@rayadesu/dsh-billing 0.3.9 → 0.3.10

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (5) hide show
  1. package/AGENTS.md +1 -1
  2. package/README.i18n.yaml +2 -2
  3. package/README.md +4 -4
  4. package/README.zh.md +4 -4
  5. package/package.json +3 -3
package/AGENTS.md CHANGED
@@ -47,7 +47,7 @@ cordis.patch.yml DSH profile bundle 补丁层：挂载 llm-billing + ui-
47
47
  - **密钥不进仓库**：`DEEPSEEK_API_KEY` 等一律由用户环境或凭据 seam 提供，仓库不含真实值。
48
48
  - **README 双语**：每个 README 遵循 DSH 结构 `README.md`(EN) + `README.zh.md`(ZH) +
49
49
  `README.i18n.yaml`（记录两文件 git blob hash，改动后需更新）。
50
- - **版本对齐**：根 bundle 与两个包统一版本号（当前 0.3.9），`pnpm-lock.yaml` 随依赖变更更新。
50
+ - **版本对齐**：根 bundle 与两个包统一版本号（当前 0.3.10），`pnpm-lock.yaml` 随依赖变更更新。
51
51
  - **文本规范**：LF 换行、文件末尾一个换行（`.editorconfig`/`.gitattributes` 已声明）。
52
52
 
53
53
  ## 常用命令
package/README.i18n.yaml CHANGED
@@ -2,5 +2,5 @@
2
2
  # last confirmed-consistent state. Both languages carry equal authority; after
3
3
  # editing either side, bring the other along and re-record both hashes with:
4
4
  # git hash-object README.md README.zh.md
5
- README.md: 2ad92f8dc8d2cac65fd6260eb5d5966e8edcba77
6
- README.zh.md: 0686afd8b6141bb1df88215584487fa437c715c1
5
+ README.md: c83e7559af62aba5c8ceb4dfffc18de50138f333
6
+ README.zh.md: 01127599e394e374adcb77a4109ad4b70c123801
package/README.md CHANGED
@@ -236,18 +236,18 @@ Both packages ship sane defaults; everything below is optional.
236
236
  | --- | --- | --- |
237
237
  | `apiKeyEnv` | `DEEPSEEK_API_KEY` | Credential-reference (environment-variable) name resolved per call. |
238
238
  | `baseURL` | `$DEEPSEEK_BASE_URL` then `https://api.deepseek.com` | Endpoint base; `/user/balance` is appended. |
239
- | `models` | V4 Flash + V4.1 Flash + V4 Pro + V4 Flash Vision Exp + MiMo-V2.5 series | Advisory display rows, in presentation order. |
239
+ | `models` | V4.1 Flash (`deepseek-flash`) + V4 Flash + V4 Pro + V4 Flash Vision Exp + MiMo-V2.5 series | Advisory display rows, in presentation order; they mirror DSH's `llm-deepseek` catalog. |
240
240
  | `billing.peakHours` | 09:00–12:00, 14:00–18:00 (Beijing, weekdays) | Peak-hour windows, applied weekdays (Mon–Fri) only; weekends and all other hours are off-peak. |
241
- | `billing.models` | Published V4 + MiMo rates | Per-model peak/off-peak price rows (`cacheHitInput`, `cacheMissInput`, `output`, in CNY per 1M tokens). |
241
+ | `billing.models` | Published V4 + MiMo rates | Per-model price rows (`cacheHitInput`, `cacheMissInput`, `output`, in CNY per 1M tokens) with an optional inclusive `effectiveFrom`; several rows sharing a model are its rate revisions. |
242
242
 
