## [2.43.2](https://github.com/n8n-io/n8n/compare/n8n@2.43.1...n8n@2.43.2) (2026-10-08)
### Bug Fixes
* **core:** Fix Kimi K3 and other OpenAI-compatible Assistant model providers on self-hosted Assistant ([#40552](https://github.com/n8n-io/n8n/issues/40552)) ([509a3f3](https://github.com/n8n-io/n8n/commit/509a3f36a8443e544714e3874dc55ba14f2c9463))
* **editor:** Show the Agent artifact while the builder creates it ([#40550](https://github.com/n8n-io/n8n/issues/40550)) ([204e2dd](https://github.com/n8n-io/n8n/commit/204e2ddf1745095f940659d827b6f8ca000ead49))
<!-- This is an auto-generated description by cubic. -->
<a href="https://cubic.dev/pr/n8n-io/n8n/pull/40631?utm_source=github" target="_blank" rel="noopener noreferrer" data-no-image-dialog="true"><picture><source media="(prefers-color-scheme: dark)" srcset="https://www.cubic.dev/buttons/review-in-cubic-dark.svg"><source media="(prefers-color-scheme: light)" srcset="https://www.cubic.dev/buttons/review-in-cubic-light.svg"><img
## Features
- feat(buffer): complete stable API tool coverage (#8779)
- feat(api): expose credential sharing and SSO administration (#8770)
- feat(models): add current frontier models (#8777)
- feat(integrations): add Ramp and Microsoft Intune (#8780)
- feat(permission-groups): add agent default (#8771)
- feat(providers): add Nebius Token Factory (#8759)
- feat(desktop): import local files from the background executor (#8672)
- feat(desktop): keep the machine awake for background chats and yield the page to the user (#8671)
- feat(desktop): show background desktop chats and keep the chat view display-only for them (#8670)
- feat(desktop): run a chat's desktop tools in the background executor (#8668)
- feat(mothership): let the worker choose models when the model picker is off (#8669)
- feat(desktop): bind turns to a desktop and enforce its deadlines from the row (#8650)
- feat(sso): allow self-hosted DNS verification bypass (#8681)
- feat(plane): add core integration with self-hosted
## What's Changed
* server: proxy cloud usage and balance APIs by @drifkin in https://github.com/ollama/ollama/pull/18829
* llama: fix clef head reads past 2GiB on windows by @Gigrise in https://github.com/ollama/ollama/pull/18777
* cmd: remove account step from CLI onboarding by @hoyyeva in https://github.com/ollama/ollama/pull/18826
* manifest: avoid symlinks on Windows by @dhiltgen in https://github.com/ollama/ollama/pull/18852
* docs: fix 6 dead links in README community integrations list by @aniketkrs in https://github.com/ollama/ollama/pull/18814
* docs: fix broken download links in app README by @chenlichao in https://github.com/ollama/ollama/pull/18233
* mlx: drop carried metal residency patch now that it is upstream by @dhiltgen in https://github.com/ollama/ollama/pull/18854
## New Contributors
* @Gigrise made their first contribution in https://github.com/ollama/ollama/pull/18777
* @aniketkrs made their first contribution in https://github.com/ollama/ollama/pull/1
## What's Changed
### Features
- Add crewai eval to print a markdown brief when run by an agent
- Queue relevant background replies
- Add experimental turn and reply identities
- Add Oracle Integrations
- Add experimental job lifecycle and runner
- Add crewai eval --models, and llm_overlay to swap models as well as roles
### Bug Fixes
- Fix train filename error message in CLI
- Allow a start step to re-run on the events it listens to
- Let human_feedback emit steps expose the review in outputs
- Ensure crewai eval exits with code 1 unless the gate passed and prompt to log in when nothing was traced unattended
- Report tracing sent usage from the grant exporter
- Address multiple dependency advisories and update relevant packages
### Refactoring
- Move message summarization into SummarizeMessages
- Centralize and refresh context windows
## Contributors
@Velmet44, @Vidit-Ostwal, @dependabot[bot], @fileames, @gabemilani, @github-actions[bot], @joaomdmoura, @lorenzejay
## 🧹 Maintenance
* chore(engine): evaluate template-expression scripts with the legacy sandbox (#16189) @MrChaker
* chore(engine): use the legacy sandbox for the shared script session too (#16190) @MrChaker
This routes `{{ }}` template-expression evaluation through the legacy sandbox instead of spawning a Deno process per token, relieving the memory pressure and slowdowns on flows that map many expressions over large step outputs.
> 📌 **Upgrading a self-hosted instance?** Review the [Breaking Changes](https://www.activepieces.com/docs/install/reference/breaking-changes) page for any actions required before you upgrade.
