n8n Release Notes

Follow

76 release notes curated from 1 source by the Releasebot Team. Last updated: Nov 11, 2026

Get this feed:
  • Nov 10, 2026
    • Date parsed from source:
      Nov 10, 2026
    • First seen by Releasebot:
      Nov 11, 2026
    n8n logo

    n8n

    2.48.0

    n8n releases a feature-rich update with improved Apps previews and bindings, deeper Assistant integration, a new Work IQ OAuth2 credential, and agent and migration enhancements. It also fixes issues across workflows, integrations, security, and installation reliability.

    Bug Fixes

    • ai-builder: Return the raw body when fetch-url reads JSON, XML, CSV or YAML (#42949) (6640010)
    • Align workflow history header dividers (#43167) (73698d6)
    • Compression Node: Preserve custom gzip file names (#42063) (a196d7d)
    • core: Apply the redaction policy to log streaming, telemetry and error reports (#42905) (c4c66d3)
    • core: Decode webhook bodies in the declared charset (#42037) (71ea718)
    • core: Exclude Nano Banana models from Gemini chat model pickers (#43082) (5038878)
    • core: Keep Anthropic thinking valid in agents after prompt rewrites and web search (#43160) (92b6fea)
    • core: Keep observational memory running after a user stops a HITL card (#43192) (cf28f65)
    • core: Keep retry backoff when a trigger fails right after reactivation (#43105) (b43750c)
    • core: Keep the OAuth JWKS available when a retired signing key cannot be read (#42465) (7a15776)
    • core: Keep the warning level of sub-workflow errors rebuilt for the parent (#42727) (4dcbe9e)
    • core: Only allow users who can edit a workflow to own its migration findings (#43091) (1faa2fa)
    • core: Retire stale scheduled tasks in repeated batches in each reaper pass (#43076) (505c0c0)
    • core: Settle abandoned tool calls when an Agents runtime turn starts (#43194) (75b8ea0)
    • core: Subscribe Telegram agent channels to button clicks (#43221) (4cff3b3)
    • editor: Keep the API settings empty state in the header column (#43219) (c3ba6a3)
    • editor: Polish skill files and version history (#43180) (4b7b145)
    • editor: Update favicon and preview image branding (#43214) (c2ea734)
    • editor: Use the current Assistant icon across the editor (#42441) (5ee06d3)
    • Exit with distinct codes for failed and incomplete community package scans (CE-3548) (#42780) (0db6d6b)
    • Extract document IDs from Drive URLs (#42478) (fe45950
    • Honor Continue On Fail for initial connection errors (#41118) (ce23494)
    • Make npm install of n8n work on all platforms again (#43028) (01c87f9)
    • Preserve API version headers regardless of case (#42473) (d49b632)
    • RabbitMQ Node: Await queue bindings before returning channel (#43033) (e87308e)
    • Show the credential redaction cause without sharing permission (#42711) (b3a40ee)
    • Update Multer to 2.5.0 and preserve upload cleanup (#43157) (731c17c)
    • Use the workflow's owning project for node parameter lookups (#43179) (8823b65)

    Features

    • Add an ability to select an element in Apps preview (#42930) (b85c9d7)
    • ai-builder: Bump the default Assistant model to Claude Opus 5.5 (#42990) (44bc5b0)
    • App bindings UI (#42986) (2509674)
    • core: Add Microsoft Work IQ OAuth2 credential (#43172) (a3ef7d9)
    • core: Emit telemetry and audit events when a user logs out (#42413) (612d1d3)
    • core: Hide archived workflows in the migration report by default (#42781) (a070476)
    • core: Stop agent runs when the Gateway credits wallet is empty (#41473) (5dbef9a)
    • editor: Create Listbox primitive for Design System (#42754) (588918d)
    • editor: Link Apps to n8n Assistant chats (#42969) (5339f0c)
    • editor: Show a message when the migration report takes long to load (#42996) (c1420c6)
    • editor: Show a restriction callout in the credential modal (#42678) (38666b6)
    • editor: Unify chat messages and Markdown rendering (#42315) (5e38fe6)
    • Node operation annotations for engine (#41835) (b3ecad1)
    • Open the migration report filtered to the recipient from notification emails (#43089) (010f33c)
    • Paddle Node: Rename node to Paddle Classic (#43042) (ddabd54)
    Original source
  • Nov 3, 2026
    • Date parsed from source:
      Nov 3, 2026
    • First seen by Releasebot:
      Nov 4, 2026
    n8n logo

    n8n

    2.47.0

    n8n releases a broad update with app-building and publishing tools, Agent version history, and expanded Assistant and MCP capabilities. It also adds integration features and delivers numerous fixes and performance improvements across workflows, security, and the editor.

    Bug Fixes

    • Add missing period to data table storage limit banner copy (#37943) (d1dc4d6)
    • AI Agent Node: Point the deprecated agent type callout to an action that works (#42898) (7a44fcb)
    • ai-builder: Include instance admins in team self-healing reviews (#42325) (58f160d)
    • ai-builder: Open self-healing chat in the result project (#42399) (0b1849a)
    • ai-builder: Update the Assistant chat title when you build a new agent (#42739) (c98324f)
    • Align logs panel header button styles and spacing (#42162) (f5329d0)
    • Align promotion binding and blocker typography (#42681) (4f8bbb6)
    • API: Escape unsafe ids in package export paths (#42038) (1576aef
    • API: Use planned publication actions for package imports (#42899) (a60e58c)
    • Apply execution redaction to MCP workflow run errors (#42574) (53bf60c)
    • Apply project scopes to folder list queries (#42171) (cd64ada)
    • Apply project scopes to MCP instance context run summaries (#42173) (1e3335f)
    • Bound Agent token counting and guard settled errors (#42569) (9281106)
    • Clear workflow search when entering a folder (#42884) (4877e1d)
    • core, editor: Align agent cleanup and telemetry (#42910) (a7c5271)
    • core, editor: Use the managed OAuth app after a switch from a custom app (#42593) (3cbe84c)
    • core: Add a cooldown before resending migration owner reminders (#42419) (dddcc70)
    • core: Add row details to the missing execution data report (#42897) (d33d38a)
    • core: Align GitLab token guidance with merge request requirements (#42628) (a85b88d)
    • core: Close promotion reviews when their environment target changes (#42555) (de61319)
    • core: Count unsaved crashed executions for auto-deactivation (#41947) (fc4c4c3)
    • core: Export the stored last success of durable system tasks on every main (#42319) (db28d8b)
    • core: Give each new queue job to one idle worker in turn (#42367) (b45761c)
    • core: Guide agents to valid JSON Pointers in offloaded tool results (#42909) (86d52c3)
    • core: Handle concurrent source control initialization (#42248) (bd1c731)
    • core: Improve credential resolution for node parameter loading (#41764) (6c9d310)
    • core: Improve removed-node and Edit Image entries in v3 migration report (#42244) (8ed6f20)
    • core: Include jobs in the claiming list when reading waiting queue jobs (#42405) (42f59f6)
    • core: Keep agent sandbox file writes within the sandbox file size limit (#42479) (f416643)
    • core: Keep Agent token counting from blocking the event loop (#42436) (cdc3f4c)
    • core: Keep draft channel settings when a user completes channel setup (#42302) (b3142f5)
    • core: Keep internal-only error metadata out of REST error responses (#42703) (c2d1003)
    • core: Keep own proto keys in values that cross the expression runtime (#42766) (20c7401)
    • core: Keep template literal text next to interpolations when the literal contains new lines (#42181) (e54adab)
    • core: Keep the ExpressionError name in minified builds (#42269) (96cfba9)
    • core: Keep the name and fields of an Error that an expression returns (#42767) (8acfffe)
    • core: Keep the workflow dependency index current after source-control pull and unpublish (#42407) (56fd96d)
    • core: Keep undefined values in QuickJS expression results (#42253) (248d069)
    • core: Let expressions read Error objects in item data (#42768) (c16f6f2)
    • core: Limit resume attempts for waiting and queued executions (#42135) (c08ba2d)
    • core: Limit Sentry trace header propagation (#42749) (37c9f05)
    • core: Measure the memory guard heap ratio on the old generation (#42380) (4538dd7)
    • core: Normalize tool suffixes in agent node type checks (#42228) (5168dd3)
    • core: Publish and unpublish workflows from the CLI through the workflow service (#42320) (6c21bb1)
    • core: Re-sync the migration finding table after an n8n upgrade (#42384) (3d271ac)
    • core: Read Data Table rows without taking the SQLite write lock (#42598) (c92280e)
    • core: Read item fields named like Object.prototype methods through computed keys (#42364) (686c3e8)
    • core: Read named array keys in expressions (#42912) (a19d843)
    • core: Rebuild the Postgres pool only when a fresh connection shows the database is reachable (#42202) (91fa27d)
    • core: Recommend moving alerting into the preExecute hook in the v3 migration report (#42279) (1063a6e)
    • core: Record dynamic time saved for executions in queue mode (#42397) (0b3321a)
    • core: Refresh the variables cache when a project is deleted (#42310) (c93a93f)
    • core: Remove exportedAt from n8n package manifests (#42278) (df2f6ed)
    • core: Remove waiting executions from memory on queue workers (#42662) (ed912a6)
    • core: Require execution:read when workflow-scoped routes read execution data (#42305) (cbe4d6c)
    • core: Resolve host data paths once per expression evaluation (#42571) (d50a446)
    • core: Resolve IMAP trigger expressions after activation (#42579) (a5aeea6)
    • core: Resolve linked items across long pagination loops (#42744) (c2c5c57)
    • core: Return user data with an __isError key as data in expressions (#42316) (5d640a2)
    • core: Route Assistant fetch and model fallback through environment proxies (#41901) (e0fd81c)
    • core: Route error items to the error output when the paired item lookup fails (#41943) (8ae06e2)
    • core: Run partial manual executions when the workflow has NULL pinned data (#42376) (6813162)
    • core: Show MCP webhook header names for team-project credentials (#42885) (7ea4731)
    • core: Show the paid plan when a Registered Community license is also active (#42920) (c07ba0c)
    • core: Stop a queue-mode job on the worker when the stop request comes from a different process (#42311) (d8b80c8)
    • core: Stop counting runs that fail before their first node as billable (#41638) (cd37d78
    • core: Stop self-referencing parameter expressions from crashing n8n on startup (#42317) (43af959)
    • core: Use UTC day boundaries when compacting Insights metrics (#42581) (c20b847)
    • Display tooltips above open select menus (#42261) (f0942c8)
    • editor: Add icons to Agent configuration actions (#42031) (1a00f5d)
    • editor: Align the icon and list of the migration report How to fix panel (#42788) (f3097ec)
    • editor: Enlarge the preference modals and their text areas (#42682) (e112130)
    • editor: Fix sticky note color selector padding and toolbar visibility (#23789) (b921757)
    • editor: Hide Finish setup for published agents (#42689) (9c09a6f)
    • editor: Load the insights summary when the agents list mounts (#42282) (f8e7ded)
    • editor: Localize the more details and retrying text on the credential error banner (#42817) (3bb3cc2)
    • editor: Localize the value missing labels on the variables page (#42586) (d93f613)
    • editor: Match compact sidebar icon sizes (#42323) (5065fe4)
    • editor: Move an AI node's sub-nodes with it when an insert shifts it (#41961) (b4f115a)
    • editor: Open Assistant by default for unpublished agents (#42447) (df325ca)
    • editor: Open form test popup without a background request to the webhook host (#41107) (7cb7d0b)
    • editor: Reconnect the push connection when the backend comes back online (#42461) (b379c65)
    • editor: Remove the optional marker from the version description label (#42753) (71987de)
    • editor: Render the migration rule detail table one page at a time (#42784) (662905b)
    • editor: Replace self-healing loading text with placeholders (#42313) (b9e51b7)
    • editor: Show a readable label for native tool search in agent chat (#42402) (6d9a049)
    • editor: Show how many owners a bulk migration notification emails (#42440) (d654c48)
    • editor: Show scroll hints on horizontally scrollable tables and pin the User column on Settings > Users (#42459) (f8db621)
    • editor: Show the New test action with a flask icon on Agent cards (#42433) (1b0dc15)
    • editor: Show the workflow project under its name in the migration report (#42580) (a4962d4)
    • editor: Snap programmatic node positions to the nearest grid line (#41964) (8e19522)
    • editor: Stop dialogs from clipping select dropdowns (#42684) (74b16a7)
    • editor: Stop production checklist from reopening on every workflow load (#42460) (a386563)
    • editor: Stop sending agent instructions in test chat telemetry (#42906) (d4b04a0)
    • editor: Translate the HTML display mode label and hide its unused pagination bar (#42401) (757ab8c)
    • Fix clipped add-row hover and inconsistent data table dividers (#42533) (5dc4ab3)
    • Handle missing conference properties (#41115) (4a04606)
    • Jenkins Node: Support CSRF crumb and queue redirect responses (#41301) (e7ffa7a)
    • MCP Client Tool Node: Preserve user tool argument in Agent V3 (#35067) (c131349)
    • Microsoft Teams Trigger Node: Keep one subscription per resource and remove orphans (#41735) (4546b39
    • n8n Node: Fail the credential test when the Base URL has no API path (#41791) (beae5f2)
    • Pin runners base images and update launcher, urllib3 and moment (#42901) (3fcd12e)
    • Preserve literal keys in external secret discovery (#42607) (c820696)
    • Preserve MCP webhook details when credential lookup fails (#42808) (50bdfb2)
    • Read instance name from configured sources for apps (#42896) (b8aee9c)
    • Return execution details for MCP test_workflow credential (#42746) (3198958)
    • Run nodes-base watch tasks sequentially (#42858) (77623e9)
    • Scope workflow dependencies by resource type (#42133) (7252b98)
    • Show the real error when node parameter options fail to load (#42448) (6e3704a)
    • Snowflake Node: Return node errors for failed Snowflake requests (#41697) (f8fa484)
    • Splunk Node: Read Return All and Limit from the item being processed (#38648) (77bd594)
    • Splunk Node: Stop turning a relative time bound into the string NaN (#38650) (d42c701)
    • Validate and serialize log streaming destination saves (#42161) (e8fc187)
    • Validate credentials with the Agent models endpoint (#41017) (c084848)

    Features

    • Add an on/off switch and env var for the n8n Assistant (#42121) (d5bea2f)
    • Add Apps frontend module and list page (#42180) (24905aa)
    • Add command bar entries for the Skills and Preferences settings (#42944) (3656bb9)
    • Add publish Apps in UI (#42634) (8ec26d5)
    • ai-builder: Add project members as self-healing reviewers (#42283) (72e5802)
    • ai-builder: Send request labels on direct Assistant model calls (#41951) (073e2f8)
    • App detail route and the app view component (#42410) (e0df089)
    • Apps preview frontend (#42552) (73f7064)
    • Configure App view with basics (#42704) (bd05c81)
    • core, ai-builder: Allow Assistant and MCP to update credential descriptions (#42425) (0c10bc5)
    • core, editor: Add Agent version history and publication timeline (#42296) (66a82cb)
    • core, editor: Create missing projects from Apply connections (#42870) (243eec2)
    • core: Add $evaluateExpression rule and align v3 migration report copy with docs (#42298) (0179883)
    • core: Add Agent version and publication storage (#41816) (caa6e27)
    • core: Add capture guidance for cross-session memory (#42170) (1075876)
    • core: Add CIMD support to outbound MCP OAuth (#42608) (929779f)
    • core: Add MCP tools to read Agent session logs (#42190) (6d47284)
    • core: Add pagination for more than 10 options for whatsapp list… (#41705) (6820f73)
    • core: Add the otel.configure external hook (#42164) (721a3db)
    • core: Improve episodic memory recall and consolidate captured facts (#42438) (4761830)
    • core: Increase the agent knowledge file upload limit to 25 MB (#42395) (5cba4ba)
    • core: Let the n8n Assistant read unsaved manual executions (#42125) (681ad50)
    • core: Load the promotions module by default and remove its rollout flag (#42247) (5fcad47)
    • core: Pass W3C baggage from webhooks to outbound requests (#42532) (a8cde7f)
    • core: Publish saved Agent versions independently of drafts (#41817) (8791d76)
    • core: Select managed OAuth app by version stored on the credential (#41623) (1a222dd)
    • core: Send WhatsApp template messages outside the customer serv… (#41133) (df2086b)
    • core: Show recalled and flagged memories in agent session traces (#42434) (2abfa99)
    • core: Upgrade Sentry to v11 and set up OpenTelemetry once at startup (#41584) (9f8dc74)
    • editor: Add Agent builder layout experiments (#41879) (f4006d0)
    • editor: Add resolution guidance to the migration rule detail page (#42531) (576e4fe)
    • editor: Open a resource from the Assistant header when no tabs are open (#42671) (66f6b7e)
    • editor: Redesign the agent session trace (#41536) (53c8296)
    • editor: Show agent test chat over the Assistant chat (#42328) (45ea5b2)
    • editor: Show app blueprint card before creating an app (#42815) (3eae292)
    • editor: Show Meta review status and a removal warning for the W… (#41580) (5f55c42)
    • editor: Show the project of each workflow in the migration report (#41989) (b3210ec)
    • editor: Warn before a move into a project that restricts its types (#41870) (18f1234)
    • Integrate App building in n8n assistant (#42636) (ddd9aa0)
    • Mailchimp Trigger Node: Add webhook signature verification (#41561) (bf6a4de)
    • Microsoft Agent 365 Node: Send spans to Microsoft through the OpenTelemetry setup (#42174) (e7ce327)
    • n8n Node: Add user get operation (#42566) (7514f84)
    • OpenWeatherMap Node: Use the credential base URL and authentication (#42184) (02cb18e)
    • Postgres Node: Add custom SSL certificate support (#41593) (a428c28)
    • Show skills created or edited by the n8n Assistant as artifacts (#41631) (4d45133)
    • Venafi TLS Protect Cloud Trigger Node: Add webhook signature verification (#42250) (ec21c27)
    • Warn on community node operation names that break the UX guidelines (CE-3602, CE-3603) (#41932) (b39429d)
    • Zendesk Node: Default new nodes to OAuth2 authentication (#39310) (53c39cb)

    Performance Improvements

    • ai-builder: Prepare the Assistant sandbox while the model writes a sandbox tool call (#42565) (ee2b20a)
    • ai-builder: Run SDK source lint in the build and remove the separate validate step (#42346) (82e88e0)
    • core: Index executions by workflow id for workflow deletion (#42677) (68c277a)
    • core: Load the eligible users once per migration report sync (#42700) (2df0b78)
    • core: Read each Slack credential once per migration report scan (#42686) (8cd8e76)
    • core: Restore lazy loading of credential types (#42403) (d6100ca)
    • core: Skip role scopes when loading users for owner suggestions (#42613) (8f81bc6)
    • core: Store episodic memory embeddings as binary and read less per search (#42487) (1d5d982)
    • core: Use keyset paging in the migration report scan (#42691) (6d64b09)
    • core: Use latest models with low effort for workflow verification helpers (#42231) (92589e0)
    • Google Drive Trigger Node: Read watched item instead of listing changes (#42134) (a40aea4)
    Original source
  • All of your release notes in one feed

    Join Releasebot and get updates from n8n and hundreds of other software products.

