wwskills/dsh-long-memory0

@wwskills/dsh-long-memory

Long-term cross-session memory plugin for DeepSeek Harness (L5 + L7 layers): SQLite-backed, FTS5 + optional embedding recall, append-only audit log, single-bundle dual-face packaging.

包名
@wwskills/dsh-long-memory
版本
0.1.0
许可证
MIT
最近更新
2026年8月25日

安装

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

Configuration

Defaults are sensible. Override via your profile's patch layer as needed.

Embedding

ProviderUse caseCost
noneFTS5 keyword only (default)Zero
ollamaLocal Ollama serviceZero (local)
openai-compatibleAny OpenAI-style APIPer-call
- id: long-memory
  config:
    embedding:
      provider: 'ollama'          # 'none' | 'ollama' | 'openai-compatible'
      model: 'bge-m3'
      dimension: 1024
      ollama:
        base_url: 'http://127.0.0.1:11434'

L7 Auto-extraction

L7 reads your DSH LLM provider config automatically — no extra API key needed.

- id: long-memory
  config:
    l7:
      enabled: true               # enable auto memory extraction
      auto_extract: true          # LLM-based + keyword fallback
      extractor_model: ''         # empty = use cheapest model from your DSH config
      extractor_temp: 0.2
      interval_ms: 21600000       # 6h minimum between extractions

Storage

    storage:
      path: '${DSH_HOME}/long-memory/long-memory.db'
      markdown_dir: '${DSH_HOME}/long-memory/markdown'