243
243
  ## How session spend is computed
244
244
 
245
245
  - Each `assistant/message` event reports three billed token buckets: **cache-hit input**, **cache-miss input** (uncached input + cache writes), and **output** (including reasoning). A failed or retried `assistant/attempt` reports its usage only in its embedded stream; that sample is priced too (with the model of the latest `request/header`), a later sample for the same `(turn, step)` **replaces** the earlier one, and `llm/retry-started` makes the retried attempt **add** — the same accounting DSH's own turn-usage disclosure uses.
246
- - Each sample is priced at the peak/off-peak rate of its own **Beijing-time** hour, the three buckets are billed separately (`缓存命中 ¥X · 未命中输入 ¥Y · 输出 ¥Z`), then summed per model. Peak windows apply weekdays (Monday–Friday) only; weekends are always off-peak.
246
+ - Each sample is priced at the peak/off-peak rate of its own **Beijing-time** hour — and of the rate revision in effect at its own timestamp — the three buckets are billed separately (`缓存命中 ¥X · 未命中输入 ¥Y · 输出 ¥Z`), then summed per model. Peak windows apply weekdays (Monday–Friday) only; weekends are always off-peak.
247
247
  - **Today's spend** aggregates every session's events on the current Beijing-time calendar day with the same pricing rules; event dates are also assigned in Beijing time.
248
248
  - **Turn cost** prices the events inside the turn's `turn/start`..`turn/end` range with the same rules (located by the closing message's session id + message id), folded in one pass for the whole session and served as a `messageId → cost` map.
249
249
  - **Today session ranking** aggregates today's spend per session with the same rules (a cross-day session counts only today's part), sorted descending; names come from the log's latest `session/title` event (the auto-generated Chinese title or a user rename).
250
- - Models without a rate row are not priced (the built-in catalog currently has the four V4 rows: V4 Flash, V4.1 Flash, V4 Pro, and V4 Flash Vision Exp; V4.1 Flash bills at the V4 Flash rates). Rates follow the DeepSeek pricing effective **August 17**; the weekend-off-peak rule (weekends billed at off-peak prices all day) follows the adjustment effective **August 23**.
250
+ - Models without a rate row are not priced (the built-in table covers the DSH `llm-deepseek` catalog — V4.1 Flash `deepseek-flash`, V4 Flash, V4 Pro, V4 Flash Vision Exp — plus the retired `deepseek-v4.1-flash-expires-on-0910` preview id and the MiMo-V2.5 series; every flash-series route shares the same pair). Each sample takes the rate revision in effect at its own timestamp: the base schedule is the DeepSeek pricing effective **August 17**; the **flash series** (V4.1 Flash, V4 Flash, V4 Flash Vision Exp, and the retired id) was re-priced effective **September 10, 12:00 Beijing time** to off-peak 0.02 / 1.0 / 4.0 CNY per 1M tokens with peak at twice those prices — samples from before that instant, the V4.1 Flash route's own earlier usage included, keep the superseded rates; the **V4 Pro** route is announced to switch to V4.1 Flash and its rates on **September 14, 12:00 Beijing time**; the MiMo-V2.5 series is untouched. The weekend-off-peak rule (weekends billed at off-peak prices all day) follows the adjustment effective **August 23**.
251
251
 
252
252
  ## Known limitations
253
253
 
package/README.zh.md CHANGED
@@ -212,18 +212,18 @@ npm publish # @rayadesu/dsh-billing bundle（仓库根）
212
212
  | --- | --- | --- |
213
213
  | `apiKeyEnv` | `DEEPSEEK_API_KEY` | 每次调用时解析的凭据引用（环境变量）名。 |
214
214
  | `baseURL` | `$DEEPSEEK_BASE_URL`，其次 `https://api.deepseek.com` | 端点基础地址；会追加 `/user/balance`。 |
215
- | `models` | V4 Flash + V4.1 Flash + V4 Pro + V4 Flash Vision Exp + MiMo-V2.5 系列 | 展示用的模型行，按展示顺序。 |
215
+ | `models` | V4.1 Flash（`deepseek-flash`）+ V4 Flash + V4 Pro + V4 Flash Vision Exp + MiMo-V2.5 系列 | 展示用的模型行，按展示顺序；与 DSH `llm-deepseek` 目录对齐。 |
216
216
  | `billing.peakHours` | 09:00–12:00、14:00–18:00（北京，仅工作日） | 高峰时段窗口，仅周一至周五适用；周末与其余时段均为低谷。 |
217
- | `billing.models` | 官方 V4 + MiMo 费率 | 每个模型的峰/谷单价行（`cacheHitInput`、`cacheMissInput`、`output`，单位：元/百万 token）。 |
217
+ | `billing.models` | 官方 V4 + MiMo 费率 | 每个模型的单价行（`cacheHitInput`、`cacheMissInput`、`output`，单位：元/百万 token），可带生效时刻 `effectiveFrom`（含该时刻）；同一模型的多行即其费率版本。 |
218
218
 
