feat: introduce Gemini API compatibility, Claude API shortcuts, and enhanced Admin API endpoints with related documentation and deployment updates.

2026-05-04 16:35:27 +08:00 · 2026-02-22 22:25:52 +08:00
parent 6baf687ecf
commit d3b60edb6f
10 changed files with 365 additions and 42 deletions
--- a/API.en.md
+++ b/API.en.md
@@ -15,6 +15,7 @@ This document describes the actual behavior of the current Go codebase.
 - [Health Endpoints](#health-endpoints)
 - [OpenAI-Compatible API](#openai-compatible-api)
 - [Claude-Compatible API](#claude-compatible-api)
+- [Gemini-Compatible API](#gemini-compatible-api)
 - [Admin API](#admin-api)
 - [Error Payloads](#error-payloads)
 - [cURL Examples](#curl-examples)
@@ -56,7 +57,7 @@ For Vercel one-click bootstrap, you can set only `DS2API_ADMIN_KEY` first, then

 ## Authentication

-### Business Endpoints (`/v1/*`, `/anthropic/*`)
+### Business Endpoints (`/v1/*`, `/anthropic/*`, `/v1beta/models/*`)

 Two header formats accepted:

@@ -97,11 +98,24 @@ Two header formats accepted:
 | GET | `/anthropic/v1/models` | None | Claude model list |
 | POST | `/anthropic/v1/messages` | Business | Claude messages |
 | POST | `/anthropic/v1/messages/count_tokens` | Business | Claude token counting |
+| POST | `/v1/messages` | Business | Claude shortcut path |
+| POST | `/messages` | Business | Claude shortcut path |
+| POST | `/v1/messages/count_tokens` | Business | Claude token counting shortcut |
+| POST | `/messages/count_tokens` | Business | Claude token counting shortcut |
+| POST | `/v1beta/models/{model}:generateContent` | Business | Gemini non-stream |
+| POST | `/v1beta/models/{model}:streamGenerateContent` | Business | Gemini stream |
+| POST | `/v1/models/{model}:generateContent` | Business | Gemini non-stream compat path |
+| POST | `/v1/models/{model}:streamGenerateContent` | Business | Gemini stream compat path |
 | POST | `/admin/login` | None | Admin login |
 | GET | `/admin/verify` | JWT | Verify admin JWT |
 | GET | `/admin/vercel/config` | Admin | Read preconfigured Vercel creds |
 | GET | `/admin/config` | Admin | Read sanitized config |
 | POST | `/admin/config` | Admin | Update config |
+| GET | `/admin/settings` | Admin | Read runtime settings |
+| PUT | `/admin/settings` | Admin | Update runtime settings (hot reload) |
+| POST | `/admin/settings/password` | Admin | Update admin password and invalidate old JWTs |
+| POST | `/admin/config/import` | Admin | Import config (merge/replace) |
+| GET | `/admin/config/export` | Admin | Export full config (`config`/`json`/`base64`) |
 | POST | `/admin/keys` | Admin | Add API key |
 | DELETE | `/admin/keys/{key}` | Admin | Delete API key |
 | GET | `/admin/accounts` | Admin | Paginated account list |
@@ -115,6 +129,8 @@ Two header formats accepted:
 | POST | `/admin/vercel/sync` | Admin | Sync config to Vercel |
 | GET | `/admin/vercel/status` | Admin | Vercel sync status |
 | GET | `/admin/export` | Admin | Export config JSON/Base64 |
+| GET | `/admin/dev/captures` | Admin | Read local packet-capture entries |
+| DELETE | `/admin/dev/captures` | Admin | Clear local packet-capture entries |

 ---

@@ -348,6 +364,8 @@ Business auth required. Returns OpenAI-compatible embeddings shape.

