快速了解
它能做什么
面向 DeepSeek Harness 的只读性能诊断插件,可查看会话延迟、上下文用量、压缩、溢出和 LLM 缓存表现。
本站提供的是中文说明,不代表该项目或 Plugin 自身提供中文界面;语言支持请以上游文档为准。
deepseek-harness Profile
0.1.2-rc.1 and 0.1.5-rc.1 declared; peer range >=0.1.2-rc.1 <0.2.0 or >=0.1.5-alpha.1 <0.2.0
证据已验证
核对日期 2026/9/10 UTC 14:05
选择前先看
将此插件包挂载到 DeepSeek Harness Profile 后重启 Profile,再通过 /fast 或 fast_report 查看当前会话的时间和 token 预算去向。它会报告加载耗时、压缩、工具结果溢出信号、上下文 token 占比、缓存命中率和基于阈值的建议。
适合谁
需要调优缓慢、上下文较重或频繁压缩的 DeepSeek Harness 会话的用户。
常见任务
- 判断会话加载是新建还是恢复路径,并比较加载耗时。
- 定位过大的系统提示词、工具 schema 或对话上下文。
- 在调整 Profile 设置前,查看压缩频率、溢出信号和 LLM 缓存命中率。
权限与数据
清单声明 session 读写权限;仓库文档说明其以只读方式观察 session 和 agent 事件。
权限- session:read
- session:write
- native-code:none
- 声明会将指标以每会话有界历史的形式保存到 dsh_fast 存储域。
- 可选的经处理工作目录默认关闭。
- 仓库文档称,报告身份信息和可选工作目录会在展示或持久化前进行清理。
- 仓库文档称该插件不会发起出站网络请求。
- 提供的证据未声明需要凭据。
局限
- 溢出检测在文档中被说明为基于持久化通知的尽力而为启发式判断。
- 系统提示词会将 AGENTS.md、技能和 persona 合并统计,不能按部分细分。
- 恢复加载耗时从发布时刻开始,不包含更早的磁盘读取阶段。
- 安装后必须重启 DeepSeek Harness Profile 才会生效。
DSHub 已核对
- 固定源提交和插件包补丁结构已验证。
- 软件包声明了事务性 Profile 插件包安装方式、Node ^22.19.0 或 >=24.0.0,以及 DeepSeek Harness 兼容性信息。
- 已声明 Apache-2.0 许可证。
DSHub 未核对
- 本次整理未实际执行安装、重启、/fast、fast_report 或运行时诊断。
- 未审计 npm 注册表包内容。
固定版本安装
安装 dsh-fast
这个Plugin Bundle没有 DSH Plugin 安装操作,请根据源码文档使用真实交付方式。
维护者原文
项目 README
⚡ dsh-fast
- 1024 store channel:
npm i -g dsh1024once, thendsh1024 plugin --profile web add dsh-fast(counts toward the deepseek1024.com install ranking).
Read-only performance diagnostics for DeepSeek Harness.
Observes the session event stream — never the model hot path — and reports where latency and context budget actually go.
Official repository. This is the only official repository of dsh-fast, maintained by PerryLink. Same-name repositories under other accounts are not affiliated.
English · 简体中文 · Español · Português · हिन्दी
</div>Compatibility
- DeepSeek Harness
dsh-v0.1.5-rc.1(adapted 2026-09-09; public tag commit183f08e9c6): the system prompt is surface node 0 (asystem/message) instead of a request-envelope field, so the report reads it from the surface and prices the meter's surface net of it. Verified 2026-09-10 with the published0.1.5-rc.1peers (full local gate chain); the monthly compat workflow re-runs the profile install smoke against the same pins. - Node
^22.19.0 || >=24.0.0, ESM only ("type": "module"). - Peer dependencies:
@deepseek-ai/cordis ^4.0.2,@deepseek-ai/schemastery ^3.18.2, and@deepseek-ai/dsh-session,@deepseek-ai/dsh-tools,@deepseek-ai/dsh-commands,@deepseek-ai/dsh-compaction,@deepseek-ai/dsh-storage-domainat>=0.1.2-rc.1 <0.2.0 || >=0.1.5-alpha.1 <0.2.0(devDependencies pin0.1.5-rc.1); the0.1.2-rc.1line stays supported at runtime through a structural fallback to the pre-0.1.5header.system.
What you get
- Session load timing — publication-to-first-request latency, classified
open(fresh) vsrestore(seeded/resumed), plus the restored seed-event count. - Spill-hit statistics — how many tool results were spilled to a session-scoped artifact (detected from the durable spill notice).