## Thanks ❤️
@MrChaker
## What's Changed
### Features
* feat(topics): classify traces into buckets by @nimarb in https://github.com/langfuse/langfuse/pull/17664
* feat: add external media storage integration by @wochinge in https://github.com/langfuse/langfuse/pull/18320
* feat(scores): compile experiment-item and prompt-event reads through the query AST by @niklassemmler in https://github.com/langfuse/langfuse/pull/17553
* feat(openai): add structured review output and enhance customer response fixtures by @marliessophie in https://github.com/langfuse/langfuse/pull/18342
* feat(analytics): track user-visible error toasts by @nkabardin in https://github.com/langfuse/langfuse/pull/18324
* feat(sessions): Make session view use trace transcripts by @bezbac in https://github.com/langfuse/langfuse/pull/18063
### Fixes
* fix(dashboards): remove duplicate outer grid padding by @tobi12345 in https://github.com/langfuse/langfuse/pull/18329
* fix(shared): keep trace latency NULL when no observation h
## What's Changed
### Features
* feat(ai-gateway): expose resolution context in response headers, spans and logs by @hassiebp in https://github.com/langfuse/langfuse/pull/18247
### Fixes / Improvements
* fix(web): zinc neutral tokens, surface tokens, observation line and fill colours by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18264
* fix(evals): skip Bedrock URL media interpolation by @wochinge in https://github.com/langfuse/langfuse/pull/18303
* fix(web): filled badge variant, score and tag chips built on it by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18277
* fix(web): tab bar labels at 14px with a thinner neutral underline by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18275
* fix(transcript): tolerate reasoning differences in replayed history by @marliessophie in https://github.com/langfuse/langfuse/pull/18257
* fix(web): segmented toggles get an even inset and a raised selected pill by @nmtrang29 in https://github.com/langfuse
## What's Changed
### Features
* feat(trace-batch): bound batches by estimated weight and exclude oversized traces by @LysanderKie in https://github.com/langfuse/langfuse/pull/18296
* feat(web): show the organization usage breakdown on every deployment by @Steffen911 in https://github.com/langfuse/langfuse/pull/18154
* feat(auth): remember the last enterprise SSO email on the sign-in form by @dergeraetbot in https://github.com/langfuse/langfuse/pull/18258
### Fixes
* fix(llm): drop retired and superseded models from the Vertex AI default list by @pushkar in https://github.com/langfuse/langfuse/pull/18160
* fix(web): unify card surface across sign-in, sign-up and onboarding by @dergeraetbot in https://github.com/langfuse/langfuse/pull/18259
* fix(evals): use schema-compatible model preflight prompt by @wochinge in https://github.com/langfuse/langfuse/pull/18252
### Chores
* chore(otel): replay raw documents through the production queue by @sumerman in https://githu
# [2.43.0](https://github.com/n8n-io/n8n/compare/n8n@2.42.0...n8n@2.43.0) (2026-10-06)
### Bug Fixes
* **Agent Node:** Remove outdated tutorial tip callout ([#35505](https://github.com/n8n-io/n8n/issues/35505)) ([53b84d2](https://github.com/n8n-io/n8n/commit/53b84d2baac4f6975627f85ff3d550d84008e749))
* **ai-builder:** Treat a blank folder path as no folder in the build tool ([#40116](https://github.com/n8n-io/n8n/issues/40116)) ([b7071c9](https://github.com/n8n-io/n8n/commit/b7071c91c7ef959e1cc3d703495e4fee9fcc9744))
* Align From AI button with parameter inputs ([#40152](https://github.com/n8n-io/n8n/issues/40152)) ([9675fc9](https://github.com/n8n-io/n8n/commit/9675fc97fd193c0474b36c084bd3d6e928885fed))
* **API:** Emit valid schemas for untyped values in the Public API spec ([#39884](https://github.com/n8n-io/n8n/issues/39884)) ([6918fda](https://github.com/n8n-io/n8n/commit/6918fda0182e55e41efa847a8e6831d08cb3085d))
* **API:** Let global members grant variable scopes to API keys (
## 1.25.0 (2026-10-06)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat: outline the back navigation control on settings sub-pages by @errmakov in https://github.com/OpenHands/OpenHands/pull/17587
* feat(settings): bulk-add provider models as LLM profiles by @georgeglarson in https://github.com/OpenHands/OpenHands/pull/16426
* feat: add direct-prompt Model Router settings by @juanmichelini in https://github.com/OpenHands/OpenHands/pull/16147
* feat(canvas): retire streaming slots by event id and delete the text-matching reconciler by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/17465
* feat(apps): add Update action for installed Canvas Apps by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/17736
