## What's Changed
* chore(pricing): remove retired legacy OpenAI snapshots from the model picker by @langfuse-bot in https://github.com/langfuse/langfuse/pull/19176
* chore(deps): bump node to 24.22.1 by @nimarb in https://github.com/langfuse/langfuse/pull/19339
* chore(design-sync): apply fixes from the daily design-system sync by @marksalpeter in https://github.com/langfuse/langfuse/pull/19297
* chore(design-sync): apply fixes from the daily design-system sync by @marksalpeter in https://github.com/langfuse/langfuse/pull/19354
* feat(topics): make it work well on mobile by @nimarb in https://github.com/langfuse/langfuse/pull/19364
* fix(web): renew expired signed URLs when native media chips reopen by @wochinge in https://github.com/langfuse/langfuse/pull/19300
* fix(ai-gateway): give telemetry flush its own shutdown budget by @wochinge in https://github.com/langfuse/langfuse/pull/19082
**Full Changelog**: https://github.com/langfuse/langfuse/compare/v4.70.0...v4.70.1
## [1.123.88](https://github.com/n8n-io/n8n/compare/n8n@1.123.87...n8n@1.123.88) (2026-10-26)
### Bug Fixes
* **core:** Release the SQLite write lock when the write connection fails to open ([#41918](https://github.com/n8n-io/n8n/issues/41918)) ([01b5e80](https://github.com/n8n-io/n8n/commit/01b5e80adc8fc772b6622808a087234c11caa062))
* Update certifi to 2026.10.23 in task runner ([#41995](https://github.com/n8n-io/n8n/issues/41995)) ([3012503](https://github.com/n8n-io/n8n/commit/3012503701d9e1243afeb54ba389e924be1a2ec4))
## [2.44.7](https://github.com/n8n-io/n8n/compare/n8n@2.44.6...n8n@2.44.7) (2026-10-26)
### Bug Fixes
* **core:** Start sub-workflow error workflow when a pre-run check fails ([#41978](https://github.com/n8n-io/n8n/issues/41978)) ([67d0e65](https://github.com/n8n-io/n8n/commit/67d0e65f5d5d01d49b1d14ea2c26a6b803bf058b))
* **Email Trigger (IMAP) Node:** Back off reconnects when the server drops each new connection ([#41927](https://github.com/n8n-io/n8n/issues/41927)) ([10a9518](https://github.com/n8n-io/n8n/commit/10a9518f0d9d470e619b500383b5b76fc1870662))
* **Microsoft SharePoint Node:** Fix the column mapper 403 and empty items in Map Automatically ([#41906](https://github.com/n8n-io/n8n/issues/41906)) ([e67d278](https://github.com/n8n-io/n8n/commit/e67d278ef0ae3c15493e74813ecce972e384ff1b))
* Update certifi to 2026.10.19 in task runner ([#41967](https://github.com/n8n-io/n8n/issues/41967)) ([2858cfb](https://github.com/n8n-io/n8n/commit/2858cfb935487b1554f415c848623652da2af5d7))
*
## Features
- feat(library): AI Coding Agents vs Code Completion Tools: Which Should Engineering Teams Choose? (#9375)
- feat(mothership): run scheduled jobs as durable unattended chat turns (#9331)
## Improvements
- improvement(docs): build feature-branch docs previews only when docs change (#9370)
- improvement(library): single JSON-LD source, Markdown articles, and IndexNow pings (#9355)
- improvement(library): rank related posts by tag rarity, add backlinks, and widen comparison and pagination links (#9354)
- improvement(auth): encrypt stored integration tokens (#9346)
- improvement(execution): run sandbox workers on a dedicated worker host (#9348)
## Bug Fixes
- fix(mothership): hold callerless runs' sim_cli to read API scopes (#9371)
- fix(mcp): answer an unpublishable workflow input on tool updates as validation, and match bare-name alternatives titles (#9367)
- fix(mothership): retry a job dispatch whose usage read failed instead of skipping the run (#9366)
- fix(billing):
## What's Changed
### Features
* feat(public-api): add unstable read-only Topics endpoints by @LysanderKie in https://github.com/langfuse/langfuse/pull/19104
* feat(ai-gateway): update Claude Desktop setup steps and merge Claude tabs by @wochinge in https://github.com/langfuse/langfuse/pull/19298
* feat(web): warn ClickHouse staff viewing data by @maxdeichmann in https://github.com/langfuse/langfuse/pull/19266
* feat(web): syntax-highlight shell, TOML and JSON setup snippets by @wochinge in https://github.com/langfuse/langfuse/pull/19306
* feat(ai-gateway): describe gateway keys inline and invite people from the keys page by @wochinge in https://github.com/langfuse/langfuse/pull/19310
* feat(evals): runBatchEvaluation MCP tool and batch_action_id on batch run outputs by @wochinge in https://github.com/langfuse/langfuse/pull/19314
* feat(web): jump to prompts, datasets, queues and evaluators from Cmd+K by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18921
### Fix
## What's Changed
### Bug Fixes
- Fix AGENTS.md to start the login process while evaluating and stop after three rounds.
