dsh-plugin-meta-memory
适用于 DeepSeek Harness 的结构化长期记忆系统——基于单元的简要/完整配对，支持自动注入
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-plugin-meta-memory@0.1.1Plugin Meta Memory 以 dsh-plugin-meta-memory 发布，当前版本为 0.1.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Structured long-term memory system for DeepSeek Harness.
Teaches the agent how to organize memories using a structured system:
verb-modifier-noun.unitdsh plugin --profile your-profile add dsh-plugin-meta-memory
.meta-memory/
├── index.md
└── units/
├── debug-auth-module.unit/
│ ├── 0.token-refresh-fail.brief.md
│ └── 0.token-refresh-fail.full.md
└── read-deeplearning-paper.unit/
├── 0.transformer-attention.brief.md
└── 0.transformer-attention.full.md
# token-refresh-fail
JWT token refresh returns 401 due to timestamp offset calculation error.
# token-refresh-fail
## Context
Auth module was failing on token refresh after 1 hour.
## Finding
expiresAt calculated using milliseconds instead of seconds.
## Evidence
src/auth/refresh.ts:42 - Math.floor(Date.now() / 1000) fixes it.
## Relevance
Any JWT/token related debugging in the future.
mm init # Initialize memory directory
mm list # List all units and records
mm read <unit> # Read all briefs in a unit
mm search <query> # Search briefs by keyword
mm index # Show the index
- id: meta-memory
name: dsh-plugin-meta-memory
config:
memoryPath: '~/.dsh/meta-memory'
enableInjection: true
enableSkill: true
maxBriefBytes: 4096
MIT -- YYTbit