본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

context-compactor

emberdesire 제작

CLI Utilities
1.1kclawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.

설명

이 스킬이 하는 일

Client-side token estimation plugin for OpenClaw that proactively summarizes older messages before local models silently truncate or corrupt context. Works with MLX, llama.cpp, and Ollama, which don't report context overflow errors the way cloud APIs do. Configurable thresholds let you tune behavior per model size.

Built-in OpenClaw compaction only triggers when the model reports an overflow error, which local models rarely do, so this plugin catches the problem before it silently corrupts the session.

사용 시점

  • Running long coding sessions with an 8K MLX model without losing conversation history
  • Debugging why a local model started returning garbled responses mid-session
  • Checking token usage before hitting a context limit with /context-stats
  • Forcing a fresh summary cache when context feels stale
  • Tuning compaction thresholds for a 4K vs 32K local model

예시 워크플로

입력

User sends a message in a long session using an MLX 8K model

에이전트
  1. 1

    before_agent_start hook fires and estimates total context tokens

  2. 2

    Plugin counts ~6,800 tokens against the 8,000 maxTokens threshold

  3. 3

    Splits messages into old (to summarize) and recent (to keep within keepRecentTokens)

  4. 4

    Calls the session model to generate a summary of old messages and caches it

  5. 5

    Injects the summary plus recent messages as the new context before the agent responds

출력

Agent responds normally with full context awareness, without the model ever seeing a truncated or overflowed input

설치

clawhub install emberdesire/context-compactor

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크