chore: bump version to 3.3.25

Co-authored-by: Codex <noreply@openai.com>
fix(scheduling): retain valid quota signals across idle periods
2026-11-07 16:05:27 +00:00 · 2026-09-07 04:48:14 +08:00 · 2026-09-07 04:47:30 +08:00 · 2026-09-07 04:25:16 +08:00 · 2026-09-07 03:40:53 +08:00 · 2026-09-07 03:40:34 +08:00
484 changed files with 34816 additions and 18634 deletions
@@ -33,6 +33,8 @@ jobs:
    timeout-minutes: 30
    env:
      CARGO_TERM_COLOR: always
+      # Rust 1.97 编译 AWS SDK 调试信息需要更大的 codegen 线程栈。
+      RUST_MIN_STACK: 16777216
      CPR_TEST_DATABASE_URL: postgres://codex_proxy:codex_proxy@127.0.0.1:5432/codex_proxy
      CPR_TEST_REDIS_URL: redis://127.0.0.1:6379
    services:
@@ -5,195 +5,161 @@

 # Codex Proxy RS

-**基于 Rust 的多 Provider 透明 AI 网关**
+集中管理 OpenAI、xAI 账号，为 Codex 和兼容客户端提供统一的访问地址与密钥。

 [![CI](https://github.com/zyycn/codex-proxy-rs/actions/workflows/ci.yml/badge.svg)](https://github.com/zyycn/codex-proxy-rs/actions/workflows/ci.yml)
 [![Release](https://img.shields.io/github/v/release/zyycn/codex-proxy-rs?display_name=tag&sort=semver&style=flat-square)](https://github.com/zyycn/codex-proxy-rs/releases)
 [![GHCR](https://img.shields.io/badge/GHCR-codex--proxy--rs-2496ED?logo=docker&logoColor=white&style=flat-square)](https://github.com/zyycn/codex-proxy-rs/pkgs/container/codex-proxy-rs)
 [![MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](https://opensource.org/license/mit)

-[快速开始](#快速开始) · [客户端接入](#客户端接入) · [运行维护](#运行维护) · [部署](deploy/README.md) · [接口](docs/api.md) · [架构](docs/architecture.md)
+[快速开始](#快速开始) · [客户端接入](#客户端接入) · [常见问题](#常见问题) · [部署说明](deploy/README.md)

 </div>

-> [!NOTE]
-> 数据面支持 OpenAI Responses、Images 和模型目录协议，不提供 `/v1/chat/completions`。
-
 ## 功能

-| 领域 | 当前能力 |
-| --- | --- |
-| 数据面 | Responses JSON、SSE、WebSocket、review 子代理、Images 生成/编辑与模型目录 |
-| Provider | 固定 `openai`、`xai` 两个 Provider，各自拥有 OAuth、credential、额度、目录与 transport |
-| 路由 | Client Key 限定账号分组；按模型能力编译 Provider 候选；支持全局精确模型映射、会话亲和和安全 fallback |
-| 透明边界 | OpenAI 保留未知请求字段及字段顺序，并原样转发 SSE、WebSocket 与 Images 业务字节；xAI 在 Provider 内转换协议 |
-| 账号 | OAuth、OpenAI AT/RT 与账号文件导入，credential/额度刷新、账号恢复及主动额度重置卡 |
-| 管理 | 账号与分组、Client Key、运行设置、用量/错误观测、S3/R2 备份、系统更新与回滚 |
-| 计量 | Token、图片、费用、延迟、账号与 Provider 归因，并记录上游响应确认的实际 `service_tier` |
+- 在网页中添加账号，查看额度、请求记录和费用，刷新或重新授权过期账号。
+- 用账号分组控制不同密钥可使用的账号，设置并发和请求频率。
+- 接入 Codex CLI、桌面端和支持 Responses API 的客户端。
+- 支持流式对话、WebSocket、图片生成与编辑、Codex 独立搜索。
+- 支持 S3/R2 数据库备份、同大版本在线更新和回滚。

-架构边界、状态所有权和请求不变量见 [架构文档](docs/architecture.md)。
+支持 OpenAI、xAI 账号，但图片与独立搜索目前仅通过 OpenAI 提供。模型和功能是否可用取决于上游账号权限。
+**不支持 `/v1/chat/completions`**；仅支持该接口的客户端不能直接接入。

 ## 快速开始

-需要 Docker Engine 与 Docker Compose Plugin。
+使用 Docker Compose 部署发布镜像 `ghcr.io/zyycn/codex-proxy-rs:latest`，同时启动 PostgreSQL 和 Redis。
+以下命令适用于 Linux amd64/arm64，需要 Docker Engine、Docker Compose Plugin、curl 和 OpenSSL。已有部署请先看
+[升级说明](deploy/README.md#镜像升级与源码构建)，不要覆盖原配置。

-### 1. 准备配置和目录
+### 1. 下载部署文件并配置

 ```bash
-git clone https://github.com/zyycn/codex-proxy-rs.git
+mkdir -p codex-proxy-rs/deploy
 cd codex-proxy-rs

+curl -fsSL https://raw.githubusercontent.com/zyycn/codex-proxy-rs/main/deploy/compose.yaml \
+  -o deploy/compose.yaml
+curl -fsSL https://raw.githubusercontent.com/zyycn/codex-proxy-rs/main/deploy/config.example.yaml \
+  -o deploy/config.example.yaml
+
 mkdir -p .runtime/data .runtime/logs
 install -d -m 0750 .runtime/postgres .runtime/redis
 cp deploy/config.example.yaml deploy/config.yaml
 sudo chown "$(id -u):10001" deploy/config.yaml
 chmod 0640 deploy/config.yaml
-```
-
-分别生成 PostgreSQL 与 Redis 密码：
-
-```bash
-openssl rand -hex 24
-openssl rand -hex 24
-```
-
-把两个结果分别写入 `deploy/config.yaml`，再设置管理员初始密码：
-
-| 配置 | 约束 |
-| --- | --- |
-| `store.database.password` | 48 位十六进制 |
-| `store.redis.password` | 48 位十六进制 |
-| `admin.default_password` | 至少 12 位，不能包含 `$` |
-
-PostgreSQL、Redis 和应用从同一份 `config.yaml` 读取基础设施密码，不需要额外导出环境变量。
-管理员密码只在首次创建管理员时生效。
-
-Linux 需要允许容器组写入运行目录：
-
-```bash
 sudo chown -R "$(id -u):10001" .runtime/data .runtime/logs
 chmod 0770 .runtime/data .runtime/logs
 ```

-### 2. 启动
+分别生成数据库和 Redis 密码：
+
+```bash
+openssl rand -hex 24
+openssl rand -hex 24
+```
+
+编辑 `deploy/config.yaml`，填好以下三项：
+
+| 配置项 | 填写内容 |
+| --- | --- |
+| `store.database.password` | 第一个生成的 48 位十六进制密码 |
+| `store.redis.password` | 第二个生成的 48 位十六进制密码 |
+| `admin.default_password` | 管理员初始密码，至少 12 位，不能包含 `$` |
+
+不需要创建 `.env`。管理员初始密码只在首次创建账号时使用。
+
+### 2. 启动服务

 ```bash
 docker compose -f deploy/compose.yaml config --quiet
 docker compose -f deploy/compose.yaml pull
-docker compose -f deploy/compose.yaml up -d --no-build
+docker compose -f deploy/compose.yaml up -d --no-build --wait
 curl -i http://127.0.0.1:8080/healthz
 ```

-`204 No Content` 表示应用、PostgreSQL 与 Redis 均可用。管理端地址为
-`http://127.0.0.1:8080`。
+健康检查返回 `204 No Content` 后，打开 `http://127.0.0.1:8080`，
+使用 `admin@cpr.local` 和刚设置的管理员密码登录。

-### 3. 初始化网关
+默认地址只能在服务器本机访问。从其他设备使用时，需要配置
+[HTTPS 反向代理](deploy/README.md#公网访问)。

-1. 使用 `admin@cpr.local` 与初始密码登录。
-2. 导入或授权 Provider 账号：OpenAI 支持 OAuth、逐行 AT/RT 与 OAuth JSON；
-   xAI 支持 OAuth 和账号 JSON。
-3. 创建账号分组并按需配置全局模型映射。未命中的模型名原样交给候选 Provider。
-4. 创建 `sk_...` Client Key，选择可用账号分组，并设置速率和并发限制；空分组范围表示全部账号。
+### 3. 添加账号和密钥

-OpenAI RT 导入会先向官方 token endpoint 换取 AT；仅 AT 的账号不具备自动续期能力，
-能否参与调度仍取决于 token 中可验证的身份与后续上游事实。账号导入和首次 OAuth 创建会尽力读取一次额度，
-额度上游暂时失败不会回滚已提交的账号。
+1. 在「账号」中添加 OpenAI 或 xAI 账号。OpenAI 支持 OAuth 授权、AT/RT 和账号 JSON；xAI 支持 OAuth 授权和账号 JSON。
+2. 按需创建账号分组，并把账号加入分组。
+3. 创建客户端密钥，选择可用分组。**不选分组表示可使用全部账号**。
+4. 点击该密钥的「使用密钥」，复制客户端配置。

-OpenAI 账号的主动重置卡只在用户打开相应弹窗或手工刷新时查询。消费成功后管理端重新查询卡片与额度；
-系统不会通过修改本地 `reset_at` 伪造重置。完整账号合同见 [账号接口](docs/api.md#5-账号)。
-
-> [!IMPORTANT]
-> xAI 使用 OAuth session，不支持把 xAI API Key 作为上游 credential。
-
-完整的权限、密码轮换、备份和升级规则见 [部署文档](deploy/README.md)。
+只导入 AT 的账号不能自动续期。xAI 暂不支持用 API Key 导入上游账号。

 ## 客户端接入

+### Codex CLI 和桌面端
+
+在「使用密钥」中按系统复制 `config.toml` 和 `auth.json`，也可以通过 CCSwitch 导入。
+已有文件先备份，再合并配置并重启 Codex。客户端使用代理密钥，OpenAI 账号登录状态由服务端管理。
+
+新配置已启用原生生图。可以直接提出需求，例如：
+
+> 帮我做一个咖啡店首页，生成一张咖啡主题配图并用到页面中。
+
+是否调用生图由 Codex 根据任务决定，也可以明确要求生成图片。需要支持生图的客户端、模型和 OpenAI 账号；
+普通对话可用不代表账号一定有生图额度。
+
+完整配置和旧版配置迁移见 [客户端配置](deploy/README.md#客户端配置)。
+
+### 其他客户端
+
+选择支持 **Responses API** 的客户端，填写：
+
 | 配置 | 值 |
 | --- | --- |
-| Base URL | `http://127.0.0.1:8080/v1` |
-| API Key | 管理端创建的 `sk_...` |
-| 鉴权 | `Authorization: Bearer <client-api-key>` |
+| Base URL | `http://127.0.0.1:8080/v1`，远程使用时换成服务器的 HTTPS 地址 |
+| API Key | 管理端创建的 `sk_...` 密钥 |
+
+可先检查密钥是否能读取模型列表：

 ```bash
 curl http://127.0.0.1:8080/v1/models \
  -H 'Authorization: Bearer <client-api-key>'
-
-curl http://127.0.0.1:8080/v1/responses \
-  -H 'Authorization: Bearer <client-api-key>' \
-  -H 'Content-Type: application/json' \
-  -d '{
-    "model": "<model-id>",
-    "input": "Reply with pong.",
-    "stream": false
-  }'
 ```

