dsh-balance-widget 0.5.3 → 0.5.5

package/README.en.md

@@ -1,6 +1,6 @@
 # dsh-balance-widget
 
-[中文](README.md) | **English**
+[中文](https://github.com/LL-cmyk-so/dsh-balance-widget/blob/main/README.md) | **English**
 
 [![npm](https://img.shields.io/npm/v/dsh-balance-widget?style=flat-square&label=npm)](https://www.npmjs.com/package/dsh-balance-widget)
 [![Stars](https://img.shields.io/github/stars/LL-cmyk-so/dsh-balance-widget?style=flat-square&label=Stars)](https://github.com/LL-cmyk-so/dsh-balance-widget)
@@ -15,7 +15,7 @@ A balance & cost widget for the [DeepSeek Harness](https://github.com/deepseek-a
 
 | Sidebar card | Five-tier cost popover |
 | --- | --- |
-| ![Sidebar card](docs/screenshot-corner.png) | ![Cost popover](docs/screenshot-popover.png) |
+| ![Sidebar card](https://raw.githubusercontent.com/LL-cmyk-so/dsh-balance-widget/main/docs/screenshot-corner.png) | ![Cost popover](https://raw.githubusercontent.com/LL-cmyk-so/dsh-balance-widget/main/docs/screenshot-popover.png) |
 
 ## How it differs from similar plugins
 
@@ -153,6 +153,12 @@ Built-in DeepSeek official peak/off-peak pricing (CNY per 1M tokens), effective
 
 The official page currently lists only `deepseek-flash` and `deepseek-v4-pro`; older names (`deepseek-v4-flash`, `deepseek-v4-flash-vision-exp`, `deepseek-chat`) still work and are billed at the Flash rate. The plugin re-parses the page at startup and every 12h, and falls back to the table above only when parsing fails. Costs are **estimates**; the provider's bill is authoritative.
 
+### Search calls (estimated)
+
+Every **query** of a `web_search` call is a separate auxiliary model call (`@deepseek-ai/dsh-web-search-deepseek`, `deepseek-v4-flash` by default, up to `maxUses` per request). The session log records only the pre-dispatch `web/deepseek-search-llm-request` event — **no usage field** — so the real token counts exist in no local file.
+
+The plugin therefore counts requests × a calibrated constant: ~6k cache-miss input + ~2k output tokens per search, i.e. **¥0.014** off-peak and **¥0.028** at peak (calibrated 2026-09-22 against the balance delta: 14 searches measured **¥0.0133 each**). Searches are attributed to the session, workspace and day they belong to, but each amount is an estimate (±30% order).
+
 ## Security & permission boundaries
 
 This section is for the DSH Store / plugin audit: dependencies, runtime permissions, external services, and failure bounds.
@@ -183,6 +189,15 @@ This section is for the DSH Store / plugin audit: dependencies, runtime permissi
 
 ## Changelog
 
+### v0.5.5 — README assets now render on the npm package page
+- 🐛 **Fixed**: the screenshots and the language switch used repository-relative paths (`docs/screenshot-corner.png`, `README.en.md`). The npm package page renders the README body only and does not resolve in-repo paths, so both screenshots and the language link were broken on npm. They are now absolute URLs: screenshots via `raw.githubusercontent.com`, the language switch via a GitHub blob link
+- 📦 **Scope**: documentation only; no code change
+
+### v0.5.4 — search calls are now counted (previously dropped entirely)
+- 🐛 **Fixed**: the auxiliary model calls behind `web_search` contributed nothing to cost. DSH writes only a pre-dispatch `web/deepseek-search-llm-request` event per search (no usage), so any log-derived pricing undercounts systematically — measured 2026-09-22: all 1073 searches of the day were missing. Searches are now priced as requests × a calibrated constant and attributed to their session / workspace / day and turn
+- 📏 **Calibration**: ~6k cache-miss input + ~2k output tokens per search (¥0.014 off-peak, ¥0.028 at peak). Measured 2026-09-22 from the balance delta: 14 searches in one window, balance delta ¥0.28, minus ¥0.094 of log-derivable conversation cost → **¥0.0133 per search**
+- ⚠️ **Scope**: the search portion is an estimate (±30% order); conversation text is still priced exactly from the logs
+
 ### v0.5.3 — weekends no longer mispriced as peak
 - 🐛 **Fixed**: the peak/off-peak check looked only at the hour and ignored the weekday, so weekends were priced as peak (2×) during 09:00–12:00 and 14:00–18:00, up to doubling "today's cost". The official rule is **Mon–Fri** 09:00–12:00 and 14:00–18:00 (everything else, weekends included, is off-peak); Saturday and Sunday are now excluded first, using the Beijing-time weekday
 - 📄 **Docs**: the pricing section and the peak/off-peak tooltips now state the Mon–Fri restriction

