## 1.29.0 (2026-10-20)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(backends): show full organization names in the backend selector by @ak684 in https://github.com/OpenHands/OpenHands/pull/18667
* feat(launchers): read public skills from the bundled extensions package by @simonrosenberg in https://github.com/OpenHands/OpenHands/pull/18683
* feat(agent-profiles): choose skills per profile from the server catalog by @simonrosenberg in https://github.com/OpenHands/OpenHands/pull/18686
* feat(agent-profiles): edit condenser and verification per profile by @simonrosenberg in https://github.com/OpenHands/OpenHands/pull/18679
* feat(agent-profiles): choose a Model Router per profile by @simonrosenberg in https://github.com/OpenHands/OpenHands/pull/18685
* feat(home): dismiss recommended automations rail from Home and Application settings by @lx3133584 in https://github.com/OpenHands/OpenHands/pull/18538
* feat(agen
## Features
- feat(mothership): let an agent chat list its owner's other live chats for history recall (#9238)
## Improvements
- improvement(search): return 30 previews by default for a Search MCP query across every source (#9242)
- improvement(changelog): more relevant Search across sources (#9215)
## Bug Fixes
- fix(tls): distrust the roots behind the compromised eMudhra intermediates (#9248)
- fix(credentials): declare service-account oauth policy on Snowflake, NetSuite, and Managed Agent tools (#9241)
## Other Changes
- docs(library): update byok-multi-model-ai-agent-builder (#9246)
- docs(library): update best-ai-agents-for-scheduling-and-calendar-management-in-2026 (#9245)
- docs(library): update can-ai-agents-talk-to-each-other-multi-agent-communication-explained (#9244)
- docs(library): update apache-2-0-vs-fair-code (#9243)
## Contributors
- @waleedlatif1
[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.28...v0.9.29)
## What's Changed
### Features
* feat(topics): one gate for Topics visibility by @LysanderKie in https://github.com/langfuse/langfuse/pull/19091
### Fixes
* fix(sessions): Don't allow expanding empty reasoning messages by @bezbac in https://github.com/langfuse/langfuse/pull/19096
* fix(web): disable Owner role selection without ownership permission by @marksalpeter in https://github.com/langfuse/langfuse/pull/19092
* fix(web): boxed, sticky I/O sections with a collapse caret by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18684
* fix(otel): store number-like metadata strings without their JSON quotes by @niklassemmler in https://github.com/langfuse/langfuse/pull/19076
* fix(in-app-agent): bump bedrock v4 provider to accept tool calls without input by @LysanderKie in https://github.com/langfuse/langfuse/pull/19107
### Chores
* refactor(query-ast): reuse the row field map for by-id selects and type the skills columns by @niklassemmler in https://github.com/lang
## What's Changed
### Features
* feat(topics): non-blocking clustering for large numbers by @nimarb in https://github.com/langfuse/langfuse/pull/18964
* feat(topics): name topics by what their facet asks about by @LysanderKie in https://github.com/langfuse/langfuse/pull/19008
* feat(routes): add recovery option for V4 experience and update sidebar toggle logic by @marliessophie in https://github.com/langfuse/langfuse/pull/19053
* feat(skills): stabilize API and restore MCP access by @tobi12345 in https://github.com/langfuse/langfuse/pull/19025
* feat(ai-gateway): add self-hosted "None" ingestion mode by @wochinge in https://github.com/langfuse/langfuse/pull/19032
* feat(topics): be transparent about content filtered topics by @nimarb in https://github.com/langfuse/langfuse/pull/19056
* feat(topics): selection continuity in trace map by @nimarb in https://github.com/langfuse/langfuse/pull/19079
### Fixes
* fix(topics): name what a topic definition readback lost by @Lysande
# [2.45.0](https://github.com/n8n-io/n8n/compare/n8n@2.44.0...n8n@2.45.0) (2026-10-20)
### Bug Fixes
* **AI Agent Node:** Replay Anthropic thinking turns with their tool arguments ([#41241](https://github.com/n8n-io/n8n/issues/41241)) ([ea98bd0](https://github.com/n8n-io/n8n/commit/ea98bd06003b5687882c94245df837331cfbb544))
