements and maintenance updates
langsmith-0.13.13.tgzlangsmith-0.13.12
- Internal improvements and maintenance updates
langsmith-0.13.12.tgzlangsmith-0.13.11
- Internal improvements and maintenance updates
langsmith-0.13.11.tgzlangsmith-0.13.10
- Internal improvements and maintenance updates
langsmith-0.13.10.tgzlangsmith-0.13.9
- Internal improvements and maintenance updates
langsmith-0.13.9.tgzlangsmith-0.13.7
- Internal improvements and maintenance updates
langsmith-0.13.7.tgzlangsmith-0.13.6
- Internal improvements and maintenance updates
langsmith-0.13.6.tgzlangsmith-0.13.5
- Internal improvements and maintenance updates
langsmith-0.13.5.tgzlangsmith-0.13.4
- Internal improvements and maintenance updates
langsmith-0.13.4.tgzlangsmith-0.13.3
- Internal improvements and maintenance updates
langsmith-0.13.3.tgzlangsmith-0.13.2
- Internal improvements and maintenance updates
langsmith-0.13.2.tgzlangsmith-0.13.1
- Internal improvements and maintenance updates
langsmith-0.13.1.tgzlangsmith-0.13.0
- Internal improvements and maintenance updates
langsmith-0.13.0.tgzlangsmith-0.12.37
- Internal improvements and maintenance updates
langsmith-0.12.37.tgzlangsmith-0.12.36
- Internal improvements and maintenance updates
langsmith-0.12.36.tgzlangsmith-0.12.35
- Internal improvements and maintenance updates
langsmith-0.12.35.tgzlangsmith-0.12.34
- Internal improvements and maintenance updates
langsmith-0.12.34.tgzlangsmith-0.12.33
- Internal improvements and maintenance updates
langsmith-0.12.33.tgzlangsmith-0.12.32
- Internal improvements and maintenance updates
langsmith-0.12.32.tgzlangsmith-0.12.31
- Internal improvements and maintenance updates
langsmith-0.12.31.tgzlangsmith-0.12.30
- Internal improvements and maintenance updates
langsmith-0.12.30.tgzlangsmith-0.12.29
- Internal improvements and maintenance updates
langsmith-0.12.29.tgzlangsmith-0.12.28
- Internal improvements and maintenance updates
langsmith-0.12.28.tgzlangsmith-0.12.27
- Internal improvements and maintenance updates
langsmith-0.12.27.tgzlangsmith-0.8.30
- Internal improvements and maintenance updates
langsmith-0.8.30.tgzlangsmith-0.12.25
- Internal improvements and maintenance updates
langsmith-0.12.25.tgzlangsmith-0.12.24
- Internal improvements and maintenance updates
langsmith-0.12.24.tgzlangsmith-0.12.23
- Internal improvements and maintenance updates
langsmith-0.12.23.tgzlangsmith-0.12.22
- Internal improvements and maintenance updates
langsmith-0.12.22.tgzlangsmith-0.12.21
- Internal improvements and maintenance updates
langsmith-0.12.21.tgzlangsmith-0.12.20
- Internal improvements and maintenance updates
langsmith-0.12.20.tgzlangsmith-0.12.19
- Internal improvements and maintenance updates
langsmith-0.12.19.tgzlangsmith-0.15.0-rc.6
- Fixed “Enabled” column header that was being cut off in the Automations tab.
- Fixed Polly chat button icon getting stuck to the cursor when clicked near the button’s bounding box.
- Fixed a bug where creating or editing files in the file browser during an active “needs approval” interrupt caused the interrupt to disappear.
- Audit Logs: Self-hosted now uses go queue by default.
- Enforced LLM Auth Proxy URL allowlist for Polly.
- Composite feedback columns in the experiment view displayed as flat columns with sub-score visibility toggles in the column menu.
- Evaluator API responses now included a
created_byfield showing who created each evaluator, and the evaluators table UI displayed a “Created By” column. - Migrated to add a fleet-admin:read permission.
- Auth interrupt dialog now showed two options: authenticate with all provider scopes (primary) or just the requested scope (secondary).
- Salesforce tool integration was gated behind a feature flag and hidden by default until enabled per-tenant.
- Evaluators table now supported filtering by feedback key and resource (project/dataset).
- Added an experimental async subagents feature allowing subagent threads to not block fleet agent executions.
- Fixed infinite scroll in data tables requiring a scroll-up-and-back-down to load subsequent pages.
- Added a feedback banner on the evaluators page to collect user feedback on the reusable evaluators launch.
- Fixed a bug where SSO users with multiple provider records received 403 errors when their identity provider session lacked SAML metadata.
- Fixed evaluator filter badge icons showing as black/white instead of blue in light/dark mode.
- Oversized feedback fields were now gracefully truncated or dropped instead of rejecting the entire feedback entry.
- Polly now read and respected the active filter on the runs page, merging new conditions rather than replacing user-set filters.
- Fixed evaluators table column dropdown showing “feedback_keys” instead of “Feedback Key”.
- Fixed Insights clustering jobs failing on retry with UniqueViolationError by making insert operations idempotent.
- Removed the “Re-run from here” button from the Agent Builder editor chat interface.
- Evaluators created from the playground now correctly tracked who created them.
- Feedback key filter on evaluators table now showed a searchable dropdown of existing keys instead of a freeform text input.
- Added instance admin endpoint (
POST /v1/platform/ops/backfills/restart) to restart backfill jobs and introducedINSTANCE_ADMIN_EMAILSenv var (replaces deprecatedUSAGE_EXPORT_ADMIN_EMAILS). - Improved handling of custom log formats when streaming logs from the LangSmith Deployment data plane.
- Fixed a JS error when viewing experiment results in the onboarding quickstart flow.
- Added application tag support to evaluators.