    Create account
  • Oct 27, 2026
    • Date parsed from source:
      Oct 27, 2026
    • First seen by Releasebot:
      Oct 30, 2026
    n8n logo

    n8n

    2.46.0

    n8n releases a broad update with expanded Agent and AI model support, new API and migration tools, and improvements to workflow integrations, security, reliability, and editor usability.

    Bug Fixes

    • Add file-type tooltip to artifact download button (#41490) (4a74f02)
    • ai-builder: Check execution:read in Assistant execution reads (#41863) (a967486)
    • ai-builder: Send Assistant model calls through the configured AI transport (#41948) (9b63561)
    • Allow custom OAuth2 scopes (#41249) (2b450cf)
    • API: Accept expressions in number, boolean, and options credential fields (#41832) (281ce2c)
    • API: Advertise the OAuth resource challenge on every public API 401 (#41829) (182a428)
    • API: Remove node timestamps from the workflow OpenAPI schema (#41792) (a722510)
    • core: Allow agent node tools to use global credentials (#40814) (f2bfe17)
    • core: Apply execution redaction to Assistant execution reads (#41565) (f7cd678)
    • core: Apply execution redaction to Assistant one-off node runs (#41582) (9184012)
    • core: Bound agent context queries and improve Slack searches (#41806) (9d6f901)
    • core: Check agent read access and credential access for draft Agent runs (#42152) (01fbd95)
    • core: Claim an idle worker's next queue job and its lock in one step (#41525) (32a9a7a)
    • core: Close binary data streams when the client disconnects (#41077) (e167fd5)
    • core: Close chat attachment streams when the client disconnects (#41108) (79b7497)
    • core: Close upload body streams when an outbound request fails (#41078) (2dd1d15)
    • core: Compare insights date ranges in UTC on Postgres with a non-UTC time zone (#41495) (1e66e5d)
    • core: Delete binary files before removing a pruned execution (#40995) (003c47d)
    • core: Delete SDK memory threads when an agent is deleted (#41857) (67ec0c6)
    • core: Detect the removed LangChain Code node in the v3 migration (#41774) (e48fdfa)
    • core: Disable Node Web Storage in JS task runners (#41852) (3b4bfc9)
    • core: Do not report activation errors for credentials that need reconnecting (#41840) (51cfef8)
    • core: Don't close shared SSH tunnel clients that are still in use (#40114) (7ffa1b1)
    • core: Fail publication of stored versions with trigger node ids over 64 characters (#41519) (26c580e)
    • core: Fall back to Chat Completions when /responses fails on a missing field (#40927) (f11619c)
    • core: Handle client disconnects in Respond to Webhook binary responses (#41110) (da70de8)
    • core: Ignore counts of tokens when provider omits input / output tokens (#41395) (618fd7e)
    • core: Improve agent credential handling (#41873) (0347055)
    • core: Keep admin-blocked Assistant permissions after plan approval (#41497) (7229765)
    • core: Keep Agent skills in sync with field changes (#41996) (f2921bd)
    • core: Keep AI Assistant image attachments visible in history (#41528) (ba9835a)
    • core: Keep parentheses around && and || operands of ?? in expressions (#40962) (dbcfecf)
    • core: Leave execution data out of retry responses without execution:read (#41871) (cc72143)
    • core: Let the folder table migration complete when its column already exists (#41006) (26dac9a)
    • core: Make Array min() and max() work on arrays of 125k+ numbers (#42109) (f36ede8)
    • core: Omit the credential name from exported workflow JSON (#41691) (aa28191
    • core: Pair declarative node output items with their input items (#41645) (a56adb3)
    • core: Pair output items before the error output split (#41639) (8dd5182)
    • core: Persist static data written by a webhook trigger (#42081) (a15382a)
    • core: Pin Bedrock auth and validate AWS region in agents (#42148) (a78b064)
    • core: Re-arm waiting executions after leader takeover (#39896) (a32b06f)
    • core: Read the last successful execution of an engine v2 workflow from the data plane (#40560) (1c234b0)
    • core: Read type availability policies from memory at enforcement points (#41552) (7e405aa)
    • core: Record a failing sub-node run at the sub-node's own run index (#40970) (917d035)
    • core: Recreate removed n8n-sandbox sandboxes and rerun workspace setup (#41805) (26ce225)
    • core: Register Assistant eval routes only on eval instances (#41771) (5624ec3)
    • core: Reject scheduled job names longer than their column (#41521) (fe587dd)
    • core: Release the SQLite write lock when the write connection fails to open (#41843) (d10f2ef)
    • core: Release workflow data when a vm engine expression ends (#41804) (ae7eeef)
    • core: Replace the QuickJS runtime and WASM module after a native stack overflow (#40968) (b2e7e9f)
    • core: Replay reasoning to custom OpenAI-compatible models in the agents runtime (#41959) (e145ac4)
    • core: Report an unpublished sub-workflow as an operational error (#41769) (5df6733)
    • core: Report SAML logins whose asserted email differs from the linked user (#41506) (b768f6c)
    • core: Run the own Error Trigger when no error workflow is selected (#40969) (6225e62)
    • core: Send Code node buffers to task runners as base64 (#40670) (f7e36ed)
    • core: Send standalone Agent Responses calls to custom OpenAI endpoints with store disabled (#42158) (4636a33)
    • core: Send the W3C trace context on MCP server requests (#41908) (481fa2a)
    • core: Set CORS methods for waiting webhooks (#39210) (8ba05b1)
    • core: Set the class name as the name of UserError, OperationalError and UnexpectedError (#41685) (42721d0)
    • core: Show the root cause of model errors in AI Agent and Basic LLM Chain (#41388) (9ceb394)
    • core: Skip empty cache hash writes (#40937) (466f787)
    • core: Split long agent replies and repost failed streams (#42156) (0562aa2)
    • core: Start sub-workflow error workflow when a pre-run check fails (#40957) (e456b35)
    • core: Stop dependency index rebuild looping after import (#40356) (58f11bf)
    • core: Stop retrying a node after the execution is cancelled (#41786) (95d1b0f)
    • core: Stop the shutdown drain waiting on executions that park mid-drain (#42129) (7c76c53)
    • core: Stream Slack agent replies in one message (#41470) (42f783a)
    • core: Unify Agent creation and correct creation telemetry (#41378) (34d4b73)
    • core: Update regex for scoped node name validation to allow dots in organization names (#34950) (9502630)
    • core: Use mocked execution for agent check previews (#41144) (aa4a358)
    • core: Use the root execution mode to pick draft or published nested sub-workflows (#41779) (ea57730)
    • core: Widen node id columns to 64 characters (#41007) (2a9b176)
    • core: Write the final status when deleting unsaved executions (#41937) (8addd39), closes mayanksin#27
    • Databricks AI Agent Node: Scrub MLflow trace request and response previews (#41247) (bed2ab9
    • Databricks Node: Send a JSON body for a Lakebase function call that has no arguments (#41632) (6da54e1)
    • editor: Adapt Agent Builder panel widths to available space (#41562) (d8809f6)
    • editor: Align agent dialog header actions to the right edge (#41969) (0fee1e7)
    • editor: Align carets within split buttons (#42168) (1634a42)
    • editor: Align ellipsis action buttons across the editor (#41912) (e6b2c83)
    • editor: Allow dismissing the n8n Assistant limited mode banner (#41885) (50cdf14)
    • editor: Center badge text when icons are absent (#41414) (9149663)
    • editor: Center the empty Time saved tooltip icon (#42030) (85199fe)
    • editor: Clear the hover highlight when navigating menus with the keyboard (#42099) (e03fcd9)
    • editor: Correct Agent tool validation and home empty state (#41474) (744604c)
    • editor: Delay agent setup checklist until building finishes (#41559) (964ae51)
    • editor: Fill the reserved scrollbar space in server tables (#41290) (7d2e358)
    • editor: Fix Agent placeholders and memory credential menus (#42002) (db99da9)
    • editor: Hide Test agent setup task until preview is enabled (#41882) (e595e5e)
    • editor: Improve first load speed (#41942) (40a05c5)
    • editor: Increase light-mode text contrast (#41785) (5b75624)
    • editor: Keep the creation menu above the sidebar while opening (#42033) (6c926d4)
    • editor: Load and keep resource mapper fields inside a fixedCollection (#41209) (967112a)
    • editor: Localize the binary data preview messages (#41323) (6813be8)
    • editor: Localize the create menu submenu heading (#41773) (9e097d4)
    • editor: Localize the execution mode tooltips in the executions list (#41324) (c0ef4e4)
    • editor: Localize the select placeholders in workflow settings (#41325) (a5eada9)
    • editor: Localize the source control push modal messages (#41776) (4e516d2)
    • editor: Localize the use workflow button on template cards (#41778) (238376d)
    • editor: Match Evals Run Test button colors (#42154) (b8ed6dc)
    • editor: Match navigation plus button hover styling (#41826) (0af68db)
    • editor: Point migration report docs link to the v3 breaking changes page (#41900) (1430a3b)
    • editor: Preselect Agent Memory credential (#42140) (6849da6)
    • editor: Reduce Agent modal header spacing (#41585) (25010a2)
    • editor: Remove underlines from breadcrumb links (#42191) (109248f)
    • editor: Remove underlines from Data Table links (#41613) (18084bc)
    • editor: Save replacements for unresolved credentials (#41704) ([bd21faafcdc3f5ab9f9acfa8140ab8738046c805))
    • editor: Say 'Can view' on projects a credential is used in but not shared with (#41690) (25c86e0)
    • editor: Scroll data table previews in the AI Assistant panel (#41522) (db90867)
    • editor: Show manual execution results after the push connection reconnects (#41610) (ccd79cd)
    • editor: Skip empty results in the expression preview highlighter (#41655) (981f0e8)
    • editor: Stop Safari from opening its own context menu on the canvas (#42126) (0b014ee)
    • editor: Support agent test chat on HTTP origins (#41713) (8dd4319)
    • editor: Use consistent channel connect labels (#42029) (dedc37d)
    • editor: Use consistent confirmation modals in Agents (#41922) (ff95b93)
    • editor: Use n8n Assistant in history and sandboxing copy (#41566) (dba1c53)
    • Email Trigger (IMAP) Node: Back off reconnects when the server drops each new connection (#41827) (39d9c1b)
    • Execution Data Node: Store boolean and falsy expression values (#41915) (4c284b3)
    • Fall back to OpenID discovery after HTML metadata responses (#41063) (ac02213)
    • Fill empty output slots before pairing items (#42138) (a12bf1d)
    • Handle empty and invalid revision responses (#41114) (2b2eb0f)
    • Handle IMAP transport errors during connection setup (#41248) (fb08a75)
    • Handle null and undefined in manual console output (#41570) (e228ee9)
    • HTTP Request Node: Stop batching when the execution is cancelled (#41529) (d7c0244)
    • Include manual execution details in log streaming start events (#41790) (8dfdbc8)
    • Isolate LDAP clients and apply operation timeouts (#41611) (4f3896a)
    • Kafka Trigger Node: Release each execution's run data when it completes (#41531) (12e000b)
    • Keep source control tag mappings consistent (#41513) (47328a0)
    • Keep the Assistant Connect menu visible above the modal (#41124) (fc7f4c0)
    • Load all campaign dropdown options (#41065) (bbab617)
    • Make Preferences settings consistent with Skills (#41627) (ef6d31f)
    • Microsoft SharePoint Node: Fix the column mapper 403 and empty items in Map Automatically (#41671) (fbeaab9)
    • Microsoft SharePoint Node: Keep the filter and field options when Return All is on (#41205) (f930f2c), closes mayanksin#27
    • Microsoft Teams Trigger Node: Name the missing permission when Graph refuses the subscription (#41443) (5f3ab01)
    • Microsoft Teams Trigger Node: Renew the Graph subscription via lifecycle notifications (#41299) (9f074c2)
    • Open Chat Hub OAuth popups before authorization requests (#41409) (ef03659)
    • Postgres Node: Prevent global pgtypes overwrite (#41641) (a67dba1)
    • Preserve Salesforce instance URL on OAuth2 token refresh (#41415) (4d93b38)
    • Qwen Cloud Node: Route text-only DeepSeek models and add DeepSeek search alias (#41212) (8a35cf2)
    • Recognize default workflow inputs in Agent tools (#41727) (102ffae)
    • Reject task broker listen errors and use assigned test ports (#40925) (1526d6a)
    • Remove underlines from data table cards (#41719) (8c5c821)
    • Show detailed errors and correct limit maximum (#41066) (4d1fcfb)
    • Strava Trigger Node: Validate subscription challenge and events (#41617) (9126cad)
    • Summarize Node: Return null instead of NaN for an average with no numeric values (#41430) (be2da29)
    • Treat access keys as secret credential fields during linting (CE-3601) (#41931) (b46aba4)
    • Update certifi to 2026.10.19 in task runner (#41693) (282fa32)
    • Update certifi to 2026.10.23 in task runner (#41971) (8814383)
    • Update logos in credential oauth confirmation screen and instance emails (#41629) (65a2e21)
    • Use the form font for textarea text (#41068) (274ed38)
    • Warn before leaving project settings with unsaved changes (#41720) (bdb0bd9)
    • Widen the logs panel node list (#41787) (11f68c3)

    Features

    • Add an "Executions might fail" impact to the migration report (#41673) (df0c78c)
    • Add mention-only Slack replies for agents (#41815) (0406b59)
    • Add n8n Connect servers to MCP registry servers (#41313) (a46931d)
    • Add V3 migration for Edit Image node (#41389) (6dddea4)
    • API: Add dependency endpoints for workflows, credentials and data tables (#42040) (c8864e5)
    • Chat Node: Allow Respond to Chat in embedded chat mode (#41955) (6b19e62)
    • core: Add gen_ai.provider.name and gen_ai.agent.id to Agents SDK spans (#41875) (1b14cfd)
    • core: Add OTel GenAI attributes to AI Agent and chat model spans (#41874) (7e3c941)
    • core: Add v3 migration rules for the Slack signature secret (#41781) (a4b8c5e)
    • core: Authenticate Webhook and MCP Trigger nodes through trusted sources (#41455) (8708319)
    • core: Export the migration report as CSV (#41534) (db8094f)
    • core: Let the Agent Builder set up Microsoft Foundry models (#41913) (69dcaad)
    • core: Let workflow editors triage the migration findings of their workflows (#41093) (2b65576)
    • core: Limit Assistant changes to the thread's project (#41700) (b7815c9)
    • core: List Microsoft Foundry deployments in the Agents model selector (#41892) (da98e7c)
    • core: Make custom OTel attribute key prefixes configurable (#41695) (c10f805)
    • core: Make granular credential sharing always on (#41376) (36ea544)
    • core: Make the Microsoft Teams agent channel available (#41867) (d2bf458)
    • core: Make the promotion commit message optional and generate a default (#41888) (7c9a800)
    • core: Price Foundry deployments by the model they serve in Agents (#41909) (5fda71f)
    • core: Report the managed database and Redis service in telemetry (#40427) (1265d2f)
    • core: Report the whole deployment's footprint in telemetry (#40685) (d3f7a23)
    • core: Share focused credential tools between workflow and Agent builders (#41748) (5302240)
    • core: Show budget guardrail stops in the agent session timeline (#41692) (fecfbe5)
    • core: Show version mismatch warnings on all mains (#40097) (1adcf7a)
    • core: Stop Agent Builder from testing the agent after every build (#42186) (b37130f)
    • core: Support Claude deployments on Microsoft Foundry in Agents (#41905) (48332fe)
    • core: Unpublish instead of refusing a move into a restricted project (#41865) (8aa35f6)
    • Databricks Node: Enable the Lakebase resource and show the Lakebase Chat Memory sub-node (#41795) (5d6d06c)
    • Edit Image Node: Add v2 using napi-rs/canvas (#41182) (cd8e744)
    • editor: Add an All option to pagination and remove the custom datatable page-size controls (#39850) (d7fa8ad)
    • editor: Add dialog props, update the layout, and migrate existing dialogs (#40690) (c69581a)
    • editor: Add Environments group for source control API key scopes (#41537) (800821d)
    • editor: Align agent plan and message queue layouts (#40635) (68afdd3)
    • editor: Filter migration report workflows by project (#41869) (a9aab42)
    • editor: Group instance settings links under section headings (#41213) (04b3d5d)
    • editor: Improve Agent testing and documentation access (#41968) (f029f52)
    • editor: Mark required credential fields (#42028) (51a10f1)
    • editor: Prevent usage of deprecated nodes (#31392) (1a18bff)
    • editor: Refactor N8nBreadcrumbs and callers (#41196) (a59e0f1)
    • editor: Send users to the admin who can lift a type restriction (#41297) (0bfa563)
    • editor: Show the model that answered in the log details header (#41390) (6532d29)
    • editor: Update Preview and enterprise readiness tags for n8n Assistant and Chat (#41422) (443e119)
    • Implements new taxonomy experiment for sales-and-marketing responders (#41712) (14e79fa)
    • Microsoft Foundry Chat Model Node: Use the Microsoft Foundry logo (#41426) (82362c6)
    • n8n Node: Add action to add a user to a project (#41253) (794ede8)
    • Redis Vector Store Node: Consume the FluentRedisVectorStore in the RedisVectorStore Node (#27978) (9bcd57e)
    • Replace brand assets (#41510) (1587770)
    • Workable Trigger Node: Add webhook signature verification (#41683) (ea3bebc)

    Performance Improvements

    • core: Always load the model catalog search tool in Instance AI (#41545) (d5d6596)
    • core: Deduplicate episodic candidates before embedding (#41618) (fb8ae3d)
    Original source
  • Oct 20, 2026
    • Date parsed from source:
      Oct 20, 2026
    • First seen by Releasebot:
      Oct 21, 2026
    n8n logo

    n8n

    2.45.0

    n8n ships a broad update with new agent and workflow tools, improved MCP permissions, migration notifications, and expanded node capabilities, alongside fixes that make automation, integrations, and the editor more reliable.

