github n8n-io/n8n n8n@2.46.0

latest releases: stable, n8n@3.0.0, beta...
pre-release2 hours ago

2.46.0 (2026-10-27)

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) (bd21faa)
  • 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)

Don't miss a new n8n release

NewReleases is sending notifications on new releases.