- Fixed missing icons and display names for OAuth providers on non-standard deployments.
- Fixed a false “used in other resources” warning when editing a reused evaluator from the only resource it was attached to.
- The experiment comparison delta stream endpoint now supported per-session filters, enabling the comparison table to scope feedback deltas to a filtered subset of runs.
- Fixed Microsoft OAuth repeatedly prompting for consent on every connection attempt even after admin consent was granted.
- Fixed agent clone button not appearing for users with edit access to a shared agent.
- Enabled granular rollup and cleanup jobs that showed daily granularity for granular trace usage.
- Chat messages now scrolled to the top of the viewport when sent, matching the UX of ChatGPT and Claude.
- Evaluator pages now respected application tags consistently, including evaluators surfaced through tagged datasets and tracing projects.
- Google Calendar tools now accepted an optional
calendar_idparameter to read or manage other users’ calendars within the same Google Workspace organization. - Insights “Run now” failures (e.g., invalid API key) now surfaced as an error toast instead of silently disappearing.
- Fixed Microsoft integration accounts always showing “Additional permissions needed to lookup email” even after reauthorizing.
- The evaluator sample-data selector now only showed datasets and tracing projects in the currently selected application.
- Fixed a self-hosted issue where changing Fleet access controls could fail with a 405 error.
- Fixed a bug where users with “can run” permissions on an agent could modify the agent’s files through the hub backend.
- Enabled SSRF protection on all Playground touchpoints. Disabled by default in self-hosted environments.
- Added X (Twitter) integration with BYO OAuth — 17 tools for posting, searching, monitoring mentions, managing follows, and more. Existing API-key-based Twitter tools are preserved but deprecated.
- Added a public Go endpoint for fetching comparison view runs on shared datasets, enabling the shared dataset comparison table to use the Go backend when the
experiments_use_smithdbflag is on. - Clicking a workspace agent card now opened the chat view instead of the editor.
- Fixed multiple-resource filter on the Evaluators page to use AND logic (only show evaluators attached to all selected resources).
- Agents could now have custom icons and colors, selectable from the editor header.
- Fixed a bug where SCIM user updates from IDPs with different email casing were incorrectly rejected as email change attempts.
- Added fleet-admin:read permission to gate the new Fleet Admin section.
- The batch trace messages endpoint (
POST /v2/traces/messages) addedfeedback_statsper trace, eliminating the need to also query the runs endpoint for feedback data. - Improved log signal-to-noise ratio in the Deployments UI (filtered out logs from an internal server process).
- Improved playground lag on keystroke caused by per-keystroke re-renders of the entire prompt editor component tree.
- Agentify banner in the agent builder chat could again be dismissed with an X button.
- Fixed “View source run” on evaluator traces showing an Invalid trace ID error for dataset-scoped evaluators.
- Improved Agent Builder chat streaming by migrating it to the new React SDK and normalizing streamed LangGraph message handling.
- Markdown tables in Fleet chat rendered with rounded corners, styled headers, and copy/download-as-CSV buttons.
- “View source run” on evaluator traces now worked for dataset-scoped evaluators (previously it produced an Invalid trace ID page).
- Replaced the pre-run Python fetch script with direct CLI calls driven by the agent. Requires langsmith-cli ≥ v0.2.17.
- Cleaner styling and responsive behavior on the issue detail page, with a link-out to GitHub for diff file paths in the Proposed Fix section.
- Running sandbox snapshots now preserved live filesystem changes when restoring a new sandbox.
- Self-hosted: enabled ABAC and audit-logs.
- Sandbox uploads larger than 10 MiB now streamed through the router instead of failing with
Failed to read request body. - Cron schedule triggers now supported attaching skills via the same
/menu used in chat, so agents run specific skills on each trigger. - Fixed: annotation queue run rules no longer write runs to queues in a different workspace.
- Issues-board “Create Evaluator” now opened the same Configure Evaluator pane as the rest of the app, with the issue’s suggested name and prompt prefilled.
- Introduced new inline filter design.
- Fixed evaluator detail page traces/runs toggle reverting to “Traces” when a row is clicked.
- Fleet agents could now generate HTML slide decks that render natively in the in-app presentation viewer, no setup required.
- Issues-board-ao prompt now guided the agent toward fewer, broader subagent calls — screening inline on small scans, consolidating investigation subagents across related categories — reducing cost on large scans.
- GitHub App integration for agent builder — connected GitHub accounts via App installations for repo access.
- Fixed: the “Run a skill” browser in cron schedule dialogs now lets you pick a skill.
- Fixed a bug where newly created tracing projects could be missing from dashboard project selection when Go sessions routing was enabled.
- Slide presentation mode for HTML files is now available for all FLEET users.
- Rolled back the issues-board-ao Phase 1b prompt changes that caused the agent to undersample traces.
- Fixed LLM evaluators getting stuck with
llm_evaluator.commit_hash_or_tag not foundon save when the stored commit reference was a short commit-hash prefix. - Evaluator prompt handles no longer included the parent dataset or session name, so moving an evaluator between containers did not leave a stale reference in its prompt handle.
- Showed a clear message when a user without
workspaces:manageclicked Install GitHub App, instead of failing silently. - Issues board now supported BYOK Anthropic API key — configured your own key via the settings pane.
- Allowed workspace members to manage their own GitHub App connection (disconnect, switch actor preference) without requiring
workspaces:manage. - Issues-board-ao Phase 1b screening now used the new
trace messagestrajectory (input/output preview + step summary) as the first read per trace, only opening the full conversation when trajectory-level signals were ambiguous, reducing screening cost without changing coverage. - Fixed issue update API to accept
nameanddescriptionfields, allowing the CLI--titleand--descriptionflags to work correctly. - Fixed service account API keys listing extra workspaces the parent service account could reach.