- Compaction count and trigger — total compactions, split
manual(slash command) vsautomatic(pressure), and total shadowed tokens. - Context-injection volume — system-prompt (AGENTS.md + skills + persona), tool-schema, and surface tokens with their shares of the total; the surface bucket is conversation history only (the meter's surface includes the system node on
0.1.5-alpha.1, which dsh-fast subtracts). - LLM cache hit rate — input / cache-read / cache-write / output tokens aggregated from provider usage, plus the derived hit rate.
- Optimization suggestions — threshold-driven notes (trim skills, tighten tool schemas, compact earlier, enable prompt caching, enable spill-policy, …).
- Async sampling — metrics are folded O(1) per event and snapshotted on a timer, never on the append path.
Quick start
git channel
# From a scratch profile (pins the commit; runs the self-contained `prepare` build)
dsh plugin --profile demo add "github:YOUR_ORG/dsh-fast#<sha>"
# The profile's pnpm-workspace.yaml gains an allowBuilds entry for dsh-fast on first add.
npm channel
dsh plugin --profile demo add dsh-fast
Both channels install the bundle row (see cordis.patch.yml) into the profile's dsh.profile.bundles stack and take effect on restart.
Install & uninstall
dsh plugin --profile demo add dsh-fast # install
dsh plugin --profile demo remove dsh-fast # uninstall
Verify the row mounts: dsh --profile demo --dump-config | grep dsh-fast.
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. |
Tools & surfaces
/fast— a human slash command that prints the current session's health report: load timing, spill, compaction, context-volume ranking, cache hit rate, and suggestions.fast_report— a model tool returning the same report as structured JSON (so the model can reason over it), with a human-readable text render.
Permissions & data
dsh-fast consumes only public seams: session/* and agent/* events, the optional ctx.tokenMeter, ctx.storageDomain, ctx.commands, and ctx.tools. It is strictly read-only over the session log — it never mutates the model request, tool results, or the session surface. Metrics are persisted to the dsh_fast storage domain (one bounded history per session), not to the session log. Report identity and the optional working directory are sanitized before any display or durable write.
Security boundaries
- Read-only, zero model-path overhead — folding is O(1) per event; sampling runs on a timer.
- No network, no credential handling — the plugin makes no outbound requests and stores nothing sensitive.
- Fail-loud configuration — every tunable is validated at mount; invalid bounds throw.
- Sanitized display/durable data — control characters are stripped and strings are budgeted;
cwdis off by default and path-truncated when enabled. - Reversible registrations — every contribution goes through
ctx.effect()/ctx.on()/register(), so uninstall and hot reload are clean.
Known limitations
- Storage domain, not session events — rc.2
Session.appendoffers noignorablemarker and no external event-registration surface, so a customfast/*session event would make the persistence coordinator refuse the log on restore. Metrics are therefore persisted to the storage domain; the raw events remain the reconstructable source of truth. - Spill detection is heuristic — it reads the durable spill notice (
Full … stored at:); no dedicated session event exists. - System prompt is one bucket — AGENTS.md, skill directory, and persona are all part of the assembled system prompt; since
0.1.5-alpha.1it is surface node 0 (asystem/message) and carries no per-section token accounting, so they are reported together. - Load timing starts at publication — the disk-read portion of a restore happens before
session/created(owned bysessionPersistence) and is not observable from this plugin's allowed events; the reported duration is publication-to-first-request.
Development
pnpm install
pnpm run typecheck && pnpm run typecheck:ci
pnpm test
pnpm run build
pnpm run verify:self-contained && pnpm run verify:artifacts
node scripts/check-readme-sync.mjs
pnpm pack
Topics
dsh, dsh-plugin, deepseek-harness, deepseek, cordis, performance, diagnostics, profiling, context-engineering, llm-cache
Contributors
Thanks to everyone who has contributed to dsh-fast:
- PerryLink — author and maintainer: designed and built the read-only diagnostics (session-load timing, spill-hit counts, compaction metrics, context-injection volume, LLM cache hit rate), the
/fastcommand andfast_reporttool, thedsh_faststorage domain, and the five-language documentation.