package/README.md

@@ -1,6 +1,6 @@
 # dsh-balance-widget
 
-**中文** | [English](README.en.md)
+**中文** | [English](https://github.com/LL-cmyk-so/dsh-balance-widget/blob/main/README.en.md)
 
 [![npm](https://img.shields.io/npm/v/dsh-balance-widget?style=flat-square&label=npm)](https://www.npmjs.com/package/dsh-balance-widget)
 [![Stars](https://img.shields.io/github/stars/LL-cmyk-so/dsh-balance-widget?style=flat-square&label=Stars)](https://github.com/LL-cmyk-so/dsh-balance-widget)
@@ -15,7 +15,7 @@ DeepSeek Harness (DSH) Web GUI 的余额与成本小部件：侧边栏底部常
 
 | 侧边栏卡片（左下角常驻） | 点击弹出五层级成本 |
 | --- | --- |
-| ![侧边栏卡片](docs/screenshot-corner.png) | ![成本明细弹框](docs/screenshot-popover.png) |
+| ![侧边栏卡片](https://raw.githubusercontent.com/LL-cmyk-so/dsh-balance-widget/main/docs/screenshot-corner.png) | ![成本明细弹框](https://raw.githubusercontent.com/LL-cmyk-so/dsh-balance-widget/main/docs/screenshot-popover.png) |
 
 ## 与同类插件的区别
 
@@ -150,6 +150,12 @@ DSH 的插件配置统一放在这个文件里：
 
 官方页当前只列 `deepseek-flash` 与 `deepseek-v4-pro` 两列；`deepseek-v4-flash`、`deepseek-v4-flash-vision-exp`、`deepseek-chat` 等旧名仍可调用，按 Flash 价计费。插件在启动时与每 12h 从官方页重新解析，只有解析失败才回退上表。成本为**估算值**，实际以官方账单为准。
 
+### 搜索调用（估算）
+
+每次 `web_search` 的**每个查询**都会被 DSH 当作一次独立的辅助模型调用（`@deepseek-ai/dsh-web-search-deepseek`，默认 `deepseek-v4-flash`，每个请求最多 `maxUses` 次）。而会话日志只记录派发前的 `web/deepseek-search-llm-request` 事件——**不含 usage 字段**，本地任何文件都查不到这些调用的真实 token 数。
+
+插件因此按「请求次数 × 标定常数」计入：每次搜索 ≈ 6k 缓存未命中输入 + 2k 输出 token，即谷时 **¥0.014**、峰时 **¥0.028**（2026-09-22 用余额差标定：14 次搜索实测 **¥0.0133/次**）。搜索会归到它所属的会话、工作区与「今日·全部」，但单次金额是估算值（±30% 量级）。
+
 ## 安全与权限边界
 
 本节面向 DSH Store / 插件审计，列出依赖、运行时权限、外部服务与失败边界。
@@ -180,6 +186,15 @@ DSH 的插件配置统一放在这个文件里：
 