- Subagent cards now rendered at the point they were invoked in the trace view instead of being grouped after all tool calls.
- Optimized sampled run rule queries for self-hosted customers.
- Fixed layout of the few-shot corrections config on the evaluator page so the template description read as one flowing sentence instead of breaking into stacked columns.
- Fixed Playground model chip not updating after changing provider in Model Configuration.
- Fixed agent-builder chat freezing and repeated “Maximum update depth exceeded” errors when multiple sub-agents streamed in parallel on long threads.
- Fixed an issue where reloading the threads page with a selected thread did not correctly scroll the tree to the correct turn and did not show the correct turn number in the trace/turn view.
- Optimized run facet queries for self-hosted users via pre-aggregation.
- Memory updates showed semantic labels with distinct icons, and the approval card supported per-file collapsible diffs with an “Always approve” option.
- Correcting a feedback wouldn’t update the chip, just the popover. This fix updated both.
- User-flagged traces in projects with an issues agent were now automatically added to a project-specific and tenant-global annotation queue for review.
- Google Drive and Google Meet integration cards now appeared on the Agent Builder integrations page.
- Fixed smithdb ingestion stream protocol error (
h2 protocol error: error reading a body from connection) caused by abrupt stream cancellation in asynq workers. - Added
Thread Id(if present) to the trace id click to copy tooltip. - Prevented dataset-attached evaluators from being saved with thread grouping in the frontend.
- Fixed a 500 error on example creation.
langsmith-0.15.0-rc.6.tgzlangsmith-0.15.0-rc.5
- Fixed the “Enabled” column header being cut off in the Automations tab.
- Fixed the Polly chat button icon getting stuck to the cursor when clicking near the button’s bounding box.
- Fixed a bug where creating or editing files in the file browser during an active “needs approval” interrupt would cause the interrupt to disappear.
- Audit Logs: Self-hosted now uses go queue by default.
- Enforced LLM Auth Proxy URL allowlist for Polly.
- Composite feedback columns in the experiment view now displayed as flat columns with sub-score visibility toggles in the column menu.
- Evaluator API responses now included a
created_byfield showing who created each evaluator, and the evaluators table UI displayed a “Created By” column. - Migration added a fleet-admin:read permission.
- Auth interrupt dialog now showed two options: authenticate with all provider scopes (primary) or just the requested scope (secondary).
- Salesforce tool integration is now gated behind a feature flag and hidden by default until enabled per-tenant.
- Evaluators table now supported filtering by feedback key and resource (project/dataset).
- Added an experimental async sub-agent feature that allows sub-agent threads to not block fleet agent executions.
- Fixed infinite scroll in data tables requiring a scroll-up-and-back-down to load subsequent pages.
- Added a feedback banner on the evaluators page to collect user feedback on the reusable evaluators launch.
- Fixed a bug where SSO users with multiple provider records received 403 errors when their identity provider session lacked SAML metadata.
- Fixed evaluator filter badge icons showing as black/white instead of blue in light/dark mode.
- Oversized feedback fields are now gracefully truncated or dropped instead of rejecting the entire feedback entry.
- Polly now read and respected the active filter on the runs page, merging new conditions rather than replacing user-set filters.
- Fixed the evaluators table column dropdown showing “feedback_keys” instead of “Feedback Key”.
- Fixed Insights clustering jobs failing on retry with UniqueViolationError by making insert operations idempotent.
- ABAC: Added remaining
/sessions/{session_id}/endpoints. - Removed the “Re-run from here” button from the Agent Builder editor chat interface.
- Evaluators created from the playground now correctly tracked who created them.
- Feedback key filter on evaluators table now showed a searchable dropdown of existing keys instead of a freeform text input.
- Added instance admin endpoint (
POST /v1/platform/ops/backfills/restart) to restart backfill jobs. IntroducedINSTANCE_ADMIN_EMAILSenv var (replacing deprecatedUSAGE_EXPORT_ADMIN_EMAILS). - Improved handling of custom log formats when streaming logs from the LangSmith Deployment data plane.
- Fixed a JS error when viewing experiment results in the onboarding quickstart flow.
- Added application tag support to evaluators.
- Fixed missing icons and display names for OAuth providers on non-standard deployments.
- Fixed a false “used in other resources” warning that appeared when editing a reused evaluator from the only resource it was attached to.
- The experiment comparison delta stream endpoint now supports per-session filters, enabling the comparison table to scope feedback deltas to a filtered subset of runs.
- Fixed Microsoft OAuth repeatedly prompting for consent on every connection attempt even after admin consent was granted.
- Fixed agent clone button not appearing for users with edit access to a shared agent.
- Enabled granular rollup and cleanup jobs that show daily granularity for granular trace usage.
- Chat messages now scroll to the top of the viewport when sent, matching the UX of ChatGPT and Claude.
- Evaluator pages now respect application tags consistently, including evaluators surfaced through tagged datasets and tracing projects.
- Google Calendar tools now accept an optional
calendar_idparameter to read or manage other users’ calendars within the same Google Workspace organization. - Insights “Run now” failures (e.g., invalid API key) now surface as an error toast instead of silently disappearing.
- Fixed Microsoft integration accounts always showing “Additional permissions needed to lookup email” even after reauthorizing.
- The evaluator sample-data selector now only shows datasets and tracing projects in the currently selected application.
- Fixed a self-hosted issue where changing Fleet access controls could fail with a 405 error.
- Fixed a bug where users with “can run” permissions on an agent could modify the agent’s files through the hub backend.
- Enabled SSRF protection on all Playground touchpoints, disabled by default in self-hosted environments.
- Added X (Twitter) integration with BYO OAuth — 17 tools for posting, searching, monitoring mentions, managing follows, and more. Existing API-key-based Twitter tools are preserved but deprecated.