* Align data table and variable editing on protected instances ([#41258](https://github.com/n8n-io/n8n/issues/41258)) ([d4bde14](https://github.com/n8n-io/n8n/commit/d4bde146d6fa8f591a91f0d0ee44b56b96cb7019))
* Allow skipping table initialization ([#40437](https://github.com/n8n-io/n8n/issues/40437)) ([d245b17](https://github.com/n8n-io/n8n/commit/d245b17b898651a50a524a2411d703509afd8339))
* **API:** Apply projectId filter to executions for member API keys ([#40887](https://github.com/n8n-io/n8n/issues/40887)) ([3075b60](https://github.com/n8n-io/n8n/commit/3075b605766a73bee35d07b3afab02050c4e4a49))
* **API:** Log errors before returning generic 500 in Public AP
## Features
- feat(library): Best Retool Alternatives in 2026 for Building AI Agents (#9231)
- feat(library): Best Dust Alternatives in 2026 for AI Agent Workflows (#9232)
- feat(library): Best Flowise Alternatives in 2026 for Production AI Agents (#9234)
- feat(library): Best Langflow Alternatives in 2026 for Production AI Workflows (#9233)
- feat(library): Best Vellum Alternatives in 2026 for Non-Engineers (#9230)
- feat(library): Best Pipedream Alternatives in 2026 with Visual Builders (#9229)
## Improvements
- improvement(deps): shared Standard Webhooks verifier, MCP SDK 1.32.1, tiptap 3.31.4 with the prosemirror paste XSS fix (#9236)
- improvement(comparisons): noindex self-hosted marketing pages, link every comparison, and add Zapier, Retool, Flowise lead answers (#9227)
## Bug Fixes
- fix(comparisons): stop recommending Flowise after its end of life and source its facts from Flowise (#9239)
- fix(comparisons): Retool lists self-hosting on Enterprise only (#9235)
## Other C
## Features
- feat(library): How Do You Connect a Google Drive MCP Server to an AI Agent in Sim? (#9220)
- feat(library): LLMs vs AI Agents: What Is the Difference? (#9217)
- feat(greenhouse): connect Harvest v3 with a customer-owned API credential (#9214)
- feat(zoho-desk): expand help desk operations (#9205)
- feat(excel): expand workbook operations and align Graph contracts (#9203)
- feat(greenhouse): add versioned Harvest v3 integration (#9206)
- feat(cloudflare): expand API coverage and validate operations (#9194)
- feat(library): 6 Best AWS Bedrock Agents and Vertex AI Agent Builder Alternatives for Easier Deployment (#9192)
- feat(library): How Do AI Agents Use Tools and APIs? (#9190)
## Improvements
- improvement(async-jobs): warn when Trigger.dev run acceptance is slow (#9224)
- improvement(db): name chat uploads in one indexed read and index workspace payer lookups (#9208)
- improvement(landing): search-length titles, model comparison pages, and free model tools (#9184)
-
## What's Changed
### Features
* feat(trace): Move messages tab and reuse session timeline by @bezbac in https://github.com/langfuse/langfuse/pull/18953
* feat(api-keys): enable project API key permissions by default by @marksalpeter in https://github.com/langfuse/langfuse/pull/18950
* feat: rename Langfuse Assistant to Halo by @Lotte-Verheyden in https://github.com/langfuse/langfuse/pull/18898
* feat(api-keys): show the Admin role as Full access on API keys by @marksalpeter in https://github.com/langfuse/langfuse/pull/18981
* feat(topics): show cost of runs by @nimarb in https://github.com/langfuse/langfuse/pull/18668
* feat(web): page-based pagination for gateway API keys by @wochinge in https://github.com/langfuse/langfuse/pull/18965
* feat(transcript): implement message comparison and continuity features by @marliessophie in https://github.com/langfuse/langfuse/pull/19021
* feat(api): make legacy API deprecation notices visible to code agents by @niklassemmler in https:/
## 1.28.1 (2026-10-19)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Maintenance
* chore: bump agent-server to 1.56.0 by @all-hands-bot in https://github.com/OpenHands/OpenHands/pull/18670
* chore: remove merged PR artifacts by @all-hands-bot in https://github.com/OpenHands/OpenHands/pull/18570
**Full Changelog**: https://github.com/OpenHands/OpenHands/compare/v1.28.0...v1.28.1
---
This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please).