 ## 版本历史
 
+### v0.5.5 — 修复 README 在 npm 包页面上的显示
+- 🐛 **修复**：README 的截图与语言切换此前用相对路径（`docs/screenshot-corner.png`、`README.en.md`）。npm 包页面只渲染 README 正文、不解析仓库内的相对路径，所以在 npm 上两张截图和语言链接都是坏的。现改为绝对 URL：截图走 `raw.githubusercontent.com`，语言切换走 GitHub blob 链接
+- 📦 **范围**：仅文档，代码无变化
+
+### v0.5.4 — 计入搜索调用（此前全部漏算）
+- 🐛 **修复**：`web_search` 的辅助模型调用完全不计入成本。DSH 对每次搜索只写一个派发前的 `web/deepseek-search-llm-request` 事件（无 usage），所以按会话日志计价的实现系统性漏算——实测 2026-09-22 一天 1073 次搜索全部没进账。现按「请求次数 × 标定常数」计价，并归入该搜索所属的会话 / 工作区 / 当日及当轮
+- 📏 **标定**：单次搜索 ≈ 6k 缓存未命中输入 + 2k 输出 token（谷时 ¥0.014、峰时 ¥0.028）。2026-09-22 用余额差实测：同一窗口 14 次搜索、余额差 ¥0.28、扣掉日志可算的对话成本 ¥0.094，得 **¥0.0133/次**
+- ⚠️ **口径**：搜索部分是估算值（±30% 量级），会话正文部分仍是按日志精算
+
 ### v0.5.3 — 修复周末被误判为峰时
 - 🐛 **修复**：峰/谷判断只看小时、不看星期，导致周末 09:00–12:00、14:00–18:00 被误判为峰时并按 2× 计价，"今日花费"最多翻倍。官方规则为**周一至周五** 09:00–12:00、14:00–18:00（其余含周末全天为空闲时段），现按北京时间的星期先行排除周六/周日
 - 📄 **文档**：定价说明与峰谷 tooltip 补上"周一至周五"限定

package/lib/index.js

@@ -298,6 +298,40 @@ function priceUsage(usage, modelId, timeMs) {
 	return (input * table.inputMiss + hit * table.inputHit + output * table.output) / 1e6;
 }
 