    Bug Fixes

    • AI Agent Node: Replay Anthropic thinking turns with their tool arguments (#41241) (ea98bd0)
    • Align data table and variable editing on protected instances (#41258) (d4bde14)
    • Allow skipping table initialization (#40437) (d245b17)
    • API: Apply projectId filter to executions for member API keys (#40887) (3075b60)
    • API: Log errors before returning generic 500 in Public API (#41186) (fe36279)
    • Check provisioning license on Users settings page (#41048) (066480d)
    • Convert to File Node: Decode data URIs and validate Base64 input (#38554) (315e0a5)
    • core: Allow gateway model IDs and forward credential headers in agents (#40470) (791c7bc)
    • core: Allow project promotion without an instance export (#40939) (e0fe040)
    • core: Allow switching a node back to a credential the user cannot use after a save (#41198) (e7f0607)
    • core: Clear agent runtime cache when credential is updated (#40961) (4cb7a6e)
    • core: Close agent after run when invoked from workflow (#41128) (f596162)
    • core: Confirm project deletions before instance apply (#40941) (f631112)
    • core: Create an XML parser for each webhook request body (#41098) (1950434)
    • core: Describe MCP servers only from user or registry text in Agent Builder (#40974) (248c863)
    • core: Display an error message when failing to connect to oauth credentials (#41058) (952b1e7)
    • core: Evict idle mcp-browser sessions to prevent connection leak (#36850) (efd4e21)
    • core: Handle every escaped closing bracket in an expression (#40487) (b09efb7)
    • core: Improve base URL check for declarative nodes (#40778) (e45a65a)
    • core: Keep cancelled Assistant activity settled (#40786) (d74f3f2)
    • core: Keep Observer detail lines instead of discarding the response (#41134) (48edbef)
    • core: Keep offline_access when a protected resource omits it (#41384) (9675910)
    • core: Keep pending setup for nodes that n8n Assistant added in an earlier build (#41070) (50c4ced)
    • core: Keep the workflow source file when n8n Assistant sends blank source (#41201) (b78913f)
    • core: Key each OAuth authorization request to its own session (#39930) (3c447b4)
    • core: Key queue job outcomes by job on shutdown resume (#40569) (6e04287)
    • core: Let LLM failed-attempt handling retry and honour Retry-After (#41002) (67c1981)
    • core: Let preview chat agents make changes through their tools (#41403) (8323dfd)
    • core: Log custom data truncation only above the 512-character limit (#40899) (e74f1c1)
    • core: Pass reasoning effort on open router model node (#41179) (683fd11)
    • core: Redact a parent execution if any sub-workflows have redaction enabled (#41129) (c70b5d4)
    • core: Redact the parent execution when a sub-workflow uses a credential the viewer cannot use (#41085) (a57c8f3)
    • core: Reflect failed publications in the active workflows endpoints (#40641) (96eff1e)
    • core: Remove unused N8N_SCHEDULER_MIN_INTERVAL setting (#41194) (c839d6c)
    • core: Reuse connections in the log streaming webhook destination (#41261) (1581524)
    • core: Skip resource mapper validation when the mapped value is null (#41069) (898701b)
    • core: Stop asking to set up a node when n8n Assistant only adds a step next to it (#41067) (578eea4)
    • core: Trace verification helpers and provider attempts (#40936) (f73dc33)
    • core: Turn off expression spans by default (#41211) (842ec5b)
    • core: Use the module registry to decide if the Assistant has the Agents features (#41026) (726a582)
    • core: Web search misconfigs in agents as UserError (#41257) (f844135)
    • Databricks Node: Bring the AI Agent panel to parity with AI Agent 2.2 (#40989) (e859aba)
    • Databricks Node: Rename Genie resource labels to Genie Agent and the MCP tile to Databricks Genie One (#40760) (14c7790)
    • editor: Apply the standard settings layout to the Context preferences page (#40716) (b3e8634)
    • editor: Cancel the Assistant thread when the hand-off navigation fails (#41056) (d26f914)
    • editor: Cleanup legacy button variants (#41175) (ba97e46)
    • editor: Display custom evaluation metrics correctly (#40852) (f6b24d0)
    • editor: Improve destination validation and surface save errors (#40897) (eaf47cf)
    • editor: Improve NDV credential options performance on large instances (#40198) (b98640f)
    • editor: Keep pending navigation when workflows list query is unchanged (#41125) (116a81e)
    • editor: Keep the used-in rows on the credential sharing tab when personal-space sharing is disabled (#41207) (ca9661c)
    • editor: Keep workflow name in edit mode after Rename menu action (#41120) (fc9f957)
    • editor: Load credential types on startup (#41400) (9a025a1)
    • editor: Match the credential dropdown width to its field and remove horizontal scroll (#41260) (51e53ad)
    • editor: Offer the managed OAuth choice when the app is supplied (#40284) (14d2d30)
    • editor: Place sticky notes and nodes at the right-click and clear the selection (#41365) (28602ed)
    • editor: Prevent doubled base path when opening folders with N8N_PATH set (#33065) (a32c652)
    • editor: Rename Admin Panel to Cloud console (#41187) (8120328)
    • editor: Restore From AI button corner radii (#41176) (20ea671)
    • editor: Restore the new session shortcut in agent chat (#40907) (ebf078b)
    • editor: Return to the requested page after SSO sign-in (#41151) (4a5fdd5)
    • editor: Save only the OpenTelemetry status when enabling or disabling (#41142) (1903d53)
    • editor: Show follow-up run events in the Assistant after a reconnect (#40883) (ffda639)
    • editor: Start the empty-state icon cards cycling on load and use them on the MCP and external secrets pages (#40232) (1f223c8)
    • editor: Stop auto-selecting the Evaluation Trigger over other triggers (#38883) (8b5ea6d)
    • editor: Stop credential icon overlapping the credential name in the agent credential picker (#41262) (70f0131)
    • editor: Unify documentation links across settings pages (#40289) (76cce99)
    • editor: Use the deployment name on the Az Foundry path (#41103) (b3e8b7d)
    • Email Trigger (IMAP) Node: Check the mailbox when the trigger activates (#41013) (a6719b8)
    • Email Trigger (IMAP) Node: Find new mail on servers with a broken IMAP4rev2 mode (#41018) (236220b)
    • ERPNext Node: Return each row once and tolerate empty Get Many options (#36860) (3968a60)
    • Execute Command Node: Don't spawn console on Windows (#40909) (52aed7a)
    • GitlabTrigger: use NodeApiError.httpCode and safe description access in webhook checkExists (#35486) (054288e)
    • Gmail Node: Keep the References header on a draft created in a thread (#41392) (06ba85c)
    • HomeAssistant Node: Only sent Home Assistant attributes on upsert if set (#36298) (b8780d8)
    • Keep free-floating sticky notes clear of workflow nodes (#41195) (131e9c8)
    • MCP Trigger Node: Pass through MCP content arrays instead of double-wrapping tool results (#39131) (f483ebd)
    • Microsoft Teams Node: Add the TeamMember.Read.All scope and correct the Trigger scope notice (#39819) (ddc9769)
    • OpenAI Node: Report token usage for image operations (#38463) (a3f4711)
    • OpenAI Node: Send max_completion_tokens when it analyzes an image (#38656) (e972309)
    • Pass structured inputs to OpenAI Responses tools (#40638) (1d2c879)
    • Postgres Node: Keep comma-containing values as one query parameter (#40240) (f5dc06f)
    • Restore command bar focus and standardize creation icons (#41185) (9e3b52c)
    • Send Email Node: Send to every recipient when a recipient field is an array (#36467) (660849d)
    • Skip dependency files and continue after custom node load (#41117) (5a3fc39)
    • Splunk Node: Preserve errors when continuing after failed items (#40368) (e29c3a4)
    • Validate attendee values (#40953) (21221ad)

    Features

    • API: Honor Idempotency-Key on Public API POST requests (#40978) (b7b3d72)
    • API: Return the parent folder on workflow read endpoints (#40981) (a906d2f)
    • Azure OpenAI Chat Model Node: Add an optional Project field to the Foundry credentials (#41181) (0c1a787)
    • core: Add an endpoint that notifies workflow owners about migration findings (#40952) (d8a0666)
    • core: Add an optional model for n8n Assistant memory tasks (#41137) (f34c093)
    • core: Add create-with-values credential missing mode to package import (#36767) (d3bc275)
    • core: Add self-healing results to Inbox (#40741) (1405d4a)
    • core: Add the blocking project and opt-in state to policy violations (#40985) (4419fc4)
    • core: Add typing indicator, media download and media retention … (#40920) (adedbbf)
    • core: Add WhatsApp credential check and webhook handshake status (#40921) (9a524e7)
    • core: Append node tool attributions to agent replies and add Genie attribution and deep links to the Databricks node (#40765) (44c8a31)
    • core: Apply budget alerts and stops to sub-agent run (#40884) (9498088)
    • core: Enable node and credential type policies by default (#41022) (dd79a61)
    • core: Enable the durable scheduler by default (#40891) (f6861fe)
    • core: Implement automated migrations for removed nodes (#40877) (739c59e)
    • core: Only show execution input and output for agent subworkflows in timeline (#41189) (4d292a6)
    • core: Refuse revoked access tokens of the local server on the inbound pipeline (#41266) (0936dfd)
    • core: Remove the startup pass from workflow history compaction (#40886) (45eea1b)
    • core: Report the CPU and memory limits n8n was given in telemetry (#40421) (d6d24f2)
    • core: Report the runtime n8n runs on in telemetry (#40420) (b2edcb5)
    • core: Run the Form and Chat trigger redirect login against a trusted source (#41123) (862c7ec)
    • core: Store promotion exports in n8n directory (#40863) (333a010)
    • core: Surface the responding model name in LLM sub-node run data (#41161) (b10c97e)
    • core: Suspend in-flight production executions at worker shutdown (#40568) (f3e2bd8)
    • core: Treat notified migration findings as unresolved (#40951) (347385b)
    • Databricks Node: Show the Vector Store, Embeddings and AI Agent nodes in the node picker (#41206) (191ea98)
    • Don't save MCP connections without user approval (#39996) (d27de60)
    • editor: Align the WhatsApp channel setup and settings with the … (#41283) (275f7eb
    • editor: Extend N8nCopyInput with accessibility, redaction, loading and actions (#34942) (c084d99)
    • editor: Let admins notify workflow owners from the migration rule detail (#40949) (a972eeb)
    • editor: Let admins notify workflow owners in bulk from the migration rule detail (#41060) (de42c95)
    • editor: Link to the credential sharing tab when execution data is redacted (#40976) (da3491f)
    • editor: Publish agent modal and modal for warning about unpublished workflows (#40987) (e47940e)
    • editor: Rework the WhatsApp channel setup to match the new design (#40923) (af0202d)
    • editor: Show agent personalisation icon in subagent modal (#41094) (6160624)
    • editor: Show multiple workflows in the review detail view (#40695) (f6d70c1)
    • editor: Show policy-blocked items in the source control pull modal (#40604) (1ea18e9)
    • editor: Show the model that answered in the AI log header (#40988) (caeaff7)
    • editor: Show the policy reason when an agent tool call is refused (#40673) (bb45bca)
    • editor: Update budget panel when agent executes (#40971) (632d8b9)
    • editor: Update UI with n8n rebrand (#40342) (bffe7d8)
    • Implements workflow previews above Assistant empty state experiment (#40913) (eac2f46)
    • Kafka Node: Make version 2 the default for new Kafka nodes and triggers (#40744) (e5866ac)
    • Monday.com Node: Add V2 with full V1 parity as the default (#35515) (8977833)
    • Overhaul MCP tool permissions for Agents (#39878) (bda9118)
    • Show Gemini models by name and list prioritized models first in model pickers (#40965) (acf5291)
    • Text Classifier Node: Add opt-in confidence scores to the output (#40743) (3800bce)

    Performance Improvements

    • editor: Load prettier only when the user formats code (#41014) (e2529a8)
    Original source
  • Oct 13, 2026
    • Date parsed from source:
      Oct 13, 2026
    • First seen by Releasebot:
      Oct 13, 2026
    n8n logo

    n8n

    2.44.0

    n8n improves workflow reliability, access-policy enforcement, and queue handling while polishing the Assistant and editor experience. This release also fixes credential, execution, and integration issues, with clearer retry actions and better secret previews.

    Bug Fixes

    • Align execution retry menu and clarify actions (#40710) (84d2fd6)
    • Allow per-process crash journal paths (#37670) (447e939)
    • core: Allow reverting a workflow version that uses credentials the user cannot use (#40701) (033a9b5)
    • core: Apply node type policies to agent node tools (#39711) (e7d8533)
    • core: Apply the credential type policy to credential tests and probes (#39927) (9191cf3)
    • core: Block the assistant when AI credits hit zero (#40659) (8b7065a)
    • core: Check the credential save policy before package import creates stubs (#40687) (a3391ba)
    • core: Check the target project's policy on folder, credential and delete-transfer moves (#40301) (77370af)
    • core: Count jobs as running from the start of job processing (#40050) (dc5c80f)
    • core: Expose 1Password fields for secret preview and autocomplete (#40538) (bef5f3f)
    • core: Fix Kimi K3 and other OpenAI-compatible Assistant model providers on self-hosted Assistant (#40439) (1ef7756)
    • core: Handle each Chat Hub segment once in queue mode (#40791) (9ff8d4f)
    • core: Improve node placement when n8n Assistant edits a workflow (#40139) (d900743)
    • core: Keep waiting executions unchanged when a resume request fails (#40683) (bbd35e2)
    • core: Let the editor download binary data of an Engine v2 execution (#40663) (c9cb3ee)
    • core: Let the streaming heartbeat stop on Chat Hub responses (#40792) (ee8a608)
    • core: Match regex case-insensitively when ignore case is enabled (#33589) (2596f3a)
    • core: Match the Brazilian real symbol in the in-isolate currency regex (#40893) (d3deffb)
    • core: Pass storedAt into WorkflowExecute at every callsite (#40495) (5ab2187)
    • core: Remove credentials of deleted projects on source control pull (#40692) (978f810)
    • core: Report approval tools with no tool connected in workflow validation (#40561) (bc0a9cb)
    • core: Report MCP server connection failures in verify_mcp_server (#40559) (fbbbadc)
    • core: Require workflow create scope for single node runs in n8n Assistant (#40908) (27fcb96)
    • core: Resume tool calls for deferred tools that a skill loaded (#40126) (1c84af2)
    • core: Return jobs dequeued during worker shutdown to the queue (#40086) (084f3b3)
    • core: Return jobs fetched before a worker paused to the queue (#40162) (f26747b)
    • core: Save agent draft definitions atomically (#40374) (9ee5d1a)
    • core: Serve the migration report on every main in a multi-main setup (#40180) (a6f1e79)
    • core: Show the policy block before node issues on execute and publish (#40290) (0bbea43)
    • core: Stabilise background child approval wait (#40834) (2ca4e55)
    • core: Start a new test session when call_agent gets an unknown session ID (#40458) (e16566b)
    • core: Stop marking the Message an Agent node as hidden (#40358) (3366d2b)
    • core: Validate execution timeout against the configured maximum in Instance AI saves (#40769) (2176819)
    • core: Validate the size argument of the chunk() expression extension (#40880) (3ff9c83)
    • core: Wire Entra OAuth2 into agent Azure OpenAI runtime (#40218) (96a8ff4)
    • Databricks Node: Request float encoding for embeddings from the Unity AI Gateway (#40684) (4c0902f)
    • editor: Add resend to retryable Agent preview errors (#40592) (f7e52a8)
    • editor: Align nodes panel to the embedded canvas in the n8n Assistant split view (#40795) (37799ad)
    • editor: Align tooltip trigger box with its content (#40422) (a694531)
    • editor: Keep Agent Builder settings inside a narrow column (#40759) (e2b4fee)
    • editor: Keep Assistant fixes in Agent builder and correct tooltips (#40348) (a13705a)
    • editor: Keep folder creation available globally after Community registration (#40082) (e1025f3)
    • editor: Keep same-named parameter values apart when their types differ (#40170) (6013045)
    • editor: Keep the prompt visible while the assistant starts a new thread (#40796) (be402be)
    • editor: Keep the selected credential visible when the picker does not list it (#40450) (66b382d)
    • editor: Keep the workflow setup step counter on one line (#40771) (55eb2ce)
    • editor: Keep typed characters in Markdown fields (#40805) (16e29da)
    • editor: Load node types before authenticated pages render (#40812) (8297b2e)
    • editor: Place the restricted node popover per host, keep one open, and stack the admin dialog (#40678) (b28dceb)
    • editor: Polish n8n Assistant and Execute button UI details (#40414) (76cab1e)
    • editor: Preserve Live Data highlights on scroll in expression editor (#33842) (0f02b50)
    • editor: Remove redundant description for create workflow option in agent config (#40882) (b542f66)
    • editor: Rename the
    Original source
  • Similar to n8n with recent updates:

  • Oct 6, 2026
    • Date parsed from source:
      Oct 6, 2026
    • First seen by Releasebot:
      Oct 6, 2026
    n8n logo

    n8n

    2.43.0

    n8n improves its AI Assistant, Agent, editor, and core workflow engine with stronger guardrails, better publishing and shutdown behavior, cleaner UI, and expanded node support across Azure OpenAI, Databricks, Google Calendar, Supabase, and more.