### Documentation
- Update snapshot and changelog for v1.15.29.
## Contributors
@joaomdmoura
## Speech
Ollama can now generate [speech](https://docs.ollama.com/capabilities/speech) on macOS. `ollama run` plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible `/v1/audio/speech` endpoint.
```sh
ollama run phonon "Hello from Ollama."
```
## d3 decision models
[d3](https://ollama.com/library/d3) brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, or an image, and ask it to classify, answer yes or no, or score options with probabilities. The family includes 2B, 4B, 9B, and 27B sizes.
```sh
ollama run d3 "A customer says their card was charged twice." --ask "Is this a billing issue?"
```
## New Contributors
* @SynapShift made their first contribution in https://github.com/ollama/ollama/pull/19173
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.10...v0.40.11
## What's Changed
### Features
- Add support for LiteLLM-compatible kwargs.
- Implement platform application search in CLI.
- Highlight action picker search in CLI.
- Trace conversation routes and public replies in flow.
- Select organization during login in CLI.
- Add offline jev routing and guardrail evaluation runner.
- Run integration app actions directly with call: tool.
- Promote AgentExecutor out of experimental status.
- Add Azure DocumentDB vector search integration.
- Add read-only notebook text loader and standard-library jsonl loader.
- Ensure crewAI eval keeps the evaluation's full data in the project.
- Enable crewAI eval to run the crew itself for verdict from one command.
- Allow crewAI eval to export evaluations as files.
### Bug Fixes
- Fix platform integration token derivation from login.
- Resolve logging issues by preserving JSON logs on serialization errors.
- Skip non-UTF-8 cached skill metadata.
- Fix tool actions to honor failure policies and get fresh usage
### Hotfix on top of 0.92.3
* chore(docker): upgrade Node.js to 24.22.1
Fixes the [Node.js October 2026 security vulnerabilities](https://nodejs.org/en/blog/vulnerability/october-2026-security-releases).
## NVIDIA Nemotron 3.5 Bolt E4B
[Nemotron 3.5 Bolt E4B](https://ollama.com/library/nemotron-3.5-bolt) is NVIDIA’s smaller, Gemma 4-based vision-language model for fast local conversations, image understanding, and tool use. It supports a 128K-token context window.
The model includes a DFlash draft for speculative decoding.
ollama run nemotron-3.5-bolt:e4b
**Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.9...v0.40.10
## What's Changed
### Features
* feat(ai-gateway): show per-tool setup instructions after creating a gateway key by @wochinge in https://github.com/langfuse/langfuse/pull/19186
* feat(topics): write rules as target trace transcript by @marliessophie in https://github.com/langfuse/langfuse/pull/19236
* feat(blob-storage): add an outbound host allowlist for blob storage endpoints by @niklassemmler in https://github.com/langfuse/langfuse/pull/18907
* feat(web): gate self-hosted AI gateway on LANGFUSE_AI_GATEWAY_DEPLOYED by @wochinge in https://github.com/langfuse/langfuse/pull/19237
* feat(tracing): show requested skill loads and file paths by @tobi12345 in https://github.com/langfuse/langfuse/pull/19239
* feat(ai-gateway): guided gateway setup by @wochinge in https://github.com/langfuse/langfuse/pull/19231
* feat(mcp): create skill versions and manage labels and tags by @tobi12345 in https://github.com/langfuse/langfuse/pull/19247
* feat(ai-gateway): let LANGFUSE_AI_GATEWAY_PU
## 1.33.0 (2026-10-23)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(verify-openhands): launch --mars-web and --lock-to-cloud by @enyst in https://github.com/OpenHands/OpenHands/pull/18848
* feat(digitalocean): keep the web build signed in across restarts by @enyst in https://github.com/OpenHands/OpenHands/pull/18705
### Bug Fixes
* fix(automations): render the shipped current_phase on live runs by @aartem1 in https://github.com/OpenHands/OpenHands/pull/17122
* fix(verify-openhands): bug run puts back the viewport a block changed by @enyst in https://github.com/OpenHands/OpenHands/pull/18850
* fix(digitalocean): default new agents to the smallest VM by @smolpaws in https://github.com/OpenHands/OpenHands/pull/18702
* fix: mask secret values in request and Settings forms by @neubig in https://github.com/OpenHands/OpenHands/pull/18870
### Documentation
* docs(verify-openhands): map maintenance 2026-10-22 by @eny
Dify 1.18.0 brings **Agents that route workflows**, **portable app packages**, **deeper visibility into nested workflow runs**, and the opt-in **Agent Knowledge Base** experience. OpenAPI and the new difyctl expand how you build and manage apps from the command line.
