DiligenceLai/dsh-memory-ga0

dsh-memory-ga

Gated GA-style layered memory for DeepSeek Harness: hard-injected L1, working checkpoint, settlement to Skills/L1/L2 — no silent auto-retain.

包名
dsh-memory-ga
版本
0.1.0
许可证
MIT
最近更新
2026年8月22日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DiligenceLai/dsh-memory-ga

Configuration

Cordis config on plugin id memory-ga (optional):

- id: memory-ga
  config:
    # root: null            # default: $DSH_HOME/memory
    bootstrap: true
    injectL1: true
    injectWorking: true
    l1MaxChars: 1200
    workingMaxChars: 1200
    persistWorkingFile: true
    nudge:
      enabled: true
      workingEvery: 12
      settleAfterSteps: 15
      maxWorkingNudges: 3
      maxSettleNudges: 2

Hard dependency: the plugin declares inject: ["tools", "systemPrompt", "llm"]. @deepseek-ai/dsh-llm (with createUserMessage) must be present in the host composition — working-memory and nudge injection rely on it. If it is missing, the plugin still loads but memory_status will warn that working/nudges are not injected, rather than silently failing.

workingMaxChars is the single cap for both storing and injecting the working notepad, so memory_status.workingChars always reflects what the model actually sees.