-<details>
-<summary>公开数据面路由</summary>
+接口列表与请求示例见 [接口文档](docs/api.md)。

-| 路由 | 用途 |
-| --- | --- |
-| `POST /v1/responses` | JSON 响应或 SSE Responses 流 |
-| `GET /v1/responses` | Responses WebSocket 升级 |
-| `POST /v1/responses/review` | review 子代理请求 |
-| `POST /v1/images/generations` | OpenAI Images 生成 JSON 透明转发 |
-| `POST /v1/images/edits` | OpenAI Images 编辑 JSON 透明转发 |
-| `GET /v1/models` | 当前 Client Key 账号范围内的模型列表 |
-| `GET /v1/models/catalog` | Codex 客户端展示用模型目录 |
-| `GET /v1/models/{model_id}/info` | Codex 客户端展示用模型详情 |
-| `GET /v1/models/{model_id}` | OpenAI 兼容模型详情 |
+## 常见问题

-所有 `/v1/*` 路由都需要 Client Key。Images 是 OpenAI Provider 自有端点，不读取模型字段，也不参与
-文本模型映射。
+### 仍然要求登录，或无法生成图片

-</details>
+重新从管理端复制配置，确认修改的是客户端实际读取的用户配置目录，然后完全退出并重启客户端。
+保留仅含代理密钥的 `auth.json` 不会使新配置失效。详细检查步骤见
+[登录与生图排查](deploy/README.md#登录与生图排查)。

-完整的客户端与管理端路由、鉴权、请求字段和 mutation 语义见 [接口文档](docs/api.md)。
+### 没有可用账号或模型

-## 运行维护
+检查账号是否启用、凭据是否过期、额度是否耗尽，以及密钥绑定的分组是否包含可用账号。
+「恢复账号」只清除本地错误状态，不能恢复上游权限或增加额度。
+
+### 如何更新或查看日志
+
+同一大版本内拉取发布镜像并重建应用容器：

 ```bash
-# 同一大版本内升级发布镜像
 docker compose -f deploy/compose.yaml pull codex-proxy-rs
-docker compose -f deploy/compose.yaml up -d --no-build
-
-# 查看日志
-docker compose -f deploy/compose.yaml logs -f codex-proxy-rs
-
-# 从当前源码构建
-docker compose -f deploy/compose.yaml build codex-proxy-rs
-docker compose -f deploy/compose.yaml up -d
+docker compose -f deploy/compose.yaml up -d --no-build codex-proxy-rs
+docker compose -f deploy/compose.yaml logs --tail=100 -f codex-proxy-rs
 ```

-> [!IMPORTANT]
-> `.runtime/` 保存 PostgreSQL、Redis、日志、OpenAI 会话锚点和在线更新状态。删除该目录会永久清除
-> 本地运行状态。
-
 > [!WARNING]
-> 不支持跨大版本在线升级。升级到新的大版本时请使用全新的 `.runtime/` 数据目录，并重新导入或授权
-> Provider 账号与 Client Key。
-
-Compose 默认只绑定 `127.0.0.1`。公网接入应使用 HTTPS 反向代理，转发 WebSocket upgrade 与真实客户端
-IP；不要暴露 PostgreSQL 或 Redis。当前运行拓扑为单副本，不能通过复制应用容器扩容。
-
-## 维护与发布
-
-仓库版本只能从干净、已同步上游的发布分支发布：
-
-```bash
-release/publish <version>
-```
-
-脚本依赖已登录的 GitHub CLI（`gh auth login`），会更新 `release/version.yaml`、创建约定提交和带注释的
-`v<version>` tag，原子推送分支与 tag，再触发 Release 构建。源码提交、仓库发版和运行实例升级是三个
-独立状态；脚本不会登录服务器或改变任何运行实例。
+> 升级前先备份。跨大版本需使用新的数据目录重新部署，不支持直接沿用旧库在线升级。
+> `.runtime/` 包含数据库和运行数据，请勿删除；账号文件、密钥和日志也不要公开分享。

 ## 文档

- [部署与运维](deploy/README.md)
- [客户端与管理端接口](docs/api.md)
+- [客户端接入与生图](deploy/README.md#客户端配置)
+- [部署、备份与恢复](deploy/README.md)
+- [API 参考](docs/api.md)
 - [系统架构](docs/architecture.md)
- [数据库迁移规则](backend/migrations/README.md)
- [Release](https://github.com/zyycn/codex-proxy-rs/releases)
- [容器镜像](https://github.com/zyycn/codex-proxy-rs/pkgs/container/codex-proxy-rs)
+- [管理端主题](docs/theme.md)
+- [数据库迁移](backend/migrations/README.md)
@@ -154,9 +154,9 @@ dependencies = [

 [[package]]
 name = "aws-lc-rs"
-version = "1.17.1"
+version = "1.16.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4342d8937fc7e5dd9b1c60292261c0670c882a2cd1719cfc11b1af41731e32ad"
+checksum = "a054912289d18629dc78375ba2c3726a3afe3ff71b4edba9dedfca0e3446d1fc"
 dependencies = [
 "aws-lc-sys",
 "untrusted 0.7.1",
@@ -165,15 +165,14 @@ dependencies = [

 [[package]]
 name = "aws-lc-sys"
-version = "0.42.0"
+version = "0.39.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6d9ceb1da931507a12f4fccea479dccd00da1943e1b4ae72d8e502d707361444"
+checksum = "1fa7e52a4c5c547c741610a2c6f123f3881e409b714cd27e6798ef020c514f0a"
 dependencies = [
 "cc",
 "cmake",
 "dunce",
 "fs_extra",
- "pkg-config",
 ]

 [[package]]
@@ -195,7 +194,7 @@ dependencies = [
 "bytes-utils",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 0.4.6",
 "http-body 1.0.1",
 "percent-encoding",
@@ -231,7 +230,7 @@ dependencies = [
 "hex",
 "hmac",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "lru",
 "percent-encoding",
@@ -257,7 +256,7 @@ dependencies = [
 "hex",
 "hmac",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.4.0",
 "percent-encoding",
 "sha2 0.11.0",
 "time",
@@ -286,7 +285,7 @@ dependencies = [
 "bytes",
 "crc-fast",
 "hex",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "http-body-util",
 "md-5",
@@ -320,7 +319,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "http-body-util",
 "percent-encoding",
@@ -339,7 +338,7 @@ dependencies = [
 "aws-smithy-runtime-api",
 "aws-smithy-types",
 "h2",
- "http 1.4.2",
+ "http 1.4.0",
 "hyper",
 "hyper-rustls",
 "hyper-util",
@@ -389,7 +388,7 @@ dependencies = [
 "bytes",
 "fastrand",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 0.4.6",
 "http-body 1.0.1",
 "http-body-util",
@@ -410,7 +409,7 @@ dependencies = [
 "aws-smithy-types",
 "bytes",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.4.0",
 "pin-project-lite",
 "tokio",
 "tracing",
@@ -436,7 +435,7 @@ checksum = "7d56e0a4e53127a632224e43633b0fe045fa9e1e3cfc68b9830f1115e103f910"
 dependencies = [
 "aws-smithy-runtime-api",
 "aws-smithy-types",
- "http 1.4.2",
+ "http 1.4.0",
 ]

 [[package]]
@@ -450,7 +449,7 @@ dependencies = [
 "bytes-utils",
 "futures-core",
 "http 0.2.12",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 0.4.6",
 "http-body 1.0.1",
 "http-body-util",
@@ -503,7 +502,7 @@ dependencies = [
 "bytes",
 "form_urlencoded",
 "futures-util",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "http-body-util",
 "hyper",
@@ -535,7 +534,7 @@ checksum = "08c78f31d7b1291f7ee735c1c6780ccde7785daae9a9206026862dab7d8792d1"
 dependencies = [
 "bytes",
 "futures-core",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "http-body-util",
 "mime",
@@ -954,6 +953,29 @@ dependencies = [
 "rand_core 0.10.1",
 ]

+[[package]]
+name = "cssparser"
+version = "0.37.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8c9cdaae01d5ed7882b04d795e7f752f46ff52d2fa3b50a20d28c464510bba98"
+dependencies = [
+ "cssparser-macros",
+ "dtoa-short",
+ "itoa",
+ "phf 0.13.1",
+ "smallvec",
+]
+
+[[package]]
+name = "cssparser-macros"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10a2a99df6e410a8ff4245aa2006499ea662245f967cc7c0a38c83ef8eb44dbf"
+dependencies = [
+ "quote",
+ "syn 2.0.119",
+]
+
 [[package]]
 name = "ctutils"
 version = "0.4.2"
@@ -1005,6 +1027,27 @@ version = "0.5.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7cd812cc2bc1d69d4764bd80df88b4317eaef9e773c75226407d9bc0876b211c"

+[[package]]
+name = "derive_more"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d751e9e49156b02b44f9c1815bcb94b984cdcc4396ecc32521c739452808b134"
+dependencies = [
+ "derive_more-impl",
+]
+
+[[package]]
+name = "derive_more-impl"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "799a97264921d8623a957f6c3b9011f3b5492f557bbb7a5a19b7fa6d06ba8dcb"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "rustc_version",
+ "syn 2.0.119",
+]
+
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -1053,6 +1096,21 @@ version = "0.15.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1aaf95b3e5c8f23aa320147307562d361db0ae0d51242340f558153b4eb2439b"

+[[package]]
+name = "dtoa"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c3cf4824e2d5f025c7b531afcb2325364084a16806f6d47fbc1f5fbd9960590"
+
+[[package]]
+name = "dtoa-short"
+version = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd1511a7b6a56299bd043a9c167a6d2bfb37bf84a6dfceaba651168adfb43c87"
+dependencies = [
+ "dtoa",
+]
+
 [[package]]
 name = "dunce"
 version = "1.0.5"
@@ -1074,6 +1132,12 @@ dependencies = [
 "zeroize",
 ]

+[[package]]
+name = "ego-tree"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b04dc5a38e4f151a79d9f2451ae6037fb6eaf5cba34771f44781f80e508498e3"
+
 [[package]]
 name = "either"
 version = "1.16.0"
@@ -1413,11 +1477,14 @@ name = "gateway-core"
 version = "0.1.0"
 dependencies = [
 "async-trait",
+ "base64 0.23.1",
 "bytes",
 "futures",
 "futures-timer",
+ "semver",
 "serde",
 "serde_json",
+ "sha2 0.11.0",
 "thiserror",
 "tracing",
 "uuid",
@@ -1438,6 +1505,7 @@ dependencies = [
 "gateway-core",
 "hex",
 "reqwest",
+ "scraper",
 "semver",
 "serde",
 "serde_json",
@@ -1466,6 +1534,7 @@ dependencies = [
 name = "gateway-store"
 version = "0.1.0"
 dependencies = [
+ "async-stream",
 "async-trait",
 "aws-credential-types",
 "aws-sdk-s3",
@@ -1501,6 +1570,15 @@ dependencies = [
 "version_check",
 ]

+[[package]]
+name = "getopts"
+version = "0.2.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cfe4fbac503b8d1f88e6676011885f34b7174f46e59956bba534ba83abded4df"
+dependencies = [
+ "unicode-width",
+]
+
 [[package]]
 name = "getrandom"
 version = "0.2.17"
@@ -1562,7 +1640,7 @@ dependencies = [
 "fnv",
 "futures-core",
 "futures-sink",
- "http 1.4.2",
+ "http 1.4.0",
 "indexmap",
 "slab",
 "tokio",
@@ -1610,7 +1688,7 @@ dependencies = [
 "base64 0.22.1",
 "bytes",
 "headers-core",
- "http 1.4.2",
+ "http 1.4.0",
 "httpdate",
 "mime",
 "sha1 0.10.7",
@@ -1622,7 +1700,7 @@ version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "54b4a22553d4242c49fddb9ba998a99962b5cc6f22cb5a3482bec22522403ce4"
 dependencies = [
- "http 1.4.2",
+ "http 1.4.0",
 ]

