Dify 更新:CLI Skill 管理、嵌套工作流追踪与 Agent 文件处理
如果你在用 Dify 搭 Agent,这批更新很实用:CLI 能管 Skill 版本和跨 Agent 发布,嵌套工作流出问题能逐层排查,批量上传和 PDF 预览省去不少手工操作。
Dify 发布一批平台更新,其中 difyctl 新增 Skill 管理,让编码类 Agent 通过 CLI 完成可复用 Skills 的导入、版本审查和向多个 Dify Agents 发布更新。
工作流方面,新增嵌套工作流追踪,可以逐层查看单个 workflow 步骤的执行情况,更快定位失败节点;同时支持在不同工作空间之间迁移应用,无需手动重建 Workflow Tool 依赖。
Agent 文件处理也有改进,包括批量上传、应用内 PDF 预览,以及改进 DOCX 图片提取。完整发布说明见 Dify 的 GitHub 仓库。
3/3 More updates: • difyctl Skill management: Let coding agents manage reusable Skills through the CLI, from importing and reviewing versions to publishing updates across Dify Agents. • Nested workflow tracing: Find failures faster by tracing individual workflow steps, and move apps between workspaces without manually rebuilding Workflow Tool dependencies. • Agent file handling: Prepare Agent context faster with batch uploads, in-app PDF previews, and improved DOCX image extraction. Full release notes github.com/langgenius/dif…
This report is categorized under AITOP's "Products" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Dify, difyctl, agents, workflows.
Source attribution: curated from Dify (@dify_ai).