From 4da3e57fcf325ce19eb283d0d77f499f4a278bd6 Mon Sep 17 00:00:00 2001 From: argszero Date: Mon, 19 Oct 2026 03:26:58 +0800 Subject: [PATCH] docs: feature lists describe the catalogue that actually ships Four carriers still described this project as shipping DeepSeek pricing only, with every other vendor left to the reader to configure: - README.md / README.en.md, the "transparent billing" feature line; - docs/user-stories.md, the capability list that mirrors it; - docs/plan-api-matrix.md, which said "DeepSeek pricing built in; other vendors can be configured in the same format" and listed eight provider names, two of which (`bytedance`, `aliyun`) are not the ids the config actually uses. The example config ships ten providers, sixteen plans and twenty-four models, with thirteen rows priced in CNY and eleven in USD: the four international vendors became selectable in #414, and the new-generation rows landed in #415. The old wording was accurate when written; it is incomplete now, and incomplete in the direction that undersells the feature list -- a reader of the front page is told to expect one vendor's prices and to configure the rest themselves. The fix names no counts. Those are owned by the config and by catalog_gate's MODEL_COUNT / PLAN_COUNT, and restating them in prose is the stale-copy family this repo has had to clean up before. The provider roster is spelled with the real ids and checked to be exact in both directions; the model-family roster gains the two families it was missing (Kimi, grok). Docs only: 4 files, +6/-6, no behaviour change. --- README.en.md | 2 +- README.md | 2 +- docs/plan-api-matrix.md | 6 +++--- docs/user-stories.md | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/README.en.md b/README.en.md index a9a485c..67c29dd 100644 --- a/README.en.md +++ b/README.en.md @@ -12,7 +12,7 @@ AITokenPool is an open-source **AI token sharing platform / multi-model gateway* ## Features - **Multi-protocol gateway** — bidirectional conversion between OpenAI Chat / OpenAI Responses / Anthropic Messages, for both non-streaming and SSE streaming requests; clients only need one OpenAI-compatible endpoint -- **Transparent billing** — every call shows an input / cache-hit / output token breakdown; built-in DeepSeek official CNY pricing with peak-hour pricing support +- **Transparent billing** — every call shows an input / cache-hit / output token breakdown; vendor price lists ship with the release, each recorded in its own currency (CNY / USD), with peak-hour pricing support - **Point system** — daily gift, 90/10 sharing split, admin top-up, self-registration with email verification - **Enterprise controls** — departments, member credits, usage reports, and a dedicated operator view - **Security** — upstream keys encrypted with AES-256-GCM, argon2 password hashing, email verification, admin role isolation diff --git a/README.md b/README.md index ce6f1f5..bd5b770 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ AITokenPool 是一个开源的 **AI Token 共享平台 / 多模型网关**：把 ## 特性 - **多协议网关互转** — OpenAI Chat / OpenAI Responses / Anthropic Messages 三协议双向转换，非流式 + SSE 流式全支持；客户端只需对接一个 OpenAI 兼容端点 -- **透明计费** — 每次调用展示「输入 / 缓存命中 / 输出」三档 token 明细；内置 DeepSeek 官方 CNY 定价，支持高峰时段计价 +- **透明计费** — 每次调用展示「输入 / 缓存命中 / 输出」三档 token 明细；价目随发行预置，各厂商按原币记价（人民币 / 美元），支持高峰时段计价 - **点数体系** — 每日赠送、共享分成（90/10）、管理员加额、自助注册 + 邮箱验证 - **企业管控** — 部门管理、成员点数、用量报表、运营者视图，成本一目了然 - **安全** — 上游 Key AES-256-GCM 加密存储、argon2 密码哈希、邮箱验证、管理员角色隔离 diff --git a/docs/plan-api-matrix.md b/docs/plan-api-matrix.md index e21a540..de9bc6a 100644 --- a/docs/plan-api-matrix.md +++ b/docs/plan-api-matrix.md @@ -27,9 +27,9 @@ Base URL 统一由 AITokenPool 提供（`[server].public_url` 配置），设置 - 上游 key 在「共享管理」页上架（provider + plan + model + key + 额度 + 可用时段） - 模型价格由 `config/config.example.toml` 的 `[[models]]` 定义（唯一真源，启动 seed 入 `models` 表） -- 内置 DeepSeek 官方 CNY 定价（含高峰时段价）；其余厂商可按同格式配置 -- 支持的 provider：deepseek、zhipu(glm)、openai、anthropic、google、bytedance、minimax、aliyun 等（随 `[[models]]` 配置扩展，无需改代码） +- 各厂商价目已随 `config/config.example.toml` 预置（含高峰时段价）；新增厂商只需按同格式补 `[[models]]`，无需改代码 +- 预置 provider：`deepseek`、`zhipu`、`aliyun-bailian`、`bytedance-ark`、`moonshot`、`minimax`、`openai`、`anthropic`、`google`、`xai`（随 `[[models]]` 配置扩展，无需改代码） ## 4. 模型目录 -内置 DeepSeek / GLM / GPT / Claude / Gemini / 豆包 / MiniMax / 通义等模型，含 context window、vision 支持、缓存价与高峰价字段。**数量与明细以 `config/config.example.toml` 的 `[[models]]` 为唯一真源**（由 `src/catalog_gate.rs` 的 `MODEL_COUNT` 守卫，此处不抄写数字以免随之陈旧）。模型列表可经管理端「模型管理」页 CRUD（需 admin 角色）。 +内置 DeepSeek / GLM / GPT / Claude / Gemini / 豆包 / Kimi / MiniMax / 通义 / grok 等模型，含 context window、vision 支持、缓存价与高峰价字段。**数量与明细以 `config/config.example.toml` 的 `[[models]]` 为唯一真源**（由 `src/catalog_gate.rs` 的 `MODEL_COUNT` 守卫，此处不抄写数字以免随之陈旧）。模型列表可经管理端「模型管理」页 CRUD（需 admin 角色）。 diff --git a/docs/user-stories.md b/docs/user-stories.md index f012e8c..9cadb3d 100644 --- a/docs/user-stories.md +++ b/docs/user-stories.md @@ -33,7 +33,7 @@ ## 3. 能力清单（对照 README 特性） - **多协议网关**：OpenAI Chat / Responses / Anthropic Messages + SSE 流式互转 -- **透明计费**：输入 / 缓存命中 / 输出 token 明细；DeepSeek 官方 CNY 价；高峰时段计价 +- **透明计费**：输入 / 缓存命中 / 输出 token 明细；各厂商价目按原币记（人民币 / 美元）；高峰时段计价 - **点数体系**：每日赠送、分享分成、管理员充值、自助注册 + 邮箱验证、找回密码 - **企业管控**：部门、成员点数、用量报表、运营者视图、模型管理 CRUD - **安全**：上游 key AES-256-GCM 加密、argon2 哈希、角色隔离、主密钥机制