<!-- AGENT_CANVAS_DOCKER_START -->
## 1.28.0 (2026-10-19)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(verify-openhands): executable known bugs and a repeatable fix proof by @enyst in https://github.com/OpenHands/OpenHands/pull/18348
* feat(i18n): add Bahasa Indonesia (id) locale by @analisaperlengkapan in https://github.com/OpenHands/OpenHands/pull/18067
* feat: add close control to Getting started checklist by @DevinVinson in https://github.com/OpenHands/OpenHands/pull/18185
* feat(secrets): let the agent request a secret through an in-conversation modal by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/18408
* feat(verify-openhands): adopt the shared known-bug contract by @enyst in https://github.com/OpenHands/OpenHands/pull/18355
* feat(chat): smooth, reading-pace streaming with word fade-in by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/18491
* feat(secrets): ask for requested secrets inline in the chat by @Vas
## What's Changed
* [pplx-decider](https://ollama.com/library/pplx-decider) is a 27B decision model from Perplexity, fine-tuned from
Qwen3.8-27B
* Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without
thinking, or when the history contains another provider's compaction items
* Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open
reasoning items, producing misordered/duplicate tool call events
* Requests routed to remote models are now cancelled on ollama.com when the client disconnects, instead of continuing
to run
* `ollama show` now reports which renderer and parser a model uses and where its chat template comes from; the API
exposes the same values in new `renderer`, `parser`, and `template_source` fields
* More draft models now work with speculative decoding: llama-server infers the draft type automatically instead of
requiring Ollama to identify it
## Features
- feat(library): 6 Best Relevance AI Alternatives for Flexible AI Agents in 2026 (#9172)
- feat(library): How Much Does It Cost to Build and Run an AI Agent? (#9171)
- feat(library): 6 Best Make.com Alternatives for AI Agents in 2026 (#9173)
- feat(databricks): expand API coverage and preserve paginated results (#9163)
- feat(oracle-fusion): add core financial business operations (#9165)
- feat(data-drains): add Microsoft Sentinel ingestion (#9162)
- feat(project-files): let Chat read and write Project files (#9034)
## Improvements
- improvement(computer-use): roll out computer use per organization (#9182)
- improvement(landing): serve the homepage as Markdown when clients ask for text/markdown (#9154)
- improvement(library): refresh license comparison and Zapier alternatives (#9140)
## Bug Fixes
- fix(logs): remove the client log-persistence route that let a run's actor rewrite its log and cost (#9183)
- fix(resume): require write access to resume a paused run on the
## What's Changed
* win: prevent orphaned runners by @dhiltgen in https://github.com/ollama/ollama/pull/18500
* gguf: add the q2_0 tensor and file types by @jmorganca in https://github.com/ollama/ollama/pull/18967
* Launch clef in Ollama's cloud by @jberg5 in https://github.com/ollama/ollama/pull/19036
* use identifiers for --ask mode question keys by @jberg5 in https://github.com/ollama/ollama/pull/19041
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.5...v0.40.6-rc0
## Features
- feat(library): How Do You Embed an AI Agent Inside Your SaaS Product? (#9130)
- feat(library): How Do You Build an AI Agent That Remembers Context Across Multiple Sessions? (#9131)
- feat(library): 6 Best Microsoft Copilot Studio and Power Automate Alternatives for AI Agents in 2026 (#9132)
- feat(library): 6 Best CrewAI Alternatives in 2026 for Visual and Flexible Agent Building (#9133)
## Improvements
- improvement(search): rank live results across sources by the query terms they hold (#9134)
## Bug Fixes
- fix(search): keep the Jira half-terms summary tier within the all-terms match (#9129)
- fix(desktop): let computer use type into date and time pickers (#9128)
## Contributors
- @waleedlatif1
