@kenz1117/dsh-ui-usage-billing 1.7.0 → 1.7.2

package/README.en.md

@@ -40,7 +40,7 @@ Most billing plugins stop at "token count × unit price". dsh-ui-usage-billing t
 Usage is aggregated live from persisted session logs — never fabricated (an empty snapshot shows until real data arrives); daily official-balance deltas are cross-checked against the local ledger, and deviations beyond the threshold prompt a review — a bill that survives scrutiny.
 
 ### Live prices, history never rewritten
-A live models.dev catalog + a built-in catalog of 110 models across 25 vendors + user-defined prices in the settings panel (bindable per relay origin) mean new models never wait for a release; DeepSeek time-of-day prices are **segmented by official change boundaries** (base price before 08-17, weekend peak hours 08-17~08-23, weekend all-day off-peak from 08-23) and later price changes never rewrite old bills.
+A live models.dev catalog + a built-in catalog of 241 models across 25 vendors + user-defined prices in the settings panel (bindable per relay origin) mean new models never wait for a release; DeepSeek time-of-day prices are **segmented by official change boundaries** (base price before 08-17, weekend peak hours 08-17~08-23, weekend all-day off-peak from 08-23) and later price changes never rewrite old bills.
 
 ### Peak/off-peak aware, alerts follow the model
 The billing channel is detected from the current session's model: DeepSeek metered uses time-of-day prices (weekday 9-12 / 14-18 peak ×2, weekend all-day off-peak), Zhipu Coding Plan uses credit windows (weekday 14-18 peak at full rate, off-peak at **50% of base credits**) — the channel layer is extensible for more providers; a popover / system notification fires automatically before each switch, and only sessions whose current model actually involves peak/off-peak get alerted or show the tier section — no watching the clock.
@@ -184,34 +184,36 @@ cost (CNY) = (missInput × p_input + cacheHit × p_cacheHit + output × p_output
 
 `input` in the stats is total input (cacheHit + cacheMiss); estimation splits it into hit / miss to avoid double counting. Models with two-band billing are mixed by `DEFAULT_PEAK_SHARE` (default 0.5); weekends (Beijing Sat/Sun) are charged at the off-peak rate all day.
 
-### Supported models (2026-10 lineup, OpenAI-compatible series, 110 models)
+**Month-to-date forecast**: month-to-date spend + last-7-calendar-day pace × the days still left in the month. Only the days that have not happened yet are extrapolated, so a quiet recent week never inflates the number — earlier versions averaged over the month's *recorded* days and multiplied by the whole month length, which inflated sparsely used months several times over.
 
-The full catalog lives in the Rates tab and in `BUILTIN_MODEL_CATALOG` of `src/builtin-catalog.ts` (109 active + 1 retired model kept for historical repricing); representative models per vendor below.
+### Supported models (2026-10 lineup, OpenAI-compatible series, 241 models)
+
+The full catalog lives in the Rates tab and in `BUILTIN_MODEL_CATALOG` of `src/builtin-catalog.ts` (240 active + 1 retired model kept for historical repricing); representative models per vendor below.
 
