LangChain releases Managed Deep Agents v0.9 with Schedules SDK, per-run config, Slack reactions

LangChain has released Managed Deep Agents v0.9, which adds a Schedules SDK for agents to create their own reminders, follow-ups, and recurring tasks mid-conversation, and per-run configuration that lets users pick the model, skills, MCP servers, and sandbox for each run so one deployment can serve multiple teams or repos. The company's X announcement and a LangChain blog post also describe Slack reactions, where agents react to messages when a run starts. According to the blog post, the reactions attribute accepts either a fixed emoji or a function that returns one, with examples choosing an emoji by message content or classifier confidence. A later LangChain post describes the same feature as a Reactions API for building loading states and receipts using heuristics, decision models, or custom logic. These are LangChain's own claims about its product; no independent testing or customer results have been reported.