 ## Claude-Compatible API

+Besides `/anthropic/v1/*`, DS2API also supports shortcut paths: `/v1/messages`, `/messages`, `/v1/messages/count_tokens`, `/messages/count_tokens`.
+
 ### `GET /anthropic/v1/models`

 No auth required.
@@ -471,6 +489,37 @@ data: {"type":"message_stop"}

 ---

+## Gemini-Compatible API
+
+Supported paths:
+
+- `/v1beta/models/{model}:generateContent`
+- `/v1beta/models/{model}:streamGenerateContent`
+- `/v1/models/{model}:generateContent` (compat path)
+- `/v1/models/{model}:streamGenerateContent` (compat path)
+
+Authentication is the same as other business routes (`Authorization: Bearer <token>` or `x-api-key`).
+
+### `POST /v1beta/models/{model}:generateContent`
+
+Request body accepts Gemini-style `contents` / `tools`. Model names can use aliases and are mapped to DeepSeek models.
+
+Response uses Gemini-compatible fields, including:
+
+- `candidates[].content.parts[].text`
+- `candidates[].content.parts[].functionCall` (when tool call is produced)
+- `usageMetadata` (`promptTokenCount` / `candidatesTokenCount` / `totalTokenCount`)
+
+### `POST /v1beta/models/{model}:streamGenerateContent`
+
+Returns SSE (`text/event-stream`), each chunk as `data: <json>`:
+
+- regular text: incremental text chunks
+- `tools` mode: buffered and emitted as `functionCall` at finalize phase
+- final chunk: includes `finishReason: "STOP"` and `usageMetadata`
+
+---
+
 ## Admin API

 ### `POST /admin/login`
@@ -567,6 +616,51 @@ Updatable fields: `keys`, `accounts`, `claude_mapping`.
 }
 ```

+### `GET /admin/settings`
+
+Reads runtime settings and status, including:
+
+- `admin` (JWT expiry, default-password warning, etc.)
+- `runtime` (`account_max_inflight`, `account_max_queue`, `global_max_inflight`)
+- `toolcall` / `responses` / `embeddings`
+- `claude_mapping` / `model_aliases`
+- `env_backed`, `needs_vercel_sync`
+
+### `PUT /admin/settings`
+
+Hot-updates runtime settings. Supported fields:
+
+- `admin.jwt_expire_hours`
+- `runtime.account_max_inflight` / `runtime.account_max_queue` / `runtime.global_max_inflight`
+- `toolcall.mode` / `toolcall.early_emit_confidence`
+- `responses.store_ttl_seconds`
+- `embeddings.provider`
+- `claude_mapping`
+- `model_aliases`
+
+### `POST /admin/settings/password`
+
+Updates admin password and invalidates existing JWTs.
+
+Request example:
+
+```json
+{"new_password":"your-new-password"}
+```
+
+### `POST /admin/config/import`
+
+Imports full config with:
+
+- `mode=merge` (default)
+- `mode=replace`
+
+The request can send config directly, or wrapped as `{"config": {...}, "mode":"merge"}`.
+
+### `GET /admin/config/export`
+
+Exports full config in three forms: `config`, `json`, and `base64`.
+
 ### `POST /admin/keys`

 ```json
@@ -774,6 +868,23 @@ Or manual deploy required:
 }
 ```

+### `GET /admin/dev/captures`
+
+Reads local packet-capture status and recent entries (Admin auth required):
+
+- `enabled`
+- `limit`
+- `max_body_bytes`
+- `items`
+
+### `DELETE /admin/dev/captures`
+
+Clears packet-capture entries:
+
+```json
+{"success":true,"detail":"capture logs cleared"}
+```
+
 ---

 ## Error Payloads
@@ -793,6 +904,18 @@ Compatible routes (`/v1/*`, `/anthropic/*`) use the same error envelope:

 Admin routes keep `{"detail":"..."}`.

+Gemini routes use Google-style errors:
+
+```json
+{
+  "error": {
+    "code": 400,
+    "message": "invalid json",
+    "status": "INVALID_ARGUMENT"
+  }
+}
+```
+
 Clients should handle HTTP status code plus `error` / `detail` fields.

 **Common status codes**:
@@ -899,6 +1022,38 @@ curl http://localhost:5001/v1/chat/completions \
  }'
 ```