 | Provider  | Representatives                                        |
 | -------- | -------------------------------------------- |
 | DeepSeek | V4.1 Flash, V4 Pro (3 models; priced per official change boundary: base tier → peak/off-peak v1 → weekend off-peak) |
-| Zhipu AI  | GLM-5.3, GLM-5.2 (13 models)                     |
-| Aliyun    | Qwen3.8 Max, Qwen3-Coder 480B (11 models)        |
-| Doubao    | Doubao Seed-2.1 Pro, Doubao Seed-2.0 Pro (9 models) |
-| Moonshot  | Kimi K3, Kimi K2.7 Code (10 models)              |
-| Xiaomi    | MiMo V2.6 Pro (5 models)                         |
-| MiniMax   | MiniMax-M3, MiniMax-M2.7 (4 models)              |
+| Zhipu AI  | GLM-5.3, GLM-5.2 (17 models)                     |
+| Aliyun    | Qwen3.8 Max, Qwen3-Coder 480B (27 models)        |
+| Doubao    | Doubao Seed-2.1 Pro, Doubao Seed-2.0 Pro (13 models) |
+| Moonshot  | Kimi K3.1 Pro, Kimi K3.1 Pro Highspeed, Kimi K3, Kimi K2.7 Code (18 models) |
+| Xiaomi    | MiMo V2.6 Pro (6 models)                         |
+| MiniMax   | MiniMax-M3, MiniMax-M2.7 (8 models)              |
 | Unisound  | U2 Flash, Unisound U2 (3 models)                 |
 | Baidu     | ERNIE-5.1, ERNIE-4.5 300B (2 models)             |
 | Tencent   | Hunyuan Hy3, Hunyuan T1 (3 models)                       |
-| Anthropic | Claude Opus 4.6, Claude Sonnet 4.6 (12 models)    |
-| Mistral AI | Mistral Large 3, Mistral Small 4 (3 models)     |
-| Cohere    | Command A, Command R (2 models)                 |
-| OpenAI    | GPT-6 Astra, GPT-5.6 Sol / Terra / Luna (10 models) |
-| Google    | Gemini 3.1 Pro, Gemini 3.6 Flash (4 models)      |
-| xAI       | Grok 4.7, Grok 4.6 (5 models)                     |
-| Meta      | Llama 4 Maverick (2 models)                     |
+| Anthropic | Claude Opus 5, Claude Sonnet 5 (14 models)    |
+| Mistral AI | Mistral Large 3, Mistral Small 4 (30 models)     |
+| Cohere    | Command A, Command R (7 models)                 |
+| OpenAI    | GPT-6 Astra, GPT-5.6 Sol / Terra / Luna (38 models) |
+| Google    | Gemini 3.1 Pro, Gemini 3.6 Flash (25 models)      |
+| xAI       | Grok 4.7, Grok 4.20 (8 models)                     |
+| Meta      | Llama 4 Maverick, Muse Spark 1.3 (8 models)                     |
 | Meituan   | LongCat 2.0 (estimated)                             |
 | ModelBest | MiniCPM-V 4.5 (estimated)                           |
 | Xiaohongshu | Dots3-Note Preview (estimated)                      |
 | 01.AI     | Yi-Lightning                                  |
-| StepFun   | Step 3.7 Flash                                |
+| StepFun   | Step 3.7 Flash, Step 5 Preview (3 models)                                |
 | iFlytek   | Spark 4.0 Ultra (plan-based)¹                       |
 | SenseTime | SenseNova 6.5 (beta)¹                         |
 | Baichuan  | Baichuan M3-Plus                              |
@@ -232,7 +234,7 @@ The public HTTP endpoints and field definitions are documented in source: `GET /
 | `statsPath`             | unset                                   | Absolute path to a fallback `.dsh-usage-stats.json` (used when `sessionPersistence` is unavailable)                    |
 | `ledgerPath`            | `<harness home>/.dsh-usage-ledger.json` | Independent durable ledger path; stores folded metrics only (no message bodies or session titles), so deletion does not erase recorded usage. The default root follows the host harness home (`DSH_HOME` env first, falling back to `~/.dsh`), so isolated environments never share ledger data (issue #52) |
 | `balanceApiKeyEnv`      | `DEEPSEEK_API_KEY`                      | Credential ref for the DeepSeek balance query; only used as a fallback when llm-pi-ai has no `apiKeyEnv` for deepseek |
-| `subscriptionProviders` | built-in channel list (incl. `tencent-token-plan`) | Subscription (coding / token plan) provider id list — tokens counted, cost 0; aligned with the subscription-card recognition      |
+| `subscriptionProviders` | built-in channel list (incl. `tencent-token-plan`) | Subscription (coding / token plan) provider id list — tokens counted, cost 0; aligned with the subscription-card recognition. Note it **replaces** the built-in list rather than appending to it — when customizing, list the built-in entries too, otherwise removed subscription channels fall back to pay-as-you-go |
 | `routeAliases`          | not set                                | Historical route aliases (old provider route name -> current route): renamed/deleted routes relocate into their channel instead of the "unknown" bucket. Example: `{ "deepseek-official": "tencent" }` |
 | `modelKeyAliases`       | not set                                | User model aliases (log model id -> billing catalog key, value must be an existing `MODEL_CATALOG` key): bind uncatalogued ids without waiting for a release. Example: `{ "hy4-preview": "hunyuan" }` |
 | `monthlyBudget`         | unset                                   | Default monthly budget (CNY); sent with usage-stats as the budget bar's initial amount (user UI settings take precedence and persist locally) |