- Added a public Go endpoint for fetching comparison view runs on shared datasets, enabling the shared dataset comparison table to use the Go backend when the
experiments_use_smithdbflag is on. - Clicking a workspace agent card now opens the chat view instead of the editor.
- Fixed multiple-resource filter on the Evaluators page to use AND logic, showing only evaluators attached to all selected resources.
- Agents can now have custom icons and colors, selectable from the editor header.
- Fixed a bug where SCIM user updates from IDPs with different email casing were incorrectly rejected as email change attempts.
- Added fleet-admin:read permission to gate the new Fleet Admin section.
- Fixed an error when creating custom code evaluators from a dataset that use
perform_eval(run, example)with two arguments. - CSV export for the experiment comparison view now routes through the Go backend when the
experiments_use_smithdbflag is enabled, streaming up to 10,000 rows with per-session and feedback key columns. - Fixed workspace-agent navigation so read-only users can reach the editor and clone shared agents, and added hover-panel action buttons for agent cards.
- Agent Builder: HTML file previews now detect slides and offer a presentation mode with thumbnail navigation and fullscreen viewing.
- Added
projects:increase-trace-tierandprojects:decrease-trace-tierpermissions replacingprojects:update-retentionfor granular control over project trace retention changes. - Unified files sidebar is now enabled for all tenants in Agent Builder chat.
- CSV export for experiments now includes per-annotator feedback detail (score, value, comment, user) when the “include annotator detail” option is selected.
- Filters in progress on the tracing and threads pages are now preserved when clicking away from the filter popover and reopening it.
- Hamburger menu is now hidden when inbox history is open.
- Hardened built-in integrations access controls so ABAC-allowed tools stay available and unauthorized tool execution is blocked.
- Fixed CSV file upload when creating a dataset in self-hosted and split data plane deployments.
- Fleet usage dashboard now tracks agent names on run metadata for display alongside agent IDs.
- Fleet usage API now returns agent names alongside agent IDs.
- Issue board linked traces now show a short summary of why each trace is evidence for the issue.
- Fixed a bug where numeric metadata values were silently dropped during ingestion for large metadata values when blob storage was enabled, causing metadata filtering to return no results for affected runs.
- Clicking the back arrow on evaluator details now returns to the tracing project or dataset you came from, instead of always going to the global evaluators list.
- Fixed a bug where hiding the Outputs column had no effect on single-experiment views without saved column configuration.
- Context canceled errors on run query endpoints are now classified as 499 (client closed) instead of 500, reducing false alerts.
- Users can now view and assign resource tags to integrations and MCP servers in Settings.
- Issues board proposed fix now renders diff blocks with GitHub-style line highlighting instead of plain text.
- Issues agent now requires at least two example traces before creating an issue and will look further back in history to find corroborating evidence when only one trace is found.
- Issues board suggested evaluators now include both Python and JavaScript versions, and switching languages in the evaluator editor preserves the suggested code.
- New
GET /v1/platform/orgs/current/membersendpoint returning paginated org members (active and pending) with per-workspace roles and glob filtering. - Fleet usage dashboard now displays agent names alongside agent IDs.
- Code evaluators that return
{"score": value}or{"value": value}(with optional “comment”) without a named key now display the evaluator name as their feedback key instead of “score” or “value.” - Added a setup-guide banner in the Salesforce integration dialog to help users prepare for the admin install step before connecting.
- Fixed a bug where rows with no feedback results in the experiment comparison table would show a loading spinner indefinitely instead of showing “No feedback.”
- Fixed the workspace integrations access-control message to reference the correct
workspaces:managepermission. - Fixed evaluator configuration pane back arrow showing prebuilt evaluators instead of closing.
- Improved issue board UI with better empty states, loading skeletons, consistent timestamps, and visual polish.
POST /workspaces/current/membersnow requiresrole_idfor RBAC-enabled organizations. Requests without it return 400 instead of defaulting toWORKSPACE_ADMIN.- Issue board issues now always include a suggested evaluator.
- Users can now flag traces for issues agent review directly from the trace detail view.
- After forking an evaluator, you are now redirected to the new evaluator’s page with a confirmation toast.
- Added filtering (by priority, status, tags) and sorting (by severity, last updated, created) to the issue board.
- Audit logs now capture dataset download events (
download_dataset) separately from generic dataset reads, applying to all export formats (CSV, JSONL, OpenAI, OpenAI FT). - Fixed duplicate tracing projects appearing in the projects list.
- Salesforce tool integration is now available to all tenants (no longer gated behind a feature flag).
- Fixed dataset experiment LLM calls failing when the customer’s auth proxy requires a non-empty JWT
subclaim. - Fixed a bug where the Hallucination prebuilt evaluator would crash with a KeyError when its prompt template contained variables not covered by the variable mapping.
- Traces flagged for issues agent review are now automatically added to a project-specific annotation queue for team review and test harness creation.
- GitHub links in the datasets table now support right-click to open in a new tab or copy the link address.
- Issues now record an
open_prevent when a user opens a PR, enabling full PR lifecycle tracking in the issue activity timeline. - Members API (
GET /v1/platform/orgs/current/members) now includeslinked_login_methods(auth provider info) andscim_groups(SCIM group memberships) on each member. - ABAC for runs:create on the POST /runs endpoint.
- Skills Library can now be served from the template API behind the
fleet_template_apifeature flag. No user-visible behavior change on either side of the flag — the flag is OFF by default. - Polly now uses the built-in time range picker for time-based queries instead of embedding absolute timestamps in the filter string.
- Agent Templates page now loads templates from the new template API and auto-installs any required skills when creating an agent from a template — both from the templates page directly and from agents generated through the GPA chat. Behind feature flag during rollout.