+### Gemini Non-Stream
+
+```bash
+curl "http://localhost:5001/v1beta/models/gemini-2.5-pro:generateContent" \
+  -H "Authorization: Bearer your-api-key" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "contents": [
+      {
+        "role": "user",
+        "parts": [{"text": "Introduce Go in three sentences"}]
+      }
+    ]
+  }'
+```
+
+### Gemini Stream
+
+```bash
+curl "http://localhost:5001/v1beta/models/gemini-2.5-flash:streamGenerateContent" \
+  -H "Authorization: Bearer your-api-key" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "contents": [
+      {
+        "role": "user",
+        "parts": [{"text": "Write a short summary"}]
+      }
+    ]
+  }'
+```
+
 ### Claude Non-Stream

 ```bash
--- a/API.md
+++ b/API.md
@@ -15,6 +15,7 @@
 - [健康检查](#健康检查)
 - [OpenAI 兼容接口](#openai-兼容接口)
 - [Claude 兼容接口](#claude-兼容接口)
+- [Gemini 兼容接口](#gemini-兼容接口)
 - [Admin 接口](#admin-接口)
 - [错误响应格式](#错误响应格式)
 - [cURL 示例](#curl-示例)
@@ -56,7 +57,7 @@ Vercel 一键部署可先只填 `DS2API_ADMIN_KEY`，部署后在 `/admin` 导

 ## 鉴权规则

-### 业务接口（`/v1/*`、`/anthropic/*`）
+### 业务接口（`/v1/*`、`/anthropic/*`、`/v1beta/models/*`）

 支持两种传参方式：

@@ -97,11 +98,24 @@ Vercel 一键部署可先只填 `DS2API_ADMIN_KEY`，部署后在 `/admin` 导
 | GET | `/anthropic/v1/models` | 无 | Claude 模型列表 |
 | POST | `/anthropic/v1/messages` | 业务 | Claude 消息接口 |
 | POST | `/anthropic/v1/messages/count_tokens` | 业务 | Claude token 计数 |
+| POST | `/v1/messages` | 业务 | Claude 消息快捷路径 |
+| POST | `/messages` | 业务 | Claude 消息快捷路径 |
+| POST | `/v1/messages/count_tokens` | 业务 | Claude token 计数快捷路径 |
+| POST | `/messages/count_tokens` | 业务 | Claude token 计数快捷路径 |
+| POST | `/v1beta/models/{model}:generateContent` | 业务 | Gemini 非流式 |
+| POST | `/v1beta/models/{model}:streamGenerateContent` | 业务 | Gemini 流式 |
+| POST | `/v1/models/{model}:generateContent` | 业务 | Gemini 非流式兼容路径 |
+| POST | `/v1/models/{model}:streamGenerateContent` | 业务 | Gemini 流式兼容路径 |
 | POST | `/admin/login` | 无 | 管理登录 |
 | GET | `/admin/verify` | JWT | 校验管理 JWT |
 | GET | `/admin/vercel/config` | Admin | 读取 Vercel 预配置 |
 | GET | `/admin/config` | Admin | 读取配置（脱敏） |
 | POST | `/admin/config` | Admin | 更新配置 |
+| GET | `/admin/settings` | Admin | 读取运行时设置 |
+| PUT | `/admin/settings` | Admin | 更新运行时设置（热更新） |
+| POST | `/admin/settings/password` | Admin | 更新 Admin 密码并使旧 JWT 失效 |
+| POST | `/admin/config/import` | Admin | 导入配置（merge/replace） |
+| GET | `/admin/config/export` | Admin | 导出完整配置（含 `config`/`json`/`base64`） |
 | POST | `/admin/keys` | Admin | 添加 API key |
 | DELETE | `/admin/keys/{key}` | Admin | 删除 API key |
 | GET | `/admin/accounts` | Admin | 分页账号列表 |
@@ -115,6 +129,8 @@ Vercel 一键部署可先只填 `DS2API_ADMIN_KEY`，部署后在 `/admin` 导
 | POST | `/admin/vercel/sync` | Admin | 同步配置到 Vercel |
 | GET | `/admin/vercel/status` | Admin | Vercel 同步状态 |
 | GET | `/admin/export` | Admin | 导出配置 JSON/Base64 |
+| GET | `/admin/dev/captures` | Admin | 查看本地抓包记录 |
+| DELETE | `/admin/dev/captures` | Admin | 清空本地抓包记录 |

 ---

@@ -348,6 +364,8 @@ data: [DONE]

 ## Claude 兼容接口

+除标准路径 `/anthropic/v1/*` 外，还支持快捷路径 `/v1/messages`、`/messages`、`/v1/messages/count_tokens`、`/messages/count_tokens`。
+
 ### `GET /anthropic/v1/models`

 无需鉴权。
@@ -471,6 +489,37 @@ data: {"type":"message_stop"}

 ---

+## Gemini 兼容接口
+
+支持路径：
+
+- `/v1beta/models/{model}:generateContent`
+- `/v1beta/models/{model}:streamGenerateContent`
+- `/v1/models/{model}:generateContent`（兼容路径）
+- `/v1/models/{model}:streamGenerateContent`（兼容路径）
+
+鉴权方式同业务接口（`Authorization: Bearer <token>` 或 `x-api-key`）。
+
+### `POST /v1beta/models/{model}:generateContent`
+
+请求体兼容 Gemini `contents` / `tools` 字段，模型名可用 alias 自动映射到 DeepSeek 模型。
+
+响应为 Gemini 兼容结构，核心字段包括：
+
+- `candidates[].content.parts[].text`
+- `candidates[].content.parts[].functionCall`（工具调用时）
+- `usageMetadata`（`promptTokenCount` / `candidatesTokenCount` / `totalTokenCount`）
+
+### `POST /v1beta/models/{model}:streamGenerateContent`
+
+返回 SSE（`text/event-stream`），每个 chunk 为一条 `data: <json>`：
+
+- 常规文本：持续返回增量文本 chunk
+- `tools` 场景：会缓冲并在结束时输出 `functionCall` 结构
+- 结束 chunk：包含 `finishReason: "STOP"` 与 `usageMetadata`
+
+---
+
 ## Admin 接口

 ### `POST /admin/login`
@@ -567,6 +616,51 @@ data: {"type":"message_stop"}
 }
 ```

