dsh-live-token-stats
Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.
在输入框下方实时渲染 token 状态带：基于 DeepSeek 官方 BPE 分词表显示流式 token/s、输出 token 与首字延迟，并对比每次 step 的估算与实际偏差，用于判断生成是慢还是卡住。
How to install
dsh plugin add dsh-live-token-stats About
dsh·实时 Token 统计·溺水检测插件 引言 DeepSeek Harness 经常会看起来像卡住了，只显示**深度潜水中**而没有更详细的说明，根本不知道是在准备大惊喜还是仅仅是**溺水**了。 这里点名批评 Opencode Go，先是在 X 上宣传自己能够复现 DeepSeek 的价格，结果半夜悄悄同步涨价和峰谷价的同时，还把额度削减到原来的 1/4。虽然后续回调到 1/2，但代价是从不知道哪里找来的超级量化还超级慢又超级不稳定的模型，不仅思考强度无法调整，首字延迟还高达数十秒，完全就是溺水死掉了。 此插件两个核心功能，读取实时的大模型流式返回并实时使用 DeepSeek 分词表分词，得到实时的 token/s 计数，并在流式结束后显示估计与实际的偏差；另外轮询首字是否返回以实时更新首字延迟，用于判断是否溺水。 功能 **估算算法**：默认 bpe 模式将流式文本的每个 delta 增量喂入字节级 BPE 切分器，本地内置 DeepSeek V4 词表；跨 delta 维护未完成尾段，计数与整段一次性切分逐 token 一致，并已用 transformers 逐 token id 黄金对照验证。可选 density 双密度回退，按字符类别分别折算，配置见下方。 **added tokens 对齐**：内置完整 added tokens 元数据，与官方 tokenizer…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 4
- mo. downloads
- 2.1K
- Last push
- 2026-09-16
- Created
- 2026-08-21
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- ai-tool, deepseek, dsh, dsh-plugin, llama-tokenizer, token-counter, token-usage
Related plugins
TokenLedger
zh667/TokenLedger
Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.
dsh-context
bowenliang123/dsh-context
DSH context insight panel: Context dashboard + /context command + Context browser — one-stop context lifecycle management with categorized composition, content details, evolution trends, compaction/injection events, and stats.
dsh-usage-statistics-panel
HaoyueQin/dsh-usage-statistics-panel
Usage statistics settings panel: 26-week activity heatmap, daily token trend with a cache hit-rate curve, per-model donut and breakdown, time-range filters, summary cards, one-time historical backfill and lossless rebuild.
dsh-all-usage
ParticleLight/dsh-all-usage
Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.