2.44.0 (2026-10-13)

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 "Executions fail" label to "Executions will fail" (#40888) (2a51f38)
• editor: Respect the default voice for chat read aloud (#40440) (022b239)
• editor: Shorten the share button label on the credential sharing tab (#40637) (c133d6c)
• editor: Show the Agent artifact while the builder creates it (#40535) (1c63119)
• editor: Show the owner and credential type for credentials the user cannot use (#40669) (63dc285)
• editor: Show the renamed agent name in the assistant artifact tab (#40770) (4032797)
• editor: Show the unavailable credential at the top of the node picker (#40693) (1933723)
• editor: Show why a node on another branch can't be referenced (#40565) (a195096)
• editor: Small UI fixes to budget guardrail setup components (#40383) (958d23d)
• editor: Use pulsing status dot for the enabled n8n Assistant setting (#40712) (3ba5229)
• Google Gemini Chat Model Node: Point the AI builder to the model catalog for new Gemini models (#40159) (c21ed4f)
• Invoice Ninja Node: Fix retrieving currencies for bank transactions (#12997) (00849c4)
• Keep execution details clear of preview canvas (#40176) (af98327)
• Load only the publish history that the editor shows (#40183) (b28adf9)
• Microsoft Outlook Trigger Node: Report failed polls and limit the backlog per poll (#40147) (6bc5c93)
• Multiple migration timestamps withing a single PR (#40379) (7db7fa4)
• Odoo Node: Normalize datetime fields to Odoo format before write (#34186) (6b77613)
• Prevent node types corruption when multiple loaders run at the same time (#40633) (fdc3948)
• Remove loading flashes from data tables (#39874) (2f4a386)
• Report resource-operation violations as errors (#40830) (a180010)
• Return UTC ISO dates without changing other cells (#40156) (8059b63)
• S3 Node: Percent-encode the copy source path (#40282) (81f34c2)
• Separate agent response steps and show saved reasoning (#40590) (1e6da4e)
• Update matching nodes when selecting imported credentials (#39650) (4b5b68e)
• Use configured OAuth server rate limits (#40542) (4c8b76b)
• Use ID token claims when UserInfo is unavailable (#40779) (b8b0387)
• Validate and default public API pagination limits (#40483) (f212d5b)
• Wait for MockServer HTTP status without following logs (#40846) (4593838)

Features

• Add Antigravity to the MCP client connection dialog (#40879) (f0a38cf)
• Add Google Vertex AI credentials (#40665) (a7cba90)
• ai-builder: Reopen closed AI Assistant tabs when the agent changes the artifact (#40081) (5d38667)
• Azure AI Foundry Chat Model Node: Speak the Anthropic Messages schema for Claude deployments (#40306) (c134edf)
• Azure OpenAI Chat Model Node: Rename the Foundry nodes and credentials to Microsoft Foundry (#40398) (e5c8a8b)
• Configure workflow tool inputs for Agents (#40285) (4cb98ae)
• core: Add credentialTransfer policy enforcement point (#40300) (c2f6920)
• core: Add execution identity to every OTel span (#40649) (22ba4e7)
• core: Add overwrite schema conflict policy to data table package import (#40345) (3af9817)
• core: Add overwrite-non-destructive schema conflict policy to data table package import (#40446) (dc33c29)
• core: Add Prometheus metrics for database connection recovery (#39890) (d904e7a)
• core: Add the WhatsApp agent channel (#38750) (b0d1a30)
• core: Add workflow suggestion review actions (#39858) (eaf8c25)
• core: Allow confirming destructive data table changes when continuing an apply (#40491) (9946cfe)
• core: Apply the member credential rule to Owners and admins in team projects (#40448) (3cff8dc)
• core: Block create/update of workflows with deprecated nodes (#31360) (ea8417e)
• core: Email the agent owner when a monthly budget alert is crossed (#40544) (19e1f70)
• core: Emit opt-in start marker spans for workflow and node executions (#40762) (c713545)
• core: Experiment to show assistant composer and starter templates in agent list (#40396) (fe26ba8)
• core: Handle inbound media handling for whatsapp (#39409) (50c2ca0)
• core: Handle message quality rate limits for whatsapp integration (#39205) (3c33856)
• core: Hide credential-only nodes under a credential type policy (#39652) (370b30f)
• core: Pair data table columns by id on package import (#40709) (27b43de)
• core: Persist self-healing results and handoffs (#40115) (168a0ac)
• core: Post a budget-stop message on external agent channels (#40767) (5e01906)
• core: Promote folder and project renames alongside selected workflows (#40502) (a249e20)
• core: Report crashed executions from startup log recovery (#40390) (668e71d)
• core: Report destructive data table changes in the promotion apply preflight (#40454) (5d208c8)
• core: Report the deployment artifact in telemetry (#40319) (344dea5)
• core: Run the workflow history trim as a durable daily system task (#40085) (38eea65)
• core: Search, create and reopen agents from the command bar (#40504) (75a9cc7)
• core: Serve Prometheus metrics while the database is unavailable (#39908) (4e217ae)
• core: Serve the instance CSP on all non-script responses (#40205) (cabf0bf)
• core: Show every user the migration report, scoped to the workflows they can edit (#40449) (f4f7dcf)
• core: Show the agent chat attach button on the left of the composer (#40320) (209adf9)
• Databricks Node: Guard the Vector Store insert against the wrong index (#39699) (0932e95)
• editor: Add a state column to the migration rule detail (#40388) (682d092)
• editor: Add agent setup checklist (#39919) (883ade4)
• editor: Add order to settings sidebar links (#40505) (cef87cf)
• editor: Add project selection to Vertex AI credentials (#40667) (cdc23c6)
• editor: Animate the n8n Assistant activity indicator (#40497) (04e1e7f)
• editor: Disable restricted model providers in the agent model selector (#40658) (cde7a9d)
• editor: Explain a restricted model provider with the restriction popover (#40705) (75de193)
• editor: Explain instance-role access in the credential sharing "Used in" row (#40555) (48f05f9)
• editor: Rebuild the command bar with type tabs and paged search (#40461) (e36093b)
• editor: Rebuild the personal settings page with the design-system settings components (#40298) (09436b7)
• editor: Recommend Claude Opus 5.5 and GPT-6 models in AI Assistant setup (#40660) (1ad3c54)
• editor: Replace Windsurf with Devin in the MCP client dialog (#40912) (e2c4054)
• editor: Show the restriction callout and lock the agent tool configuration form (#40657) (01da889)
• editor: Show who created each preference on the Preferences page (#40868) (22ff2a0)
• editor: Sort the credential sharing list by people, then projects (#40478) (02af7e7)
• Embeddings Azure OpenAI Node: Add Entra ID authentication (#39390) (830486a)
• Google Gemini Node: Show Nano Banana 2.1 and 2 Lite in the image model list (#40596) (97c54f6)
• Make health check timeout configurable (#39548) (df8605e)
• Microsoft SharePoint Trigger Node: Add the Microsoft SharePoint Trigger node (#40055) (7c126fa)

Performance Improvements

• core: Keep agent builder system prompt static for prompt caching (#40364) (ee1db0b)
• core: Let the agent builder chain config writes without re-reading the config (#40462) (6b4da93)
• core: Let the agent builder edit skill instructions in place (#40447) (1de45a1)
• core: Prepare Instance AI skill sandbox in the background (#40363) (b36c2b5)
• core: Send agent builder config writes as objects with changed fields only (#40666) (2aa3fbf)