- Enforce directional trace tier permissions: users need
projects:increase-trace-tierto raise retention andprojects:decrease-trace-tierto lower it. - Dataset description tooltips in the table now only appear when the text is actually truncated, and show formatted GitHub links when they do.
- Dataset detail page description tooltips now render GitHub links with a clickable icon, matching the table view.
- Bulk export destinations now support
config_kwargs_s3for configuring S3 addressing style, fixing compatibility with S3-compatible services that require virtual-hosted addressing (e.g., Volcengine TOS). - Annotation queues list view now supports sorting by name, total runs, updated at, and created at columns.
- Enterprise SSO users can now log in from the main login page by entering their email, without needing their organization’s SSO URL.
- ABAC: runs:create for POST /runs/batch.
- The batch trace messages endpoint (
POST /v2/traces/messages) now returnsfeedback_statsper trace, eliminating the need to also query the runs endpoint for feedback data. - Improved log signal-to-noise ratio in the Deployments UI (filters out logs from an internal server process).
- Improves playground lag on keystroke caused by per-keystroke re-renders of the entire prompt editor component tree.
- Agentify banner in agent builder chat can again be dismissed with an X button.
- Fixed “View source run” on evaluator traces showing an Invalid trace ID error for dataset-scoped evaluators.
- Improved Agent Builder chat streaming by migrating it to the new React SDK and normalizing streamed LangGraph message handling.
- Markdown tables in Fleet chat now render with rounded corners, styled headers, and copy/download-as-CSV buttons.
- “View source run” on evaluator traces now works for dataset-scoped evaluators (previously it produced an Invalid trace ID page).
- Replaced the pre-run Python fetch script with direct CLI calls driven by the agent. Requires LangSmith-CLI ≥ v0.2.17.
- Cleaner styling and responsive behavior on the issue detail page, with a link-out to GitHub for diff file paths in the Proposed Fix section.
- Running sandbox snapshots now preserve live filesystem changes when restoring a new sandbox.
- Sandbox uploads larger than 10 MiB now stream through the router instead of failing with
Failed to read request body. - Cron schedule triggers now support attaching skills via the same
/menu used in chat, so agents run specific skills on each trigger. - Annotation queue run rules no longer write runs to queues in a different workspace.
- Issues Board “Create Evaluator” now opens the same Configure Evaluator pane as the rest of the app, with the issue’s suggested name and prompt prefilled.
- Introduced new inline filter design.
- Fix evaluator detail page traces/runs toggle reverting to “Traces” when a row is clicked.
- Fleet agents can now generate HTML slide decks that render natively in the in-app presentation viewer, no setup required.
- Issues-board-ao prompt now guides the agent toward fewer, broader sub-agent calls — screening inline on small scans, consolidating investigation sub-agents across related categories, reducing cost on large scans.
- GitHub App integration for Agent Builder — connect GitHub accounts via App installations for repo access.
- The “Run a skill” browser in cron schedule dialogs now lets you actually pick a skill.
- Fixed a bug where newly created tracing projects could be missing from dashboard project selection when Go sessions routing was enabled.
- Slide presentation mode for HTML files is now available for all FLEET users.
- Fixed LLM evaluators getting stuck with
llm_evaluator.commit_hash_or_tag not foundon save when the stored memory reference is a short commit-hash prefix. - Evaluator prompt handles no longer include the parent dataset or session name, so moving an evaluator between containers does not leave a stale reference in its prompt handle.
- Showed a clear message when a user without
workspaces:manageclicks Install GitHub App, instead of failing silently. - Issues board now supports BYOK Anthropic API key — configure your own key via the settings pane.
- Allow workspace members to manage their own GitHub App connection (disconnect, switch actor preference) without requiring
workspaces:manage. - Issues-board-ao Phase 1b screening now uses the new
trace messagestrajectory (input/output preview + step summary) as the first read per trace, only opening the full conversation when trajectory-level signals are ambiguous, reducing screening cost without changing coverage. - Fixed issue update API to accept
nameanddescriptionfields, allowing the CLI--titleand--descriptionflags to work correctly. - Fixed service account API keys listing extra workspaces the parent service account could reach.
- Sub-agent cards now render at the point they were invoked in the trace view instead of being grouped after all tool calls.
- Optimized sampled run rule queries for self-hosted customers.
- Fixed layout of the few-shot corrections config on the evaluator page so the template description reads as one flowing sentence instead of breaking into stacked columns.
- Fixed Playground model chip not updating after changing provider in Model Configuration.
- Fixed agent-builder chat freezing and repeated “Maximum update depth exceeded” errors when multiple sub-agents stream in parallel on long threads.
- Fixed an issue where reloading the threads page with a selected thread did not correctly scroll the tree to the correct turn and did not show the correct turn number in the trace/turn view.
- Optimized run facet queries for self-hosted users via pre-aggregation.
- Memory updates show semantic labels with distinct icons, and the approval card supports per-file collapsible diffs with an “Always approve” option.
- Correcting feedback now updates both the chip and the popover.
- User-flagged traces in projects with an issues agent are now automatically added to a project-specific and tenant-global annotation queue for review.
- Fixed smithdb ingestion stream protocol error (
h2 protocol error: error reading a body from connection) caused by abrupt stream cancellation in asynq workers. - Added
Thread Id(if present) to the trace ID click-to-copy tooltip. - Prevented dataset-attached evaluators from being saved with thread grouping in the frontend.
- Fixed a 500 error on example creation.
- Fixed a bug where issues board suggested Python code evaluators failed with
AttributeErrordue to incorrect attribute-style access on run dicts.
langsmith-0.15.0-rc.5.tgzlangsmith-0.15.0-rc.4
- Added support for new UI features including a redesigned evaluator settings section and issue board interface.
- Improved performance and UI responsiveness across various components including the evaluator interfaces and tracing projects.
