Search headlines, summaries and articles to connect the dots.
## [1.123.91](https://github.com/n8n-io/n8n/compare/n8n@1.123.90...n8n@1.123.91) (2026-10-30) ### Bug Fixes * **core:** Fix $('Node') expressions returning null for legacy Code node output ([#42249](https://github.com/n8n-io/n8n/issues/42249)) ([18c89cd](https://github.com/n8n-io/n8n/commit/18c89cdf2eda635fbb892730189a2de1a48b46da))
# Release v5.21.0 ## New Model additions ### MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model. It is specialized for reading text-dense images such as scanned pages, screenshots, receipts and tables. **Links:** [Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/minicpm_ocr) | [Paper](https://huggingface.co/papers/2509.18154) * Feat test (#49920) by @guarin in [#49920](https://github.com/huggingface/transformers/pull/49920) ### Flint Flint is Recursive's mixture-of-experts language model. Compared to a standard SwiGLU MoE transformer such as Qwen3-MoE, it uses hybrid attention (sliding-windo
