Max-Null/dsh-habit

Name: Max-Null/dsh-habit
Author: Max-Null

插件Plugin 原生Native ⭐ 2 cat_label.deepseek-harnesscat_label.deepseek-harness cat_label.habitcat_label.habit cat_label.ssidcat_label.ssid

DeepSeek Harness 的自学习习惯引擎——纠错信号、阈值判断、两级人工门控

项目介绍Project Overview

由知微Agent(zhiwei)编辑Edited by Zhiwei Agent (zhiwei)

@max-null/dsh-habit 是 DSH 自学习习惯插件，属 SSID 桌面体验。它确定性监听会话中的用户纠正信号，累计达阈值后用低成本模型判定习惯候选，再经两级人工确认写入 dsh-memory 并自动召回。适合希望从反复纠正中沉淀稳定偏好、且不受上下文衰减影响的场景。需宿主提供 storage 与 llm；模型不能自行提升习惯，必须人工把关。

@max-null/dsh-habit is a self-learning habit plugin for DeepSeek Harness, part of the SSID desktop experience. It deterministically observes user-correction signals in session events, invokes a low-cost model once a threshold is reached, and routes habit candidates through a two-level human gate before dsh-memory stores and recalls them. Use it to turn repeated corrections into durable preferences without context decay. It requires host storage and llm, and the model can never auto-promote habits.

在 GitHub 查看View on GitHub

发给你的 DSH 安装Send to your DSH

请帮我了解并安装插件：【dsh-habit】【https://github.com/Max-Null/dsh-habit】

把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.

或使用命令行安装（适合开发者）Or use CLI install (for developers)

命令行安装CLI Install

dsh plugin --profile web add github:Max-Null/dsh-habit

把 Max-Null/dsh-habit 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

2.8 KB · 缓存于 2026-08-27 05:42:15 · 2.8 KB

@max-null/dsh-habit

本插件属于 @max-null/* 插件系列——这一系列共同构成 SSID（思灵 · Seek Soul in Darkness） 桌面体验。SSID 是整合它们的盒：dsh-capture · dsh-chat-rail · dsh-chinese-thinking · dsh-draft-polish · dsh-guardian · dsh-habit · dsh-header-unify · dsh-memory · dsh-node-appearance · dsh-plugin-center · dsh-skill-mcp-center · dsh-ssid-panels · dsh-ssid-zh-ui。

This plugin belongs to the @max-null/* family — a set of plugins that together form the SSID (思灵 · Seek Soul in Darkness) desktop experience.

Self-learning habit engine for the DeepSeek Harness — observes user-correction signals from session events, judges habits with a low-cost model on threshold, and settles candidates behind a two-level human gate. No new agent role: the judgment is an event-driven plugin, immune to context decay.

The loop

① observe   session/event → correction-signal detection (deterministic, zero-token)
② judge     >=3 signals in one session → one flash call (evidence slices + existing habits)
③ settle    candidate zone → user confirms → dsh-memory remember() (suggested)
            → user confirms again → auto → recall injection

Compose

- id: habit
  name: '@max-null/dsh-habit'

Requires storage and llm in the host composition (dsh-base ships both). Installs as a bundle: dsh plugin --profile <name> add @max-null/dsh-habit.

Service

ctx.habit — the engine:
- snapshot() → candidates (newest first)
- confirm(id) / discard(id) → first-level human gate
- (the second gate is dsh-memory's own suggested→auto confirmation)

Config

Field	Default	Meaning
`signalThreshold`	`3`	Correction signals before one judgment call
`provider`	`deepseek-official`	Judgment model provider
`model`	`deepseek-v4-flash`	Judgment model (cheap, deterministic)
`storageRoot`	`$DSH_HOME/storages/habit`	JSON storage root

Design notes

Deterministic observation, LLM on demand: correction detection is a fixed phrase list + length cap (task descriptions are not corrections); the LLM only runs when a session accumulates enough signals.
Two-level human gate: candidates must be confirmed in the UI AND then pass dsh-memory's own suggested→auto gate. The model can never promote its own habits.
Narrow input for quality: the judgment call gets at most 5 evidence texts plus the existing habit list — judgment quality comes from precise context, not volume.

Develop

npm install --legacy-peer-deps
npm test
npm run typecheck
npm run build

SSID 系列

渲染基于仓库 Max-Null/dsh-habit 的 README.md。在 GitHub 查看原文 →

命令行安装CLI Install 复制安装命令Copy Install