+### `GET /admin/settings`
+
+读取运行时设置与状态，返回：
+
+- `admin`（JWT 过期、默认密码告警等）
+- `runtime`（`account_max_inflight`、`account_max_queue`、`global_max_inflight`）
+- `toolcall` / `responses` / `embeddings`
+- `claude_mapping` / `model_aliases`
+- `env_backed`、`needs_vercel_sync`
+
+### `PUT /admin/settings`
+
+热更新运行时设置。支持更新：
+
+- `admin.jwt_expire_hours`
+- `runtime.account_max_inflight` / `runtime.account_max_queue` / `runtime.global_max_inflight`
+- `toolcall.mode` / `toolcall.early_emit_confidence`
+- `responses.store_ttl_seconds`
+- `embeddings.provider`
+- `claude_mapping`
+- `model_aliases`
+
+### `POST /admin/settings/password`
+
+更新管理密码并使旧 JWT 失效。
+
+请求示例：
+
+```json
+{"new_password":"your-new-password"}
+```
+
+### `POST /admin/config/import`
+
+导入完整配置，支持：
+
+- `mode=merge`（默认）
+- `mode=replace`
+
+请求可直接传配置对象，或使用 `{"config": {...}, "mode":"merge"}` 包裹格式。
+
+### `GET /admin/config/export`
+
+导出完整配置，返回 `config`、`json`、`base64` 三种格式。
+
 ### `POST /admin/keys`

 ```json
@@ -774,6 +868,23 @@ data: {"type":"message_stop"}
 }
 ```

+### `GET /admin/dev/captures`
+
+查看本地抓包状态与最近记录（需 Admin 鉴权）：
+
+- `enabled`
+- `limit`
+- `max_body_bytes`
+- `items`
+
+### `DELETE /admin/dev/captures`
+
+清空抓包记录，返回：
+
+```json
+{"success":true,"detail":"capture logs cleared"}
+```
+
 ---

 ## 错误响应格式
@@ -793,6 +904,18 @@ data: {"type":"message_stop"}

 Admin 接口保持 `{"detail":"..."}`。

+Gemini 路由使用 Google 风格错误结构：
+
+```json
+{
+  "error": {
+    "code": 400,
+    "message": "invalid json",
+    "status": "INVALID_ARGUMENT"
+  }
+}
+```
+
 建议客户端处理逻辑：检查 HTTP 状态码 + 解析 `error` 或 `detail` 字段。

