dsh-proactive
自主智能多模型协同调度系统 — 主动感知、自主决策、多模型并行、质量反思自愈、经验沉淀进化
11 results
自主智能多模型协同调度系统 — 主动感知、自主决策、多模型并行、质量反思自愈、经验沉淀进化
Heartbeat plugin for DeepSeek Harness: wakes the agent on a configurable interval so it proactively reports progress, risks, or blockers — and makes small talk when there is nothing to report.
dsh IM hub: WeChat(ilinkai) / QQ / Feishu bridge with proactive push & remote monitoring
Proactive scheduling v2: value network + file/process/http sensors + HMAC webhook triggers + off-peak window
DeepSeek Harness-native Feishu (Lark) gateway: chat with the DSH agent from Feishu via long connection, with persistent sessions, /new, Markdown replies, live streaming progress cards, native Typing reactions, click-to-answer approval / Q&A cards, and proactive push.
Semantic long-term memory for DeepSeek Harness: embedding-based retrieval over a persistent cross-session memory store, with model-facing tools, proactive per-question recall, automatic conversation summarization, and auto-selected embedding provider (apiKey present → API, otherwise local).
OpenCode Go billing layer for DeepSeek Harness (dsh): cached official pricing, proactive update checks, bill computation and a resident bill line in the web composer dock.
dsh heartbeat plugin: periodic proactive checks + message tool (send iMessage) + settings UI. Independent of the iMessage gateway.
Linux crontab-style scheduled tasks for DeepSeek Harness: the LLM can schedule recurring workflow runs and prompt-driven tasks with cron expressions, plus proactive task suggestions inferred from the chat.
DSH 主动通知插件:按类型区分通知文案,审批通知等页面弹窗就位后才弹出
Skill manager for DeepSeek Harness: proactive skill activation with trigger hooks, GitHub source sync, and a Settings management UI.