Dify v1.16.1 adds multi-select inputs and workflow node locator
New debugging and collaboration features make building AI workflows easier than ever.
Dify, the popular open‑source LLM app development platform, has shipped v1.16.1 with a focus on workflow usability and collaboration. The standout addition is the multi‑select dropdown input for tool nodes, allowing users to pick multiple values from a predefined list when configuring tool parameters. A new workflow node locator lets developers click a node_id in run logs or error messages to instantly highlight the corresponding node on the canvas, dramatically speeding up debugging. The block selector panel now features better keyboard navigation, category previews, and an improved search, making node addition more intuitive.
Agent apps gain the ability to export DSL YAML directly from the sidebar menu, simplifying backup and version control. Knowledge tracing adds observability traces to RAG document processing, giving better visibility into indexing pipelines. Bug fixes address hidden‑tab collaboration conflicts, agent conversation history issues, and web app edge cases like JWT expiration and TTS playback on Safari/Firefox. The release also corrects document cleaner character stripping (preserving ï, ¿, ¾) and ensures spaces are kept during recursive text splitting. These improvements build on Dify’s mission to provide a robust, developer‑friendly platform for building AI‑powered applications.
- Workflow tool nodes now support multi‑select dropdown inputs for configuring parameters.
- Click a node_id in logs to locate and highlight the corresponding workflow node on the canvas.
- Agent apps can be exported as DSL YAML directly from the sidebar for easy version control.
Why It Matters
Dify continues to refine its open‑source platform, making AI workflow building and debugging more efficient for developers.