 [[package]]
@@ -1661,6 +1739,16 @@ dependencies = [
 "digest 0.11.3",
 ]

+[[package]]
+name = "html5ever"
+version = "0.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "46a1761807faccc9a19e86944bbf40610014066306f96edcdedc2fb714bcb7b8"
+dependencies = [
+ "log",
+ "markup5ever",
+]
+
 [[package]]
 name = "http"
 version = "0.2.12"
@@ -1674,9 +1762,9 @@ dependencies = [

 [[package]]
 name = "http"
-version = "1.4.2"
+version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
+checksum = "e3ba2a386d7f85a81f119ad7498ebe444d2e22c2af0b86b069416ace48b3311a"
 dependencies = [
 "bytes",
 "itoa",
@@ -1700,7 +1788,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
 dependencies = [
 "bytes",
- "http 1.4.2",
+ "http 1.4.0",
 ]

 [[package]]
@@ -1711,7 +1799,7 @@ checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
 dependencies = [
 "bytes",
 "futures-core",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "pin-project-lite",
 ]
@@ -1747,21 +1835,22 @@ dependencies = [

 [[package]]
 name = "hyper"
-version = "1.10.1"
+version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "55281c53a1894c864990125767da440a4e630446785086f52523b20033b74498"
+checksum = "2ab2d4f250c3d7b1c9fcdff1cece94ea4e2dfbec68614f7b87cb205f24ca9d11"
 dependencies = [
 "atomic-waker",
 "bytes",
 "futures-channel",
 "futures-core",
 "h2",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "httparse",
 "httpdate",
 "itoa",
 "pin-project-lite",
+ "pin-utils",
 "smallvec",
 "tokio",
 "want",
@@ -1773,7 +1862,7 @@ version = "0.27.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3c93eb611681b207e1fe55d5a71ecf91572ec8a6705cdb6857f7d8d5242cf58"
 dependencies = [
- "http 1.4.2",
+ "http 1.4.0",
 "hyper",
 "hyper-util",
 "log",
@@ -1795,7 +1884,7 @@ dependencies = [
 "bytes",
 "futures-channel",
 "futures-util",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "hyper",
 "ipnet",
@@ -2064,6 +2153,17 @@ version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154"

+[[package]]
+name = "markup5ever"
+version = "0.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7122d987ec5f704ee56f6e5b41a7d93722e9aae27ae07cafa4036c4d3f9757de"
+dependencies = [
+ "log",
+ "tendril",
+ "web_atoms",
+]
+
 [[package]]
 name = "matchers"
 version = "0.2.0"
@@ -2132,6 +2232,12 @@ dependencies = [
 "windows-sys 0.61.2",
 ]

+[[package]]
+name = "new_debug_unreachable"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
+
 [[package]]
 name = "nu-ansi-term"
 version = "0.50.3"
@@ -2283,7 +2389,7 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
 dependencies = [
- "phf_macros",
+ "phf_macros 0.11.3",
 "phf_shared 0.11.3",
 ]

@@ -2296,6 +2402,27 @@ dependencies = [
 "phf_shared 0.12.1",
 ]

+[[package]]
+name = "phf"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1562dc717473dbaa4c1f85a36410e03c047b2e7df7f45ee938fbef64ae7fadf"
+dependencies = [
+ "phf_macros 0.13.1",
+ "phf_shared 0.13.1",
+ "serde",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49aa7f9d80421bca176ca8dbfebe668cc7a2684708594ec9f3c0db0805d5d6e1"
+dependencies = [
+ "phf_generator 0.13.1",
+ "phf_shared 0.13.1",
+]
+
 [[package]]
 name = "phf_generator"
 version = "0.11.3"
@@ -2306,19 +2433,42 @@ dependencies = [
 "rand 0.8.7",
 ]

+[[package]]
+name = "phf_generator"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "135ace3a761e564ec88c03a77317a7c6b80bb7f7135ef2544dbe054243b89737"
+dependencies = [
+ "fastrand",
+ "phf_shared 0.13.1",
+]
+
 [[package]]
 name = "phf_macros"
 version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f84ac04429c13a7ff43785d75ad27569f2951ce0ffd30a3321230db2fc727216"
 dependencies = [
- "phf_generator",
+ "phf_generator 0.11.3",
 "phf_shared 0.11.3",
 "proc-macro2",
 "quote",
 "syn 2.0.119",
 ]

+[[package]]
+name = "phf_macros"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "812f032b54b1e759ccd5f8b6677695d5268c588701effba24601f6932f8269ef"
+dependencies = [
+ "phf_generator 0.13.1",
+ "phf_shared 0.13.1",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
 [[package]]
 name = "phf_shared"
 version = "0.11.3"
@@ -2337,6 +2487,15 @@ dependencies = [
 "siphasher",
 ]

+[[package]]
+name = "phf_shared"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e57fef6bc5981e38c2ce2d63bfa546861309f875b8a75f092d1d54ae2d64f266"
+dependencies = [
+ "siphasher",
+]
+
 [[package]]
 name = "pin-project-lite"
 version = "0.2.17"
@@ -2389,6 +2548,12 @@ dependencies = [
 "zerocopy",
 ]

+[[package]]
+name = "precomputed-hash"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
+
 [[package]]
 name = "primefield"
 version = "0.14.0"
@@ -2431,6 +2596,7 @@ version = "0.0.0"
 dependencies = [
 "async-stream",
 "async-trait",
+ "aws-lc-rs",
 "base64 0.23.1",
 "bytes",
 "chrono",
@@ -2442,6 +2608,7 @@ dependencies = [
 "gateway-protocol",
 "getrandom 0.4.3",
 "hex",
+ "hyper",
 "hyper-rustls",
 "reqwest",
 "roxmltree",
@@ -2457,6 +2624,7 @@ dependencies = [
 "tempfile",
 "thiserror",
 "tokio",
+ "tokio-rustls",
 "tokio-tungstenite 0.28.0",
 "tokio-util",
 "tracing",
@@ -2748,7 +2916,7 @@ dependencies = [
 "futures-core",
 "futures-util",
 "h2",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "http-body-util",
 "hyper",
@@ -2858,9 +3026,9 @@ dependencies = [

 [[package]]
 name = "rustls-native-certs"
-version = "0.8.4"
+version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dab5152771c58876a2146916e53e35057e1a4dfa2b9df0f0305b07f611fdea4d"
+checksum = "612460d5f7bea540c490b2b6395d8e34a953e52b491accd6c86c8164c5932a63"
 dependencies = [
 "openssl-probe",
 "rustls-pki-types",
@@ -2870,9 +3038,9 @@ dependencies = [

 [[package]]
 name = "rustls-pki-types"
-version = "1.15.1"
+version = "1.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2f4925028c7eb5d1fcdaf196971378ed9d2c1c4efc7dc5d011256f76c99c0a96"
+checksum = "be040f8b0a225e40375822a563fa9524378b9d63112f53e19ffff34df5d33fdd"
 dependencies = [
 "web-time",
 "zeroize",
@@ -2917,6 +3085,21 @@ version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"

+[[package]]
+name = "scraper"
+version = "0.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bdd0be4d296f048bfb06dd01bbc80ef789ddd2e55583e8d2e6b804942abfabc2"
+dependencies = [
+ "cssparser",
+ "ego-tree",
+ "getopts",
+ "html5ever",
+ "precomputed-hash",
+ "selectors",
+ "tendril",
+]
+
 [[package]]
 name = "sec1"
 version = "0.8.1"
@@ -2964,6 +3147,25 @@ dependencies = [
 "libc",
 ]

+[[package]]
+name = "selectors"
+version = "0.38.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8adfa1c298912827b8a28b223b3b874357397ae706e6190acd9bf28cee99114d"
+dependencies = [
+ "bitflags",
+ "cssparser",
+ "derive_more",
+ "log",
+ "new_debug_unreachable",
+ "phf 0.13.1",
+ "phf_codegen",
+ "precomputed-hash",
+ "rustc-hash",
+ "servo_arc",
+ "smallvec",
+]
+
 [[package]]
 name = "semver"
 version = "1.0.28"
@@ -3047,6 +3249,15 @@ dependencies = [
 "serde",
 ]

+[[package]]
+name = "servo_arc"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "170fb83ab34de17dc69aa7c67482b22218ddb85da56546f9bd6b929e32a05930"
+dependencies = [
+ "stable_deref_trait",
+]
+
 [[package]]
 name = "sha1"
 version = "0.10.7"
@@ -3386,6 +3597,30 @@ version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"

+[[package]]
+name = "string_cache"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a18596f8c785a729f2819c0f6a7eae6ebeebdfffbfe4214ae6b087f690e31901"
+dependencies = [
+ "new_debug_unreachable",
+ "parking_lot",
+ "phf_shared 0.13.1",
+ "precomputed-hash",
+]
+
+[[package]]
+name = "string_cache_codegen"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "585635e46db231059f76c5849798146164652513eb9e8ab2685939dd90f29b69"
+dependencies = [
+ "phf_generator 0.13.1",
+ "phf_shared 0.13.1",
+ "proc-macro2",
+ "quote",
+]
+
 [[package]]
 name = "stringprep"
 version = "0.1.5"
@@ -3469,12 +3704,21 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
 "fastrand",
- "getrandom 0.4.3",
+ "getrandom 0.3.4",
 "once_cell",
 "rustix",
 "windows-sys 0.61.2",
 ]

+[[package]]
+name = "tendril"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5fed54709c5b3a53d09bb1c113ea4f5ceafd1e772ddcb0030a82e1d56c087b08"
+dependencies = [
+ "new_debug_unreachable",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.20"
@@ -3561,9 +3805,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"

 [[package]]
 name = "tokio"
-version = "1.53.1"
+version = "1.52.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "202caea871b69668250d242070849eb495be178ed697a3e98aebce5bc81a0bed"
+checksum = "8fc7f01b389ac15039e4dc9531aa973a135d7a4135281b12d7c1bc79fd57fffe"
 dependencies = [
 "bytes",
 "libc",
@@ -3673,7 +3917,7 @@ dependencies = [
 "bitflags",
 "bytes",
 "futures-util",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "pin-project-lite",
 "tower",
@@ -3692,7 +3936,7 @@ dependencies = [
 "bytes",
 "futures-core",
 "futures-util",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body 1.0.1",
 "http-body-util",
 "http-range-header",
@@ -3824,7 +4068,7 @@ dependencies = [
 "data-encoding",
 "flate2",
 "headers",
- "http 1.4.2",
+ "http 1.4.0",
 "httparse",
 "log",
 "rand 0.9.4",
@@ -3843,7 +4087,7 @@ checksum = "6c01152af293afb9c7c2a57e4b559c5620b421f6d133261c60dd2d0cdb38e6b8"
 dependencies = [
 "bytes",
 "data-encoding",
- "http 1.4.2",
+ "http 1.4.0",
 "httparse",
 "log",
 "rand 0.9.4",
@@ -3890,6 +4134,12 @@ version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7df058c713841ad818f1dc5d3fd88063241cc61f49f5fbea4b951e8cf5a8d71d"

+[[package]]
+name = "unicode-width"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
+
 [[package]]
 name = "untrusted"
 version = "0.7.1"
@@ -4074,10 +4324,22 @@ dependencies = [
 ]

