Starlight-bananice/dsh-status-bar ↗★ 3
@Starlight-bananice/dsh-status-bar
DSH 底栏管理插件：提供可配置的会话状态栏（包含状态、模型、上下文、费用等 17 个数据段），替换内置统计行，带设置页与快速开关菜单。
AI 分析
核心用途是美化并增强 DSH 网页端底栏的信息展示。适合需要实时监控 Token 消耗、会话费用、推理速度和上下文状态的用户。配置完全在浏览器本地保存。
安装
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Starlight-bananice/dsh-status-bar说明文档
阅读完整 README ↗Configuration
All configuration is client-side, stored in browser localStorage under dsh.statusBar.v1, edited via the settings page or the in-composer gear menu.
| Option | Default | Meaning |
|---|---|---|
enabled | true | Master switch; false hides the bar entirely |
wrap | true | Allow the bar to wrap onto multiple lines within the input card's width instead of eliding (the bar never runs past the input box's edges in either mode) |
segments | 13 on / 4 off (see below) | Ordered list of enabled segments |
cost.currency | CNY | Currency for cost display (CNY / USD) |
cost.models | {} | User-maintained model price book (model id → prices + schedule) |
Default segment state: on — status, model, counts, durations, speeds, cache hit, tokens, context, TPS, session time, jobs, queue, errors; off — title, workspace, agent, cost.
Model price book entry (values added when a model is configured): input 2, cache read 0.5, cache write 2, output 8 (per 1M tokens, in the configured currency); peak/off-peak disabled by default; when enabled, defaults to DeepSeek's official windows 09:00–12:00, 14:00–18:00, timezone local.
Environment variables: DSH_HOME (host-side) — base directory for the plugin's local data (default ~/.dsh). No other env vars, no secrets, no tokens.
Segment reference (all 17, toggleable & reorderable):
| Segment | Shows | Source |
|---|---|---|
| Status | ● running / idle / error dot | snapshot running / partial / lastAgentError |
| Model | model of the latest response | sessionModel projection (host fold of assistant/message events) |
| Title | session title (truncated) | SessionSummary |
| Workspace | workspace dir name | SessionSummary |
| Agent preset | preset name | SessionSummary |
| Turns & steps | N turns · M steps | sessionStats projection (window-fold fallback) |
| Model & tool time | LLM · tool-call wall time | sessionStats |
| TTFT & decode | avg first token · tok/s | sessionStats |
| Cache hit | prompt cache-hit share (2 decimals, capped at 99.99%) | tokenUsage |
| Tokens | billed input/output totals | tokenUsage |
| Context | context-window occupancy % | contextPressure |
| Throughput TPS | live generation rate (default on) | liveTokenUsage projection — folded from assistant/chunk in real time; block-aware estimation (~4 chars/token + block/role framing, re-priced at block-end, EWMA against burst flushes), exact once the provider reports usage; 0 while the session is not generating |
| Session time | wall clock, ticks while running | turnTimings |
| Cost estimate | ≈¥0.0123 (off by default) | sessionUsage projection — each model's usage × its own effective price (flat or peak/off-peak at now), summed across models |
| Jobs | running background jobs | jobsBySession |
| Queue | queued messages | snapshot queue |
| Errors | failed/retried/over-limit count (>0 only) | node fold |