> [!IMPORTANT]
> **Read the upgrade guide below before deploying.** Upgrade the API, workers, Agent Backend, and Agent runtime images together. Local Agent sandboxes require a non-empty authentication token, and Agent Backend uses a new run protocol. Source installations require Python 3.13. Install the new difyctl client and sign in again. Preserve your existing `PASSWORD_PEPPER` configuration.
### Release highlights
#### Agents that choose the next step
Let an Agent decide which workflow branch to take. Enable **Output Routes**, give each route a selection condition, and connect it to the next step—such as resolving a request directly or handing it to a specialist. The read-only `switch` output exposes the c
## Features
- feat(knowledge): import knowledge base bundles through the API and `sim knowledge import` (#9327)
- feat(monitoring): log event-loop lag, stalls, and in-flight route handlers (#9312)
- feat(ec2): add Amazon EC2 integration (#9304)
- feat(library): n8n vs Zapier vs Make: Which Automation Platform Is Best in 2026? (#9302)
- feat(library): LangChain vs LangGraph: What’s the Difference and Which Should You Use? (#9301)
- feat(library): CrewAI vs LangGraph vs AutoGen: Which Multi-Agent Framework Should You Choose? (#9300)
- feat(library): OpenClaw vs Claude Cowork: Setup, Pricing, Security, and Scheduling Compared (#9299)
## Improvements
- improvement(insights): shorten the unassigned usage tooltip (#9330)
- improvement(ci): balance integration jobs and retain documentation build caches (#9328)
- improvement(executor): size payload compaction bottom-up instead of re-serializing every subtree (#9316)
- improvement(file-parsers): parse spreadsheets on a worker thread (#9313)
## 1.32.0 (2026-10-23)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(home): store pinned automations in agent-server settings by @abhayymishraa in https://github.com/OpenHands/OpenHands/pull/18190
* feat(mcp): let the install dialog choose between installable library options by @ak684 in https://github.com/OpenHands/OpenHands/pull/18836
* feat(automations): list every cloneable provider's repositories in the automation picker by @ak684 in https://github.com/OpenHands/OpenHands/pull/18821
* feat(canvas): quiet backend logs by default by @neubig in https://github.com/OpenHands/OpenHands/pull/18830
### Maintenance
* chore: bump @openhands/extensions to 0.34.0 by @ak684 in https://github.com/OpenHands/OpenHands/pull/18842
* chore(deps): enforce seven-day third-party release-age policy by @smolpaws in https://github.com/OpenHands/OpenHands/pull/18800
* chore: bump agent-server to 1.58.1, automation to 1.25.1, and
## 1.31.0 (2026-10-22)
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
### Features
* feat(automations): hide the GitHub token secret field on self-hosted instances when GitHub is connected (OHE-3699) by @hieptl in https://github.com/OpenHands/OpenHands/pull/18829
### Bug Fixes
* fix(mcp): install OAuth-only library entries through the MCP server's own OAuth by @ak684 in https://github.com/OpenHands/OpenHands/pull/18780
* fix: keep automation repositories when editing by @ak684 in https://github.com/OpenHands/OpenHands/pull/18776
* fix(mars): forward typed session key to web bridge on non-baked binds by @lx3133584 in https://github.com/OpenHands/OpenHands/pull/18465
* fix(mars): preserve DigitalOcean sessions through auth recovery by @smolpaws in https://github.com/OpenHands/OpenHands/pull/18604
* fix(mcp): say the sign-in was not completed when an OAuth install pop-up is abandoned by @ak684 in https://github.com/OpenHands/OpenHan
## What's Changed
### Features
- feat(mcp): add listLlmConnections tool by [@wochinge](https://github.com/wochinge) in [#19139](https://github.com/langfuse/langfuse/pull/19139)
- feat(web): Treemap and Grid views for Topics results by [@nmtrang29](https://github.com/nmtrang29) in [#19106](https://github.com/langfuse/langfuse/pull/19106)
- feat(ai-gateway): log per-connection socket writes and output completeness by [@wochinge](https://github.com/wochinge) in [#19154](https://github.com/langfuse/langfuse/pull/19154)
- feat(blob-export): add opt-in score metadata and provenance field groups by [@niklassemmler](https://github.com/niklassemmler) in [#19138](https://github.com/langfuse/langfuse/pull/19138)
- feat(ai-gateway): global enable flag and derived JWT public key / key ID for self-hosting by [@wochinge](https://github.com/wochinge) in [#19159](https://github.com/langfuse/langfuse/pull/19159)
- feat(topics): internal users don't need feature flag by [@nimarb](https://github.co