* feat(settings): per-connection bulk-add LLM profiles by @juanmichelini in https://github.com/OpenHands/OpenHands/pull/17723
* feat: add Model Router "Run at conversation start" toggle by @juan
## What's Changed
### Features
* feat(mcp): support decision-model evaluators by @wochinge in https://github.com/langfuse/langfuse/pull/18166
* feat(experiments): annotate directly from comparison grid by @marliessophie in https://github.com/langfuse/langfuse/pull/17990
* feat(audit-logs): log actor info for audited actions and deletions by @pratimapatel2008 in https://github.com/langfuse/langfuse/pull/18107
* feat(web): pin evaluator actions during table scrolling by @wochinge in https://github.com/langfuse/langfuse/pull/18163
* feat(ai-gateway): correlate requests with a gateway request ID by @hassiebp in https://github.com/langfuse/langfuse/pull/18052
* feat(skills): unify file and folder uploads by @tobi12345 in https://github.com/langfuse/langfuse/pull/18064
* feat(web): add hover copy for agent code and tables by @nimarb in https://github.com/langfuse/langfuse/pull/18136
* feat(experiments): add persistent resizable charts by @marliessophie in https://github.com/langfu
## Bug Fixes
- fix(mothership): preserve workflow identity in background confirmations (#8615)
- fix(files): retain known lineage through binary exports and extraction (#8614)
- fix(code-placeholders): make python bare-placeholder classification and tagged-template edits linear (#8611)
- fix(execution): make code placeholder and reference scans linear (#8608)
## Contributors
- @icecrasher321
- @waleedlatif1
[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.13...v0.9.14)
## [2.42.3](https://github.com/n8n-io/n8n/compare/n8n@2.42.2...n8n@2.42.3) (2026-10-05)
### Bug Fixes
* **API:** Let global members grant variable scopes to API keys ([#40150](https://github.com/n8n-io/n8n/issues/40150)) ([d09b8a1](https://github.com/n8n-io/n8n/commit/d09b8a11fb097e47b04dbe04ed1d330f736fb507))
* **core:** Keep the task runner running on an unhandled promise rejection ([#40091](https://github.com/n8n-io/n8n/issues/40091)) ([50f2e96](https://github.com/n8n-io/n8n/commit/50f2e96e5bb40f23962b372d78ba11af32a3bbe8))
### Features
* **editor:** Show Gateway credits promotions on community nodes ([#40108](https://github.com/n8n-io/n8n/issues/40108)) ([1ea168e](https://github.com/n8n-io/n8n/commit/1ea168ee557355eefae7a3858a2c435ee83671f1))
<!-- This is an auto-generated description by cubic. -->
<a href="https://cubic.dev/pr/n8n-io/n8n/pull/40259?utm_source=github" target="_blank" rel="noopener noreferrer" data-no-image-dialog="true"><picture><source media="(prefers-color
## Features
- feat(library): Slack AI Agent Security: Permissions, Data, and Audit Guide (#8600)
- feat(library): Best HubSpot Alternatives for AI Marketing Automation in 2026 (#8599)
- feat(library): How do you build an AI voice agent with Twilio and Sim? (#8598)
## Improvements
- improvement(knip): check entry exports of private packages and delete their dead barrels (#8595)
- improvement(tools): stop exporting tool types used only in their own file (#8597)
- improvement(tools): delete unreferenced tool response types and the dead generic resource data path (#8596)
- improvement(guidance): make every ratchet shrink-only, scope rules to their files, fix stale guidance (#8594)
## Bug Fixes
- fix(tools): reject dot path segments in tool request URLs (#8604)
- fix(webhooks): check existing path owners before claiming on deploy (#8605)
- fix(code-placeholders): skip heredoc bodies when scanning shell quote context (#8603)
- fix(tools): check usage limits before running hosted-key too
## Features
- feat(forks): compare last synced source deployments (#8586)
- feat(youcom): add You.com integration (#8584)
- feat(search): browse Lucid folders and Notion pages (#8579)
- feat(library): How to Use a Postgres MCP Server With AI Agents: Security, Deployment, and Evaluation (#8576)
- feat(powerbi): add Power BI actions (#8538)
## Bug Fixes
- fix(docs): document You.com tools and expand shared output spreads (#8592)
- fix(credentials): make Claude Platform API keys available in the provider catalog (#8593)
- fix(audits): apply browser-runtime rules to @sim/utils; align settings checklist with the standalone description rule (#8591)
- fix(files): read offset 0 as the first line instead of rejecting it (#8588)
- fix(landing): return 404 for unknown library, blog, integration, model, and author slugs (#8587)
- fix(mothership): make chat fork complete, consistent and safe to retry (#8583)
- fix(sdk): default both SDKs to the www.sim.ai host (#8581)
- fix(integrations): list t