lmst2/dsh-asc0

dsh-asc

DeepSeek Harness 智能表面压缩(ASC):由模型决定何时及压缩什么,作为持久会话日志替代,支持完整重放、搜索和降级

AI 分析

通过智能压缩和确定性降级来主动管理上下文。适合长对话、高 Token 消耗,需要防止上下文溢出的用户。

套件
dsh-asc
版本
0.1.0
授權
MIT
最近更新
2026年8月14日

安裝

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lmst2/dsh-asc

Usage

After installing and restarting, no configuration is required — the plugin:

  • injects the context-management discipline into the system prompt (judgment rules, tool usage, tiered compaction cadence), so the model actively manages context from the very first turn;
  • injects nudge prompts on demand when context usage runs high (gated by real growth and cadence — no per-turn nagging);
  • provides deterministic degradation (tool-result pruning + LLM summarization) on overflow or manual compaction, without requiring model cooperation.

The plugin provides five model tools:

ToolPurpose
context_statuscontext usage, tiered checkpoints, system/dialogue composition, recommended ranges, recent surface nodes
context_compressreplace a surface range with a checkpoint you write (batching supported; tool-call pairs auto-extended; quality gate)
context_decompressundo a compaction: the original text returns to the surface at the checkpoint's own position (tier-aware; full: true reaches raw content)
context_recapre-read checkpoint summaries without decompressing the originals
context_searchfull-text search over the whole log (including compacted content)

Compacted content is never lost: the originals stay in the session log and can be decompressed or searched at any time.