- Fixed several UI bugs affecting the display and behavior of feedback, evaluator tabs, tracing identifiers, amongst others.
- Added new integrations including support for Google workspace tools and Anthropic APIs within the agent builder.
- Enhanced security and authentication measures with features like audit logging for sensitive data and improved SSO login functionality.
- Introduced new API endpoints to support features like org-based exclusion for time window enforcement and managing self-hosted licenses.
- Enabled performance improvements through optimizations in session syncing and experiments sync processes.
- Added functionality to track consumption and spending within fleet projects, including an interactive usage dashboard with CSV export capabilities.
- Released updates to allow custom, tenant-specific API keys and OAuth flows for platform integrations and execution contexts.
langsmith-0.15.0-rc.4.tgzlangsmith-0.14.5
- Internal improvements and maintenance updates
langsmith-0.14.5.tgzlangsmith-0.15.0-rc.3
- Internal improvements and maintenance updates
langsmith-0.15.0-rc.3.tgzlangsmith-0.14.4
- Fixed an issue in the playground where the environment was being polluted by an older version of a dependency.
langsmith-0.14.4.tgzlangsmith-0.14.3
- Internal improvements and maintenance updates
langsmith-0.14.3.tgzlangsmith-0.15.0-rc.2
- Improved the ‘Enabled’ column in the automations table to prevent header truncation.
- Fixed the “polly” button icon from sticking to the cursor on click.
- Made the MCP server filter dropdown scrollable in the fleet.
- Added sorting to the evaluator’s table with ‘created’ and ‘updated at’ fields.
- Implemented fallback to LANGSMITH_AUTH_ENDPOINT for workspace in “polly”.
- Fixed file creation from clearing the active interrupt state in the fleet.
- Added URL allowlist enforcement for JWT injection in “polly”.
- Added user cost table and agent/user toggle in the fleet.
- Added new fleet-admin:read permission.
- Improved loading performance by removing unnecessary joins from session stats queries.
- Added analytics tracking for template/card selection in the frontend.
- Added timestamps and improved layout for issue board UI.
- Fixed bug causing the evaluator reuse playground to malfunction.
- Added PostgreSQL mTLS support for migrations.
- Added support for mCP servers with composable databases.
- Enhanced security by handling non-SSO login for users with multiple SSO provider records.
- Made evaluator source-run link resilient against invalid IDs.
- Added evaluator details page UX improvements.
- Added mobile-friendly login and installable PWA support.
- Improved overall UX in the evaluator tab with a carousel of suggested evaluators.
- Enabled audit logging for sensitive data access endpoints.
- Added session/dataset activity tracking in Redis for run rules to SmithDB.
- Added tracing project and usage dashboard for fleet projects.
- Added “create agent manually” button to the navbar in the Agent Builder section.
- Fixed rendering issue of tool calls in message view.
- Improved session sync performance to prevent idle sessions.
- Added new model support (Opus 4.7, GLM5, and minimax 2.5) for agent evaluation.
- Improved evaluator fork and usage UX in the frontend.
- Reduced unnecessary re-renders in the playground to improve performance.
- Enabled ‘wrap experiment quickstart’ with ComparisonStoreProvider to address UI bugs.
- Introduced new endpoint to update self-hosted licenses.
- Optimized idle session processing with performance improvements.
- Added audit logging for all remaining Go write endpoints.
- Enhanced “byoc” support with new verification mechanisms and separation of Python service routes.
langsmith-0.15.0-rc.2.tgzlangsmith-0.15.0-rc.1
- Fixed truncation issue by widening the ‘Enabled’ column in the automations table for better header visibility.
- Updated details view header for improved user experience.
- Improved performance by removing dead run_stats_facets join from session stats queries.
- Fixed MCP server filter dropdown to make it scrollable.
- Added ‘user cost’ table and toggle for agent/user view in the fleet.
- Enhanced security by adding URL allowlist enforcement for JWT injection.
- Added ability to sort evaluators by creation and update time in the backend.
- Added ‘Feedback Key’ filtering in the evaluators table for more precise searches.
- Showed back button on the full-page trace view to enhance navigation.
- Fixed audit-logs and various performance improvements for lower latency.
- Enhanced UI by showing ‘Feedback Key’ in evaluator column dropdown.
- Added session insights, views, metadata, and dashboard endpoints to improve data accessibility.
- Fixed file creation issues to prevent active interrupt state clearance.
- Provided async support for agents in the fleet to improve reliability.
- Fixed issues with agent cloning that previously caused flow issues.
- Added spend limit enforcement and the ability to track usage, enhancing cost management features.
- Made more efficient use of resources with new skill memory-store mirror updates in fleets.
- Improved evaluator reuse UX for users with better management of evaluator actions on issue generation.
- Enhanced security features by preventing sub-agents from triggering unauthorized actions.
- Optimized memory and resource management in the agent builder chat.
- Improved evaluator trace detail navigation by preserving search model in URLs.
- Upgraded per-environment favicon colors for clarity in staging and dev environments.
- Performance improvements in session sync reducing resource usage.
- Added default agent name support in usage dashboard for clarity in report generation.
- Made UI improvements to evaluator details for a smoother experience.
- Enabled auto-wake and auto-stop for Sandbox environments to save resources.
- Integrated tracing tool functionality in issue creation for better context and reliability.
- Added “create agent manually” button to navigation for easier agent management.
- Enhanced memory management tools UI for better approval process visualization.
- Fixed tool usage table and improved its performance for a better UX.
- Enabled auditing for sensitive data access endpoints for enhanced security compliance.
- Improved tracing project name display in usage dashboard for better project clarity.
- Introduced keyboard shortcuts in the editor page for rapid interaction.
- Set default MSP cron schedule as standard to reduce manual setup effort.