package/README.md

@@ -40,7 +40,7 @@
 用量从持久化会话日志实时聚合，绝不伪造样本（数据到达前显示空快照）；官方余额当日变动与本地账本交叉对账，偏差超阈值主动提示核对——账单经得起质疑。
 
 ### 价格是活的，历史不重算
-models.dev 实时目录 + 内置 25 厂商 110 款模型 + 设置面板自定义单价（可按中转站绑定同模型不同价），新模型无需等发版；DeepSeek 分时价按官方变更节点**分段计价**（8-17 前基础价、8-17~8-23 周末计峰、8-23 起周末全谷），价格调整永不回写旧账。
+models.dev 实时目录 + 内置 25 厂商 241 款模型 + 设置面板自定义单价（可按中转站绑定同模型不同价），新模型无需等发版；DeepSeek 分时价按官方变更节点**分段计价**（8-17 前基础价、8-17~8-23 周末计峰、8-23 起周末全谷），价格调整永不回写旧账。
 
 ### 峰谷全感知，提醒跟着模型走
 计费通道按当前会话使用的模型自动识别：DeepSeek 按量走分时价（工作日 9-12 / 14-18 高峰 ×2、周末全天低谷），智谱 Coding Plan 走积分峰谷（工作日 14-18 高峰全额、非高峰**积分 5 折**），通道层可扩展、更多厂商逐步接入；切档前弹窗 / 系统通知自动提醒，且只有当前模型真正涉及峰谷才会提醒、费用条才显示档位——不用你盯时间表。
@@ -191,36 +191,38 @@ cost（CNY）= (missInput × p_input + cacheHit × p_cacheHit + output × p_outp
 
 **联网搜索请求按次估算**（issue #15）：DSH 的联网搜索绕过对话通道直连官方 `api.deepseek.com`，会话日志只记请求、无用量事件，而开放平台照常计费。插件对这类 `web/deepseek-search-llm-request` 事件按次估值计入费用（默认 0.02 元/次，配置 `searchCallEstimateCny` 可调整；设 0 关闭），并单独累计 `searchCalls` 供面板提示估算口径。
 
+**「本月预计」的口径**：本月已发生 + 近 7 个自然日节奏 × 本月剩余天数。只外推还没发生的天数，近期没花钱就不虚增——早期版本拿「本月有记录的天数」当分母求日均再乘整月天数，稀疏使用的月份会被放大数倍（实测 4 天记录、其余 19 天没用的月份被外推成实际值的 4 倍）。
+
 **自定义单价（设置 Tab，issue #16）**：结构化条目表（模型 + 可选来源 + 输入/缓存命中/输出 + 币种），不再手编 JSON。来源（中转站域名）留空 = 该模型默认价；填入中转站域名（如 `https://api.my-relay.com`）= 仅该来源的同名模型用此价（同名模型可同时存在默认价与多个来源价，互不覆盖）。显示层按「模型 × 来源」精确匹配重算，命中不到来源时回落该模型默认价，再无则用内置目录价。
 
-### 支持模型（2026-10 主流阵容，OpenAI 兼容系列，共 110 款）
+### 支持模型（2026-10 主流阵容，OpenAI 兼容系列，共 241 款）
 
