Liangebra/dsh-smart-compact ↗★ 0
dsh-smart-compact
Custom DSH CompactionEngine backend: configurable threshold prompting, mandatory fallback at the limit, DCP-inspired dedup/purge, custom summary prompt, and /compact like the original. Zero external state — everything is rebuilt from the append-only session log.
AI 분석
核心用途是自动或手动压缩长会话上下文，防止超出模型限制。适合需要进行超长对话、频繁触发上下文超限的重度用户。
설치
검증된 bundle이 없거나 호환성 검사에 실패했습니다. 먼저 저장소 설명을 읽어 주세요. 전체 README 읽기 ↗
Configuration
| Option | Default | Meaning |
|---|---|---|
thresholdRatio | 0.5 | Context-usage fraction where the advisory nudge appears (agent/pre-step); the model decides whether to use the compress tool. |
mandatoryRatio | 0.9 | At/above this the engine auto-compacts the largest compressible span once per turn. |
summarizationMaxTokens | 8192 | Generation cap for the direct ctx.llm.stream summary call (purpose: 'compaction'). |
preserveRecent | 5 | Number of newest surface nodes never auto-compressed. |
dedupEnabled | true | Offer DCP-style dedup suggestions in dcp_status. |
purgeErroredTurns | 4 | Offer purge suggestions for the N most recent errored turns. |
protectedTools | [] | Tool names whose call/result pairs are never compressed. |
protectUserMessages | false | Keep every user message verbatim (never compress them). |
summaryPrompt | built-in | Full prompt template; {content} is replaced with the span text. |
modelContextLimit | auto-probed | Explicit context window (tokens) that wins over model probing. |
autoNudge | true | Enable the threshold advisory nudge. |
autoTools | true | Register compress and dcp_status model tools. |