dsh-fast
Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via the /fast command and the fast_report tool, persisted as reconstructable fast/* session events with async sampling off the model path.
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PerryLink/dsh-fast说明文档
阅读完整 README ↗Configuration
All tunables are Schemastery Config fields; invalid values fail the profile load loudly.
| Key | Default | Description |
|---|---|---|
enabled | true | Master switch; false mounts nothing. |
privacy.includeCwd | false | Include the sanitized session working directory in reports. |
sampling.snapshotIntervalMs | 60000 | How often active sessions are sampled (ms). |
sampling.maxHistorySamples | 20 | Samples retained per session in the durable history. |
thresholds.systemPromptTokens | 20000 | Warn when the system prompt exceeds this many tokens. |
thresholds.toolSchemaTokens | 8000 | Warn when the tool schema exceeds this many tokens. |
thresholds.surfaceTokens | 60000 | Warn when the conversation surface exceeds this many tokens. |
thresholds.cacheHitRateFloor | 0.1 | Warn when the cache hit rate falls below this (0..1). |
thresholds.compactionCountWarn | 10 | Warn once this many compactions have triggered. |
thresholds.compactionShadowTokens | 40000 | Warn when the average shadowed token count per summary exceeds this. |
spill.detectSpilledResults | true | Detect spilled tool results from the durable notice marker. |