 [[package]]
-name = "webpki-roots"
-version = "1.0.8"
+name = "web_atoms"
+version = "0.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf85cb06032201fa7c6f829d7db5a7e5aa45bcc0655327713065f6f0576731bf"
+checksum = "ba8b815c1b593dc0baf78dd0f4fc8fdb2de53198fb1163738093e9a311c33fb3"
+dependencies = [
+ "phf 0.13.1",
+ "phf_codegen",
+ "string_cache",
+ "string_cache_codegen",
+]
+
+[[package]]
+name = "webpki-roots"
+version = "1.0.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "12bed680863276c63889429bfd6cab3b99943659923822de1c8a39c49e4d722c"
 dependencies = [
 "rustls-pki-types",
 ]
@@ -4279,7 +4541,7 @@ dependencies = [
 "base64 0.22.1",
 "deadpool",
 "futures",
- "http 1.4.2",
+ "http 1.4.0",
 "http-body-util",
 "hyper",
 "hyper-util",
@@ -26,7 +26,7 @@ tokio = { version = "1.52.3", default-features = false, features = ["rt-multi-th
 [dev-dependencies]
 config = { version = "0.15.23", default-features = false, features = ["yaml"] }
 serde_json = "1"
-syn = { version = "3.0.3", features = ["full"] }
+syn = { version = "3.0.3", features = ["full", "visit"] }
 tempfile = "3.27.0"

 [lints]
@@ -79,6 +79,7 @@ pub async fn run() -> Result<(), BootstrapError> {
        vec![openai.admin_provider(), xai.admin_provider()],
        core.snapshot_control(),
        core.account_probe(),
+        host.client_distribution_resolver(),
        host.system_operations(),
    )
    .await?;
@@ -1,6 +1,6 @@
 use std::{env, error::Error, io};

-use provider_openai::transport::tls::ensure_rustls_provider;
+use provider_openai::ensure_rustls_provider;

 fn main() -> Result<(), Box<dyn Error + Send + Sync>> {
    ensure_rustls_provider();
@@ -1,12 +1,15 @@
 //! docs/architecture.md 依赖 DAG 与生产源码纪律的 workspace 级机器校验。

 use std::{
+    collections::{BTreeMap, BTreeSet},
    fs,
    path::{Path, PathBuf},
 };

+use syn::{Item, visit::Visit};
+
 /// workspace 成员冻结清单;新增 crate 必须同步扩展本文件的依赖规则。
-const WORKSPACE_MEMBERS: &[&str] = &[
+pub(super) const WORKSPACE_MEMBERS: &[&str] = &[
    "apps/gateway",
    "crates/gateway-admin",
    "crates/gateway-api",
@@ -58,6 +61,82 @@ fn gateway_core_depends_on_no_http_db_redis_or_provider_crate() {
    );
 }

+#[test]
+fn core_value_owners_do_not_depend_on_execution_or_routing() {
+    let root = backend_root().join("crates/gateway-core/src");
+    for relative in super::rust_files(&root) {
+        let allowed: Option<&[&str]> = match relative.to_str().expect("source path") {
+            "validation.rs" => Some(&[]),
+            "identity.rs" => Some(&["validation"]),
+            "upstream.rs" => Some(&["validation"]),
+            "event.rs" => Some(&["metering", "operation", "upstream", "validation"]),
+            "account/store.rs" => Some(&["account", "error", "identity", "validation"]),
+            path if path.starts_with("policy/") => Some(&["account", "policy", "validation"]),
+            path if path.starts_with("account/") => Some(&["account", "identity", "validation"]),
+            _ => None,
+        };
+        let Some(allowed) = allowed else { continue };
+        let source = fs::read_to_string(root.join(&relative)).expect("read core source");
+        let syntax = syn::parse_file(&source).expect("parse core source");
+        let mut references = CrateReferences::default();
+        references.visit_file(&syntax);
+        for dependency in references.0 {
+            assert!(
+                allowed.contains(&dependency.as_str()),
+                "{} must not depend on crate::{dependency}",
+                relative.display()
+            );
+        }
+    }
+}
+
+#[derive(Default)]
+struct CrateReferences(BTreeSet<String>);
+
+impl<'ast> Visit<'ast> for CrateReferences {
+    fn visit_path(&mut self, path: &'ast syn::Path) {
+        let mut segments = path.segments.iter();
+        if segments
+            .next()
+            .is_some_and(|segment| segment.ident == "crate")
+            && let Some(owner) = segments.next()
+        {
+            self.0.insert(owner.ident.to_string());
+        }
+        syn::visit::visit_path(self, path);
+    }
+
+    fn visit_item_use(&mut self, item: &'ast syn::ItemUse) {
+        self.use_tree(&item.tree, false);
+    }
+}
+
+impl CrateReferences {
+    fn use_tree(&mut self, tree: &syn::UseTree, crate_root: bool) {
+        match tree {
+            syn::UseTree::Path(path) if crate_root => {
+                self.0.insert(path.ident.to_string());
+            }
+            syn::UseTree::Name(name) if crate_root => {
+                self.0.insert(name.ident.to_string());
+            }
+            syn::UseTree::Rename(rename) if crate_root => {
+                self.0.insert(rename.ident.to_string());
+            }
+            syn::UseTree::Path(path) => self.use_tree(&path.tree, path.ident == "crate"),
+            syn::UseTree::Group(group) => {
+                for item in &group.items {
+                    self.use_tree(item, crate_root);
+                }
+            }
+            syn::UseTree::Glob(_) if crate_root => {
+                self.0.insert("*".to_owned());
+            }
+            _ => {}
+        }
+    }
+}
+
 #[test]
 fn gateway_protocol_has_no_workspace_dependencies() {
    for name in dependency_names("crates/gateway-protocol") {
@@ -95,6 +174,36 @@ const PACKAGE_TO_MEMBER: &[(&str, &str)] = &[
    ("provider-xai", "crates/providers/xai"),
 ];

+/// Adapter/provider 根门面的稳定合同模块；任何增减都必须同步完成边界审计。
+const ADAPTER_PUBLIC_MODULES: &[(&str, &[&str])] = &[
+    ("crates/gateway-api", &["admin", "openai"]),
+    (
+        "crates/gateway-host",
+        &[
+            "client_distribution",
+            "config",
+            "serve",
+            "system_update",
+            "workers",
+        ],
+    ),
+    ("crates/gateway-store", &["backup", "postgres", "redis"]),
+    (
+        "crates/providers/openai",
+        &["config", "credential", "transport"],
+    ),
+    (
+        "crates/providers/xai",
+        &["config", "credential", "transport"],
+    ),
+];
+
+/// 不对应单一生产模块、而是校验 crate/workspace 整体契约的根级测试场景。
+const ROOT_TEST_SCENARIOS: &[(&str, &[&str])] = &[
+    ("apps/gateway", &["architecture"]),
+    ("crates/gateway-api", &["architecture"]),
+];
+
 /// 冻结的 workspace 内部运行时依赖边；新增/删除任何边都必须同步本表。
 const ALLOWED_INTERNAL_EDGES: &[(&str, &str)] = &[
    ("codex-proxy-rs", "gateway-admin"),
@@ -123,6 +232,46 @@ const ALLOWED_INTERNAL_EDGES: &[(&str, &str)] = &[
 #[test]
 fn workspace_internal_dependency_edges_match_frozen_dag() {
    let metadata = cargo_metadata_json();
+    let actual = workspace_runtime_dependency_edges(&metadata);
+    let mut expected: Vec<(String, String)> = ALLOWED_INTERNAL_EDGES
+        .iter()
+        .map(|(from, to)| ((*from).to_owned(), (*to).to_owned()))
+        .collect();
+    expected.sort();
+
+    assert_eq!(
+        actual, expected,
+        "workspace internal dependency edges diverged from the frozen DAG"
+    );
+}
+
+#[test]
+fn runtime_dependency_edges_exclude_dev_build_and_external_dependencies() {
+    let metadata = serde_json::json!({
+        "packages": [
+            {
+                "name": "gateway-api",
+                "dependencies": [
+                    { "name": "gateway-core", "kind": null },
+                    { "name": "gateway-store", "kind": "dev" },
+                    { "name": "gateway-host", "kind": "build" },
+                    { "name": "serde", "kind": null }
+                ]
+            },
+            {
+                "name": "external-package",
+                "dependencies": [{ "name": "gateway-core", "kind": null }]
+            }
+        ]
+    });
+
+    assert_eq!(
+        workspace_runtime_dependency_edges(&metadata),
+        vec![("gateway-api".to_owned(), "gateway-core".to_owned())]
+    );
+}
+
+fn workspace_runtime_dependency_edges(metadata: &serde_json::Value) -> Vec<(String, String)> {
    let packages = metadata["packages"]
        .as_array()
        .expect("cargo metadata packages");
@@ -140,31 +289,43 @@ fn workspace_internal_dependency_edges_match_frozen_dag() {
            if !internal_names.contains(dep_name) {
                continue;
            }
-            let is_runtime_edge = dependency["dep_kinds"]
-                .as_array()
-                .map(|kinds| {
-                    kinds
-                        .iter()
-                        .any(|kind| kind["kind"].as_str() == Some("normal"))
-                })
-                .unwrap_or(true);
-            if is_runtime_edge {
+            if dependency.get("kind").expect("dependency kind").is_null() {
                actual.push((name.to_owned(), dep_name.to_owned()));
            }
        }
    }

-    let mut expected: Vec<(String, String)> = ALLOWED_INTERNAL_EDGES
-        .iter()
-        .map(|(from, to)| ((*from).to_owned(), (*to).to_owned()))
-        .collect();
    actual.sort();
-    expected.sort();
+    actual
+}

-    assert_eq!(
-        actual, expected,
-        "workspace internal dependency edges diverged from the frozen DAG"
-    );
+#[test]
+fn adapter_public_module_surfaces_match_allowlist() {
+    for (member, allowed) in ADAPTER_PUBLIC_MODULES {
+        let root = backend_root().join(member).join("src/lib.rs");
+        let source = fs::read_to_string(&root).expect("read adapter crate root");
+        let syntax = syn::parse_file(&source).expect("parse adapter crate root");
+        let actual = syntax
+            .items
+            .iter()
+            .filter_map(|item| match item {
+                Item::Mod(module) if matches!(module.vis, syn::Visibility::Public(_)) => {
+                    Some(module.ident.to_string())
+                }
+                _ => None,
+            })
+            .collect::<BTreeSet<_>>();
+        let expected = allowed
+            .iter()
+            .map(|module| (*module).to_owned())
+            .collect::<BTreeSet<_>>();
+        assert_eq!(
+            actual,
+            expected,
+            "{} public module surface diverged from its allowlist",
+            root.display()
+        );
+    }
 }

 #[test]
@@ -185,7 +346,192 @@ fn production_sources_do_not_host_tests() {
    }
 }