    Bug Fixes

    • Agent Node: Remove outdated tutorial tip callout (#35505) (53b84d2)
    • ai-builder: Treat a blank folder path as no folder in the build tool (#40116) (b7071c9)
    • Align From AI button with parameter inputs (#40152) (9675fc9)
    • API: Emit valid schemas for untyped values in the Public API spec (#39884) (6918fda)
    • API: Let global members grant variable scopes to API keys (#40064) (c95e34f)
    • API: Return an execution when its stored trace context is incomplete (#39715) (dfd7a52)
    • Azure OpenAI Chat Model Node: Support Responses-only deployments (#39403) (6610987)
    • Brevo Node: Accept both spellings of the recipients parameter (#40015) (e144b33)
    • Center pasted nodes in the canvas viewport (#39995) (bd9e1d8)
    • Clear connection hover promptly (#39958) (fa93a7f)
    • core: Apply MCP availability rules to error workflow settings (#39885) (e13c480)
    • core: Apply policy checks to CLI import and execute commands (#39714) (c575f18)
    • core: Apply removed fields when the Agent Builder patches agent config (#40122) (93c0a5c)
    • core: Block publishing workflows with unconnected required node inputs (#37265) (5e28ff8)
    • core: Cap pending task request timeouts to the shutdown deadline (#40136) (28bd124)
    • core: Connect Slack Agent channels through managed setup in MCP (#39776) (93b658c)
    • core: Correct Agent session pagination on SQLite (#39802) (1882cff)
    • core: Deduplicate agent message deliveries (#39794) (0811443)
    • core: Emit unique keys and conditional requirements in generated node type definitions (#39960) (1700702)
    • core: Generate missing workflow IDs in the import:workflow command (#40011) (d12cab0)
    • core: Improve workflow SDK group layout for AI subtrees and sticky notes (#39981) (7675d2b)
    • core: Keep concurrent credential tests from sharing one node type registry (#40054) (1cac1e0)
    • core: Keep floating entitlements attached when a multi-main instance shuts down (#39713) (ad90c63)
    • core: Keep jobs a worker enqueued out of its shutdown drain (#39800) (cd9d1ac)
    • core: Keep node parameters when n8n Assistant cannot see them (#39454) (f82fa0c)
    • core: Keep the task runner running on an unhandled promise rejection (#39946) (59c6ab2)
    • core: Limit background task continuation to the latest stop group (#40333) (314c430)
    • core: Load workflow publish history in a separate query (#40171) (548bd57)
    • core: Pass graceful-shutdown timeout to runners in the runners image (#39796) (d8dcc92)
    • core: Pass registry and auth token to npm outdated for community packages (#31515) (1998011)
    • core: Redact MCP tool telemetry properties (#39887) (fc99aaf)
    • core: Reload static data for queued executions (#39668) (439e8ba)
    • core: Report empty node output in Instance AI workflow verification (#40047) (6438ead)
    • core: Resolve the request target against the dispatcher origin (#39506) (9183d04)
    • core: Resume Preview agents after waiting workflows finish (#40043) (bdab0b1)
    • core: Return upstream error details from the explore_node_resources MCP tool (#39775) (a931dd8)
    • core: Stop waiting on Bull job.finished() for queued executions (#39723) (c83fee0)
    • core: Stop waiting on enqueued jobs in worker shutdown (#40065) (fc3954b)
    • core: Use the new client ID and secret for OAuth2 client credentials (#39891) (44d9adf)
    • core: Wait for credential deletion to finish (#40103) (407cf23)
    • Databricks Trigger Node: Cap pipeline event pages at 250, the limit Databricks enforces (#40154) (b8cd29f)
    • DataTable Node: Continue paginated reads when row counts change (#39764) (d2eae41)
    • editor: Align Agent confirmation warning icons (#40040) (f1d4017)
    • editor: Align input heights on the project settings page (#39611) (ea9f451)
    • editor: Align Preview and Assistant chat history controls (#40165) (a30bb7d)
    • editor: Align workflow and agent action menus (#39234) (d09e6d6)
    • editor: Close the AI Assistant tab hover card when the pointer leaves the tab (#40003) (0817b0e)
    • editor: Correct the expanded Markdown editor close label (#40041) (ee46834)
    • editor: Do not run the workflow when the save before execute fails (#39763) (7204df6)
    • editor: Enable Save when SSO role provisioning switches back to manual (#39925) (360ec09)
    • editor: Extend workflow review divider to full height (#40035) (c5658ba)
    • editor: Fix copy button hover state in MCP settings (#39888) (f0b7013)
    • editor: Keep credentials unchanged on read-only canvases (#39889) (d69b52e)
    • editor: Keep execution filters when navigating away from executions (#39781) (fefb2da)
    • editor: Leave the sweep time of interrupted tool calls out of the Assistant thinking duration (#40161) (3879051)
    • editor: Preserve Agent instruction edits during autosave (#39972) (4d931ca)
    • editor: Refresh the Assistant chat list when the tab becomes visible (#40158) (064c3bf)
    • editor: Remove the new-agent pill from the AI assistant composer (#40014) (e79a2ba)
    • editor: Remove the one-click connector for the ChatGPT MCP client (#40123) (cbaea98)
    • editor: Restore full-width Agent preview (#39986) (5c0aff8)
    • editor: Scale up node icons that declare a size smaller than their slot (#40181) (3fe4612)
    • editor: Show full reasoning on first expand of assistant thinking block (#39892) (57ef0d1)
    • editor: Show remaining credits on Assistant banner for Cloud UBB (#39901) (29c09c6)
    • editor: Show warning when moving a workflow with data table dependency (#39752) (fce9570)
    • editor: Stop credential icon overlapping the credential name (#39944) (1694727)
    • editor: Unify MCP access labels (#40090) (88d6579)
    • editor: Use only server-provided hints for the OAuth consent screen icon (#37317) (01e5ebf)
    • editor: Wait for OAuth sign-in before the assistant credential card continues (#39998) (0a1ed4e)
    • Execute Workflow Node: Return declared sub-workflow outputs (#39755) (41a0cca)
    • Google Calendar Trigger Node: Handle all-day event boundaries (#39898) (900fe0c)
    • Hide node types that the instance does not load (#39571) (0afda58)
    • Keep workflow sharing open until changes are saved (#40137) (9e5eb79)
    • Limit MCP Agent model discovery results (#39973) (996dec3)
    • Pass shutdown margin to JavaScript runner in runners image (#40178) (df27223)
    • Persist nested node custom span attributes (#40107) (4a0865b)
    • Replace deprecated APIs in services and tooling (#40199) (be2ee6f)
    • Report the real cause when a module entrypoint fails to load (#37625) (5db0c39)
    • Scope the legacy setup credential picker to the target workflow and report unusable credentials on apply (#38197) (5c1f8f7)
    • Split Out Node: Support dot notation in destination fields (#39661) (f9dbd2c)
    • WhatsApp Node: Fetch all templates for the dropdown (#39497) (ce295b6)

    Features

    • ai-builder: Change knowledge subtitle (#39838) (6cc8c0d)
    • Azure OpenAI Chat Model Node: Add the deployment dropdown (#39643) (022f4a6)
    • core: Add 'align' prop to Select component (#39965) (b15ffa9)
    • core: Add a guardrail runner to the agent loop (#39621) (3745c83)
    • core: Add an instance setting for Agents (#40153) (628ada7)
    • core: Add an opt-in budget guardrail for agent runs (#39765) (d5937ed)
    • core: Add engine suspension at node boundaries for resumable executions (#37649) (680f958)
    • core: Add inbound-auth-core module with trusted source entities and migration (#39642) (0f63032)
    • core: Add remote search and programmatic focus to N8nCombobox so the MCP selects can leave N8nSelect (#40140) (8f13f28)
    • core: Add tool to mark an agent session as failed (#39754) (114a573)
    • core: Capture sidecall generation usd cost (#39627) (8c9733b)
    • core: Change IAI permissions logic (#39303) (99182c2)
    • core: Escalate background sub-agent approvals to parent chats (#39552) (5d40d83)
    • core: Export the stored schedule of durable system tasks as metrics (#40009) (3faf54f)
    • core: Hide current Agent references and show built Workflow cards in the embedded Assistant (#40149) (1043504)
    • core: Indicate unpublished changes in agent resource list view (#40177) (6a5aa78)
    • core: New agent styled differently on agent list view (#39856) (f931ea8)
    • core: Persist agent budget spend in the database (#40138) (a2fd418)
    • core: Run legacy Cron node schedules on the durable scheduler (#39411) (bab2978)
    • core: Send a log streaming audit event when a policy blocks an action (#39581) (55fd9da)
    • core: Serve the migration report overview from the finding table (#39969) (6769662)
    • core: Serve the migration rule detail from the finding table (#39974) (b8ff99f)
    • core: Stop engine v2 executions from the control plane (#39786) (56d6e9d)
    • core: Store isolated workflow suggestions for review (#39505) (0352a19)
    • core: Vanish Fix with Assistant banner when AIA fixes error (#39977) (0f11660)
    • Crypto Node: Add RSA-OAEP hash option (#39853) (94a49d0)
    • Databricks Node: Enable the Job resource (#40142) (fb69206)
    • editor: Add activation menus to Agent capabilities (#40104) (53b6a68)
    • editor: Add keyboard controls to n8n Assistant panel (#39386) (41994bc)
    • editor: Add Remove context menus to Agent configuration (#40089) (3d70eef)
    • editor: Add Stop all tasks to the Preview task panel (#40120) (25831a8)
    • editor: Add usage and budget settings for agents (#39909) (c4d31db)
    • editor: Allow reordering queued messages in Agent Preview (#40101) (33505d7)
    • editor: Close AI Assistant tabs and keep the open tabs per thread (#39660) (9ab649f)
    • editor: Open and collapse the logs panel around runs in the AI Assistant artifact view (#38773) (9a4a1dc)
    • editor: Open any project resource as an AI Assistant tab (#39663) (0c4bf38)
    • editor: Refine the workflow review detail layout (#39866) (373bf77)
    • editor: Release Browser Use to all users (#39762) (f58f0ec)
    • editor: Reorder AI Assistant tabs by dragging (#39664) (2f4bbfa)
    • editor: Replace severity with impact categories in the migration report (#39551) (0f77ba5)
    • editor: Show Gateway credits promotions on community nodes (#40010) (190d7c0)
    • editor: Show migration progress on report overview (#39861) (9d11369)
    • editor: Show n8n logo on canvas in canvas-only mode (#39846) (1153702)
    • editor: Show the trigger icon on the execute button and run a trigger from its menu (#39580) (55a8787)
    • editor: Show whose credential a node uses and let others switch from it (#40281) (92ae1b3)
    • editor: Stop Execute and Publish when a credential is not yours to use (#39883) (deaa9b1)
    • editor: Submit selected project changes from the promote modal (#39609) (f7cfb52)
    • Hide generated AI tools listed in NODES_EXCLUDE and empty node creator entries (#39577) (5e376b6)
    • Implements n8n Assistant nudge on workflow errors (#39774) (af26954)
    • Supabase Node: Add OAuth credentials and reuse them for MCP (#39979) (8e339d7)
    • Tell the AI Assistant which preview tabs are open (#39768) (10e484f)
    Original source
  • Sep 29, 2026
    • Date parsed from source:
      Sep 29, 2026
    • First seen by Releasebot:
      Sep 29, 2026
    n8n logo

    n8n

    2.42.0

    n8n improves AI Agent, MCP, API and editor behavior with a broad set of bug fixes, including workflow creation, session handling, telemetry, Redis recovery, and several node updates for more reliable automation.

    Bug Fixes

    • AI Agent Node: Let an AI Agent Tool use its own tools under a pre-v3 parent agent (#39160) (60d0598)
    • Align MCP workflow headings and remove outdated notice (#39463) (b096147)
    • API: Accept workflow descriptions on creation (#39705) (6c1edac)
    • API: Allow extendsCredential in workflow create/update (#39243) (9e7bc66)
    • API: Validate OpenAPI path parameter names (#39067) (a2a2638)
    • Azure OpenAI Chat Model Node: Make the Azure Entra credential sign in as the app (#39377) (2f98090)
    • core: Close Chat integration runtime on shutdown and let followers send (#38958) (3628dc1)
    • core: Count a database ping as successful when its reply arrives during event-loop lag (#39645) (bda9453)
    • core: Enforce one instance report per day with a unique index (#39536) (20807d2)
    • core: Gate the AI Assistant project list on the team-projects license (#39235) (dec7c71)
    • core: Keep one failed binary-data dir from aborting the delete batch (#39194) (34f77c0)
    • core: Keep OpenTelemetry export working after a restart when Sentry is enabled (#38480) (dbefd92)
    • core: Link MCP workflow access errors to workflow settings (#39738) (9f5c752)
    • core: Record live n8n Assistant test runs as verification evidence (#39361) (fb35797)
    • core: Release the expression isolate when the webhook response ends (#39138) (82cd04c)
    • core: Remove checkpoints when deleting agent sessions (#39175) (6a678f0)
    • core: Remove feature flag for MCP Registry in AI Assistant (#39018) (ecfec19)
    • core: Restore pubsub subscriptions after Redis reconnect and detect half-open subscriber connections (#39174) (3f76dcc)
    • core: Resume only private sessions in Preview (#39151) (dda9a56)
    • core: Retry each file removal in the byte store's delete (#39193) (7bebbe4)
    • core: Retry instance reports that cross the UTC midnight boundary (#39290) (f914770)
    • core: Retry the recursive removal of an execution's binary-data directory (#39185) (3a31c38)
    • core: Return test webhook response when the call lands on another main (#39382) (73bdae5)
    • core: Stop retrying instance reports the receiver rejects with 400 or 413 (#39502) (d9c9d6e)
    • core: Store queue job results only for executions this process enqueued (#39712) (5d508ec)
    • core: Use Sessions tab terminology in n8n Assistant (#39265) (43d7cc7)
    • core: Validate token payload before resolving the user (#39078) (7d1bae5)
    • editor: Fetch publication status when a new workflow becomes saved (#38382) (d658d18)
    • editor: Improve Agent layout and sub-agent guidance (#39791) (3daa34d)
    • editor: Keep agent builder chat messages within the panel (#39233) (9142b47)
    • editor: Keep agent capability chips within card width (#39532) (9329d1f)
    • editor: Keep quick-connect OAuth credentials out of lists until the user authorizes (#39297) (4c2f220)
    • editor: Keep typed text in the AI Assistant chat rename input (#39570) (42dc399)
    • editor: Make agent configuration header more compact (#39172) (1c82574)
    • editor: Move agent AI entry point below header (#39318) (afa5fc3)
    • editor: Prefill the server URL in the Mistral Vibe connector link (#39518) (d4999a2)
    • editor: Remove half-checked permissions from system instance roles and restore the Member preset (#38652) (c114a18)
    • editor: Shorten the Assistant name in navigation and settings (#39288) (5cc6640)
    • editor: Show a cached role at once and align the personal space block in the instance role editor (#39394) (e648610)
    • editor: Show Agent Builder activity on prompt submission (#39501) (8a0d833)
    • editor: Show project icons in Agent breadcrumbs (#39649) (1fe19db)
    • editor: Show when update available for community packages if only verified packages are enabled (#39424) (070d9fe)
    • editor: Sorting data table rows by unknown column returns raw database error (#39733) (b8cda55)
    • Google Cloud Storage Node: Preserve request headers on object create (#35218) (bc9faf2)
    • googleFirebaseCloudFirestore Node: Preserve field types for numeric strings and falsy values (#27399) (b3d4cfe)
    • LinkedIn Node: Validate post text (#39201) (d1cd34b)
    • Make n8n-node release work with release-it 21 (#39378) (d23f949)
    • MCP Client Node: Terminate session before closing the client (#39526) (11acaa3)
    • Microsoft Teams Node: Correct the v2 resource-locator copy (#39443) (a924724)
    • Mistral Cloud Node: Support citation reference chunks (#38952) (a9bc9c5)
    • Notion Node: Clarify simplified output for AI workflow generation (#39051) (67b70ea)
    • Preserve tables in AI workflow builder web fetch (#38879) (07a741b)
    • Preserve tool arguments in reconstructed history (#39153) (fe0fad5)
    • Recover running preview chat after reload (#39311) (98f012e)
    • Validate node codex categories during linting (#39543) (a3aa6c0)
    • Wise Node: Use current sandbox API (#39255) (3c48cef)
    • Xero Node: Send tenant header on every page when returning all items (#39431) (58e55b5)
    • Zoho CRM Node: Update logo to current Zoho branding (#39305) (be12181)
    Original source
  • Sep 22, 2026
    • Date parsed from source:
      Sep 22, 2026
    • First seen by Releasebot:
      Sep 26, 2026
    n8n logo

    n8n

    2.41.0

    n8n adds major AI Assistant and Agent Builder updates, including standalone node execution, improved workflow verification and editor polish, plus new API, role and node enhancements across Databricks, Microsoft Teams, OpenAI, S3 and more.