-完整目录见费率 Tab 及源码 `src/builtin-catalog.ts` 的 `BUILTIN_MODEL_CATALOG`（109 款在售 + 1 款退役型号保留历史回算），此处每厂商仅列代表型号。
+完整目录见费率 Tab 及源码 `src/builtin-catalog.ts` 的 `BUILTIN_MODEL_CATALOG`（240 款在售 + 1 款退役型号保留历史回算），此处每厂商仅列代表型号。
 
 | 厂商       | 代表模型                                        |
 | -------- | -------------------------------------------- |
 | DeepSeek | V4.1 Flash、V4 Pro（等 3 款；按官方变更节点分段计价：基础价 → 峰谷 v1 → 周末全谷） |
-| 智谱 AI    | GLM-5.3、GLM-5.2（等 13 款）                     |
-| 阿里通义     | Qwen3.8 Max、Qwen3-Coder 480B（等 11 款）        |
-| 字节豆包     | Doubao Seed-2.1 Pro、Doubao Seed-2.0 Pro（等 9 款） |
-| 月之暗面     | Kimi K3、Kimi K2.7 Code（等 10 款）              |
-| 小米       | MiMo V2.6 Pro（等 5 款）                         |
-| MiniMax  | MiniMax-M3、MiniMax-M2.7（等 4 款）              |
+| 智谱 AI    | GLM-5.3、GLM-5.2（等 17 款）                     |
+| 阿里通义     | Qwen3.8 Max、Qwen3-Coder 480B（等 27 款）        |
+| 字节豆包     | Doubao Seed-2.1 Pro、Doubao Seed-2.0 Pro（等 13 款） |
+| 月之暗面     | Kimi K3.1 Pro、Kimi K3.1 Pro Highspeed、Kimi K3、Kimi K2.7 Code（等 18 款） |
+| 小米       | MiMo V2.6 Pro（等 6 款）                         |
+| MiniMax  | MiniMax-M3、MiniMax-M2.7（等 8 款）              |
 | 云知声      | U2 Flash、Unisound U2（等 3 款）                 |
 | 百度文心     | ERNIE-5.1、ERNIE-4.5 300B（等 2 款）             |
 | 腾讯混元     | 混元 Hy3、混元 T1（等 3 款）                       |
-| Anthropic | Claude Opus 4.6、Claude Sonnet 4.6（等 12 款）    |
-| Mistral AI | Mistral Large 3、Mistral Small 4（等 3 款）     |
-| Cohere    | Command A、Command R（等 2 款）                 |
-| OpenAI   | GPT-6 Astra、GPT-5.6 Sol / Terra / Luna（等 10 款） |
-| Google   | Gemini 3.1 Pro、Gemini 3.6 Flash（等 4 款）      |
-| xAI      | Grok 4.7、Grok 4.6（等 5 款）                     |
-| Meta     | Llama 4 Maverick（等 2 款）                     |
+| Anthropic | Claude Opus 5、Claude Sonnet 5（等 14 款）    |
+| Mistral AI | Mistral Large 3、Mistral Small 4（等 30 款）     |
+| Cohere    | Command A、Command R（等 7 款）                 |
+| OpenAI   | GPT-6 Astra、GPT-5.6 Sol / Terra / Luna（等 38 款） |
+| Google   | Gemini 3.1 Pro、Gemini 3.6 Flash（等 25 款）      |
+| xAI      | Grok 4.7、Grok 4.20（等 8 款）                     |
+| Meta     | Llama 4 Maverick、Muse Spark 1.3（等 8 款）                     |
 | 美团       | LongCat 2.0（估算价）                             |
 | 面壁智能     | MiniCPM-V 4.5（估算价）                           |
 | 小红书      | Dots3-Note Preview（估算价）                      |
 | 零一万物     | Yi-Lightning                                  |
-| 阶跃星辰     | Step 3.7 Flash                                |
+| 阶跃星辰     | Step 3.7 Flash、Step 5 Preview（等 3 款）                                |
 | 科大讯飞     | Spark 4.0 Ultra（套餐制）¹                       |
 | 商汤       | SenseNova 6.5（公测中）¹                         |
 | 百川智能     | Baichuan M3-Plus                              |
@@ -228,7 +230,7 @@ cost（CNY）= (missInput × p_input + cacheHit × p_cacheHit + output × p_outp
 