-fn backend_root() -> PathBuf {
+#[test]
+fn workspace_modules_follow_conventional_file_layout() {
+    for member in WORKSPACE_MEMBERS {
+        let member_root = backend_root().join(member);
+        assert_module_tree(&member_root.join("src"), &["lib.rs", "main.rs"]);
+
+        let tests = member_root.join("tests");
+        if tests.is_dir() {
+            assert_module_tree(&tests, &["main.rs"]);
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+enum ModuleLayout {
+    File,
+    Directory,
+}
+
+#[test]
+fn integration_tests_mirror_production_module_tree() {
+    for member in WORKSPACE_MEMBERS {
+        let member_root = backend_root().join(member);
+        let tests_root = member_root.join("tests");
+        if !tests_root.is_dir() {
+            continue;
+        }
+
+        let production = module_layouts(&member_root.join("src"), &["lib.rs", "main.rs"]);
+        let tests = module_layouts(&tests_root, &["main.rs"]);
+        for (module, test_layout) in tests {
+            if module == Path::new("support") {
+                continue;
+            }
+
+            if let Some(production_layout) = production.get(&module) {
+                assert_eq!(
+                    test_layout,
+                    *production_layout,
+                    "{} must mirror the production module layout for {}",
+                    tests_root.join(module.with_extension("rs")).display(),
+                    member_root.join("src").join(&module).display(),
+                );
+                continue;
+            }
+
+            let has_production_owner = module
+                .parent()
+                .into_iter()
+                .flat_map(Path::ancestors)
+                .take_while(|ancestor| !ancestor.as_os_str().is_empty())
+                .any(|ancestor| production.contains_key(ancestor));
+            assert!(
+                has_production_owner || root_test_scenario_allowed(member, &module),
+                "{} has no mirrored production module owner",
+                tests_root.join(module.with_extension("rs")).display(),
+            );
+        }
+    }
+}
+
+fn module_layouts(root: &Path, crate_roots: &[&str]) -> BTreeMap<PathBuf, ModuleLayout> {
+    super::rust_files(root)
+        .into_iter()
+        .filter(|relative| {
+            !crate_roots
+                .iter()
+                .any(|candidate| relative == Path::new(candidate))
+        })
+        .map(|relative| {
+            if relative.file_name().and_then(|value| value.to_str()) == Some("mod.rs") {
+                (
+                    relative.parent().expect("mod.rs parent").to_path_buf(),
+                    ModuleLayout::Directory,
+                )
+            } else {
+                (relative.with_extension(""), ModuleLayout::File)
+            }
+        })
+        .collect()
+}
+
+fn root_test_scenario_allowed(member: &str, module: &Path) -> bool {
+    let Some(module) = module.to_str() else {
+        return false;
+    };
+    ROOT_TEST_SCENARIOS
+        .iter()
+        .any(|(candidate, scenarios)| *candidate == member && scenarios.contains(&module))
+}
+
+fn assert_module_tree(root: &Path, crate_roots: &[&str]) {
+    let files = super::rust_files(root);
+    for relative in &files {
+        if crate_roots
+            .iter()
+            .any(|candidate| relative == Path::new(candidate))
+        {
+            continue;
+        }
+
+        let file_name = relative
+            .file_name()
+            .and_then(|value| value.to_str())
+            .expect("Rust source file name");
+        let parent = relative.parent().expect("Rust source parent");
+        let module_name = if file_name == "mod.rs" {
+            parent
+                .file_name()
+                .and_then(|value| value.to_str())
+                .expect("mod.rs module name")
+        } else {
+            relative
+                .file_stem()
+                .and_then(|value| value.to_str())
+                .expect("Rust source module name")
+        };
+
+        if file_name != "mod.rs" {
+            assert_ne!(
+                parent.file_name().and_then(|value| value.to_str()),
+                Some(module_name),
+                "{} repeats its parent module name",
+                root.join(relative).display()
+            );
+            let child_directory = relative.with_extension("");
+            assert!(
+                !files
+                    .iter()
+                    .any(|candidate| candidate.starts_with(&child_directory)),
+                "{} mixes a leaf module with a same-name module directory",
+                root.join(relative).display()
+            );
+        }
+
+        let declaration_parents = if parent.as_os_str().is_empty()
+            || (file_name == "mod.rs"
+                && parent
+                    .parent()
+                    .is_some_and(|ancestor| ancestor.as_os_str().is_empty()))
+        {
+            crate_roots
+                .iter()
+                .map(|candidate| root.join(candidate))
+                .collect::<Vec<_>>()
+        } else {
+            let declaration_directory = if file_name == "mod.rs" {
+                parent.parent().expect("nested mod.rs parent")
+            } else {
+                parent
+            };
+            vec![root.join(declaration_directory).join("mod.rs")]
+        };
+        let declaration_count = declaration_parents
+            .iter()
+            .map(|path| external_module_declaration_count(path, module_name))
+            .sum::<usize>();
+        assert_eq!(
+            declaration_count,
+            1,
+            "{} must be declared exactly once by its parent module",
+            root.join(relative).display()
+        );
+    }
+}
+
+fn external_module_declaration_count(path: &Path, module_name: &str) -> usize {
+    if !path.is_file() {
+        return 0;
+    }
+    let source = fs::read_to_string(path).expect("read parent module source");
+    let syntax = syn::parse_file(&source).expect("parse parent module source");
+    syntax
+        .items
+        .iter()
+        .filter(|item| {
+            matches!(
+                item,
+                Item::Mod(module)
+                    if module.content.is_none() && module.ident == module_name
+            )
+        })
+        .count()
+}
+
+pub(super) fn backend_root() -> PathBuf {
    Path::new(env!("CARGO_MANIFEST_DIR"))
        .join("../..")
        .canonicalize()
@@ -143,10 +143,7 @@ fn config_loader_should_reject_removed_fingerprint_section() {

 #[test]
 fn config_loader_should_reject_invalid_codex_cli_version() {
-    assert_rejected(valid_config().replace(
-        "codex_version: '0.151.0-alpha.7.2'",
-        "codex_version: 'latest'",
-    ));
+    assert_rejected(valid_config().replace("codex_version: '0.153.4'", "codex_version: 'latest'"));
 }

 #[test]
@@ -165,7 +162,7 @@ fn config_loader_should_reject_zero_server_port() {

 #[test]
 fn config_loader_should_reject_invalid_desktop_profile_fields() {
-    assert_rejected(valid_config().replace("desktop_build: '7377'", "desktop_build: 'build'"));
+    assert_rejected(valid_config().replace("desktop_build: '8109'", "desktop_build: 'build'"));
 }

 fn assert_rejected(config: String) {
@@ -43,31 +43,33 @@ fn cargo_library_root_is_conventional_lib() {
 }

 #[test]
-fn production_files_have_no_hidden_modules_or_test_hooks() {
-    let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("src");
-    for relative in ["bootstrap.rs", "lib.rs", "main.rs"] {
-        let path = root.join(relative);
-        let source = fs::read_to_string(&path).expect("read production source");
-        assert!(
-            !source.contains("include!("),
-            "{} uses include!",
-            path.display()
-        );
-        let syntax = syn::parse_file(&source).expect("parse production source");
-        for item in &syntax.items {
-            if let Item::Mod(module) = item {
-                assert!(
-                    module.content.is_none(),
-                    "{} has an inline module",
-                    path.display()
-                );
-            }
-            for attribute in item_attrs(item) {
-                assert!(
-                    !is_path_or_test_cfg(attribute),
-                    "{} has a production test/path hook",
-                    path.display(),
-                );
+fn workspace_production_files_have_no_hidden_modules_or_test_hooks() {
+    for member in architecture::WORKSPACE_MEMBERS {
+        let root = architecture::backend_root().join(member).join("src");
+        for relative in rust_files(&root) {
+            let path = root.join(relative);
+            let source = fs::read_to_string(&path).expect("read production source");
+            assert!(
+                !source.contains("include!("),
+                "{} uses include!",
+                path.display()
+            );
+            let syntax = syn::parse_file(&source).expect("parse production source");
+            for item in &syntax.items {
+                if let Item::Mod(module) = item {
+                    assert!(
+                        module.content.is_none(),
+                        "{} has an inline module",
+                        path.display()
+                    );
+                }
+                for attribute in item_attrs(item) {
+                    assert!(
+                        !is_path_or_test_cfg(attribute),
+                        "{} has a production test/path hook",
+                        path.display(),
+                    );
+                }
            }
        }
    }
@@ -22,6 +22,7 @@ gateway-core = { path = "../gateway-core" }
 hex = "0.4.3"
 rand_core = { version = "0.6.4", features = ["getrandom"] }
 serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 secrecy = { version = "0.10.3", features = ["serde"] }
 subtle = "2.6.1"
 thiserror = "2.0.18"
@@ -32,7 +33,6 @@ chrono-tz = "0.10"
 tokio = { version = "1.52", features = ["rt", "time", "macros", "sync"] }

 [dev-dependencies]
-serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 sha2 = "0.11"
 tempfile = "3"
 tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt"] }
@@ -9,7 +9,7 @@ use std::time::Duration;
 use chrono::{DateTime, Utc};
 use futures::future::BoxFuture;
 use gateway_core::{
-    engine::CancellationToken,
+    lifecycle::CancellationToken,
    task::{DaemonTask, WorkerTaskError},
 };
 use tracing::{info, warn};
@@ -6,7 +6,8 @@ use std::{fmt, path::Path, sync::Arc, time::Duration};

 use gateway_core::{
    engine::probe::AccountProbe,
-    routing::{ProviderKind, snapshot::SnapshotControl},
+    routing::ProviderKind,
+    runtime::SnapshotControl,
    task::{
        DaemonRestartPolicy, WorkerContribution, WorkerId, WorkerKind, WorkerRegistration,
        WorkerRunnable,
@@ -22,19 +23,22 @@ mod use_case;

 pub use use_case::{
    account_groups::AccountGroupService, accounts::AccountsService, auth::AuthService,
-    backup::BackupService, client_keys::ClientKeyService, observability::ObservabilityService,
-    openai::OpenAiService, settings::SettingsService, system::SystemService, xai::XaiService,
+    backup::BackupService, client_distribution::ClientDistributionService,
+    client_keys::ClientKeyService, observability::ObservabilityService, openai::OpenAiService,
+    settings::SettingsService, system::SystemService, xai::XaiService,
 };

 use model::{AdminError, AdminErrorKind};
 use ports::{
+    client_distribution::ClientDistributionResolver,
    provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind, ProviderAdminRegistry},
    store::AdminStorePorts,
    system::SystemOperations,
 };
 use use_case::{
    account_groups::DefaultAccountGroupService, accounts::DefaultAccountsService,
-    auth::DefaultAuthService, backup::DefaultBackupService, client_keys::DefaultClientKeyService,
+    auth::DefaultAuthService, backup::DefaultBackupService,
+    client_distribution::DefaultClientDistributionService, client_keys::DefaultClientKeyService,
    observability::DefaultObservabilityService, openai::DefaultOpenAiService,
    settings::DefaultSettingsService, system::DefaultSystemService, xai::DefaultXaiService,
 };
@@ -149,6 +153,7 @@ pub struct AdminServices {
    accounts: Arc<dyn AccountsService>,
    account_groups: Arc<dyn AccountGroupService>,
    client_keys: Arc<dyn ClientKeyService>,
+    client_distribution: Arc<dyn ClientDistributionService>,
    observability: Arc<dyn ObservabilityService>,
    settings: Arc<dyn SettingsService>,
    system: Arc<dyn SystemService>,
@@ -178,6 +183,11 @@ impl AdminServices {
        self.client_keys.as_ref()
    }

+    #[must_use]
+    pub fn client_distribution(&self) -> &dyn ClientDistributionService {
+        self.client_distribution.as_ref()
+    }
+
    #[must_use]
    pub fn observability(&self) -> &dyn ObservabilityService {
        self.observability.as_ref()
@@ -238,6 +248,7 @@ pub async fn initialize(
    providers: Vec<Arc<dyn ProviderAdmin>>,
    snapshot: Arc<dyn SnapshotControl>,
    probe: Arc<dyn AccountProbe>,
+    client_distribution: Arc<dyn ClientDistributionResolver>,
    system: Arc<dyn SystemOperations>,
 ) -> Result<AdminBundle, AdminError> {
    config
@@ -290,8 +301,10 @@ pub async fn initialize(
            store.client_keys(),
            snapshot.clone(),
        )),
+        client_distribution: Arc::new(DefaultClientDistributionService::new(client_distribution)),
        observability: Arc::new(DefaultObservabilityService::new(
            store.observability(),
+            store.accounts(),
            store.settings(),
            registry,
        )),
@@ -3,7 +3,7 @@
 use std::collections::BTreeMap;

 use chrono::{DateTime, Utc};
-use gateway_core::{engine::credential::AccountStatusFacts, routing::AccountGroupId};
+use gateway_core::{account::AccountStatusFacts, routing::AccountGroupId};

 use super::{PageSize, Revision, observability::DecimalAmount};

