dsh-composer-tokens
Real-time token estimates for the DSH conversation composer, combining the current context baseline with the draft and showing exact or heuristic counts.
为 DSH 对话输入框实时估算 token 数，将当前上下文基线与草稿合并计算，并区分精确计数与启发式估算。
How to install
dsh plugin add dsh-composer-tokens About
dsh-composer-tokens DSH（DeepSeek Harness）web GUI 输入框实时 token 计数插件（纯客户端，v1）。 设计文档：docs/design.md（权威）· 实现前验证结论与决策门 G1：docs/m0-spike.md 形态 conversation.input.right 行内小徽标： ≈12,345 · 38% ← 预计总 tokens（基线 + 草稿 + 消息帧常数）· 上下文占用率 hover/focus 展开 Tooltip：基线（基于最近一次请求）、草稿增量、消息帧常数、会话累计真实 usage（tokenUsage 四桶）、输入缓存命中率、模型名、口径标记（精确/估算）。 打字 250ms 防抖刷新草稿部分；历史基线随 session/projection 帧自动更新，不闪。 基线口径：优先真实锚点 projectedTokens（已含系统提示词+工具定义，不重复计）；新会话首次请求前用 contextBreakdown 的官方启发式（系统+工具），仍无则用上次会话规模缓存占位（均标 ~），首次发送后自动校准（docs/m0-spike.md「口径修正」）。 @skill 等引用：引用文本按发送同路径计入草稿；技能内容体由 host 在请求侧展开，发送后自动进入基线校正（发送前不可预知是其固有口径）。 精确引擎不可用（未知…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 0
- mo. downloads
- 606
- Last push
- 2026-09-03
- Created
- 2026-08-31
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin
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.