+/**
+ * Estimated token footprint of one auxiliary web-search turn.
+ *
+ * DeepSeek runs every `web_search` query as its own Messages call (see
+ * @deepseek-ai/dsh-web-search-deepseek) and DSH records only the
+ * pre-dispatch `web/deepseek-search-llm-request` event — never the response
+ * usage — so the real token counts are not recoverable from any local file.
+ * These constants were calibrated on 2026-09-22 against the account balance
+ * delta (14 searches over one window: ~¥0.0133 per search at off-peak Flash
+ * rates, i.e. ~6k cache-miss input + ~2k output per search).
+ */
+const SEARCH_TURN_INPUT_TOKENS = 6000;
+const SEARCH_TURN_OUTPUT_TOKENS = 2000;
+
+/** Price one auxiliary web-search turn (estimated; see constants above). */
+function priceSearchTurn(modelId, timeMs) {
+	const table = isPeak(new Date(timeMs ?? Date.now())) ? pricingTable[pricingKey(modelId)].peak : pricingTable[pricingKey(modelId)].offPeak;
+	return (SEARCH_TURN_INPUT_TOKENS * table.inputMiss + SEARCH_TURN_OUTPUT_TOKENS * table.output) / 1e6;
+}
+
+/** Cost of one parsed sample — a real usage sample, or an estimated search turn. */
+function sampleCost(sample) {
+	return sample.search === true ? priceSearchTurn(sample.model, sample.time) : priceUsage(sample.usage, sample.model, sample.time);
+}
+
+/** Token totals of one parsed sample (a search turn contributes its estimate). */
+function sampleTokens(sample) {
+	if (sample.search === true) return { input: SEARCH_TURN_INPUT_TOKENS, output: SEARCH_TURN_OUTPUT_TOKENS };
+	return {
+		input: (sample.usage.inputTokens ?? sample.usage.uncachedInputTokens ?? 0) + (sample.usage.cacheReadTokens ?? 0),
+		output: sample.usage.outputTokens ?? 0
+	};
+}
+
 /**
  * Parse the official pricing page into our pricingTable shape.
  * The page is HTML; we look for per-model peak/off-peak "per 1M tokens" rates.
@@ -543,6 +577,7 @@ async function decompressSession(path) {
 function parseSessionUsages(text) {
 	const samples = [];
 	let currentModel = void 0;
+	let currentTurn = 0;
 	let cwd = void 0;
 	let title = void 0;
 	for (const line of text.split("\n")) {
@@ -558,6 +593,8 @@ function parseSessionUsages(text) {
 			cwd = event.cwd;
 		} else if (type === "session/title") {
 			title = event.data?.title ?? title;
+		} else if (type === "turn/start") {
+			currentTurn = event.data?.turn ?? currentTurn;
 		} else if (type === "request/header") {
 			currentModel = event.data?.header?.config?.model ?? currentModel;
 		} else if (type === "assistant/message") {
@@ -570,6 +607,15 @@ function parseSessionUsages(text) {
 					usage
 				});
 			}
+		} else if (type === "web/deepseek-search-llm-request") {
+			// One auxiliary search turn: no usage is recorded anywhere, so it is
+			// priced from the calibrated estimate below.
+			samples.push({
+				turn: currentTurn,
+				time: event.time ?? Date.now(),
+				model: event.data?.body?.model ?? currentModel,
+				search: true
+			});
 		}
 	}
 	return { samples, cwd, title };
@@ -585,9 +631,10 @@ function lastTurnCost(samples) {
 	let output = 0;
 	for (const s of samples) {
 		if (s.turn !== lastTurn) continue;
-		cost += priceUsage(s.usage, s.model, s.time);
-		input += (s.usage.inputTokens ?? s.usage.uncachedInputTokens ?? 0) + (s.usage.cacheReadTokens ?? 0);
-		output += s.usage.outputTokens ?? 0;
+		cost += sampleCost(s);
+		const t = sampleTokens(s);
+		input += t.input;
+		output += t.output;
 	}
 	return { cost, inputTokens: input, outputTokens: output };
 }
@@ -602,9 +649,10 @@ function todaySessionCost(samples) {
 	let output = 0;
 	for (const s of samples) {
 		if (s.time < dayStart || s.time >= dayEnd) continue;
-		cost += priceUsage(s.usage, s.model, s.time);
-		input += (s.usage.inputTokens ?? s.usage.uncachedInputTokens ?? 0) + (s.usage.cacheReadTokens ?? 0);
-		output += s.usage.outputTokens ?? 0;
+		cost += sampleCost(s);
+		const t = sampleTokens(s);
+		input += t.input;
+		output += t.output;
 	}
 	return { cost, inputTokens: input, outputTokens: output };
 }
@@ -653,9 +701,10 @@ function todayCost(sessionList, cwdFilter) {
 		if (cwdFilter !== void 0 && session.cwd !== cwdFilter) continue;
 		for (const s of session.samples) {
 			if (s.time < dayStart || s.time >= dayEnd) continue;
-			cost += priceUsage(s.usage, s.model, s.time);
-			input += (s.usage.inputTokens ?? s.usage.uncachedInputTokens ?? 0) + (s.usage.cacheReadTokens ?? 0);
-			output += s.usage.outputTokens ?? 0;
+			cost += sampleCost(s);
+			const t = sampleTokens(s);
+			input += t.input;
+			output += t.output;
 		}
 	}
 	return { cost, inputTokens: input, outputTokens: output };

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "dsh-balance-widget",
   "description": "Balance & cost widget for the dsh web GUI: a sidebar footer card shows the DeepSeek account balance and today's costs; clicking opens a popover with a five-tier cost breakdown (last prompt with session name / today-this-session / today-this-workspace / today-all-workspaces), peak/off-peak status tags, term explanations, and a one-click top-up link. Zero external dependencies — works on Node 24.",
-  "version": "0.5.3",
+  "version": "0.5.5",
   "type": "module",
   "main": "lib/index.js",
   "files": [