@@ -6,14 +6,13 @@ use chrono::{DateTime, Utc};
 use futures::Stream;

 use gateway_core::{
-    engine::{UpstreamSendState, probe::AccountProbeErrorSource},
-    error::GatewayErrorKind,
-    routing::ProviderKind,
+    engine::probe::AccountProbeErrorSource, error::GatewayErrorKind, routing::ProviderKind,
+    upstream::UpstreamSendState,
 };

 use super::{PageSize, Revision, account_groups::AccountGroupRef, observability::TimeRange};

-pub use gateway_core::engine::credential::{
+pub use gateway_core::account::{
    AccountConcurrencyLimit, AccountErrorReason, AccountStatus, AccountStatusFacts,
    AccountStatusProjection, AccountWeight, CredentialState, QuotaAccessState, QuotaEvidence,
    QuotaState, resolve_account_status,
@@ -218,7 +217,7 @@ pub struct UpdateAccount {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountUpdateResult {
    pub config_revision: Revision,
-    pub account_id: gateway_core::engine::credential::ProviderAccountId,
+    pub account_id: gateway_core::account::ProviderAccountId,
 }

 /// 一批账号可编辑事实的一次性替换命令。
@@ -235,7 +234,7 @@ pub struct BatchUpdateAccounts {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountsUpdateResult {
    pub config_revision: Revision,
-    pub account_ids: Vec<gateway_core::engine::credential::ProviderAccountId>,
+    pub account_ids: Vec<gateway_core::account::ProviderAccountId>,
 }

 /// 账号批量删除命令。
@@ -4,6 +4,12 @@ use chrono::{DateTime, Utc};

 use super::{MutationActor, MutationContext, Revision};

+/// 会话审计使用的稳定管理员标识。
+#[must_use]
+pub fn admin_session_actor_ref(admin_user_id: &str) -> String {
+    format!("admin:{admin_user_id}")
+}
+
 /// 已认证的管理主体。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum AdminPrincipal {
@@ -0,0 +1,34 @@
+//! 备份领域的稳定错误码。
+
+/// 配置或参数非法。
+pub const INVALID_CONFIG: &str = "backup.invalid_config";
+/// Cron 表达式非法。
+pub const INVALID_CRON: &str = "backup.invalid_cron";
+/// IANA 时区非法。
+pub const INVALID_TIMEZONE: &str = "backup.invalid_timezone";
+/// 记录不存在。
+pub const RECORD_NOT_FOUND: &str = "backup.record_not_found";
+/// 已存在活跃任务，拒绝创建。
+pub const ACTIVE_TASK_CONFLICT: &str = "backup.active_task_conflict";
+/// 记录状态与期望不符，无法迁移。
+pub const STATE_CONFLICT: &str = "backup.state_conflict";
+/// 已有记录时禁止切换存储目标。
+pub const STORAGE_IDENTITY_LOCKED: &str = "backup.storage_identity_locked";
+/// `pg_dump` 非零退出或失败。
+pub const PG_DUMP_FAILED: &str = "backup.pg_dump_failed";
+/// 暂存磁盘空间不足。
+pub const STAGING_SPACE_EXHAUSTED: &str = "backup.staging_space_exhausted";
+/// S3 认证失败。
+pub const S3_AUTH_FAILED: &str = "backup.s3_auth_failed";
+/// S3 权限拒绝。
+pub const S3_PERMISSION_DENIED: &str = "backup.s3_permission_denied";
+/// S3 上传失败。
+pub const S3_UPLOAD_FAILED: &str = "backup.s3_upload_failed";
+/// 远端对象校验失败。
+pub const REMOTE_VERIFICATION_FAILED: &str = "backup.remote_verification_failed";
+/// 任务被取消。
+pub const CANCELLED: &str = "backup.cancelled";
+/// 仓储或对象存储暂不可用。
+pub const STORE_UNAVAILABLE: &str = "backup.store_unavailable";
+/// 上游 S3 服务返回无效或失败响应。
+pub const UPSTREAM_FAILURE: &str = "backup.upstream_failure";
@@ -447,40 +447,7 @@ impl BackupError {
 }

 /// 构造稳定错误码常量。
-pub mod code {
-    /// 配置或参数非法。
-    pub const INVALID_CONFIG: &str = "backup.invalid_config";
-    /// Cron 表达式非法。
-    pub const INVALID_CRON: &str = "backup.invalid_cron";
-    /// IANA 时区非法。
-    pub const INVALID_TIMEZONE: &str = "backup.invalid_timezone";
-    /// 记录不存在。
-    pub const RECORD_NOT_FOUND: &str = "backup.record_not_found";
-    /// 已存在活跃任务，拒绝创建。
-    pub const ACTIVE_TASK_CONFLICT: &str = "backup.active_task_conflict";
-    /// 记录状态与期望不符，无法迁移。
-    pub const STATE_CONFLICT: &str = "backup.state_conflict";
-    /// 已有记录时禁止切换存储目标。
-    pub const STORAGE_IDENTITY_LOCKED: &str = "backup.storage_identity_locked";
-    /// `pg_dump` 非零退出或失败。
-    pub const PG_DUMP_FAILED: &str = "backup.pg_dump_failed";
-    /// 暂存磁盘空间不足。
-    pub const STAGING_SPACE_EXHAUSTED: &str = "backup.staging_space_exhausted";
-    /// S3 认证失败。
-    pub const S3_AUTH_FAILED: &str = "backup.s3_auth_failed";
-    /// S3 权限拒绝。
-    pub const S3_PERMISSION_DENIED: &str = "backup.s3_permission_denied";
-    /// S3 上传失败。
-    pub const S3_UPLOAD_FAILED: &str = "backup.s3_upload_failed";
-    /// 远端对象校验失败。
-    pub const REMOTE_VERIFICATION_FAILED: &str = "backup.remote_verification_failed";
-    /// 任务被取消。
-    pub const CANCELLED: &str = "backup.cancelled";
-    /// 仓储或对象存储暂不可用。
-    pub const STORE_UNAVAILABLE: &str = "backup.store_unavailable";
-    /// 上游 S3 服务返回无效或失败响应。
-    pub const UPSTREAM_FAILURE: &str = "backup.upstream_failure";
-}
+pub mod code;

 /// 构建对象 key：`{prefix}/YYYY/MM/DD/codex-proxy-rs_{UTC seconds}_{backup id}.dump`。
 ///
@@ -0,0 +1,58 @@
+//! 管理设置页使用的 Codex 客户端下载信息。
+
+use chrono::{DateTime, Utc};
+
+/// Windows 安装包架构。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
+pub enum ClientArchitecture {
+    X64,
+    Arm64,
+}
+
+impl ClientArchitecture {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::X64 => "x64",
+            Self::Arm64 => "arm64",
+        }
+    }
+}
+
+/// 下载地址的可信来源。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ClientDownloadSource {
+    MicrosoftStore,
+    OfficialOpenAi,
+}
+
+impl ClientDownloadSource {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::MicrosoftStore => "microsoft_store",
+            Self::OfficialOpenAi => "official_openai",
+        }
+    }
+}
+
+/// 一个已经过 Host 校验、可以直接交给浏览器下载的安装包。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ClientDownloadPackage {
+    pub architecture: ClientArchitecture,
+    pub source: ClientDownloadSource,
+    pub version: Option<String>,
+    pub file_name: String,
+    pub size_bytes: Option<u64>,
+    pub download_url: String,
+    pub expires_at: Option<DateTime<Utc>>,
+}
+
+/// Codex Desktop Windows 下载解析结果。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct CodexDesktopWindowsDownloads {
+    pub resolved_at: DateTime<Utc>,
+    pub cached: bool,
+    pub warning: Option<String>,
+    pub packages: Vec<ClientDownloadPackage>,
+}
@@ -6,6 +6,7 @@ pub mod account_groups;
 pub mod accounts;
 pub mod auth;
 pub mod backup;
+pub mod client_distribution;
 pub mod client_keys;
 pub mod observability;
 pub mod provider_credentials;
@@ -135,13 +135,11 @@ pub struct OpsErrorFilter {
    pub provider_kind: Option<String>,
    pub provider_account_ref: Option<String>,
    pub operation: Option<String>,
-    pub endpoint: Option<String>,
    pub model: Option<String>,
    pub transport: Option<String>,
    pub attempt_index: Option<u32>,
    pub response_id: Option<String>,
    pub upstream_request_id: Option<String>,
-    pub failure_kind: Option<String>,
    pub status_code: Option<u16>,
    pub search: Option<String>,
 }
@@ -189,11 +187,11 @@ impl DecimalAmount {
        Self::from_decimal(self.to_decimal()?.checked_div_u64(divisor)?)
    }

-    fn to_decimal(&self) -> Option<gateway_core::accounting::Decimal> {
+    fn to_decimal(&self) -> Option<gateway_core::metering::Decimal> {
        self.0.parse().ok()
    }

-    fn from_decimal(value: gateway_core::accounting::Decimal) -> Option<Self> {
+    fn from_decimal(value: gateway_core::metering::Decimal) -> Option<Self> {
        Some(Self(value.canonical()))
    }
 }
@@ -493,6 +491,8 @@ pub struct DashboardAccountUsage {
    ///
    /// `None` 表示上游未提供可比较的百分比，不应伪造为零。
    pub quota_used_percent: Option<f64>,
+    /// Provider 返回的代表窗口；缺失时保留未知语义。
+    pub quota_window: Option<super::provider_credentials::ProviderQuotaWindow>,
    pub models: Vec<DashboardAccountModelUsage>,
 }

@@ -704,6 +704,8 @@ pub struct UsageAttempt {
 /// 一条请求及其全部尝试。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UsageDetail {
+    pub trace: Option<serde_json::Value>,
+    pub related_requests: Vec<serde_json::Value>,
    pub request: UsageRecord,
    pub attempts: Vec<UsageAttempt>,
 }
@@ -776,6 +778,7 @@ pub struct OpsError {
    pub upstream_model_id: Option<String>,
    pub upstream_transport: Option<String>,
    pub failure_kind: String,
+    pub upstream_send_state: Option<String>,
    pub client_status_code: Option<u16>,
    pub upstream_status_code: Option<u16>,
    pub provider_error_code: Option<String>,
@@ -783,7 +786,7 @@ pub struct OpsError {
    pub upstream_request_id: Option<String>,
    pub latency_ms: Option<u64>,
    pub message: String,
-    pub occurrence_count: u32,
+    pub raw_upstream_error: Option<String>,
    pub client_ip: Option<String>,
    pub user_agent: Option<String>,
    pub reasoning_effort: Option<String>,
@@ -791,6 +794,18 @@ pub struct OpsError {
    pub request_kind: Option<String>,
    pub subagent_kind: Option<String>,
    pub compact: Option<bool>,
+    pub continuation_affinity_hash: Option<String>,
+    pub continuation_previous_response_id_hash: Option<String>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_id: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub upstream_connection_age_ms: Option<u64>,
+    pub upstream_connection_idle_ms: Option<u64>,
+    pub recovery_request_id: Option<String>,
+    pub recovered_at: Option<DateTime<Utc>>,
+    pub recovery_attempt_count: u32,
+    pub recovery_retry_delay_ms: Option<u64>,
+    pub recovery_total_latency_ms: Option<u64>,
    pub occurred_at: DateTime<Utc>,
    pub stable_sort_id: String,
 }
@@ -7,9 +7,11 @@ use bytes::Bytes;
 use chrono::{DateTime, NaiveDate, Utc};
 use futures::Stream;
 use gateway_core::{
-    engine::credential::{OpaqueProviderData, ProviderAccountId, ProviderAccountIdentity},
+    account::{OpaqueProviderData, ProviderAccountId, ProviderAccountIdentity},
    routing::{ProviderKind, UpstreamModelId},
 };
+use serde::Deserialize;
+use serde_json::{Map, Value};
 use uuid::Uuid;