- Added integration user flow with prompt messages for smooth operation and understanding.
- Fixed default tracing project selection to Fleet to prevent inconsistencies.
langsmith-0.15.0-rc.1.tgzlangsmith-0.14.2
- Internal improvements and maintenance updates
langsmith-0.14.2.tgzlangsmith-0.14.1
- Fixed an issue where the system looked back further to determine Redis eligibility, improving reliability in self-hosted environments.
langsmith-0.14.1.tgzlangsmith-0.14.0
LangSmith Self-Hosted v0.14 brings Polly (our AI assistant for traces and runs) to self-hosted, takes ABAC and audit logs GA (on by default), and enables the LLM Auth Proxy by default with URL allowlisting and richer JWT claims. Admins get unified model configurations shared across Agent Builder, Polly, Insights, Playground, and Evaluators, and fine-grained Prompt Owners for locking down who can promote or delete individual prompts. Evaluators gain multi-modal support and workspaces can now set cost alerts on tracing projects. Playground model support expands (Anthropic via Vertex AI, custom Azure models, Bedrock inference profiles, Gemini 3.1 Pro, GPT-5.3 / 5.4, Baseten + GLM-5), and new agent tools and triggers land for Google Sheets & Docs, Outlook, Teams, and Salesforce SOQL. On the infrastructure side, v0.14 adds GCS Workload Identity support for blob storage, Valkey as a drop-in Redis replacement, and a pre-upgrade migration hook for safer rollouts.Follow the upgrade instructions to get access to everything. To book time with LangChain support for your upgrade, contactsupport@langchain.dev.Breaking changes
- Fixed an issue where
host-backendwasn’t picking upcommonEnv. This may result in duplicate environment variables that need to be removed.
Infrastructure changes
- Migrations now run as a
Pre-upgradehook prior to image versions rolling out. This will prevent issues when migrations fail. - GCS Workload Identity support — authenticate to GCS blob storage using cloud-native workload identity instead of long-lived credentials.
- Valkey support — Valkey can now be used as a drop-in replacement for Redis.
New features
- Polly on self-hosted — our AI assistant for understanding traces, runs, and evaluator feedback is now available in self-hosted.
- ABAC and audit logs GA — Attribute-Based Access Control and audit logs are enabled by default for self-hosted deployments.
- LLM Auth Proxy on by default — URL allowlist prevents credential forwarding to unintended hosts, and JWTs now carry
organization_nameandworkspace_nameclaims. - Unified model configurations — Agent Builder, Polly, Insights, Playground, and Evaluators now share a single set of model configs, with workspace-admin controls over model access across all AI features.
- Prompt Owners — designate a specific group of users with fine-grained permission to promote or delete individual prompts, without granting broader org access.
- Multi-modal evaluators — pass attachments and base64 content (images, audio, PDFs) directly into evaluators.
- Cost alerts on tracing projects — set alerts on tracing project-level costs alongside existing LangSmith alerts.
- Expanded playground model support — Anthropic via Vertex AI, custom Azure models, Bedrock inference profiles and configurable base URLs, Gemini 3.1 Pro, GPT-5.3 / 5.4 (now default), and Baseten + GLM-5.
- New agent tools and triggers — Google Sheets and Docs, Outlook mail and calendar, Microsoft Teams, Salesforce SOQL, Gmail OAuth v2 with refresh tokens, and an Outlook Trigger.
- Insights enhancements — scheduled Insights reports, categories trending over time, full feedback comments in analysis, and a lower minimum job interval (6h → 1h).
- Annotation and review upgrades — required reviewers per queue, pairwise queues that honor
reviewer_access_mode, an “Assigned to me” filter, per-annotator CSV export, and bulk table actions. - Prompt Hub and tool registry — commit tag search, model select in template creation, a workspace-scoped tool registry API, and a private registry UI.
- Evaluator workflow improvements — prebuilt LLM evaluators use strict structured outputs by default, evaluators support tagging and reuse, retries no longer lose scores, and a new API runs playground experiments programmatically.
- Custom iframe output renderer — drag-to-resize HTML chart outputs in experiments and trace views.
- Thread and inbox UX — auto-generated thread titles, redesigned run details in threads, session-level feedback stats, keyboard shortcuts, and filtering out internal helper threads.
Admin changes
- Granular usage reporting — granular billable usage APIs that allow you to retrieve detailed trace usage data broken down by workspace, project, user, or API key.