    Bug Fixes

    • ai-builder: Pass parent ask-user answers into Agent Builder (#38693) (e149dfa)
    • ai-builder: Reactive subject name on chip (#39097) (233afff)
    • cli: allow importing workflows and credentials with --userId for existing owner (#36278) (0b9c174)
    • core: Always cast resource mapper string fields when type conversion is enabled (#37851) (768e74a)
    • core: Apply the same mandatory roles when creating role from API and frontend (#38860) (ec54145)
    • core: Bound concurrent HashiCorp Vault external secrets reads (#38866) (43fa826)
    • core: Bump Strapi listing version for streamable-http-templated (#38595) (4514a35)
    • core: Eliminate false-negative 500s in workflow builder tools (#34975) (4f26727)
    • core: Expose Telegram photo context to agents (#38979) (3f06dd8)
    • core: Finalize the active execution when a stalled job turns out to have succeeded (#38220) (a5995d7)
    • core: Fix workflow publishing silently failing in multi-main mode (#38431) (fb0917c)
    • core: Follow user language changes in Assistant and Builder (#39119) (a378ba3)
    • core: Guard worker execution save against overwriting a canceled status (#38957) (f4f3011)
    • core: Hide the Custom Scopes toggle when an MCP registry row pins the credential scope (#38635) (d05cf2b)
    • core: Include sub-workflow tool calls in the workflow dependency index (#38062) (d3c8eee)
    • core: Keep Assistant and Agent Builder replies in the user's language (#39101) (0781378)
    • core: Keep breaking change detection running when a rule throws (#38738) (c2a2733)
    • core: Keep collecting insights after one un-attributable event (#38518) (0b2ff22)
    • core: Keep workflow version ids out of the package content file and the promotion diff (#39091) (f3c5a57)
    • core: Observe agent execution tail when observation cursor moved in the middle of the run (#38907) (d1c805a)
    • core: Offer Computer Use only where the client shows its entry points (#38108) (2f352bd)
    • core: Preserve unchanged nodes during n8n Assistant edits (#38967) (3f7c984)
    • core: Recheck the execution status before failing a stalled queue job (#38138) (a4c977d)
    • core: Repair data-encryption keys stored as the raw instance key (#38707) (d7e2dcd)
    • core: Report publication state after n8n assistant workflow restores (#39037) (c2534c5)
    • core: Report saved and executed workflow revisions to n8n Assistant accurately (#38902) (0f3c8f0)
    • core: Reserve canvas space for collapsed node groups during workflow layout (#38149) (7d8d58f)
    • core: Resolve hidden OAuth endpoint fields from the credential type for all credentials (#38697) (e82a373)
    • core: Return available build errors in one tool result (#38231) (e36572e)
    • core: RFC 9068 compliance for MCP OAuth access tokens (#38310) (45a3833)
    • core: Show an explicit error for unsupported end-user credential triggers (#37332) (c5935b9)
    • core: Simulate Agent write tools during workflow verification (#38553) (cd623fd)
    • core: Stop an unreachable external secrets provider from blocking startup (#38257) (f960330)
    • core: Stop pages hanging while the Browser Use extension is attached (#39159) (048f0a7)
    • core: Sweep parents parked on a finished sub-execution (#37553) (48445f5)
    • core: Tear down workflow triggers when publication meets a node type the instance cannot load (#38754) (378e926)
    • core: Test the posted OAuth2 credential values instead of the stored credential (#38877) (247e441)
    • core: Update undici to 7.29.1 (#38844) (41e1780)
    • core: Update vm2 to 3.12.2 (#38823) (74ab9c2)
    • Databricks Node: Enforce the credential domain allowlist on chat model requests (#38694) (2f31b65)
    • Databricks Node: Name Databricks in the Chat Model rate limit error and keep its message (#38642) (bf5d488)
    • editor: Add tooltips to assistant header actions (#38946) (3ea0397)
    • editor: Add top padding to the n8n Assistant permission dropdowns (#38718) (92a3a28)
    • editor: Agent preview thread wiring update and error markers (#38826) (8fcb236)
    • editor: Align agent knowledge sections with panels (#38696) (506b768)
    • editor: Align AI Assistant permission dropdowns with the group control (#38196) (dba75ff)
    • editor: Align AI chat history menus (#38983) (3544561)
    • editor: Apply Gateway credits eligibility to Agent tool resource and operation selectors (#38828) (67c304b)
    • editor: Clarify n8n Assistant approval details (#38422) (8dd2b78)
    • editor: Convert a pasted expression into expression mode in the resource locator input (#38872) (b26bb7f)
    • editor: Correct Agent Builder chat layout and update notices (#38987) (9f57c91)
    • editor: Disable 'pinning' redacted data if user does not have permission to un-redact it (#38334) (c247cff)
    • editor: Fix blank workflow previews in AI Assistant (#38608) (062e99e)
    • editor: Improve Assistant chat controls and history menu layout (#39212) (263eda0)
    • editor: Keep agent icon background visible (#39112) (30b3226)
    • editor: Keep NDV input and output panel content visible at narrow widths (#38615) (6a9bbd9)
    • editor: Keep the Instance AI chat input live during plan review (#38086) (c4c7365)
    • editor: Match n8n Assistant header background (#38944) (0f0fca1)
    • editor: Prevent agent builder shift during assistant transition (#38948) (536ae3e)
    • editor: Prevent agent credential warnings during tab switches (#38816) (1ad183a)
    • editor: Prevent dropdown menu overlap (#38835) (b681645)
    • editor: Refine agent instructions and trace view (#39104) (e94dff4)
    • editor: Remove empty agent button hover background (#38788) (da55339)
    • editor: Render bare URLs in Instance AI chat as clickable links (#39060) (d5393f2)
    • editor: Restore MCP connection popup retries (#37956) (4d9cd43)
    • editor: Send number values in credential inputs (#38715) (efc9c85)
    • editor: Show step indicators in dark mode (#38937) (76fd3a0)
    • editor: Split global variable scopes to be added to custom roles separately (#38724) (7b059d6)
    • Email Trigger (IMAP) Node: Recover from silently dead connections by moving to imapflow (#36716) (5f6627a)
    • Form Node: Validate content type (#38720) (1d0c658)
    • Keep the logs panel header height fixed (#38675) (386fedf)
    • Limit declarative routing during base URL ownership checks (#39058) (3d00ed9)
    • Monday.com Node: Migrate to API version 2026-07 (#26262) (75a2fe5)
    • Open the EULA modal when a license is activated from a link (#38712) (5c1dfef)
    • OpenAI Node: Accept object values for JSON-typed parameters (#33886) (92b1aad)
    • S3 Node: Handle files with + in names (#38688) (7ff87c4)
    • Show a reveal prompt for expressions over redacted data (#38577) (34f7327)
    • Show only chat models in the Gemini and Qwen model dropdowns (#38800) (94c12a6)
    • Slack Node: Point OAuth2 scopes notice to an existing docs anchor (#38992) (1525f3a)
    • Snowflake Node: Update the Snowflake SDK to 3.3.0 (#38798) (5334420)
    • Unify startup deadlines and cancellation (#37927) (9e18c4a)

    Features

    • Add admin permission for node execution in n8n assistant (#39102) (2f65a6b)
    • Add standalone node execution as a Workflow Builder and AI Assistant tool (#37512) (2d56eee)
    • API: Allow credential creation with source IDs (#38791) (85b3be3)
    • API: Pause promotion Apply until bindings are resolved (#38741) (74334d2)
    • core: Add an AI Assistant tool that runs one node of a workflow (#38601) (ac752e7)
    • core: Add promotion binding preflight with creation context (#38657) (62ff356)
    • core: Add push-based reload endpoint for custom node development (#36837) (8bafdfa)
    • core: Add view and delete permissions for executions to project roles (#38698) (f032577)
    • core: Filter out MCP servers from the registry based on instance capabilities (#38867) (873948b)
    • core: Return credential descriptions in assistant and MCP tools (#38984) (6f74038)
    • core: Send maxN8nNodesApiVersion in community-nodes catalog requests (#38968) (c16bf24)
    • core: Track AI Assistant response start latency (#37003) (288e5e3)
    • Databricks Node: Add hidden Databricks Embeddings sub-node (#38989) (48b1274)
    • Databricks Node: Show the Chat Model node in the node picker (#38918) (d42a753)
    • editor: Add instance promote action to Environments settings (#38985) (d8882f7)
    • editor: Distinguish skills from tools in session timelines (#38481) (77e10b0)
    • editor: Explain agent task schedules (#39117) (add77db)
    • editor: Improve agent builder interactions (#38728) (b7b4722)
    • editor: Improve AI Assistant sidebar and history dropdown (#38419) (25dc45d)
    • editor: Make view related tag permissions available by default (#38640) (f9fcf37)
    • editor: Move agent skills to a separate card (#38993) (7683e1c)
    • editor: Move web search to agent capabilities (#38646) (a6ca37c)
    • editor: Open Edit with AI without a greeting turn (#38745) (0a4976e)
    • editor: Open new agents in the builder with the n8n Assistant panel (#38727) (d3b8445)
    • editor: Refactor ResizeWrapper and add to Agents Preview Dock (#38250) (d7d8c03)
    • editor: Render a restricted node type on the canvas with a replace path (#38859) (f03ffd7)
    • editor: Show recent agent changes (#38796) (ee9177d)
    • editor: Show the personal space permissions in the instance role editor (#39108) (51a0512)
    • editor: Show timestamp dividers in the agent preview chat (#38962) (a70938f)
    • Microsoft Teams Node: Add @mention support to message Create (#37624) (9c83613)
    • Microsoft Teams Node: Add @mentions on Reply and team tag mentions (#38023) (2627912)
    • Microsoft Teams Node: Add a Chat resource with create, get and get many (#38035) (0b559b5)
    • MiniMax Node: Fetch available models from the API instead of a hardcoded list (#37646) (0392123)
    • Pin the sandbox service version in get-n8n.sh and update it on --upgrade (#38799) (914eabb)
    • Wire up the email change confirmation flow (#38730) (ccaeeb7)
    Original source
  • Sep 15, 2026
    • Date parsed from source:
      Sep 15, 2026
    • First seen by Releasebot:
      Sep 15, 2026
    n8n logo

    n8n

    2.40.0

    n8n fixes a broad set of issues across AI Agent, builder, editor, API and core workflows, improving reliability, permissions, trigger handling and UX while tightening redaction, retries and publishing behavior.

    Bug Fixes

    • AI Agent Node: Preserve Anthropic thinking blocks with empty text across tool calls (#38302) (7ac975c)
    • ai-builder: Enhance guidance UX for agents with no sessions on builder session tab (#38243) (1ed3a24)
    • ai-builder: Guard against 429 errors on channel integrations (#38106) (93ca2d1)
    • ai-builder: Show reusable credentials in the Instance AI agent credential card (#38276) (999b541)
    • Allow one icon file for the light and dark icon slots (#37711) (9095e9a)
    • API: Let global members grant folder scopes to API keys (#37654) (aa91e71)
    • API: Return null variable values as empty string & fix newly imported source control variable values (#38488) (b9a7f03)
    • Azure OpenAI Chat Model Node: Resolve the proxy against the Azure endpoint so NO_PROXY applies (#38026) (7383fd7)
    • Bump task-runner-launcher to 1.5.0 (#38309) (9135888)
    • Center the registration badge in the Usage and Plan heading (#38275) (cf6cb77)
    • Close the variable modal on a backdrop click (#38286) (45a7f74)
    • Confluence Node: Match hyphenated and multi-word titles in the page picker search (#38175) (fdb31d2)
    • Confluence Node: Return the page sub-tree in tree order and skip drafts (#38403) (b0f47eb)
    • core: Accept null headers from mcp registry api (#38614) (02ee221)
    • core: Accept numeric pagination tokens from resource locator list methods (#38147) (7ab1582)
    • core: Add model boundaries to external tool results (#37316) (d328bbf)
    • core: Allow a fallback model alongside the primary on AI nodes (#38007) (2550501)
    • core: Apply the SSO expression mapping env var in the provisioning loader (#37170) (b4fee56)
    • core: Ask which MCP connector to set up before the AI Assistant gives a URL (#37992) (899d52d)
    • core: Batch LangSmith agent session exports (#38030) (79d936f)
    • core: Bound the wait for the workflow publication lock (#38019) (5212777)
    • core: Check Gateway credits eligibility against the correct sub-node (#38193) (9823c2e)
    • core: Consolidate secret redaction in @n8n/utils and redact more credential shapes (#38054) (c5653f6)
    • core: Correct the expression prefix warnings on fields that cannot hold an expression (#37791) (c7c179b)
    • core: Count executions that crash recovery marks as crashed (#37733) (3521e54)
    • core: Do not persist an execution when preExecute throws (#37701) (53ecf6b)
    • core: Enforce execution timeout for stuck jobs in queue mode (#36258) (92f702d)
    • core: Execute MCP toolkit members on workers (#38069) (c0f6471)
    • core: Forward the receiver in the lazy-proxy set trap (#37321) (b3306b2)
    • core: Ground provider OAuth scope guidance in n8n docs (#38066) (2afb5b6)
    • core: Keep a resumed execution in the trace of the parked execution (#38033) (5414403)
    • core: Keep node settings, positions and error routes through an assistant workflow edit (#38254) (c95756d)
    • core: Keep nodes clear of the agent card in SDK-generated workflow layouts (#38093) (4b4d670)
    • core: Memoize pairedItem ancestry traversal (#38085) (f3db19d)
    • core: Merge system messages for strict providers (#37908) (19651de)
    • core: Prefer native nodes over Code nodes in n8n Assistant workflow builds (#38598) (4e1fcf6)
    • core: Preserve link URLs in inbound agent chat messages (#38294) (2beccad)
    • core: Prevent false agent model stream stalls and show run errors in chat history (#37558) (26afe95)
    • core: Re-register the n8n Trigger on every publish through the publication service (#38153) (cbda01a)
    • core: Read the Instance AI folder-exploration flag as a variant, not a boolean (#38479) (4579e78)
    • core: Recognize always-loaded tools in agent tool discovery (#38204) (4a6e625)
    • core: Reconnect the Email Trigger (IMAP) on every publish through the publication service (#38190) (db60f99)
    • core: Reconnect the Postgres Trigger on every publish through the publication service (#38211) (0c3c9d7)
    • core: Redact execution data on partial private-credential runs (#38364) (840aef6)
    • core: Redact opaque field values in confirmed secret containers (#38067) (3bd0e69)
    • core: Register redaction context hook on all instance types (#37298) (56383fc)
    • core: Repair legacy-format data-encryption keys during bootstrap (#38100) (4b36c51)
    • core: Require verification coverage for every workflow trigger (#37961) (429116f)
    • core: Retry Instance AI model turns when the provider stream closes without output (#38080) (b6b5ecd)
    • core: Return Instance AI node output grouped per output branch (#38414) (e44fbd3)
    • core: Return luxon values from expressions as instances (#38034) (0c6c9e3)
    • core: Reuse an existing consent grant after the visitor authenticates mid-flow (#38084) (3b6faa2)
    • core: Route "trigger my workflow" to the existing workflow, not the builder (#38073) (219402c)
    • core: Run tool nodes of an AI Agent upstream of the destination node (#38348) (40b6d84)
    • core: Scope data table Overview access by project role, not a global gate (#37676) (a47f19b)
    • core: Scope end-user credential checks to reachable nodes (#36970) (37e50b5)
    • core: Select sandbox npm install flags by provider (#38358) (ab101d5)
    • core: Send a JSON Accept header in the Brave Search credential test (#38594) (2f55165)
    • core: Settle answered confirmation cards in the AI Assistant run-sync frame (#38328) (4890d04)
    • core: Stop MCP workflow updates from dropping unknown operation fields (#38148) (a1f8405)
    • core: Stop the workflow SDK collapsing inline branch chains to their branching node (#37717) (37efe11)
    • core: Treat empty strings as empty in Data Table filters (#32887) (0c82743)
    • core: Treat Instance AI model stream stalls as dropped provider connections (#38079) (b7a58c2)
    • core: Trust the CA from GIT_SSL_CAINFO for source control HTTPS remotes (#38258) (e803d4b)
    • core: Unpublish workflows before a source control pull deletes them (#37967) (ecc4ba3)
    • editor: Align Instance AI input controls (#37162) (a234034)
    • editor: Allow creating web search credentials from the agent builder settings (#38574) (5213246)
    • editor: Allow switching a toggle parameter from expression to fixed (#32762) (a053578)
    • editor: Center modal dialogs vertically in the viewport (#38081) (f3196f1)
    • editor: Clear tag loading state after failed requests (#37901) (b4fbcc5)
    • editor: Fixes issue that prevented some users from revoking their end-user credentials (#38311) (fc8a021)
    • editor: Hide Custom API Call option in node tool configuration (#38365) (79f0e04)
    • editor: Hide the AI Assistant settings page when it has nothing to show (#38063) (4f05c24)
    • editor: Rename the first agent builder tab to Build (#38184) (06fc433)
    • editor: Reserve space for list and table scrollbars (#38603) (f81cbcd)
    • editor: Restore legacy sticky note markdown spacing (#38333) (064e909)
    • editor: Restore tag text hidden by zero line-height (#38107) (7e152a4)
    • editor: Show friendly labels for the activity and conversation-history tools in the n8n Assistant chat (#38447) (fe5de38)
    • editor: Show loading skeletons in the AI Assistant artifacts sidebar (#38180) (b3e1b7f)
    • editor: Show renamed credentials in the AI Assistant setup picker (#38295) (39dfe59)
    • editor: Stop rendering task and sub-agent labels with no text (#38059) (8cb5159)
    • editor: Stop the Publish modal from hanging after a workflow is published (#38151) (d0f94da)
    • editor: Strip Evaluation Trigger metadata fields from test case inputs (#37572) (c410581)
    • editor: Truncate long AIA context chips (#37878) (af2bd80)
    • editor: Use the push scope for the source control owner filter (#38682) (8671d83)
    • Email Trigger (IMAP) Node: Restore the connection after the server drops it (#36801) (1776a51)
    • Enforce protected instance execution restrictions (#37947) (793136b)
    • Guard the getWebhookInfo response shape (#38680) (d057d86)
    • Guardrails Node: Align threshold hint with behavior (#29018) (0396ef8)
    • Hide the deprecated node and show a deprecation notice (#38571) (c220447)
    • Hint the Microsoft OAuth2 scope format and link the Service Principal credential docs (#38451) (404ab49)
    • Keep GitHub Actions expressions intact in scaffolded workflow files (#37973) (8c8bd23)
    • Microsoft Excel Node: Accept personal OneDrive workbook IDs in the By ID field (#38471) (d04d3a4)
    • Microsoft Excel Node: Show only workbook files in the Workbook picker (#38244) (763e0cf)
    • Microsoft Outlook Trigger Node: Fetch the latest message when executing manually (#34486) (ef16421)
    • Microsoft SharePoint Node: Keep the resource dropdowns working when the API omits a label (#38411) (d6fe24d)
    • Postgres Node: Stop reporting parameter-loading errors to Sentry (#28865) (663bb3e)
    • Refresh the Confluence/Jira OAuth2 token automatically when it has expired (#37776) (3d293b5)
    • Resolve node source path before the translation lookup (#38281) (092e53b)
    • Scope deployment key lookups by type (#38410) (11cc120)
    • Scope workflow sharing candidates to personal projects (#38222) (dcb1d17)
    • Serve binary data stored in the temp execution dir (#38270) (7bac547)
    • Show credentials shared with all users and projects in the (#38287) (30d44a5)
    • Show custom role scope tooltips next to the hovered scope (#38284) (78ea57e)
    • Stop requiring Organization.Read.All for the Microsoft Entra Service Principal credential test (#38568) (59715e8)
    Original source
  • Sep 8, 2026
    • Date parsed from source:
      Sep 8, 2026
    • First seen by Releasebot:
      Sep 9, 2026
    n8n logo

    n8n

    2.39.0

    n8n fixes a broad set of core, editor, AI, and node issues, improving stability, security, and workflow reliability across agent tools, chat features, credentials, webhooks, and integrations.