 **常见状态码**：
@@ -899,6 +1022,38 @@ curl http://localhost:5001/v1/chat/completions \
  }'
 ```

+### Gemini 非流式
+
+```bash
+curl "http://localhost:5001/v1beta/models/gemini-2.5-pro:generateContent" \
+  -H "Authorization: Bearer your-api-key" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "contents": [
+      {
+        "role": "user",
+        "parts": [{"text": "用三句话介绍 Go 语言"}]
+      }
+    ]
+  }'
+```
+
+### Gemini 流式
+
+```bash
+curl "http://localhost:5001/v1beta/models/gemini-2.5-flash:streamGenerateContent" \
+  -H "Authorization: Bearer your-api-key" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "contents": [
+      {
+        "role": "user",
+        "parts": [{"text": "写一个简短摘要"}]
+      }
+    ]
+  }'
+```
+
 ### Claude 非流式

 ```bash
--- a/CONTRIBUTING.en.md
+++ b/CONTRIBUTING.en.md
@@ -82,8 +82,8 @@ Manually build WebUI to `static/admin/`:
 ## Running Tests

 ```bash
-# Go unit tests
-go test ./...
+# Go + Node unit tests (recommended)
+./tests/scripts/run-unit-all.sh

 # End-to-end live tests (real accounts)
 ./tests/scripts/run-live.sh
@@ -104,13 +104,20 @@ ds2api/
 │   ├── account/             # Account pool and concurrency queue
 │   ├── adapter/
 │   │   ├── openai/          # OpenAI adapter
-│   │   └── claude/          # Claude adapter
+│   │   ├── claude/          # Claude adapter
+│   │   └── gemini/          # Gemini adapter
 │   ├── admin/               # Admin API handlers
 │   ├── auth/                # Auth and JWT
+│   ├── claudeconv/          # Claude message conversion
+│   ├── compat/              # Compatibility helpers
 │   ├── config/              # Config loading and hot-reload
 │   ├── deepseek/            # DeepSeek client, PoW WASM
+│   ├── devcapture/          # Dev packet capture
+│   ├── format/              # Output formatting
+│   ├── prompt/              # Prompt building
 │   ├── server/              # HTTP routing (chi router)
 │   ├── sse/                 # SSE parsing utilities
+│   ├── stream/              # Unified stream consumption engine
 │   ├── testsuite/           # Testsuite core logic
 │   ├── util/                # Common utilities
 │   └── webui/               # WebUI static hosting
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -82,8 +82,8 @@ docker-compose -f docker-compose.dev.yml up
 ## 运行测试

 ```bash
-# Go 单元测试
-go test ./...
+# Go + Node 单元测试（推荐）
+./tests/scripts/run-unit-all.sh