 use super::{
@@ -279,6 +281,101 @@ impl PendingAuthorizationMutation {
    }
 }

+impl PendingAuthorizationMutation {
+    /// 编码 v1 中立事务字段；版本号的位置和 Provider 私有外层文档由 adapter 保持。
+    #[must_use]
+    pub fn to_storage_v1(&self) -> Map<String, Value> {
+        let target = match &self.target {
+            AuthorizationMutationTarget::Create { name } => {
+                serde_json::json!({"kind": "create", "name": name})
+            }
+            AuthorizationMutationTarget::Reauthorize { account_id } => {
+                serde_json::json!({"kind": "reauthorize", "account_id": account_id.to_string()})
+            }
+        };
+        let owner = match self.owner_binding.owner() {
+            AuthorizationOwner::AdminSession { admin_user_id } => {
+                serde_json::json!({"kind": "admin_session", "admin_user_id": admin_user_id})
+            }
+            AuthorizationOwner::AdminApiKey => serde_json::json!({"kind": "admin_api_key"}),
+            AuthorizationOwner::System => serde_json::json!({"kind": "system"}),
+        };
+        Map::from_iter([
+            (
+                "provider_kind".to_owned(),
+                Value::String(self.provider_kind.as_str().to_owned()),
+            ),
+            ("target".to_owned(), target),
+            ("owner".to_owned(), owner),
+            (
+                "started_request_id".to_owned(),
+                Value::String(self.owner_binding.started_request_id().to_owned()),
+            ),
+        ])
+    }
+
+    /// 恢复 adapter 已确认版本为 v1 的中立事务字段。
+    ///
+    /// # Errors
+    ///
+    /// 文档字段、Provider kind 或账号身份非法时返回错误，不携带原始 pending 内容。
+    pub fn from_storage_v1(value: Value) -> Result<Self, AdminError> {
+        let invalid = || AdminError::invalid("invalid pending authorization mutation");
+        let document: StoredAuthorizationMutationV1 =
+            serde_json::from_value(value).map_err(|_| invalid())?;
+        let provider_kind = ProviderKind::new(document.provider_kind).map_err(|_| invalid())?;
+        let target = match document.target {
+            StoredAuthorizationTargetV1::Create { name } => {
+                AuthorizationMutationTarget::Create { name }
+            }
+            StoredAuthorizationTargetV1::Reauthorize { account_id } => {
+                AuthorizationMutationTarget::Reauthorize {
+                    account_id: ProviderAccountId::new(account_id).map_err(|_| invalid())?,
+                }
+            }
+        };
+        let owner = match document.owner {
+            StoredAuthorizationOwnerV1::AdminSession { admin_user_id } => {
+                AuthorizationOwner::AdminSession { admin_user_id }
+            }
+            StoredAuthorizationOwnerV1::AdminApiKey => AuthorizationOwner::AdminApiKey,
+            StoredAuthorizationOwnerV1::System => AuthorizationOwner::System,
+        };
+        Ok(Self::new(
+            provider_kind,
+            target,
+            AuthorizationOwnerBinding {
+                owner,
+                started_request_id: document.started_request_id,
+            },
+        ))
+    }
+}
+
+#[derive(Deserialize)]
+#[serde(deny_unknown_fields)]
+struct StoredAuthorizationMutationV1 {
+    provider_kind: String,
+    target: StoredAuthorizationTargetV1,
+    owner: StoredAuthorizationOwnerV1,
+    started_request_id: String,
+}
+
+#[derive(Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
+enum StoredAuthorizationTargetV1 {
+    Create { name: String },
+    Reauthorize { account_id: String },
+}
+
+#[derive(Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
+enum StoredAuthorizationOwnerV1 {
+    AdminSession { admin_user_id: String },
+    AdminApiKey,
+    System,
+}
+
 /// 启动 Provider OAuth Authorization Code 流程。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct StartAuthorization {
@@ -776,6 +873,20 @@ impl ProviderQuota {
            .map(|(_, used_percent)| used_percent)
    }

+    /// 选择 Dashboard 展示的真实窗口；没有百分比时仍保留 Provider 的滚动窗口语义。
+    #[must_use]
+    pub fn representative_window(&self) -> Option<&ProviderQuotaWindow> {
+        self.representative_used_window()
+            .map(|(index, _)| &self.windows[index])
+            .or_else(|| {
+                self.windows
+                    .iter()
+                    .enumerate()
+                    .min_by_key(|(index, window)| (quota_usage_priority(window), *index))
+                    .map(|(_, window)| window)
+            })
+    }
+
    /// 将已确认的账号级额度耗尽事实投影到展示窗口。
    ///
    /// Provider 已指出具体触顶窗口时只归一化这些窗口；否则归一化 Dashboard
@@ -908,7 +1019,7 @@ impl fmt::Debug for ProviderExport {
 #[derive(Debug, Clone, PartialEq)]
 pub struct AccountDirectoryItem {
    pub account: AccountRecord,
-    pub projection: gateway_core::engine::credential::AccountStatusProjection,
+    pub projection: gateway_core::account::AccountStatusProjection,
    pub usage: Option<super::accounts::AccountUsage>,
    pub quota: ProviderQuota,
 }
@@ -12,7 +12,7 @@ use super::Revision;
 pub type ModelMappings = BTreeMap<PublicModelId, UpstreamModelId>;

 /// 账号调度策略；由 Core 拥有稳定值与 wire 映射。
-pub use gateway_core::engine::credential::RotationStrategy;
+pub use gateway_core::account::RotationStrategy;

 /// 完整运行设置事实。
 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -24,6 +24,8 @@ pub struct RuntimeSettings {
    pub max_concurrent_per_account: u32,
    pub request_interval_ms: u64,
    pub rotation_strategy: RotationStrategy,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
    pub usage_retention_days: u32,
    pub ops_event_retention_days: u32,
    pub audit_retention_days: u32,
@@ -39,6 +41,8 @@ pub struct ReplaceRuntimeSettings {
    pub max_concurrent_per_account: u32,
    pub request_interval_ms: u64,
    pub rotation_strategy: RotationStrategy,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
    pub usage_retention_days: u32,
    pub ops_event_retention_days: u32,
    pub audit_retention_days: u32,
@@ -145,7 +145,7 @@ pub trait DatabaseDumpPort: Send + Sync {
 #[derive(Debug, Clone)]
 pub struct DumpRequest {
    pub backup_id: String,
-    pub cancellation: gateway_core::engine::CancellationToken,
+    pub cancellation: gateway_core::lifecycle::CancellationToken,
 }

 /// 已完成并落盘的归档事实。
@@ -212,7 +212,7 @@ pub struct UploadObjectRequest {
    pub object_key: String,
    pub source: PathBuf,
    pub metadata: BackupObjectMetadata,
-    pub cancellation: gateway_core::engine::CancellationToken,
+    pub cancellation: gateway_core::lifecycle::CancellationToken,
 }

 /// 备份控制面所需的全部 Store 能力集合。
@@ -0,0 +1,10 @@
+//! 客户端安装包解析的外部能力端口。
+
+use async_trait::async_trait;
+
+use crate::model::client_distribution::CodexDesktopWindowsDownloads;
+
+#[async_trait]
+pub trait ClientDistributionResolver: Send + Sync {
+    async fn resolve_codex_desktop_windows(&self, refresh: bool) -> CodexDesktopWindowsDownloads;
+}
@@ -1,6 +1,7 @@
 //! 管理用例依赖的外部能力端口。

 pub mod backup;
+pub mod client_distribution;
 pub mod provider;
 pub mod store;
 pub mod system;
@@ -4,7 +4,7 @@ use std::{collections::BTreeMap, sync::Arc};

 use async_trait::async_trait;
 use gateway_core::{
-    engine::credential::ProviderAccountId,
+    account::ProviderAccountId,
    operation::Operation,
    routing::{ProviderKind, UpstreamModelId},
 };
@@ -6,6 +6,7 @@ use std::sync::Arc;

 use async_trait::async_trait;
 use chrono::{DateTime, Utc};
+use futures::stream::BoxStream;

 use super::backup::BackupStorePorts;
 use crate::model::{
@@ -118,13 +119,13 @@ pub trait AccountStore: Send + Sync {
    async fn credential_details(
        &self,
        provider_kind: &gateway_core::routing::ProviderKind,
-        account_id: &gateway_core::engine::credential::ProviderAccountId,
+        account_id: &gateway_core::account::ProviderAccountId,
    ) -> AdminStoreResult<Option<CredentialDetails>>;

    async fn load_credentials_for_export(
        &self,
        provider_kind: &gateway_core::routing::ProviderKind,
-        account_ids: &[gateway_core::engine::credential::ProviderAccountId],
+        account_ids: &[gateway_core::account::ProviderAccountId],
    ) -> AdminStoreResult<Vec<ProviderExportCredentialInput>>;

    async fn commit_credential_import(
@@ -159,7 +160,7 @@ pub trait AccountStore: Send + Sync {

    async fn recover_account(
        &self,
-        account_id: &gateway_core::engine::credential::ProviderAccountId,
+        account_id: &gateway_core::account::ProviderAccountId,
        context: &MutationContext,
    ) -> AdminStoreResult<AccountUpdateResult>;

@@ -177,7 +178,7 @@ pub trait AccountStore: Send + Sync {

    async fn record_credential_export(
        &self,
-        account_ids: &[gateway_core::engine::credential::ProviderAccountId],
+        account_ids: &[gateway_core::account::ProviderAccountId],
        context: &MutationContext,
    ) -> AdminStoreResult<()>;
 }
@@ -289,6 +290,10 @@ pub trait AccountGroupStore: Send + Sync {
    ) -> AdminStoreResult<AccountGroupMutation>;
 }

+/// 逐条读取的已计算费用事实；消费结束或丢弃时释放查询资源。
+pub type UsageCalculatedBillingStream<'a> =
+    BoxStream<'a, AdminStoreResult<UsageCalculatedBillingFact>>;
+
 /// 用量、趋势、诊断与运维错误的只读能力。
 #[async_trait]
 pub trait ObservabilityStore: Send + Sync {
@@ -318,12 +323,13 @@ pub trait ObservabilityStore: Send + Sync {
        filter: UsageFilter,
    ) -> AdminStoreResult<Vec<RequestMetricPoint>>;

-    /// 返回可由 Provider 重新校验的已计算费用事实，用于恢复标准费用趋势。
-    async fn usage_calculated_billing_facts(
+    /// 流式返回可由 Provider 重新校验的已计算费用事实，不保证顺序。
+    /// 查询及解码错误由流返回；调用方应逐条聚合，避免收集整个区间。
+    fn usage_calculated_billing_facts(
        &self,
        range: TimeRange,
        filter: UsageFilter,
-    ) -> AdminStoreResult<Vec<UsageCalculatedBillingFact>>;
+    ) -> UsageCalculatedBillingStream<'_>;

    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage>;

@@ -8,8 +8,9 @@ use std::{

 use async_trait::async_trait;
 use gateway_core::{
-    engine::credential::{AccountStatus, resolve_account_status},
-    routing::{AccountGroupId, snapshot::SnapshotControl},
+    account::{AccountStatus, resolve_account_status},
+    routing::AccountGroupId,
+    runtime::SnapshotControl,
 };
 use uuid::Uuid;