    Bug Fixes

    • ai-builder: UI tweak to prevent overflowing text on err callout when on Agent Preview (#37615) (c2e8d02)
    • AMQP Trigger Node: Reattach the receiver link when the broker detaches it (#37431) (ddf6534)
    • Anthropic Chat Model Node, AI Agent Node: Send disabled thinking to the provider and parse content-block output (#37954) (309fa8d)
    • API: Check publish permission when a workflow save republishes (#37264) (485e370)
    • Chat Trigger Node: Fix singular copy on the connect bar (#37945) (369c9e2)
    • Chat Trigger Node: Re-authenticate hosted chat on session change (#37868) (64ba49d)
    • Check constructor-assigned and type-asserted node descriptions (#37523) (e23ee05)
    • Code Node: Keep identity and reporting fields when wrapping task runner errors (#37490) (b0550cb)
    • core: Allow HashiCorp Vault external secrets to read a KV v2 sub-path (#37748) (fed5d70)
    • core: Allow webhook nodes to set Set-Cookie response headers (#37883) (6828320)
    • core: Always redact OTel header values in settings responses (#37283) (4b0de25)
    • core: Cap task runner task timeouts to the graceful shutdown window (#37651) (9a64820)
    • core: Complete a scheduled occurrence as not dispatched when its workflow is unpublished (#37721) (29c7d9f)
    • core: Ensure running job cleanup when a workflow run rejects (#37621) (51ac147)
    • core: Execute multi-input nodes re-fired through a loop-back edge in legacy order (#37561) (903fe57)
    • core: Fix Azure OpenAI classic and Foundry credential setup and execution for agents (#37251) (731ea42)
    • core: Forward all output branches when a waiting webhook node resumes (#31714) (7c21f4b)
    • core: Give every simulated node at least one plausible item (#37557) (918067a)
    • core: Harden agent workflow tools against unpublished, missing, or incompatible workflows (#37772) (1994332)
    • core: Hide instance MCP OAuth discovery when MCP access is disabled (#36726) (9768c1b)
    • core: Keep a serving external secrets provider active when its replacement fails (#37781) (217c7b3)
    • core: Keep Instance AI data-table queries targeted while diagnosing (#37489) (df4d30b)
    • core: Keep reporting the original job error when the job key is gone (#37993) (7ce17be)
    • core: List the valid techniques when get_workflow_best_practices rejects input (#37580) (53b1ad7)
    • core: Make pending agent creation and thread binding idempotent (#37074) (085a7a9)
    • core: Make scoped workspace path errors actionable for agents (#37887) (03e1793)
    • core: Mark retired node types as deprecated in their workflow-sdk type definitions (#37628) (cf0ef47)
    • core: Prefer service-specific credentials for HTTP requests (#37844) (500ea39)
    • core: Prevent Anthropic agent threads from breaking permanently and keep run errors visible (#37640) (dc5f420)
    • core: Redirect failed OIDC logins to the sign-in page (#37428) (3e09299)
    • core: Report the provider response when a chat model returns no choices (#37959) (49e7821)
    • core: Return 503 when the AI assistant service is unreachable (#37957) (36426a8)
    • core: Stop npm audit from stalling Instance AI sandbox setup (#37864) (7ac335d)
    • core: Stop task broker before task runner processes on shutdown (#37833) (2ad8d01)
    • core: Stop the AI Assistant from pulling the whole workflow through the model for small edits (#37644) (8ef5ba6)
    • core: Take archived workflows into account during package import (#37668) (98dfb30)
    • core: Update Qdrant client and remove undici v6 dependencies so AI requests work on Node 26 (#37758) (325feb3)
    • core: Wait for detached sub-workflows before the worker stops its task runner (#37737) (afc4a54)
    • core: Workflow tools should wait and not throw if parent WF is suspended (#37087) (10ea0c8)
    • editor: Align credit balance copy to "left" across views (#37423) (9c131d6)
    • editor: Expand AI question text input automatically (#37627) (5e3774a)
    • editor: Hide Gateway credits for HTTP Request and GraphQL nodes (#37810) (c292476)
    • editor: Preserve n8n credits when copying workflows (#37253) (8946168)
    • editor: Refresh workflow checksum after publishing from an embedded editor (#37949) (8119ea3)
    • editor: Restore Instance AI draft when thread creation fails (#37874) (0820083)
    • editor: Scope end-user credential trigger warning to reachable nodes (#37081) (8399317)
    • editor: Show restart notice after license activation (#37841) (f56d87d)
    • editor: Show skill size limits as a character count (#37847) (a9d5fb7)
    • editor: Update Agent builder assistant placeholder (#37529) (20cf19f)
    • Fix attribution footer link on the Form Ending page (#37288) (e08a4fd)
    • Freshservice Node: Send change filters as dedicated query params (#34380) (5ae1861)
    • Google Gemini Node: Validate domain before downloading (#37459) (a1c1f6f)
    • Guarantee package.json restore after the FE trim step (#37446) (fd6db75)
    • Jira Node: Strip trailing slashes from domain URL (#32163) (a69155a)
    • Jira Software Node: Send expand as comma-separated string for Jira Cloud searches (#37527) (9f2ebe5)
    • Ldap Node: Escape expression output in the Custom Filter field (#37301) (91f8794)
    • Microsoft SQL Node: Fix TLS error when the IP is used to connect to the server (#37870) (5ddfb60)
    • Microsoft Teams Node: Send Online Meeting times in UTC and share the Graph helpers (#37723) (d5e05b2)
    • Mistral Cloud Chat Model Node: Handle Request objects in undici-backed proxyFetch (#37946) (7533aaa)
    • Read/Write Files from Disk Node: Allow glob character classes in File(s) Selector (#36901) (3c48b53)
    • Sign Microsoft Dynamics OAuth2 requests with the access token (#37855) (6fa5b3d)
    • Update MCP server status in AI Assistant when tool call failed or credentials updated (#37197) (b639fe5)
    • Use consistent personal space icon in the Instance AI artifacts (#38011) (cbaa0be)
    • Wordpress Node: Send OAuth2 client credentials in request body (#36082) (5aeb96c)
    Original source
  • Aug 25, 2026
    • Date parsed from source:
      Aug 25, 2026
    • First seen by Releasebot:
      Aug 25, 2026
    n8n logo

    n8n

    2.37.0

    n8n fixes a wide range of core, editor, AI Builder, and node issues, improving reliability, security, credential handling, and agent workflows while polishing the user experience across the platform.

    Bug Fixes

    • Agent Node: Show disabled reason on prompt-source option (#36612) (85869e8)
    • ai-builder: Fix for autosave and publish events issues (#36241) (87e8b9c)
    • ai-builder: Task to channel agent session bind consolidation (#36730) (07559f6)
    • ai-builder: Wrap message for openAI completions (#36760) (5f83045)
    • Anthropic Chat Model Node: Update default model to Claude Sonnet 5 and improve model guidance (#36834) (51b5579)
    • API: Require a JSON content type on decorator routes that take a body (#36748) (3bc56a4)
    • API: Return a request schema for decorator routes in /discover (#36211) (39be106)
    • AWS Bedrock Chat Model Node: List application inference profiles in model dropdown (#36728) (2b3f683)
    • core: Abandon trigger teardown that can never succeed instead of retrying it forever (#36843) (62d7e4c)
    • core: Accept multipart form submissions with an empty file input (#36832) (7f3589c)
    • core: Add project:manageUsers scope to gate project membership changes (#36243) (8c6d469)
    • core: Apply credential defaults and expressions in Agent Builder model discovery (#36721) (955c472)
    • core: Avoid restarting task runners that are only slow (#36530) (222eec5)
    • core: Capture browser secrets independently of match boundaries (#36447) (d5133e5)
    • core: Coerce the deleteBefore param when deleting executions (#36477) (aa126ab)
    • core: Handle managed credentials in workflow codegen (#36210) (59efcb9)
    • core: Handle projects better on AIA workflow listing (#36413) (e1a6ede)
    • core: Harden Daytona sandbox acquisition against transient failures and stuck sandboxes (#36528) (be44726)
    • core: Hide get-json from Instance AI (#36146) (dfe7c02)
    • core: Honor an explicit request for a new credential during setup (#36348) (4c8ae8f)
    • core: Include workflow description in source control push and pull (#33695) (fca3170)
    • core: Keep duplicate connections distinct in the workflow diff (#35652) (12a2e38)
    • core: Keep Instance AI confirmation fields intact on resume (#36468) (befb947)
    • core: Limit domain restriction errors to the target host (#36836) (0472294)
    • core: Normalize env values before schema-based parsing (#36644) (226aafc)
    • core: Offer to clean up test data left by live test runs in AI Assistant (#36448) (616dd65)
    • core: Only init the expression engine for commands that evaluate expressions (#36538) (f808447)
    • core: Pass MCP connector tools to Agent Builder (#36753) (2c12be2)
    • core: Raise AI Assistant model verification token limit (#36787) (655270b)
    • core: Reconcile license auto-renewal on startup leader takeover (#36897) (f79eccf)
    • core: Redact secrets rendered beside their label in browser snapshots (#36817) (077d778)
    • core: Reduce cold-boot community package install storm (#36814) (f2bce4e)
    • core: Release test-webhook isolate only after teardown completes (#36573) (05de343)
    • core: Report activation mode 'activate' for a first publication via the outbox (#36512) (2435ed5)
    • core: Resolve end-user credentials when loading node parameters (#36452) (83db64a)
    • core: Restore AWS Secrets Manager connection reuse (#36426) (56bb5f5)
    • core: Route leader-only channel operations through the leader (#36686) (28145a5)
    • core: Run agent scheduled tasks in the timezone they were authored in (#36226) (3d70ae7)
    • core: Serialize community package installs and make downloads non-destructive (#36505) (e95d407)
    • core: Show a clear no-access message when SSO role mapping denies a login (#36407) (85f7dde)
    • core: Stop showing working community packages as failed to load (#36727) (5439265)
    • core: Support array indices in setNodeParameter JSON Pointer paths (#36520) (7a69e3f)
    • core: Surface agent failures with a useful message and original cause (#36603) (53bd5f7)
    • core: Surface failures in agent sessions (#36492) (d551999)
    • core: Validate access token audience in OAuth2 credential resolver (#35119) (a65e0e3)
    • core: Validate chat and MCP trigger auth modes for end-user credentials (#36534) (bf700d1)
    • core: Validate chat models and recover from execution failures (#36550) (9376c57)
    • core: Validate credential types in AI Assistant credential setup (#36792) (497cf53)
    • core: Wrap a trigger's closeFunction in an expression isolate at creation time (#36638) (365b703)
    • editor: Add padding to evaluation single run view (#36929) (e75bf3e)
    • editor: Fix non-project credentials sometimes appearing as options (#36715) (ffd2b35)
    • editor: Group output panel warnings to keep it usable (#36619) (37aee61)
    • editor: Keep agent preview user messages right-aligned (#36521) (09613dc)
    • editor: Keep AI Assistant step narration inside thinking blocks (#36808) (af27b0d)
    • editor: Keep form element attributes when reordering or deleting (#36395) (c31d0e5)
    • editor: Load agent data table columns on selection (#36634) (52c29a8)
    • editor: Move the trust checkbox out of the MCP consent redirect callout (#36543) (dfae315)
    • editor: Open new agents without Instance AI (#36462) (38ec2ec)
    • editor: Open node details links in a new tab in canvas-only mode (#36446) (43220e1)
    • editor: Prevent AI Assistant verification fixtures from being pinned as real data (#36653) (fe79e4a)
    • editor: Remove doubled code block box in markdown renderer (#36844) (36c5dc3)
    • editor: Remove stale credentials from node config when switching credentials (#34937) (f34e4c6)
    • editor: Restore AI Assistant preview width after viewport resize (#36433) (48b245c)
    • editor: Restore Edit Fields type selector styles (#36400) (b0cfa93)
    • editor: Show agent validation details in tooltips (#36772) (b7c3fe7)
    • editor: Show personalization survey and community registration modal on Instance AI landing page (#36809) (7d0a445)
    • editor: Show proper MCP server status in AI Assistant UI (#36180) (76c6721)
    • editor: Show the pinned version name in the review banner (#36759) (f86bd3a)
    • editor: Treat agent persistence and channel setup as one in-flight action (#36577) (53f2750)
    • Extract From File Node: Parse date-only RRULE UNTIL values (#29522) (fa460a4)
    • Fix setup credential tool description (#36766) (40af9a0)
    • Google Calendar Node: Allow switching an event between all-day and timed (#35802) (34de8b3)
    • MCP Server Trigger Node: Emit tool schemas as JSON Schema 2020-12 (#36490) (25d0be0)
    • Message an Agent Node: Default the session to the connected Chat Trigger (#36482) (63ffacf)
    • MongoDB Chat Memory Node: Sanitize messages (#36294) (2f2e2d9)
    • OpenAI Node: Filter non-chat models out of the chat model dropdown (#35785) (207c29f)
    • PagerDuty Node: Advance pagination offset by the page size (#35778) (485a9c0)
    • Preserve explicit credential selection (#36500) (7b94975)
    • Recognise versioned nodes in node-registration-complete lint rule (#36642) (d1286e3)
    • Return list-search pagination token as a string in github-issues template (#36657) (ad22ee8)
    • Use MS Excel as default Sheets export format (#36406) (b9bdaff)
    • Use sub-agent names and publish before assignment (#36846) (131f664)
    Original source
  • Aug 18, 2026
    • Date parsed from source:
      Aug 18, 2026
    • First seen by Releasebot:
      Aug 18, 2026
    n8n logo

    n8n

    2.36.0

    n8n releases a broad update packed with AI builder and editor improvements, new MCP and agent capabilities, expanded API and node features, and a long list of fixes for workflows, credentials, chat, and integrations.

    Bug Fixes

    • ai-builder: Align HITL approval resume schemas with confirm envelope (#36047) (be1fde1)
    • ai-builder: Enable Save in agent tool modal when credential auth is selected (#36012) (4fe94d8)
    • ai-builder: Prevent agent from claiming integration tool call success early (#36196) (547cfb9)
    • ai-builder: Recover stuck tool-call UI and MCP timeout progressive update (#36162) (e1cd757)
    • ai-builder: Surface existing LLM-provider credentials when a filtered lookup finds none (#35833) (d73d625)
    • ai-builder: Surface skill save validation errors and stop reverting skill renames (#36055) (b08cde6)
    • Avoid false port-in-use error in get-n8n script on Windows/WSL (#36026) (6f2033f)
    • core: Accept Always allow scope on data-tables resume (#36070) (560455f)
    • core: Allow details field in continueErrorOutput mode (#35939) (55927c4)
    • core: Apply TLS options per hop when requests go through a proxy (#35518) (68bcdfe)
    • core: Bound database pool teardown so connection recovery always completes (#36013) (da314d3)
    • core: Bound workflow publication outbox record processing with an abort deadline (#36197) (c0278b0)
    • core: Crash enqueued executions with unreadable data (#36010) (fd67bf8)
    • core: Detect node settings changes when comparing workflow versions (#36066) (e4f0c33)
    • core: Execute tools in the order the root requested them (#36009) (acd4fda)
    • core: Explain Browser Use failures caused by other browser extensions (#36011) (f66a0e8)
    • core: Expose incoming request headers to MCP trigger tools (#35236) (64ed864)
    • core: Fix non existent workflow id pathway for AIA (#35984) (6ab2569)
    • core: Fix z-indexing of expression modal over agent NDV (#36233) (1fa6ef0)
    • core: Gate AI Assistant workflow publish offers on live verification (#36394) (602e6a0)
    • core: Handle dropped AI provider connections as transient (#35587) (72235d3)
    • core: Handle oversized chat attachments gracefully (#36061) (de8b358)
    • core: Harden agent HTTP Request tool configuration (#36463) (0791359)
    • core: Improve agent builder skill and channel handling (#35980) (a723e79)
    • core: Keep node IDs stable when the AI Assistant edits a workflow (#36236) (a71e45a)
    • core: Keep resolving end-user credentials after a trigger stops listening (#35973) (a447ac4)
    • core: Keep the account panel on hosted forms once every account is connected (#36429) (a8754b4)
    • core: Let Instance AI run a specific trigger's flow (#36410) (1a7425d)
    • core: Make published agent channel add, replace, and remove failure-safe (#36100) (79c1393)
    • core: Prefer managed OAuth auth types when the AI builder resolves credentials (#35929) (1b4c0ba)
    • core: Preserve Anthropic thinking history across agent turns (#36185) (5f6d734)
    • core: Rebuild the node registry without emptying it first (#36387) (86facbd)
    • core: Recover model turns that end without usable output (#36423) (bae82bd)
    • core: Remember skipped Instance AI credential setup for the rest of a thread (#36308) (6ace2a5)
    • core: Report the real activation mode for triggers activated via the publication outbox (#36123) (1a12af6)
    • core: Report the workflow's parent folder in get_workflow_details (#36234) (9b97fb5)
    • core: Require trigger node name for MCP workflow executions (#36341) (7ea9d54)
    • core: Resolve agent credentials through the node decryption path so external secrets work (#36275) (9cbbd59)
    • core: Resolve AI Assistant sticky note placement after layout (#36320) (b671cf4)
    • core: Resolve Custom API Call support through inherited credential types (#35820) (88efdb9)
    • core: Resolve operation defaults per resource in generated node schemas (#35952) (79a7bd2)
    • core: Respect the editor write lock when Instance AI writes workflows (#36335) (f19c452)
    • core: Return final responses from workflow agents (#36127) (5e2779e)
    • core: Scope AI Assistant credential setup cards to the thread's project (#36425) (b50ea9c)
    • core: Stop auto-selecting the only generic auth credential (#35963) (237c503)
    • core: Stop duplicated workflows from inheriting the original's static data (#35921) (25c1521)
    • core: Stop routing unrelated pre-existing nodes into workflow setup after AI Assistant edit (#36280) (c89dba8)
    • core: Surface model discovery authentication failures to users (#35979) (c44c7de)
    • Default all navigations to domcontentloaded (#36238) (5a1e186)
    • Don't detach child process on Windows so external programs write (#36327) (de6f3d9)
    • editor: Clarify external secret expression previews (#36064) (7792fdb)
    • editor: Display tool execution data in Agent sessions (#36085) (a94ffe9)
    • editor: Improve agent error handoff to AI Assistant (#36076) (598c1f3)
    • editor: Keep agent nodes inside canvas group borders (#35972) (174d0d8)
    • editor: Name the AI Assistant browser tab after the conversation (#35958) (e4a414d)
    • editor: Never autosave a read-only preview canvas (#36023) (56a2d20)
    • editor: Only show Markdown placeholder when empty (#36336) (95515d7)
    • editor: Open OAuth sign-in popup before network calls and report blocked pop-ups clearly (#35948) (0f9bff0)
    • editor: Polish workflow header actions menu and production checklist placement (#36209) (f3f075a)
    • editor: Preserve saved credential data after connect-save to prevent false disconnect prompt (#35598) (59ea1f4)
    • editor: Redirect to sign-in when the user's session expires (#35507) (a78ff67)
    • editor: Refresh chat history when switching executions (#35312) (36f2b68)
    • editor: Remove misleading reset zoom control (#35843) (cce5401)
    • editor: Restore the connection test for Kafka and Odoo credentials (#36195) (40a5901)
    • editor: Settle navigation instead of hanging when auth-init guard errors (#36190) (ddd5494)
    • editor: Show agent context after assistant handoff (#36310) (d810315)
    • editor: Show placeholder while MCP settings counts load (#35894) (870099f)
    • editor: Show the connected provider account, not the n8n account email (#35553) (ee03e02)
    • editor: Stop the workflow actions menu shifting when a new workflow is saved (#36077) (a914319)
    • editor: Stop write-lock polling from re-arming after session expiry (#34750) (26be86d)
    • editor: Update ready-to-run demo templates to a current OpenAI model (#36189) (a27c90c)
    • Fix decompress size calculation for zip64 archives (#35856) (d094b6a)
    • Google Ads Node: Migrate from sunset v21 API to v25 (#36255) (bab2649)
    • Google Ads Node: Select the renamed video views metric on API v25 (#36347) (7b64b94)
    • Handle exponential-notation numbers in smartDecimal (#35967) (08052c1)
    • Kafka Trigger Node: Fail v2 activation when the consumer group cannot be joined (#36046) (67a458e)
    • Kafka Trigger Node: Refuse activation when the topic does not exist (#36044) (b025ff0)
    • MCP Server Trigger Node: Keep sessions working when the caller's end-user credentials are unconnected (#36221) (5044810)
    • Microsoft SharePoint Node: Require subdomain in OAuth2 credential (#35680) (620c40c)
    • Microsoft Teams Node: Restore Group.ReadWrite.All OAuth2 scope (#36005) (653dfc6)
    • Microsoft Teams Node: Surface Graph errors instead of returning an empty chat list (#36200) (1cc20d5)
    • Remove default model from one-script docker compose setup (#36034) (a91e012)
    • Rethrow unreachable-element errors in getElementValue (#36199) (1ad64b8)
    • Surface Zoho API error message on duplicate record (#35840) (0a30c03)
    • Wait for task runner registration before executing in e2e test (#36212) (2bca080)
    • Wordpress Node: Send no-cache header on write requests (#20473) (077370f)