[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.24...v0.9.25)
## Features
* feat(web): link personal feature previews from organization settings by @nimarb in https://github.com/langfuse/langfuse/pull/18887
* feat(traces): integrate PostHog analytics for IO parser comparison tracking by @marliessophie in https://github.com/langfuse/langfuse/pull/18896
* feat(skills): improve browsing and editing UX by @tobi12345 in https://github.com/langfuse/langfuse/pull/18940
* feat(ai-gateway): route slugless codex- models to OpenAI connections by @wochinge in https://github.com/langfuse/langfuse/pull/18938
* feat(ai-gateway): attribute errors by origin and measure gateway overhead by @wochinge in https://github.com/langfuse/langfuse/pull/18919
* feat(experiments): unify per-experiment filter targeting by @marliessophie in https://github.com/langfuse/langfuse/pull/17944
* feat(web): create actions and recent picks in Cmd+K by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18910
* feat(ai-gateway): validate connection names server-side and aut
## What's Changed
* ci: run ai-gateway e2e tests on ai-gateway crate changes by @wochinge in https://github.com/langfuse/langfuse/pull/18915
* ci(deps): let the security maintainer remediate Rust Dependabot alerts by @wochinge in https://github.com/langfuse/langfuse/pull/18885
* fix(web): tracing page header and search row spacing by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18352
* feat(ai-gateway): raise request limit to 16 MiB and make execution limits configurable by @wochinge in https://github.com/langfuse/langfuse/pull/18820
* build: ship Rust license notices and cache AI gateway dependency builds by @wochinge in https://github.com/langfuse/langfuse/pull/18889
* fix(search): escape LIKE wildcards in remaining substring searches by @niklassemmler in https://github.com/langfuse/langfuse/pull/18873
* fix(prompts): preserve cache epoch across prompt reads by @FazlulKarimC in https://github.com/langfuse/langfuse/pull/18752
* refactor(ai-gateway): SecretString cre
## What's Changed
### Features
* feat(topics): unify manual trace processing and topic generation by @LysanderKie in https://github.com/langfuse/langfuse/pull/18840
* feat(ingestion): measure synchronous OTEL work and preparation codepaths by @sumerman in https://github.com/langfuse/langfuse/pull/18844
* feat: Add status information on integrations screen directly by @jordibosch20 in https://github.com/langfuse/langfuse/pull/18718
* feat(traces): add dedicated skills tab by @tobi12345 in https://github.com/langfuse/langfuse/pull/18872
* feat(observability): gate ECS and container resource detectors behind a flag by @Steffen911 in https://github.com/langfuse/langfuse/pull/18854
* feat(ai-gateway): route models by connection slug by @wochinge in https://github.com/langfuse/langfuse/pull/18628
* feat(gateway): add per-connection model controls by @wochinge in https://github.com/langfuse/langfuse/pull/18642
* feat(skills): add getting-started onboarding by @tobi12345 in https://
## Features
- feat(memory): authorize scoped note access and durable cleanup (#9096)
- feat(library): How Do You Build a WhatsApp AI Agent With Sim? (#9080)
- feat(library): 5 Best Discord AI Bot Builders for Community Automation in 2026 (#9081)
- feat(library): 6 Best AI Agent Options for Ecommerce Operations in 2026 (#9082)
- feat(library): Best AI Agents for Querying SQL Databases in Plain English (#9083)
## Improvements
- improvement(search): follow Jira summaries holding every term with those holding half of them (#9121)
- improvement(search): fall back to Jira summaries holding half the terms of a longer query (#9115)
- improvement(search): lead an overflowing Jira all-terms match with issues whose summary holds every term (#9111)
- improvement(seo): lead comparison pages with a direct answer, re-verify competitor pricing, and rebuild the GitHub, Shopify, and Snowflake integration pages (#9098)
- improvement(seo): list the v2 API as a catalog item and answer markdown 404s (#90