langsmith-0.13.43
- Internal improvements and maintenance updates
langsmith-0.13.43.tgzlangsmith-0.13.42
- Internal improvements and maintenance updates
langsmith-0.13.42.tgzlangsmith-0.13.41
- Internal improvements and maintenance updates
langsmith-0.13.41.tgzlangsmith-0.13.40
- Internal improvements and maintenance updates
langsmith-0.13.40.tgzlangsmith-0.13.39
- Internal improvements and maintenance updates
langsmith-0.13.39.tgzlangsmith-0.13.38
- Internal improvements and maintenance updates
langsmith-0.13.38.tgzlangsmith-0.13.37
- Internal improvements and maintenance updates
langsmith-0.13.37.tgzlangsmith-0.13.36
- Internal improvements and maintenance updates
langsmith-0.13.36.tgzlangsmith-0.13.35
- Internal improvements and maintenance updates
langsmith-0.13.35.tgzlangsmith-0.13.34
- Internal improvements and maintenance updates
langsmith-0.13.34.tgzlangsmith-0.13.33
- Internal improvements and maintenance updates
langsmith-0.13.33.tgzlangsmith-0.13.32
- Internal improvements and maintenance updates
langsmith-0.13.32.tgzlangsmith-0.13.31
- Internal improvements and maintenance updates
langsmith-0.13.31.tgzlangsmith-0.13.30
- Internal improvements and maintenance updates
langsmith-0.13.30.tgzlangsmith-0.13.29
- Internal improvements and maintenance updates
langsmith-0.13.29.tgzlangsmith-0.13.28
- Internal improvements and maintenance updates
langsmith-0.13.28.tgzlangsmith-0.13.27
- Internal improvements and maintenance updates
langsmith-0.13.27.tgzlangsmith-0.13.26
- Internal improvements and maintenance updates
langsmith-0.13.26.tgzlangsmith-0.13.25
- Internal improvements and maintenance updates
langsmith-0.13.25.tgzlangsmith-0.13.24
- Internal improvements and maintenance updates
langsmith-0.13.24.tgzlangsmith-0.13.23
- Internal improvements and maintenance updates
langsmith-0.13.23.tgzlangsmith-0.13.21
- Internal improvements and maintenance updates
langsmith-0.13.21.tgzlangsmith-0.13.20
- Internal improvements and maintenance updates
langsmith-0.13.20.tgzlangsmith-0.13.19
- Internal improvements and maintenance updates
langsmith-0.13.19.tgzlangsmith-0.13.18
- Internal improvements and maintenance updates
langsmith-0.13.18.tgzlangsmith-0.13.17
- Internal improvements and maintenance updates
langsmith-0.13.17.tgzlangsmith-0.13.16
- Internal improvements and maintenance updates
langsmith-0.13.16.tgzlangsmith-0.13.15
- Internal improvements and maintenance updates
langsmith-0.13.15.tgzlangsmith-0.13.14
- Internal improvements and maintenance updates
langsmith-0.13.14.tgzlangsmith-0.13.13
- Internal improvements and maintenance updates
langsmith-0.13.13.tgzlangsmith-0.13.12
- Internal improvements and maintenance updates
langsmith-0.13.12.tgzlangsmith-0.13.11
- Internal improvements and maintenance updates
langsmith-0.13.11.tgzlangsmith-0.13.10
- Internal improvements and maintenance updates
langsmith-0.13.10.tgzlangsmith-0.13.9
- Internal improvements and maintenance updates
langsmith-0.13.9.tgzlangsmith-0.13.7
- Internal improvements and maintenance updates
langsmith-0.13.7.tgzlangsmith-0.13.6
- Internal improvements and maintenance updates
langsmith-0.13.6.tgzlangsmith-0.13.5
- Internal improvements and maintenance updates
langsmith-0.13.5.tgzlangsmith-0.13.4
- Internal improvements and maintenance updates
langsmith-0.13.4.tgzlangsmith-0.13.3
- Internal improvements and maintenance updates
langsmith-0.13.3.tgzlangsmith-0.13.2
- Internal improvements and maintenance updates
langsmith-0.13.2.tgzlangsmith-0.13.1
- Internal improvements and maintenance updates
langsmith-0.13.1.tgzlangsmith-0.13.0
- Internal improvements and maintenance updates
langsmith-0.13.0.tgzlangsmith-0.12.37
- Internal improvements and maintenance updates
langsmith-0.12.37.tgzlangsmith-0.12.36
- Internal improvements and maintenance updates
langsmith-0.12.36.tgzlangsmith-0.12.35
- Internal improvements and maintenance updates
langsmith-0.12.35.tgzlangsmith-0.12.34
- Internal improvements and maintenance updates
langsmith-0.12.34.tgzlangsmith-0.12.33
- Internal improvements and maintenance updates
langsmith-0.12.33.tgzlangsmith-0.12.32
- Internal improvements and maintenance updates
langsmith-0.12.32.tgzlangsmith-0.12.31
- Internal improvements and maintenance updates
langsmith-0.12.31.tgzlangsmith-0.12.30
- Internal improvements and maintenance updates
langsmith-0.12.30.tgzlangsmith-0.12.29
- Internal improvements and maintenance updates
langsmith-0.12.29.tgzlangsmith-0.12.28
- Internal improvements and maintenance updates
langsmith-0.12.28.tgzlangsmith-0.12.27
- Internal improvements and maintenance updates
langsmith-0.12.27.tgzlangsmith-0.8.30
- Internal improvements and maintenance updates
langsmith-0.8.30.tgzlangsmith-0.12.25
- Internal improvements and maintenance updates
langsmith-0.12.25.tgzlangsmith-0.12.24
- Internal improvements and maintenance updates
langsmith-0.12.24.tgzlangsmith-0.12.23
- Internal improvements and maintenance updates
langsmith-0.12.23.tgzlangsmith-0.12.22
- Internal improvements and maintenance updates
langsmith-0.12.22.tgzlangsmith-0.12.21
- Internal improvements and maintenance updates
langsmith-0.12.21.tgzlangsmith-0.12.20
- Internal improvements and maintenance updates
langsmith-0.12.20.tgzlangsmith-0.12.19
- Internal improvements and maintenance updates
langsmith-0.12.19.tgzlangsmith-0.12.18
- Internal improvements and maintenance updates
langsmith-0.12.18.tgzlangsmith-0.12.17
- Internal improvements and maintenance updates
langsmith-0.12.17.tgzlangsmith-0.12.16
- Internal improvements and maintenance updates
langsmith-0.12.16.tgzlangsmith-0.12.15
- Internal improvements and maintenance updates
langsmith-0.12.15.tgzlangsmith-0.12.14
- Internal improvements and maintenance updates
langsmith-0.12.14.tgzlangsmith-0.12.13
- Internal improvements and maintenance updates
langsmith-0.12.13.tgzlangsmith-0.12.12
- Internal improvements and maintenance updates
langsmith-0.12.12.tgzAdditional Helm chart releases are available in the
langchain-ai/helm GitHub repository.Connect these docs to Claude, VSCode, and more via MCP for real-time answers.