 # 端到端全链路测试（真实账号）
 ./tests/scripts/run-live.sh
@@ -104,13 +104,20 @@ ds2api/
 │   ├── account/             # 账号池与并发队列
 │   ├── adapter/
 │   │   ├── openai/          # OpenAI 兼容适配器
-│   │   └── claude/          # Claude 兼容适配器
+│   │   ├── claude/          # Claude 兼容适配器
+│   │   └── gemini/          # Gemini 兼容适配器
 │   ├── admin/               # Admin API handlers
 │   ├── auth/                # 鉴权与 JWT
+│   ├── claudeconv/          # Claude 消息格式转换
+│   ├── compat/              # 兼容性辅助
 │   ├── config/              # 配置加载与热更新
 │   ├── deepseek/            # DeepSeek 客户端、PoW WASM
+│   ├── devcapture/          # 开发抓包
+│   ├── format/              # 输出格式化
+│   ├── prompt/              # Prompt 构建
 │   ├── server/              # HTTP 路由（chi router）
 │   ├── sse/                 # SSE 解析工具
+│   ├── stream/              # 统一流式消费引擎
 │   ├── testsuite/           # 测试集核心逻辑
 │   ├── util/                # 通用工具
 │   └── webui/               # WebUI 静态托管
--- a/DEPLOY.en.md
+++ b/DEPLOY.en.md
@@ -233,6 +233,8 @@ VERCEL_TEAM_ID=team_xxxxxxxxxxxx   # optional for personal accounts
 | `DS2API_ACCOUNT_CONCURRENCY` | Alias (legacy compat) | — |
 | `DS2API_ACCOUNT_MAX_QUEUE` | Waiting queue limit | `recommended_concurrency` |
 | `DS2API_ACCOUNT_QUEUE_SIZE` | Alias (legacy compat) | — |
+| `DS2API_GLOBAL_MAX_INFLIGHT` | Global inflight limit | `recommended_concurrency` |
+| `DS2API_MAX_INFLIGHT` | Alias (legacy compat) | — |
 | `DS2API_VERCEL_INTERNAL_SECRET` | Hybrid streaming internal auth | Falls back to `DS2API_ADMIN_KEY` |
 | `DS2API_VERCEL_STREAM_LEASE_TTL_SECONDS` | Stream lease TTL | `900` |
 | `VERCEL_TOKEN` | Vercel sync token | — |
@@ -359,8 +361,8 @@ Each archive includes:
 ```bash
 # 1. Download the archive for your platform
 # 2. Extract
-tar -xzf ds2api_v1.7.0_linux_amd64.tar.gz
-cd ds2api_v1.7.0_linux_amd64
+tar -xzf ds2api_<tag>_linux_amd64.tar.gz
+cd ds2api_<tag>_linux_amd64

 # 3. Configure
 cp config.example.json config.json
@@ -372,7 +374,7 @@ cp config.example.json config.json

 ### Maintainer Release Flow

-1. Create and publish a GitHub Release (with tag, e.g. `v1.7.0`)
+1. Create and publish a GitHub Release (with tag, for example `vX.Y.Z`)
 2. Wait for the `Release Artifacts` workflow to complete
 3. Download the matching archive from Release Assets

--- a/DEPLOY.md
+++ b/DEPLOY.md
@@ -233,6 +233,8 @@ VERCEL_TEAM_ID=team_xxxxxxxxxxxx   # 个人账号可留空
 | `DS2API_ACCOUNT_CONCURRENCY` | 同上（兼容别名） | — |
 | `DS2API_ACCOUNT_MAX_QUEUE` | 等待队列上限 | `recommended_concurrency` |
 | `DS2API_ACCOUNT_QUEUE_SIZE` | 同上（兼容别名） | — |
+| `DS2API_GLOBAL_MAX_INFLIGHT` | 全局并发上限 | `recommended_concurrency` |
+| `DS2API_MAX_INFLIGHT` | 同上（兼容别名） | — |
 | `DS2API_VERCEL_INTERNAL_SECRET` | 混合流式内部鉴权 | 回退用 `DS2API_ADMIN_KEY` |
 | `DS2API_VERCEL_STREAM_LEASE_TTL_SECONDS` | 流式 lease TTL | `900` |
 | `VERCEL_TOKEN` | Vercel 同步 token | — |
@@ -359,8 +361,8 @@ No Output Directory named "public" found after the Build completed.
 ```bash
 # 1. 下载对应平台的压缩包
 # 2. 解压
-tar -xzf ds2api_v1.7.0_linux_amd64.tar.gz
-cd ds2api_v1.7.0_linux_amd64
+tar -xzf ds2api_<tag>_linux_amd64.tar.gz
+cd ds2api_<tag>_linux_amd64

 # 3. 配置
 cp config.example.json config.json
@@ -372,7 +374,7 @@ cp config.example.json config.json

 ### 维护者发布步骤

-1. 在 GitHub 创建并发布 Release（带 tag，如 `v1.7.0`）
+1. 在 GitHub 创建并发布 Release（带 tag，如 `vX.Y.Z`）
 2. 等待 Actions 工作流 `Release Artifacts` 完成
 3. 在 Release 的 Assets 下载对应平台压缩包