219
219
  ## 会话花费是怎么算的
220
220
 
221
221
  - 每条 `assistant/message` 事件报告三个计费 token 桶：**缓存命中输入**、**未命中输入**（未缓存输入 + 缓存写入）、**输出**（含推理）。失败或重试的 `assistant/attempt` 只在自身内嵌 stream 里报告用量，这份样本同样计价（模型取最近一条 `request/header`）；同一 `(turn, step)` 的后一份样本**替换**前一份，`llm/retry-started` 之后重试的那次**累加** —— 与 DSH 自己的回合用量口径一致。
222
- - 每份样本按其**发生时刻**（北京时间）所在的峰/谷时段单价计价，三个桶分别计费（`缓存命中 ¥X · 未命中输入 ¥Y · 输出 ¥Z`），再按模型汇总。高峰窗口仅周一至周五适用；周末全天按低谷价计费。
222
+ - 每份样本按其**发生时刻**（北京时间）所在的峰/谷时段单价——以及该时刻生效的费率版本——计价，三个桶分别计费（`缓存命中 ¥X · 未命中输入 ¥Y · 输出 ¥Z`），再按模型汇总。高峰窗口仅周一至周五适用；周末全天按低谷价计费。
223
223
  - **今日共花费**按同一个计价规则汇总当天（北京时间自然日）所有会话的事件；事件归属的日期同样按北京时间计算。
224
224
  - **本轮花费**按同一规则计价该回合 `turn/start`..`turn/end` 区间内的事件（定位到收尾消息的会话 id + 消息 id），整会话一趟折出 `messageId → 金额` 映射后下发。
225
225
  - **今日会话花费排行**按同一规则按会话汇总今日花费（跨天会话只统计今天的部分），从高到低排序；会话名取日志中最后一条 `session/title` 事件（自动生成的中文标题或用户重命名的新标题）。
226
- - 没有费率行的模型不计入（内置价目表目前含四个 V4 行：V4 Flash、V4.1 Flash、V4 Pro、V4 Flash Vision Exp；V4.1 Flash 按 V4 Flash 的费率计费）。计费按 DeepSeek **8 月 17 日实行**的费率；**周末按低谷价计费**的规则按 **8 月 23 日**生效的调整执行。
226
+ - 没有费率行的模型不计入（内置价目表覆盖 DSH `llm-deepseek` 目录——V4.1 Flash `deepseek-flash`、V4 Flash、V4 Pro、V4 Flash Vision Exp——外加已退役的 `deepseek-v4.1-flash-expires-on-0910` 预览 id 与 MiMo-V2.5 系列；flash 系列各路由同价）。每份样本取**自身时刻生效的费率版本**：基础价目为 DeepSeek **8 月 17 日实行**的费率；**flash 系列**（V4.1 Flash、V4 Flash、V4 Flash Vision Exp 及退役 id）自 **9 月 10 日 12:00（北京时间）** 起降为谷时 0.02 / 1.0 / 4.0 元每百万 token、峰时为其两倍——该时刻之前的样本（含 V4.1 Flash 路由自身的早先用量的）沿用被取代的旧价；**V4 Pro** 路由公告于 **9 月 14 日 12:00（北京时间）** 改由 V4.1 Flash 服务并按其实施费率计费；MiMo-V2.5 系列不受影响。**周末按低谷价计费**的规则按 **8 月 23 日**生效的调整执行。
227
227
 
228
228
  ## 已知限制
229
229
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@rayadesu/dsh-billing",
3
- "version": "0.3.9",
3
+ "version": "0.3.10",
4
4
  "description": "DeepSeek Harness billing plugin: account balance and this session's billed spend with a session-header badge.",
5
5
  "license": "MIT",
6
6
  "repository": {
@@ -40,8 +40,8 @@
40
40
  "access": "public"
41
41
  },
42
42
  "peerDependencies": {
43
- "@rayadesu/dsh-client-ui-billing": "^0.3.9",
44
- "@rayadesu/dsh-llm-billing": "^0.3.9"
43
+ "@rayadesu/dsh-client-ui-billing": "^0.3.10",
44
+ "@rayadesu/dsh-llm-billing": "^0.3.10"
45
45
  },
46
46
  "devDependencies": {
47
47
  "@deepseek-ai/cordis": "^4.0.1",