 > ¹ 讯飞、商汤及美团 / 面壁智能 / 小红书等未公布官方按量单价的模型，表内为估算价（`estimated`）；这些模型走订阅通道（coding / token plan / opencode）时费用记 0。订阅通道与 pi-ai 内置提供方对齐（kimi-coding、zai-coding-cn、opencode、opencode-go、qwen / xiaomi 的 token-plan 各区域变体），可按 `subscriptionProviders` 配置覆盖。
 
-新增模型：在 `src/builtin-catalog.ts` 的 `BUILTIN_MODEL_CATALOG` 追加条目（别名表 `BUILTIN_MODEL_KEY_ALIASES` 同文件维护；目录只随 node 半构建，经 `/api/billing/pricing` 由宿主下发注入客户端）。
+新增模型：在 `src/builtin-catalog.ts` 的 `BUILTIN_MODEL_CATALOG` 追加条目（别名表 `BUILTIN_MODEL_KEY_ALIASES` 同文件维护；目录只随 node 半构建，经 `/api/billing/pricing` 由宿主下发注入客户端）。**价源口径**：海外厂商取 models.dev 实时目录原生 USD；国内厂商优先取官方 CN 价（models.dev 的 `-cn` 目录），该目录缺项时按 USD 价 × 汇率折算并在条目注释标注。存量条目的价格更正走独立的调价节点，不与扩容混在一起。
 
 ## 🔌 HTTP API
 
@@ -241,7 +243,7 @@ cost（CNY）= (missInput × p_input + cacheHit × p_cacheHit + output × p_outp
 | `statsPath`             | 未设置                                  | 回退统计文件 `.dsh-usage-stats.json` 的绝对路径（`sessionPersistence` 不可用时生效）                                            |
 | `ledgerPath`            | `<harness home>/.dsh-usage-ledger.json` | 独立持久用量账本的绝对路径；只保存折叠后的统计（不保存消息正文或会话标题），永久删除会话不会删除已记录的费用与 token。**默认根跟随宿主 harness home**（`DSH_HOME` 环境变量优先，回退 `~/.dsh`），自定义 `DSH_HOME` 的多套隔离环境互不污染（issue #52）                           |
 | `balanceApiKeyEnv`      | `DEEPSEEK_API_KEY`                   | DeepSeek 余额查询的凭据引用；仅在 llm-pi-ai 未配置 deepseek 的 `apiKeyEnv` 时兜底使用                                             |
-| `subscriptionProviders` | 内置订阅通道清单（含 `tencent-token-plan`） | 订阅制（coding / token 套餐）provider id 列表，照常统计 token、费用记 0；与订阅卡识别口径对齐                                   |
+| `subscriptionProviders` | 内置订阅通道清单（含 `tencent-token-plan`） | 订阅制（coding / token 套餐）provider id 列表，照常统计 token、费用记 0；与订阅卡识别口径对齐。**注意是「替换」默认清单，不是追加**——自定义时要把默认项一并写全，否则被移出的订阅通道会被拉回按量计费 |
 | `routeAliases`          | 未设置                                  | 历史路由别名（旧 provider 路由名 → 当前路由名）：改名/删除过的路由，其历史用量原落「未知路由」桶且订阅/官方判定失效；配置后按目标路由归位。例：`{ "deepseek-official": "tencent", "tencent-cloud": "tencent" }` |
 | `modelKeyAliases`       | 未设置                                  | 用户自定义模型别名（真实日志 model id → 计费目录键，值须为 `MODEL_CATALOG` 既有 key）：目录外新模型无需等发版，配一条别名即完成识别与计价。例：`{ "hy4-preview": "hunyuan" }` |
 | `monthlyBudget`         | 未设置                                  | 月度预算默认金额（人民币元）；随 usage-stats 下发，作为仪表盘预算条的初始金额（用户在界面上的设置优先并本地持久化）                                             |