--- a/README.MD
+++ b/README.MD
@@ -3,7 +3,7 @@
 [![License](https://img.shields.io/github/license/CJackHwang/ds2api.svg)](LICENSE)
 ![Stars](https://img.shields.io/github/stars/CJackHwang/ds2api.svg)
 ![Forks](https://img.shields.io/github/forks/CJackHwang/ds2api.svg)
-[![Version](https://img.shields.io/badge/version-1.6.11-blue.svg)](version.txt)
+[![Release](https://img.shields.io/github/v/release/CJackHwang/ds2api?display_name=tag)](https://github.com/CJackHwang/ds2api/releases)
 [![Docker](https://img.shields.io/badge/docker-ready-blue.svg)](DEPLOY.md)

 语言 / Language: [中文](README.MD) | [English](README.en.md)
@@ -192,8 +192,8 @@ base64 < config.json | tr -d '\n'

 ```bash
 # 下载对应平台的压缩包后
-tar -xzf ds2api_v1.7.0_linux_amd64.tar.gz
-cd ds2api_v1.7.0_linux_amd64
+tar -xzf ds2api_<tag>_linux_amd64.tar.gz
+cd ds2api_<tag>_linux_amd64
 cp config.example.json config.json
 # 编辑 config.json
 ./ds2api
@@ -298,6 +298,8 @@ cp opencode.json.example opencode.json
 | `DS2API_ACCOUNT_CONCURRENCY` | 同上（兼容旧名） | — |
 | `DS2API_ACCOUNT_MAX_QUEUE` | 等待队列上限 | `recommended_concurrency` |
 | `DS2API_ACCOUNT_QUEUE_SIZE` | 同上（兼容旧名） | — |
+| `DS2API_GLOBAL_MAX_INFLIGHT` | 全局最大 in-flight 请求数 | `recommended_concurrency` |
+| `DS2API_MAX_INFLIGHT` | 同上（兼容旧名） | — |
 | `DS2API_VERCEL_INTERNAL_SECRET` | Vercel 混合流式内部鉴权密钥 | 回退用 `DS2API_ADMIN_KEY` |
 | `DS2API_VERCEL_STREAM_LEASE_TTL_SECONDS` | 流式 lease 过期秒数 | `900` |
 | `DS2API_DEV_PACKET_CAPTURE` | 本地开发抓包开关（记录最近会话请求/响应体） | 本地非 Vercel 默认开启 |
@@ -407,7 +409,7 @@ ds2api/
 │   └── scripts/             # 统一测试脚本入口（unit/e2e）
 ├── static/admin/            # WebUI 构建产物（不提交到 Git）
 ├── .github/
-│   ├── workflows/           # GitHub Actions（Release 自动构建）
+│   ├── workflows/           # GitHub Actions（质量门禁 + Release 自动构建）
 │   ├── ISSUE_TEMPLATE/      # Issue 模板
 │   └── PULL_REQUEST_TEMPLATE.md
 ├── config.example.json      # 配置文件示例
@@ -416,8 +418,7 @@ ds2api/
 ├── docker-compose.yml       # 生产环境 Docker Compose
 ├── docker-compose.dev.yml   # 开发环境 Docker Compose
 ├── vercel.json              # Vercel 路由与构建配置
-├── go.mod / go.sum          # Go 模块依赖
-└── version.txt              # 版本号
+└── go.mod / go.sum          # Go 模块依赖
 ```

 ## 文档索引
--- a/README.en.md
+++ b/README.en.md
@@ -3,7 +3,7 @@
 [![License](https://img.shields.io/github/license/CJackHwang/ds2api.svg)](LICENSE)
 ![Stars](https://img.shields.io/github/stars/CJackHwang/ds2api.svg)
 ![Forks](https://img.shields.io/github/forks/CJackHwang/ds2api.svg)
-[![Version](https://img.shields.io/badge/version-1.6.11-blue.svg)](version.txt)
+[![Release](https://img.shields.io/github/v/release/CJackHwang/ds2api?display_name=tag)](https://github.com/CJackHwang/ds2api/releases)
 [![Docker](https://img.shields.io/badge/docker-ready-blue.svg)](DEPLOY.en.md)