    Features

    • Adapt the OAuth consent screen for first-party clients (#36261) (2e97fa5)
    • Add LangSmith agent session debug export (#36309) (6cd9a2b)
    • Add snapshot option to every browser use interaction tool (#36111) (7f37137)
    • ai-builder: Add MCP server as allowed tools in skills (#35969) (d0424b4)
    • ai-builder: Auto-select a sensible default model for new agents (#36058) (30aff5d)
    • ai-builder: Offer agent building in assistant greetings (#36073) (e2e719c)
    • API: Add endpoint to create role-mapping rules (#36032) (40a0f2a)
    • API: Add endpoint to get a single role (#36279) (7bd7dac)
    • API: Add endpoint to list all roles (#35609) (48893ee)
    • API: Add endpoint to update a custom role (#36213) (28bf536)
    • API: Migrate workflow tags endpoints to decorator pattern (#35829) (6ab3f5e)
    • Confluence Node: Add Confluence Cloud OAuth2 credential (#35732) (f9fd8a8)
    • Confluence Node: Add page get operation with full sub-tree support (#36217) (d9fa966)
    • core: Add AI Assistant setup funnel telemetry (#36391) (490b368)
    • core: Add an inline Available tools card to connect MCP servers from the assistant chat (#35332) (fb430aa)
    • core: Add env var to skip workflow history compaction on startup (#36099) (5c61888)
    • core: Add get_workflow_versions_diff MCP tool (#35492) (ff7955f)
    • core: Add MCP support for folder creation and workflow moves (#35964) (d4dcc1c)
    • core: Add MCP tool to read data table rows (#35956) (de944d2)
    • core: Add n8n Sandbox support to Agent Knowledge (#35811) (6a30736)
    • core: Add new agent slack integration (#35591) (ca82fd9)
    • core: Add one-off operation flow and insertion-semantics rules to AI Assistant (#36184) (51aa6fb)
    • core: Add writable workspaces to agents (#36033) (01ce449)
    • core: Advertise the MCP 2026-07-28 routing headers in CORS (#35471) (a14ab0b)
    • core: Auto-expose new workflows to MCP from settings via toggle (#35828) (a74fbab)
    • core: Coalesce a Schedule Trigger node's catch-up runs after downtime (#35524) (026cee3)
    • core: Deprecate Array.merge from expressions, and add Array.mergeIntoObject (#36161) (04e76a3)
    • core: Enable Agent sandboxes through Instance AI setup (#36056) (5f9602b)
    • core: Isolate Agent sandboxes by principal (#36203) (ce1b521)
    • core: Let agent builder inspect and update schedules (#36449) (f7459c8)
    • core: Make n8n User Auth (OAuth2) generally available (#35900) (5bfcde5)
    • core: Redesign the account connect panel on hosted forms (#36344) (bf28af6)
    • core: Refuse durable pollers when an active workflow has duplicate trigger node ids (#36340) (faf4dc3)
    • core: Restrict end-user credential creation to team projects (#36025) (e243656)
    • core: Restrict workflow review decisions to assigned reviewers (#36040) (64dcebb)
    • core: Send projectId to the AI Gateway for usage attribution (#35885) (3300833)
    • core: Skip update approval for workflows created in the same Instance AI session (#36054) (dfa841a)
    • core: Support workflow version policies in package exports (#35962) (aecd164)
    • core: Tell the assistant which services are connected and what tools they expose (#35931) (3571c09)
    • Create workflow tools from the agent builder (#36460) (35434b0)
    • Discord Node: Add member moderation actions (#33486) (6bd31e5)
    • editor: Add docked agent preview chat (#35773) (42130c5)
    • editor: Add preview chat to SessionTimeline view (#36128) (dbb28af)
    • editor: Display authors on the review details view (#35897) (d35bb3e)
    • editor: Improve agent session tool call feedback (#36346) (b27a53e)
    • editor: Integrate n8n credits into the node credential picker (#35758) (b2df4c8)
    • editor: Let users update review descriptions (#36069) (cbb5577)
    • editor: Link review success toasts (#35888) (3a4f356)
    • editor: Show character counters on review title and description inputs (#36177) (998fc85)
    • editor: Split workflow review inbox sections (#36216) (dd82601)
    • editor: Switch credits pill after a top-up or depleted allowance (#36239) (516c19e)
    • editor: Update NumberInput styling (#35937) (a319c76)
    • editor: Update SegmentControl component (#34447) (60736dc)
    • Gate Browser Use setup steps on extension detection (#36235) (7025284)
    • Hide n8n-connect usage when aiGatewayCloudUbb is enabled (#35978) (e7fa252)
    • Improve Browser Use connect conditions (#36215) (fee8450)
    • lmChatOpenRouter Node: Add provider routing options (#24822) (d7dcba5)
    • MCP Server Trigger Node: Add server instructions option (#35945) (bfd2746)
    • MiniMax Node: Add M3 and H3 model support (#35935) (aee23f7)
    Original source
  • Aug 11, 2026
    • Date parsed from source:
      Aug 11, 2026
    • First seen by Releasebot:
      Aug 11, 2026
    n8n logo

    n8n

    2.35.0

    n8n releases a broad update with new AI Assistant and Agent Builder capabilities, expanded MCP and API support, and refreshed editor workflows. It also improves stability, security, and node behavior across task runners, agents, credentials, and integrations.

    Bug Fixes

    • AI Agent Node: Stop pre-tool-call text leaking into agent responses (#35212) (d5845df)
    • core: Apply redaction policy to Code node console output (#35121) (242da02)
    • core: Bound oversized agent tool results (#35759) (8fbcd7e)
    • core: Close review requests when a source control pull archives or cascade-deletes a workflow (#35798) (fd366ce)
    • core: Compile MCP tool schemas on their declared JSON Schema dialect (#35610) (eeaa425)
    • core: Deduplicate OAuth2 authorization URL query parameters (#35949) (0b4b044)
    • core: Detect node parameter values the connected credential cannot use (#35633) (5925f5b)
    • core: Fail stalled Instance AI model streams fast instead of hanging (#35943) (c04825d)
    • core: Fix task runner health check failing (#35808) (9c4a613)
    • core: Gate error workflows behind primary readiness (#35634) (c79bd88)
    • core: Handle errors from triggered and polled workflow executions (#35689) (1deee72)
    • core: Handle out-of-scope display option dependencies (#35845) (9241a72)
    • core: Honor dry run on data table row delete (#35713) (76fb3bc)
    • core: Ignore undeclared fields in agent resume payloads (#35607) (42754a8)
    • core: Keep agent workflow tools linked after renames (#35690) (b4736b7)
    • core: Keep database ping loop alive across connection recovery (#35752) (3f2d479)
    • core: Keep n8n-docs always loaded so n8n questions do not route to web search (#35537) (e73f0a4)
    • core: Keep valid resume payloads intact when ignoring undeclared fields (#35751) (a2c9578)
    • core: Nest agent traces under the calling workflow node (#35457) (5d0a424)
    • core: Normalize the $fromAI type argument before coercing defaults (#35641) (c0a7674)
    • core: Probe azure blob with list instead of exists() (#35719) (8bbc988)
    • core: Reattach n8n-sandbox thread sandboxes after restart, idle eviction, and across mains (#35953) (0e7e49b)
    • core: Recover unresponsive task runners (#35456) (7a79486)
    • core: Reject stale Instance AI confirmations instead of hijacking the live run (#35733) (4555145)
    • core: Report failed publishing when imported workflows share a webhook path (#35525) (32f38a3)
    • core: Require row read scope when data table writes return rows (#35651) (ae6b256)
    • core: Resolve expressions in ephemeral agent tools (#35876) (65083ab)
    • core: Return a clear error for a node type with an unknown version (#35196) (a9cde3f)
    • core: Run published agent workflow tools as production (#35784) (6cc9b28)
    • core: Show Agent references in credential usage (#35409) (a74c6fd)
    • core: Show Instance AI model overload errors clearly (#35498) (40ba0dd)
    • core: Strip leading BOM before parsing webhook request bodies (#35933) (aa03666)
    • editor: Derive workflow home project from shared relation when absent (#35810) (62e6862)
    • editor: Disable no-op workflow review updates (#35890) (bf860f3)
    • editor: Fix janky spacing between agent capability chips with long labels (#35493) (007400d)
    • editor: Focus Markdown editor input before toolbar (#35529) (698d137)
    • editor: Keep NDV panels spanning the full container width (#35818) (561af4c)
    • editor: Keep Publish button visible in narrow workflow headers (#35502) (1de80ac)
    • editor: Lock the AI Assistant canvas while the agent is working (#35339) (1206780)
    • editor: Make DropdownMenus more obviously scrollable (#35726) (d3e49b2)
    • editor: Preserve new agent artifact lifecycle (#35703) (caeb40e)
    • editor: Remove unsupported button type attributes (#35578) (980c9bd)
    • editor: Require an explicit answer or Skip on Instance AI questions (#35700) (6f765e9)
    • editor: Show agent tool credentials above configuration (#35590) (1ca0708)
    • editor: Show dependency pills on views listing more than 100 resources (#35825) (926aa1a)
    • Execute Workflow Node: Prevent invalid input mappings (#35767) (34ca40b)
    • Fix token data updates and refresh for DCR oauth credentials (#35535) (abe2959)
    • Kafka Trigger Node: Stop consumers reliably when a workflow is deactivated or updated (#35069) (03213e7)
    • Preserve Agent build intent and refresh artifact names (#35823) (daba594)
    • Schedule Node: Apply declared interval defaults to stored rules (#35271) (28d929d)
    • Send n8n version on backend posthog flag retrieval (#35621) (1ade7a2)
    • SharePoint Node: Point delegated Sites.Selected users at URL or ID mode (#35369) (305ed29)
    • Skip setup cards for credentials the workflow already settled (#35701) (4493e5a)
    • Use caller's timezone for Insights date range boundaries (#33989) (279bde3)
    • X (Formerly Twitter) Node: Update OAuth2 and API endpoints to x.com (#32699) (8ac5a60)

    Features

    • Add self-hosted AI Assistant onboarding (#35579) (4ae4cc3)
    • Add Simplified Custom Auth credential with recipe-guided setup in the AI Assistant (#35056) (53841f1)
    • Add task-runners sidecar to the get.n8n.io stack (#35426) (9493631)
    • API: Add @Deprecated decorator to the decorated controller platform (#35725) (897ce6a)
    • API: Add endpoint to create custom roles (#35522) (d225d03)
    • API: Add publishIfActive option to workflow update endpoint (#35813) (0e22fdf)
    • core: Add Agent Builder test runs (#35716) (b660ebe)
    • core: Add backend form-trigger submission gate for end-user credentials (no changelog) (#35539) (ddcc94f)
    • core: Add detailLevel option to MCP get_workflow_details (#35497) (3773c31)
    • core: Add Discord as an agent chat channel (#35331) (4e6fc65)
    • core: Add HITL to agent builder test runs (#35731) (0df0041)
    • core: Add local agent token counting (#35836) (ae1252a)
    • core: Add projectConflictPolicy to package import (#35488) (881a14f)
    • core: Add telemetry for Simplified Custom Auth templated credentials (#35832) (c485cea)
    • core: Auto-close workflow review requests when a workflow is archived or moved (#35772) (a044c0d)
    • core: Enable 'instance-ai' module by default and remove startup warning (#35670) (fcc4ef5)
    • core: Expose agent test execution through MCP (#35744) (6f761ad)
    • core: Expose MCP registry search to the assistant as a tool (#35318) (59278a7)
    • core: Extend n8n Connect to Agent Builder node tools (#35402) (104bc5c)
    • core: Gate n8n Connect with instance config (#35007) (935cfb9)
    • core: Include SDK language rules in the MCP workflow SDK reference (#35183) (1c6e992)
    • core: Make Azure Key Vault provider endpoints configurable (#35214) (82e22c9)
    • core: Make the vm expression engine the default (#35738) (98e0952)
    • core: Migrate the instance MCP server to the MCP TypeScript SDK v2 (#35467) (74631f7)
    • core: Persist agent session timelines during execution (#35490) (1546c95)
    • core: Reconcile tag ids on name collision when importing packages (#35224) (c9eeb2e)
    • core: Support the MCP 2026-07-28 discovery handshake on the instance server (#35470) (145863c)
    • core: Surface decision eligibility on the review detail (#35391) (5e4a20d)
    • core: Teach the AI assistant to organise workflows into node groups (#35646) (5bf5f38)
    • core: Warn on startup when Postgres is below the supported range (#35495) (c72b14f)
    • editor: Add Changes diff tab to workflow review detail pane (#35431) (6c8197e)
    • editor: Add ChatMessage to @n8n/design-system (#35461) (38f0691)
    • editor: Add more Markdown editor toolbar options (#35630) (32db83c)
    • editor: Add review detail metadata (#35638) (cf13bc0)
    • editor: Allow adding a workflow version description when submitting for review (#35640) (5f0e464)
    • editor: Disable command bar in canvas-only mode (#35542) (fda3301)
    • editor: Enable enhanced HITL Slack/Telegram (#35411) (5d501e3)
    • editor: Improve agent file upload visibility (#35513) (75a0cdf)
    • editor: Name the pinned workflow version when submitting for review (#35566) (fe37fe3)
    • editor: Restore one-click connector for ChatGPT MCP client (#35396) (2058a16)
    • Extract the get-n8n stack definition into a versioned standalone file (#35620) (8a1645a)
    • Form Trigger Node: Add credential connect UI for end-user credentials (#35347) (a89dc5d)
    • GitHub Node: Add timeout option to Dispatch and Wait for Completion (#35837) (a6f07db)
    • Kafka Node: Add compression options to version 2 (#35727) (21b52fb)
    • Kafka Node: Add version 2 to send messages via the new Kafka library (#35450) (d2901bd)
    • Load Instance AI models dynamically (#35927) (269a45d)
    • Merge Node: Add "Append" and "Combine" search aliases (#35709) (cc98292)
    • Salesforce Trigger Node: Add OAuth2 JWT authentication support (#32257) (eda2496)
    • Slack Node: Use Real-time Search API for message search (#35291) (204f346)

    Performance Improvements

    • core: Resolve webhook description fields via declared native resolvers (#35404) (18c2d71)
    Original source
  • Aug 4, 2026
    • Date parsed from source:
      Aug 4, 2026
    • First seen by Releasebot:
      Aug 5, 2026
    n8n logo

    n8n

    2.34.0

    n8n ships a broad round of bug fixes across core and the editor, improving AI workflows, Slack and MCP handling, execution reliability, OAuth flows, and node behavior while tightening performance, tracing, and credential management.