PerryLink DSH Plugin Family
This project is one of the 37 DeepSeek Harness plugins maintained by PerryLink. If this one helps you, the others likely will too:
| Plugin | One-liner |
|---|---|
| dsh-auto-review | Second-model auto-review on the approval chain, fail-closed by default |
| dsh-background-agents | Durable background child agents with a Web UI sidebar, messaging and interrupt |
| dsh-budget | Cost governance for DeepSeek Harness: budgets, carbon, and latency in one panel. |
| dsh-checkpoint-rewind | Claude Code /rewind-equivalent: snapshots, session forks, one-shot restore |
| dsh-claude-move | Migrate Claude Code sessions, memory, skills and CLAUDE.md into DSH |
| dsh-click | Cross-platform native desktop control for DeepSeek Harness — Windows first. |
| dsh-composer-history | Terminal-style input history for the web composer: arrows, Ctrl+R search |
| dsh-data-quality | Dataset quality checks and citation cross-checks (the optional numeric bridge consumed here) |
| dsh-defend | Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness. |
| dsh-doublecheck | Engineering-discipline guard: requirements grill, test gates, adversary review |
| dsh-draw | Unified static-image generation routing for DeepSeek Harness. |
| dsh-fund-research | Deterministic research reports for Chinese public mutual funds |
| dsh-github | GitHub PR/issues integration for DSH, every write gated by approval |
| dsh-industry-research | Industry research orchestration that seals its deliverables through this plugin's ctx.researchReport.assemble |
| dsh-library | Local document knowledge base for DeepSeek Harness. |
| dsh-local-ai | Local-model (Ollama) integration for DeepSeek Harness. |
| dsh-lsp-actions | LSP diagnostics, formatting, completion, code actions and rename over language servers |
| dsh-mask | PII masking middleware: anonymize at the model boundary, restore at the display layer |
| dsh-mcp-panel | Read-only MCP runtime panel: /mcp command + Settings tab with status, tools and errors |
| dsh-memento | Approval-gated cross-session memory: ctx.memory seam + SQLite + memory tool |
| dsh-observe | OpenTelemetry and Langfuse observability exporter for DeepSeek Harness. |
| dsh-output-styles | Claude Code outputStyles-equivalent runtime style switching |
| dsh-reach | Multi-channel approval/question bridge: WeChat/Telegram/Feishu, session console |
| dsh-permission-rules | Claude Code-style declarative allow/deny/ask permission rules with audit |
| dsh-personal-directive | Personal directive injector with top-bar toggle (framework edition) |
| dsh-plugin-guide | Plugin-development knowledge base as an on-demand agent skill |
| dsh-research-report | Verifiable research-report engine: content-addressed evidence ledger and sealed versions |
| dsh-score | Multi-dimensional quality scoring for DeepSeek Harness plugins. |
| dsh-session-pin | Pin sessions in the Web sidebar with durable ordering |
| dsh-session-sync | Cross-device session sync for DeepSeek Harness — a dedicated git mirror of your session store. |
| dsh-skill-pack-security | Security-audit skill pack: secret scan, dependency and supply-chain review |
| dsh-talk | Voice-first session loop for DeepSeek Harness: talk to it, hear it answer. |
| dsh-test-drive | Isolated install-and-smoke test drives for DeepSeek Harness plugins. |
| dsh-ticktick | TickTick/Dida365 task bridge: session-header panel + 11 tools |
| dsh-translate | Vendor parameter translation and deterministic JSON repair for DeepSeek Harness. |
| dsh-wechat | WeChat ↔ DSH bridge (Tencent iLink bot): text/image/file/voice, approvals in chat |
Install from the DSH Desktop Market
All PerryLink plugins are browsable in the built-in DSH Desktop Market: Market → Sources → add source → paste https://perrylink-dsh-catalog.perrylink.workers.dev/catalog-source.json → select it. Installation still goes through the Market's npm-identity verification and your confirmation.
License
Apache-2.0 — see LICENSE.
有意识地管理
安装与管理
前置条件与目标 Profile
目标: deepseek-harness Profile
交付方式: Git Bundle — PerryLink/dsh-fast#f03dec1b84234601298bb6ab20cbf6d93444beec。
验证、更新与移除
显示生命周期命令
dsh plugin --profile deepseek-harness list兼容性与访问范围
DeepSeek Harness plugin; restart-profile activation declared: 0.1.2-rc.1 and 0.1.5-rc.1 declared; peer range >=0.1.2-rc.1 <0.2.0 or >=0.1.5-alpha.1 <0.2.0。
风险事实
证据与编辑审查Manifest、Bundle patch、分发与新鲜度
不可变证据
审查状态与源码活动
若重视可复现性,请使用固定提交的 Git 插件包;按本地 Profile 策略审查其声明的存储行为和生命周期构建步骤。
AI 审查于 2026/9/10 UTC 14:06。GitHub 事实核对日期: 2026/9/10 UTC 14:06。
自当前证据基线以来,没有记录到重要源码变化。