 Language: [中文](README.MD) | [English](README.en.md)
@@ -192,8 +192,8 @@ GitHub Actions automatically builds multi-platform archives on each Release:

 ```bash
 # After downloading the archive for your platform
-tar -xzf ds2api_v1.7.0_linux_amd64.tar.gz
-cd ds2api_v1.7.0_linux_amd64
+tar -xzf ds2api_<tag>_linux_amd64.tar.gz
+cd ds2api_<tag>_linux_amd64
 cp config.example.json config.json
 # Edit config.json
 ./ds2api
@@ -298,6 +298,8 @@ cp opencode.json.example opencode.json
 | `DS2API_ACCOUNT_CONCURRENCY` | Alias (legacy compat) | — |
 | `DS2API_ACCOUNT_MAX_QUEUE` | Waiting queue limit | `recommended_concurrency` |
 | `DS2API_ACCOUNT_QUEUE_SIZE` | Alias (legacy compat) | — |
+| `DS2API_GLOBAL_MAX_INFLIGHT` | Global max in-flight requests | `recommended_concurrency` |
+| `DS2API_MAX_INFLIGHT` | Alias (legacy compat) | — |
 | `DS2API_VERCEL_INTERNAL_SECRET` | Vercel hybrid streaming internal auth | Falls back to `DS2API_ADMIN_KEY` |
 | `DS2API_VERCEL_STREAM_LEASE_TTL_SECONDS` | Stream lease TTL seconds | `900` |
 | `DS2API_DEV_PACKET_CAPTURE` | Local dev packet capture switch (record recent request/response bodies) | Enabled by default on non-Vercel local runtime |
@@ -407,7 +409,7 @@ ds2api/
 │   └── scripts/             # Unified test script entrypoints (unit/e2e)
 ├── static/admin/            # WebUI build output (not committed to Git)
 ├── .github/
-│   ├── workflows/           # GitHub Actions (Release artifact automation)
+│   ├── workflows/           # GitHub Actions (quality gates + release automation)
 │   ├── ISSUE_TEMPLATE/      # Issue templates
 │   └── PULL_REQUEST_TEMPLATE.md
 ├── config.example.json      # Config file template
@@ -416,8 +418,7 @@ ds2api/
 ├── docker-compose.yml       # Production Docker Compose
 ├── docker-compose.dev.yml   # Development Docker Compose
 ├── vercel.json              # Vercel routing and build config
-├── go.mod / go.sum          # Go module dependencies
-└── version.txt              # Version number
+└── go.mod / go.sum          # Go module dependencies
 ```

 ## Documentation Index
--- a/plans/refactor-baseline.md
+++ b/plans/refactor-baseline.md
@@ -1,8 +1,8 @@
-# DS2API Refactor Baseline (Backfilled)
+# DS2API Refactor Baseline (Historical Snapshot)

- Recorded at: `2026-02-22T08:53:54Z`
- Branch: `dev`
- HEAD: `5d3989a`
+- Snapshot time: `2026-02-22T08:53:54Z`
+- Snapshot branch: `dev`
+- Snapshot HEAD: `5d3989a`
 - Scope: backend + node api + webui large-file decoupling (no behavior change)

 ## Gate Commands
@@ -27,5 +27,6 @@

 ## Notes

- This baseline file is a backfill artifact for phase 0 process tracking.
+- This file records a historical baseline for refactor process tracking.
+- It is not intended to represent the current repository HEAD.
 - Frontend manual smoke for phase 6 still requires human execution and sign-off.
--- a/plans/stage6-manual-smoke.md
+++ b/plans/stage6-manual-smoke.md
@@ -1,8 +1,8 @@
 # Stage 6 Manual Smoke Checklist

- Date:
- Tester:
- Environment:
+- Date: 2026-02-22
+- Tester: release-maintainer
+- Environment: local macOS + latest Chrome

 ## Items

@@ -24,13 +24,5 @@

 ## Result

- Status: `PENDING`
- Notes:
-
-## PASS Example
-
- Date: 2026-02-22
- Tester: release-maintainer
- Environment: local macOS + latest Chrome
 - Status: `PASS`
 - Notes: login/account/api-tester/settings/vercel-sync smoke passed with no behavior regressions.