    Bug Fixes

    • ai-builder: Treat bound stored credentials as settled in setup analysis (#35340) (5decab2)
    • AWS Bedrock Chat Model Node: Enable TCP keepalive on Bedrock runtime connections (#35323) (78e27ff)
    • core: Add incremental SSE response headers (#35342) (7b8818d)
    • core: Add reactions:write to Slack agent app manifest scopes (#35238) (43831eb)
    • core: Annotate pre-existing validation warnings in MCP update_workflow (#34944) (cca4d8d)
    • core: Apply AI request timeout even without a proxy (#34992) (ab3ed79)
    • core: Block deletion of the SSO role mapping default condition role (#35086) (587b23d)
    • core: Clarify MCP trigger info for unsupported production triggers (#35209) (21dc3ad)
    • core: Classify agent execution pulse with run_type (#35346) (8f4816e)
    • core: Classify Instance AI error reports by severity and quota cause (#35353) (a97e305)
    • core: Classify no-op pseudo triggers as persisted (#35287) (2bc0f30)
    • core: Default AI-created workflows to v1 execution order (#35277) (d0d0b7a)
    • core: Disable Slack app Home tab (#35412) (c0d09a5)
    • core: Emit OTel spans for queue mode executions (#35357) (e976bd0)
    • core: Exclude AI assistant verification runs from prod execution counts (#35405) (4accb5b)
    • core: Fix broken documentation links in AWS (Assume Role) credential (#34763) (1e39ea5)
    • core: Fix SSE push backend connections in production (#35327) (c0a8f02)
    • core: Harden axios error handling against non-string error stack (#35073) (b329d57)
    • core: Import security audit risk reporters with a file extension (#35263) (8e62ca2)
    • core: Improve task broker resilience when a runner dies (#35298) (c15bbca)
    • core: Keep agent channel setup separate from publishing (#35468) (9f2f315)
    • core: Keep external secrets available while provider connections reload (#35237) (f3b052a)
    • core: Keep waitTill when storing worker job results on main (#34958) (7f50297)
    • core: Limit the size of webhook responses relayed through the queue (#35032) (bdf33c1)
    • core: Prefer n8n credits covered nodes in Instance AI workflow builds (#35019) (b2af755)
    • core: Preserve cause on execution errors (#35216) (0d4c3a7)
    • core: Preserve credential field expressions when caching preAuthentication tokens (#35064) (03894ee)
    • core: Preserve saved node positions when the assistant edits a workflow (#35268) (7034666)
    • core: Propagate sub-agent tool approvals (#35368) (edc377c)
    • core: Recover enqueued executions after a restart (#35059) (3872950)
    • core: Refresh end-user credential connection status after save (#35131) (a66fabb)
    • core: Return 405 for GET requests to the instance MCP endpoint (#34835) (982a906)
    • core: Route crash-loop auto-deactivation through the workflow unpublish flow (#35097) (eb0d966)
    • core: Skip error workflow dispatch for AI builder verification runs (#35247) (1cedd9f)
    • core: Sort node version directories by numeric version (#35206) (1f3d48d)
    • core: Tolerate JSON Schema patterns incompatible with the regex u flag (#35320) (3fe8d6e)
    • core: Unify workflow trigger teardown and make it best-effort (#35273) (9e452bb)
    • Deep-merge task metadata to preserve nested tracing attributes (#35166) (b682696)
    • editor: Add configurable origin allowlist for editor postMessage handling (#34674) (f9b4bd5)
    • editor: Add executions quota tooltip to trial banner icon (#34872) (50b56ac)
    • editor: Clarify Slack HITL "Capture Who Responded" helper text (#35432) (fff29ec)
    • editor: Create agent-builder credentials in the agent's project (#35286) (33caa35)
    • editor: Default credential modal to requested auth type and disambiguate managed OAuth2 options (#35079) (6676373)
    • editor: Dismiss archive toast immediately after permanent delete (#35207) (12f1fcc)
    • editor: Do not fail OAuth flows when the provider's COOP policy makes the popup read as closed (#34404) (b81d79a)
    • editor: Fix icon overlap in end-user credential connection banner (#35130) (2837a68)
    • editor: Gate agent reasoning by model support (#35253) (5046f24)
    • editor: Guard optional fields when reading public settings (#35281) (ba21bea)
    • editor: Keep Enter selection working when node search ends with a space (#35046) (6b9b890)
    • editor: Keep read-only execution background in sync (#35245) (cc5f334)
    • editor: Mention n8n User Auth webhook mode in end-user credential warning (#35222) (3b69d54)
    • editor: Preserve line breaks in multiline secret credential fields (#35157) (ad02a26)
    • editor: Remove brackets from docs link in credential setup assistant help (#35028) (9cdcc6d)
    • editor: Rename preview AI Agent node to V2 (#35285) (703c600)
    • editor: Show node descriptions for installed community nodes (#34914) (0839326)
    • editor: Size settings save bar off its column so its content aligns with settings rows (#34967) (982fa19)
    • editor: Update AI Agent preview label (#35102) (c9cf9bb)
    • editor: Wait for animated zoom-in transition to settle (#35244) (d512f5c)
    • Enable Save and clear stale OAuth state on auth method switch (#35367) (7eabd74)
    • Execute gated tool after approving Human Review in manual chat (#34881) (b29f38b)
    • Fixes see all button tracking on aia template examples (#35451) ([ad54d0cd63affd87dc134532825affd85f6a4233))
    • Form Node: Skip parent nodes without run data when returning binary from form ending (#35336) (d3e761e)
    • Google Vertex Chat Model Node: Preserve Gemini thought signature on single tool calls (#34797) (c6e5ecd)
    • Grist Node: Restore the stored base URL of legacy credentials (#35229) (3a2af96)
    • HTTP Request Tool Node: Pass error response bodies to the model (#34509) (f443349)
    • MCP Server Trigger Node: Save execution data only after tool call completes (#35239) (c1f5577)
    • Notion Node: Mark title as required for database page create in v3 (#35334) (736f570)
    • Preserve AI Assistant sandbox provider selection (#35122) (923a964)
    • Release Snowflake connection when a statement fails (NODE-5163) (#32932) (dc776f6)
    • Schedule Node: Run non-dividing minute intervals by elapsed time (#35062) (3a5a4a6)
    • Skip redundant workflow edit approval in AI Assistant (#35423) (852fed1)
    • Slack Node: Add groups:write OAuth scope for private channel actions (#35288) (e4e33e3)
    • Support n8n credits on nodes with multiple credential types (#35190) (47569fc)
    • Validate Send and Wait custom forms before sending (#35262) (ca54f32)
    • Webhook Node: Don't flag Respond to Webhook nodes owned by a Wait node as unused (#33911) (b7e8850)
    Original source
  • Jul 28, 2026
    • Date parsed from source:
      Jul 28, 2026
    • First seen by Releasebot:
      Jul 29, 2026
    n8n logo

    n8n

    2.33.0

    n8n adds new AI builder, workflow review, MCP, and API capabilities while strengthening admin-managed credentials and OAuth support. This release also brings broad bug fixes, editor polish, node updates, and performance improvements across the platform.

    Bug Fixes

    • ai-builder: Halt workflow verification at send-and-wait gates on loops (#34809) (e904939)
    • ai-builder: Keep assistant replies in the user's language during tool-heavy turns (#34761) (5a64744)
    • ai-builder: Make channel config dropdown enabled - Linear and Telegram - in AIA agent builder (#34706) (6b40211)
    • ai-builder: Make labels be more specific about access token for Slack setup (#34893) (490b722)
    • ai-builder: MCP Connections failures are non-blocking for agents (#34722) (3301e12)
    • ai-builder: Preview chat link fix (#34659) (54db083)
    • ai-builder: Provision agent prerequisites before build-agent delegation (#34802) (fec6cee)
    • Airtable Node: Support matching array field values in update operation (#31517) (e07eab8)
    • AMQP Trigger Node: Cap concurrent executions at the configured messages per cycle (#34787) (d2672a6)
    • Baserow Node: Format Get Many date filter values for Baserow API (#32723) (b5da074)
    • Cohere Chat Model Node: Route chat requests through the v2 endpoint (#34878) (4006c22)
    • core: Accept 5-field cron expressions in schedule trigger (#35006) (27edc54)
    • core: Advertise OAuth protected-resource metadata URL on MCP server 401 responses (#34571) (37bb354)
    • core: Avoid loading execution data during credentials security audit (#34876) (4212fc2)
    • core: Classify masked Instance AI stream failures as quota exhaustion via credit re-check (#34553) (bd89cfc)
    • core: Ensure license device fingerprint meets minimum length (#33852) (9140a06)
    • core: Expose workflowPublishingPolicy in the package import CLI command (#34632) (3117e45)
    • core: Fail fast with a node error when a Data Table node references a missing table (#34610) (68c7b55)
    • core: Fall back to the run's resolved model for AI Assistant verification LLM calls (#34627) (a8c90f8)
    • core: Fix MCP workflow update failing for active workflows on SQLite (#34964) (bc88dc4)
    • core: Handle MCP OAuth2 token expiry and PKCE negotiation (#34494) (c7b90d0)
    • core: Include RFC 9207 iss parameter on OAuth authorization error redirects (#34751) (eca731c)
    • core: Keep MCP server display names free-form in agent config (#34931) (5339b5e)
    • core: Normalize workflow rollup timestamps (#34670) (0316336)
    • core: Preserve the underlying error as cause on Instance AI workspace file reads (#34759) (206a258)
    • core: Prevent concurrent instance startups from racing database migrations (#34685) (4d861d1)
    • core: Prevent unsupported waiting operations in agent tools (#34587) (3c278f0)
    • core: Publish workspace packages required by n8n at runtime (#34886) (0c613b4)
    • core: Redact a sub-workflow's own execution record per its own policy (#34621) (d8d89cc)
    • core: Redirect form-resume waiting requests to the form endpoint (#34725) (5dfa49b)
    • core: Reject workflow deletion while unpublish is still in progress (#34836) (9e09ff4)
    • core: Require row read scope for data table CSV export (#34127) (8171aa8)
    • core: Resolve synthetic tool nodes to the requested version (#34850) (6e12426)
    • core: Return correct webhook URL in MCP get_workflow_details trigger info (#34927) (5542c1b)
    • core: Sanitize secret values before persisting to agent memory (#34622) (edbed4f)
    • core: Serve RFC 9728 metadata at bare /.well-known/oauth-protected-resource (#33776) (3e0188c)
    • core: Sign S3 object paths with strict RFC 3986 encoding (#34694) (8e5fdb4)
    • core: Skip Sentry reports for Instance AI errors that self-declare a warning level (#34617) (3bb3835)
    • core: Stop Instance AI follow-up runs from looping when they keep failing before the agent starts (#34767) (5aac66d)
    • core: Strip null optional node fields from AI-generated workflows (#34668) (94e505a)
    • core: Support fractional community node versions with PostgreSQL (#34717) (48c0e70)
    • core: Surface HITL suspend/resume content in Instance AI trace turns (#34599) (d8c3fad)
    • Databricks Node: Change default tokenExpiredStatusCode from 401 to 403 (#34325) (6f3d2b9)
    • DeepSeek Node: Preserve reasoning_content on tool-calling turns (#34924) (4d247a1)
    • editor: Add document title and adopt new settings layout on migration report pages (#34609) (0164216)
    • editor: Allow LDAP users to configure n8n 2FA in personal settings (#34655) (2b1e4b8)
    • editor: Center empty state content vertically on short viewports (#34820) (359d82f)
    • editor: Clamp persisted sidebar width when expanding the main sidebar (#34923) (4f7c725)
    • editor: Debounce node creator search filtering (#34828) (25c5a73)
    • editor: Don't show quick connect for non-main auth fields (#34449) (6195471)
    • editor: Fix an issue in some Safari versions that prevented copying invite links (#34620) (e75e412)
    • editor: Fix focus parameter button breaking selection in credential dialog (#34453) (ee029b8)
    • editor: Html strings for table names are escaped (#24522) (f4365b1)
    • editor: Inject instance UTM parameters in all links to the templates website (#34790) (d5b5d8e)
    • editor: Keep chat typing indicator visible until response arrives (#34768) (4fdf3ed)
    • editor: Keep NDV node hints visible after execution and render them in a single pane (#34920) (082b5d9)
    • editor: Keep Switch fallback outputs available with unresolved expressions (#34698) (a0f6861)
    • editor: Manage and other permissions checkboxs stuck in half-selected state during member selection (#34726) (0e186ad)
    • editor: Preserve agent tool name translations (#35039) (fd5bc7d)
    • editor: Preserve canvas groups when converting a selection to a sub-workflow (#34664) (1666f1e)
    • editor: Prevent reactive feedback loop when opening workflow diff (#34897) (962ff56)
    • editor: Reassign users when deleting a custom instance role (#34642) (fa0abd8)
    • editor: Refresh subworkflow input schema from draft on parent open (#34522) (734f957)
    • editor: Remove episodic memory callout and knowledge base publish requirement (#34888) (771d038)
    • editor: Rename preview AI Agent node to V1 (#34714) (359e1fb)
    • editor: Replace invalid link (#34652) (87115d6)
    • editor: Restore agent channel credential setup (#34737) (ac839bb)
    • editor: Restore horizontal scrolling of NDV panel header controls (#34824) (0745526)
    • editor: Stabilize icon picker scrolling (#34596) (e67c119)
    • editor: Update copy for executions tab empty state (#34731) (1138f11)
    • Form Node: Properly handle quotes in Form Trigger Node name (#34650) (95c36b8)
    • HTTP Request Node: Include error body in continueOnFail mode (#34729) (d0b254c)
    • Keep agent preview streams responsive (#35035) (8d46c6e)
    • MCP Client Tool Node: Close cached MCP client sessions when their execution finishes (#34397) (ec5f503)
    • Microsoft Teams Node: Respect limit server-side in getAll operations (#34851) (ded1697)
    • N8n Node: Update credential test to use an endpoint with no extra scopes (#34605) (4622b35)
    • Parse structured output from content-block model responses in chain nodes (#34928) (1713d9a)
    • Report real exported entity counts in package export (#34995) (f3fd559)
    • Return reversed array when calling .reverse() (#34625) (cc4dbf9)
    • Serialize dates and route binary columns to output in database nodes (#34124) (26ae903)
    • Slack Node: Handle user-list rate limits and surface real load errors (#34743) (2268149)
    • Treat blank optional enum form fields as unset in package import (#35010) (4abbc89)
    • Validate loadOption parameter in GSheet and Notion nodes (#34695) (1f82bee)
    • Wikipedia Tool Node: Surface tool errors as actionable node errors (#34643) (3f1b35d)
    • Wordpress Node: WordPress Get Many adds before filter for posts and pages (#19790) (90f1430)

    Features

    • Add admin-managed instance credentials (#34364) (7d8426f)
    • Add require-files-array ESLint rule for community node packages (#34792) (d0adaf7)
    • ai-builder: Add Fix with Assistant for failed agent preview tools - pass single execution context (#34616) (9626891)
    • ai-builder: Add support for verified community nodes as agent tools (#34922) (3d281ec)
    • ai-builder: Agent session records direct to session chat, not trace (#34997) (f62cc63)
    • ai-builder: Format zod erros on agent config - better toast msg (#34867) (bac8deb)
    • ai-builder: Single preview chat + trace modal (#35033) (687a00e)
    • ai-builder: Support execution scenarios for first-class agents in evals (#34384) (5fd800e)
    • ai-builder: Tidy up tool names and agent builder tool UX (#34646) (decb322)
    • Allow custom OAuth scopes for Microsoft Azure Monitor, Dynamics, Graph Security and Azure Storage (#34612) (69c8633)
    • Allow custom OAuth scopes for the remaining Google credentials (#34631) (4a8dd5b)
    • API: Add credentialResolverId, timeSavedMode & binaryMode properties to workflow settings schema (#34330) (9ac95b6)
    • API: Add endpoint to list workflow version history (GET /workflows/{id}/history) (#34656) (91751c3)
    • API: Add public API endpoints for OpenTelemetry configuration (#34429) (cd1e48e)
    • API: Add workflow publish/unpublish public API endpoints (#34745) (e9933bd)
    • API: Deprecate workflow activate/deactivate public API endpoints (#34771) (05c691b)
    • AWS Bedrock Chat Model Node: Surface inference-profile models in the default model picker (#34983) (cb28555)
    • Configure the AI Assistant through a redesigned instance settings page (#34493) (4078318)
    • core: Add active_workflow_info and make workflow_info leader-only (#34987) (78e55b5)
    • core: Add availableInMCP column to agents (#34665) (fdd4e33)
    • core: Add credential-unnecessary-password community node lint rule (#34791) (95da849)
    • core: Add eligible-reviewer API types and reviewer ids to revie… (#34703) (60112eb)
    • core: Add instance credential database schema (#34709) (13becf3)
    • core: Add N8N_SCHEDULER_MAX_ATTEMPTS to configure scheduler dead-letter threshold (#34633) (29f2fac)
    • core: Add storedAt column to agent_execution (#34858) (0b4bbd0)
    • core: Add telemetry events for agent publishing, builder capabilities, and interactive flows (#34887) (8017b3d)
    • core: Add workflow review request entities and migration scripts (#34062) (156ac00)
    • core: Add workflow.deactivate external hook (#34746) (697174f)
    • core: Allow Storybook components to be viewed in light and dark mode (#34361) (e592b21)
    • core: Auto-include sub-workflows in package exports (#34218) (09c90f9)
    • core: Create reviews page and render inbox (#34357) (b2cbcc1)
    • core: Detect and heal published-version skew in trigger reconciliation (#34877) (3f2bc68)
    • core: Emit agent run spans through the OTel module's tracer (#34460) (e01e996)
    • core: Include acting user identity in workflow lifecycle external hooks (#34769) (efa86c6)
    • core: Infer structured output from example JSON in AI Agent Node (#34779) (0ec49b3)
    • core: Nest delegated sub-agent spans under the parent agent trace (#34720) (bd6f617)
    • core: Return open and closed counts for the review inbox tabs (#34789) (f4edeeb)
    • core: Review submission flow endpoints and toggle (#34649) (6d38f2e)
    • core: Store agent execution logs in blob storage (#34796) (a647aef)
    • core: Support legacy sub-workflow dependencies in package exports (#34398) (41660d0)
    • core: Validate missing node types on package import (#34598) (4044d58)
    • Default package import workflowIdPolicy to source (#34989) (1f4e654)
    • editor: Add N8nStatusDot component (#34963) (f758a4b)
    • editor: Add workflow review submission flow (#34520) (5939eb5)
    • editor: Adds modal to see all projects a user can access in a list (#34619) (2748e1a)
    • editor: Keep review-required toggle synchronized with open reviews (#34606) (ca0c5f4)
    • editor: Migrate OpenTelemetry settings page to new instance settings UI (#34965) (91e1276)
    • editor: Polish end-user credential setup modal and NDV states (#34766) (01e0639)
    • editor: Revamp MCP settings view with instance settings components (#34041) (e2840a7)
    • editor: Show confirmation modal when updating a custom instance role with assigned users (#34544) (6dc2079)
    • editor: Show reviewer and requester avatars and a status indicator on review inbox items (#34885) (2ea7da2)
    • editor: Sync a new workflow version into an existing open review (#34842) (5a97bd1)
    • editor: Track Instance AI entry point as action_source on builder messages (#34671) (c0fe8ba)
    • Gmail Node: Add warning notice when Simplify is disabled (#34611) (72a311a)
    • Microsoft Excel (SharePoint) Node: Add node for Excel workbooks in SharePoint document libraries (#34847) (d67b9cd)

    Performance Improvements

    • core: Skip allowed-methods lookup on successful production webhook requests (#34833) (bf8f5d8)
    Original source
Releasebot

Curated by the Releasebot team

Releasebot is an aggregator of official release notes from hundreds of software vendors and thousands of sources.

Our editorial process involves the manual review and audit of release notes procured with the help of automated systems.