tokens 43

DeepSeek Harness usage & cost tracker plugin: per-call token/cache-hit stats, peak/off-peak billing, DeepSeek balance query, CSV/JSON/PNG export with custom destination, and persistent local storage. Ships a host half plus a web client half in one npm pac

Floating macOS-glass DeepSeek usage panel for the DSH web UI: live official balance + token usage (today, session, 24 h smooth trend, per model) without opening platform.deepseek.com/usage. · DSH 毛玻璃用量面板：官方余额 + Token 用量

A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance

DeepSeek Harness usage dashboard with model, provider, workspace, cache, balance, and CSV insights

DeepSeek 用量 / 成本 / 余额仪表盘 for DSH Web：输入框下方实时指标指示器 + 零依赖 SVG 用量可视化图表（含每轮成本视角、耗时叠加、异常标记、成本徽章、上下文压力条），token 数据来自官方 adapter 上报，成本按官方刊例价 + 用户覆盖 pricing.json 解析，余额来自官方 /user/balance 接口。

Token usage, multi-dimensional statistics, auto-detected billing plans (Code/Token) and estimated spend for the dsh web UI

Per-model token usage, cost estimation and DeepSeek account balance for the DeepSeek Harness Web settings panel.

dsh client bundle: a sidebar usage & cost dashboard — token stats, peak/off-peak aware per-model pricing, membership ladder, achievements and a daily heatmap.

DeepSeek / OpenCode Go / OpenAI 额度悬浮窗：输入框上方显示，支持 DSH 模型列表同步、自定义额度接口、可拖动、主题适配；内置 DSH 会话 token 用量统计（按 日/月/模型）与官方峰谷价费用估算。

DSH usage statistics dashboard: token / cost / duration / session aggregation with trend, heatmap and calendar views (settings.section "数据看板").

Curate tool output before it enters the model's context: keep error/warning lines and head/tail, spill the full text to disk with a pointer. Faster turns, smaller context, sharper attention — for every tool, not just bash.

Token cost tracker for DeepSeek Harness -- track usage, calculate costs, budget warnings

Usage statistics panel for DeepSeek Harness: historical token and money aggregates folded from every durable session log, drawn as a rolling-year heatmap.

Session context governor for DeepSeek Harness: prompt size and per-step cost in dollars (cache-read/cache-write aware), cache-hit, context bands, a per-session compaction threshold derived from the model window, DeepSeek balance and peak/off-peak tariff,

Draggable real-time token & context dashboard for the DSH Web GUI, mounted on the frame-wide shell.overlay seat

DeepSeek off-peak (half-price) token countdown: a durable dual-face plugin providing the deepseek_cheap_tokens tool plus an ambient 24h peak/off-peak dock widget.

DSH 用量统计插件：token 采集、活跃热力图、费用估算、超限守卫

Agent FinOps / token analytics for DeepSeek Harness: usage collection, time-aware cost engine, cache analysis, and session drill-down

统计本机全部 DSH 会话的历史 token 总消耗，按 message.id 去重，支持按天/模型/Provider/项目分组。Global token-usage totals across all DSH conversations.

Offloads large, low-judgement DeepSeek Harness tool results to small one-shot worker agents before they enter the main model context

DeepSeek Harness usage & cost tracker plugin: per-call token/cache-hit stats, peak/off-peak billing, DeepSeek balance query, CSV/JSON/PNG export with custom destination, and persistent local storage. Ships a host half plus a web client half in one npm pac

Per-turn and per-session API cost estimation for DeepSeek Harness conversations.

DeepSeek Harness native sidebar usage panel: official balance + token usage history from session logs

dsh plugin: persistent whole-machine LLM usage ledger with a markdown /llm-stats report (GFM tables + emoji: tokens, cache hit, model/tool time, per-day bars)

DeepSeek Harness plugin: a session cost chip in the conversation header - live token usage by bucket, peak/off-peak tariff, and a countdown to the next tariff switch.

DSH 模型管理层：网关可达性探测、模型目录拉取、DeepSeek + MiniMax/智谱/Moonshot/StepFun 余额与配额、本月用量统计、余额预警、Provider 健康看板，再把本机装好的 codex / claude / agy 注册成子代理（装了才出现）。零运行时依赖，不改动 DSH 安装。

DeepSeek 账户控制台：实时余额监控 / 用量统计 / 全局悬浮 HUD（官方 API 直连，Key 仅存本机后端）

dsh usage & performance statistics: settings-panel plugin + TUI (tokens / TTFT / TPS / cost)

Shows the current session's estimated monetary cost in CNY as the leading item in the DeepSeek Harness status line.

Secure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.

Real-time cost tracking for the current DSH conversation: a composer-dock line showing the running token usage and DeepSeek official price estimate (base and peak/valley pricing).

API token usage and estimated cost reports for DeepSeek Harness, with per-route pricing, session totals and CNY/USD display.

Per-turn DeepSeek spend, live official pricing, and current balance for DeepSeek Harness Web.

DeepSeek / OpenCode Go / OpenAI credit floating widget: shows above the input box, supports DSH model-list sync, custom quota endpoints, drag & theme adaptation; built-in DSH session token usage stats (by day/month/model) with official peak/off-peak cost

Token usage, model cost analytics, trends, and activity heatmaps for DeepSeek Harness

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

Track token spend and enforce budgets for every model call your dsh agent makes.

DeepSeek Harness plugin that makes agent output maximally terse, concise, and clean without sacrificing quality. Always-on, append-only.

DSH web GUI composer real-time token counter (client plugin, v1)

dsh 插件 · 使用量仪表盘：离线扫描会话日志，统计每日/每周/每月 token、估算费用、模型/工具/技能/命令榜、输出速度、工作时段与质量指标；gridstack+ECharts 卡片可拖拽编排，支持自定义公式与 AI 编排（提示词往返导入）。

Realtime model usage panel: tokens, cost, requests, trend and composition

Context occupancy and account balance for the DeepSeek Harness Web Client: a session-header readout, a balance capability seam, and a DeepSeek provider

Tool-result memoization for DeepSeek Harness — TTL cache over idempotent tool calls; cache hits short-circuit re-execution with an explanatory verdict, LRU-bounded, per-tool TTLs, JSONL audit.