dsh-narrative-ledger
Content-addressed timeline, canon and character-knowledge evidence for DeepSeek Harness
12 results
Content-addressed timeline, canon and character-knowledge evidence for DeepSeek Harness
Simulator State as Code for iOS developers, CI pipelines, MCP clients, and DeepSeek Harness
Add drag, eight-way resize, pin, maximize, backdrop controls, and persistent state to DeepSeek Harness web modals.
A structured work-state protocol for DeepSeek Harness agent handoffs
DSH web plugin: a real-time proxy (mihomo) status panel — active node, latency, run state, port.
固态电池
DSH host bundle plugin: builds a two-level (category + skill) recall index over all local SKILL.md files and routes a natural-language intent to the best-matching skills, with three-state (hit / low-confidence / miss) fallback.
Native DeepSeek Harness plugin: a turn that states a verdict without evidence does not end — it is steered back for proof.
RALPH cognitive-loop plugin for DeepSeek Harness: Reflect → Assess → Learn → Plan → Handle autonomous code-generation and error-repair state machine with a hard cycle cap and event-sourced observability.
Shared handoff kit for DeepSeek Harness: evidence-driven handoff and repo-local task-id state skills, cross-platform (macOS/Linux/Windows).
The Agent states: `thinking`, `waiting`, `idle`, and `error` are automatically synced to workled via the MCP protocol. Light‑effect parameters and touch macros can also be configured for the device over MCP.
用 GSD(Get Shit Done)项目管理法推进大型项目:把项目组织成 里程碑(Milestone) → 阶段(Phase) → 计划(Plan) → 任务(Task) 的层级,维护 .planning/ 状态文档。当项目存在 .planning/ 目录(ROADMAP.md / STATE.md / phases/),或用户要求按里程碑/阶段拆分推进大项目时使用。