@@ -6,11 +6,10 @@ use async_trait::async_trait;
 use chrono::{Duration, Utc};
 use futures::StreamExt as _;
 use gateway_core::{
-    engine::{
-        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeRequest},
-    },
-    routing::{ProviderKind, UpstreamModelId, snapshot::SnapshotControl},
+    account::ProviderAccountId,
+    engine::probe::{AccountProbe, AccountProbeRequest},
+    routing::{ProviderKind, UpstreamModelId},
+    runtime::SnapshotControl,
 };

 use crate::{
@@ -270,6 +269,11 @@ impl DefaultAccountsService {
            })
            .await
            .map_err(|error| map_provider_error(error, "provider quota"))?;
+        let stored = if refresh_quota {
+            self.load_account(account_id).await?
+        } else {
+            stored
+        };
        self.attach_quota_local_usage(
            std::slice::from_ref(&stored),
            std::slice::from_mut(&mut quota),
@@ -69,7 +69,7 @@ impl DefaultAuthService {
            id: format!("audit_{}", Uuid::now_v7().simple()),
            actor_kind: AuditActorKind::AdminSession,
            actor_admin_user_id: Some(self.default_admin_user_id.clone()),
-            actor_ref: format!("admin:{}", self.default_admin_user_id),
+            actor_ref: crate::model::auth::admin_session_actor_ref(&self.default_admin_user_id),
            request_id: None,
            action: action.to_owned(),
            entity_kind: "admin_session".to_owned(),
@@ -183,7 +183,7 @@ impl AuthService for DefaultAuthService {
        if let Some(session) = session {
            let mut event = self.auth_audit("admin.logout", Utc::now());
            event.actor_admin_user_id = Some(session.admin_user_id.clone());
-            event.actor_ref = format!("admin:{}", session.admin_user_id);
+            event.actor_ref = crate::model::auth::admin_session_actor_ref(&session.admin_user_id);
            event.entity_ref = session.admin_user_id;
            self.store
                .append_audit_event(event)
@@ -5,7 +5,7 @@ use std::time::Duration;

 use async_trait::async_trait;
 use chrono::{DateTime, Utc};
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::runtime::SnapshotControl;
 use secrecy::ExposeSecret as _;
 use uuid::Uuid;

@@ -326,7 +326,9 @@ impl DefaultBackupService {
            crate::model::MutationActor::System => AuditActorKind::System,
        };
        let actor_ref = match &context.actor {
-            crate::model::MutationActor::AdminSession { admin_user_id } => admin_user_id.clone(),
+            crate::model::MutationActor::AdminSession { admin_user_id } => {
+                crate::model::auth::admin_session_actor_ref(admin_user_id)
+            }
            crate::model::MutationActor::AdminApiKey => "admin_api_key".to_owned(),
            crate::model::MutationActor::System => "system".to_owned(),
        };
@@ -0,0 +1,33 @@
+//! Codex 客户端下载信息用例。
+
+use std::sync::Arc;
+
+use async_trait::async_trait;
+
+use crate::{
+    model::client_distribution::CodexDesktopWindowsDownloads,
+    ports::client_distribution::ClientDistributionResolver,
+};
+
+#[async_trait]
+pub trait ClientDistributionService: Send + Sync {
+    async fn codex_desktop_windows(&self, refresh: bool) -> CodexDesktopWindowsDownloads;
+}
+
+pub(crate) struct DefaultClientDistributionService {
+    resolver: Arc<dyn ClientDistributionResolver>,
+}
+
+impl DefaultClientDistributionService {
+    #[must_use]
+    pub(crate) const fn new(resolver: Arc<dyn ClientDistributionResolver>) -> Self {
+        Self { resolver }
+    }
+}
+
+#[async_trait]
+impl ClientDistributionService for DefaultClientDistributionService {
+    async fn codex_desktop_windows(&self, refresh: bool) -> CodexDesktopWindowsDownloads {
+        self.resolver.resolve_codex_desktop_windows(refresh).await
+    }
+}
@@ -5,7 +5,7 @@ use std::sync::Arc;
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
 use gateway_core::policy::ClientApiKeyId;
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::runtime::SnapshotControl;
 use rand_core::{OsRng, RngCore as _};
 use uuid::Uuid;

@@ -4,6 +4,7 @@ pub mod account_groups;
 pub mod accounts;
 pub mod auth;
 pub mod backup;
+pub mod client_distribution;
 pub mod client_keys;
 pub mod observability;
 pub mod openai;
@@ -29,8 +30,9 @@ use crate::{
    },
 };
 use gateway_core::{
-    engine::credential::ProviderAccountId,
-    routing::{ConfigRevision, ProviderKind, snapshot::SnapshotControl},
+    account::ProviderAccountId,
+    routing::{ConfigRevision, ProviderKind},
+    runtime::SnapshotControl,
 };

 fn map_store_error(error: AdminStoreError, resource: &'static str) -> AdminError {
@@ -9,7 +9,8 @@ use std::{

 use async_trait::async_trait;
 use chrono::{DateTime, Duration, Timelike as _, Utc};
-use gateway_core::{engine::credential::ProviderAccountId, routing::ProviderKind};
+use futures::TryStreamExt;
+use gateway_core::{account::ProviderAccountId, routing::ProviderKind};

 use crate::{
    model::{
@@ -29,7 +30,7 @@ use crate::{
    },
    ports::{
        provider::{ProviderAdminErrorKind, ProviderAdminRegistry},
-        store::{ObservabilityStore, SettingsStore},
+        store::{AccountStore, ObservabilityStore, SettingsStore, UsageCalculatedBillingStream},
    },
 };

@@ -126,6 +127,7 @@ pub trait ObservabilityService: Send + Sync {

 pub(crate) struct DefaultObservabilityService {
    store: Arc<dyn ObservabilityStore>,
+    accounts: Arc<dyn AccountStore>,
    settings: Arc<dyn SettingsStore>,
    providers: ProviderAdminRegistry,
    dashboard_queries: DashboardQueryCache,
@@ -135,11 +137,13 @@ impl DefaultObservabilityService {
    #[must_use]
    pub(crate) fn new(
        store: Arc<dyn ObservabilityStore>,
+        accounts: Arc<dyn AccountStore>,
        settings: Arc<dyn SettingsStore>,
        providers: ProviderAdminRegistry,
    ) -> Self {
        Self {
            store,
+            accounts,
            settings,
            providers,
            dashboard_queries: DashboardQueryCache::default(),
@@ -301,13 +305,21 @@ impl ObservabilityService for DefaultObservabilityService {
        range: TimeRange,
        filter: UsageFilter,
    ) -> Result<UsageInsights, AdminError> {
-        let (overview, trend, billing_facts) = futures::try_join!(
-            self.store.usage_summary(range, filter.clone()),
-            self.store.usage_trend(range, filter.clone()),
-            self.store.usage_calculated_billing_facts(range, filter),
-        )
-        .map_err(|error| map_store_error(error, "usage insights"))?;
-        let standard_costs = recover_standard_costs(&self.providers, billing_facts)?;
+        let aggregates = async {
+            futures::try_join!(
+                self.store.usage_summary(range, filter.clone()),
+                self.store.usage_trend(range, filter.clone()),
+            )
+            .map_err(|error| map_store_error(error, "usage insights"))
+        };
+        let ((overview, trend), standard_costs) = futures::try_join!(
+            aggregates,
+            recover_standard_costs(
+                &self.providers,
+                self.store
+                    .usage_calculated_billing_facts(range, filter.clone()),
+            ),
+        )?;
        build_usage_insights(overview, trend, standard_costs)
    }

@@ -590,12 +602,16 @@ struct UsageCostScenarios {
    no_cache: ScenarioCosts,
 }

-fn recover_standard_costs(
+async fn recover_standard_costs(
    providers: &ProviderAdminRegistry,
-    facts: Vec<UsageCalculatedBillingFact>,
+    mut facts: UsageCalculatedBillingStream<'_>,
 ) -> Result<UsageCostScenarios, AdminError> {
    let mut scenarios = UsageCostScenarios::default();
-    for fact in facts {
+    while let Some(fact) = facts
+        .try_next()
+        .await
+        .map_err(|error| map_store_error(error, "usage billing facts"))?
+    {
        let Ok(provider_kind) = ProviderKind::new(fact.provider_kind.clone()) else {
            continue;
        };
@@ -654,7 +670,7 @@ fn no_cache_cost(
        .checked_sub(decimal(&breakdown.cache_write_amount.amount)?.scaled())?
        .checked_add(replaced_input_amount)?;
    DecimalAmount::from_str(
-        &gateway_core::accounting::Decimal::from_scaled(total)
+        &gateway_core::metering::Decimal::from_scaled(total)
            .ok()?
            .canonical(),
    )
@@ -669,14 +685,14 @@ fn amount_difference(
        .scaled()
        .checked_sub(decimal(smaller?)?.scaled())?;
    DecimalAmount::from_str(
-        &gateway_core::accounting::Decimal::from_scaled(difference)
+        &gateway_core::metering::Decimal::from_scaled(difference)
            .ok()?
            .canonical(),
    )
    .ok()
 }

-fn decimal(value: &DecimalAmount) -> Option<gateway_core::accounting::Decimal> {
+fn decimal(value: &DecimalAmount) -> Option<gateway_core::metering::Decimal> {
    value.as_str().parse().ok()
 }

@@ -708,8 +724,31 @@ fn usd_cost(costs: &[CurrencyCost]) -> Option<DecimalAmount> {

 impl DefaultObservabilityService {
    async fn enrich_dashboard_quotas(&self, accounts: &mut [DashboardAccountUsage]) {
+        if accounts.is_empty() {
+            return;
+        }
+        let now = Utc::now();
+        let ids = accounts
+            .iter()
+            .map(|account| account.account_id.clone())
+            .collect::<Vec<_>>();
+        let mut rolling_usage = self
+            .accounts
+            .load_account_usage(
+                TimeRange {
+                    start: now - Duration::hours(24),
+                    end: now,
+                },
+                &ids,
+            )
+            .await
+            .unwrap_or_default()
+            .into_iter()
+            .map(|usage| (usage.account_id.clone(), usage))
+            .collect::<HashMap<_, _>>();
        let providers = self.providers.clone();
        let quota_reads = accounts.iter().map(|account| {
+            let rolling_usage = rolling_usage.remove(&account.account_id);
            let account_id = ProviderAccountId::new(account.account_id.clone()).ok();
            let provider = ProviderKind::new(account.provider_kind.clone())
                .ok()
@@ -722,16 +761,19 @@ impl DefaultObservabilityService {
                    .quota(ProviderQuotaRequest {
                        account_id,
                        refresh: false,
-                        rolling_usage: None,
+                        rolling_usage,
                    })
                    .await
                    .ok()
-                    .and_then(|quota| quota.representative_used_percent())
            }
        });
-        let quota_used = futures::future::join_all(quota_reads).await;
-        for (account, used_percent) in accounts.iter_mut().zip(quota_used) {
-            account.quota_used_percent = used_percent;
+        let quotas = futures::future::join_all(quota_reads).await;
+        for (account, quota) in accounts.iter_mut().zip(quotas) {
+            if let Some(mut quota) = quota {
+                quota.apply_limit_reached_display();
+                account.quota_used_percent = quota.representative_used_percent();
+                account.quota_window = quota.representative_window().cloned();
+            }
        }
    }

@@ -3,7 +3,7 @@
 use std::sync::Arc;

 use async_trait::async_trait;
-use gateway_core::{engine::credential::ProviderAccountId, routing::snapshot::SnapshotControl};
+use gateway_core::{account::ProviderAccountId, runtime::SnapshotControl};

 use crate::{
    model::{
@@ -3,7 +3,8 @@
 use std::sync::Arc;

 use async_trait::async_trait;
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::policy::CodexClientVersion;
+use gateway_core::runtime::SnapshotControl;
 use rand_core::{OsRng, RngCore as _};

 use crate::{
@@ -119,6 +120,8 @@ fn validate_settings(command: &ReplaceRuntimeSettings) -> Result<(), AdminError>
        && command.usage_retention_days >= 31
        && command.ops_event_retention_days > 0
        && command.audit_retention_days > 0
+        && valid_client_version(command.min_codex_desktop_version.as_deref())
+        && valid_client_version(command.min_codex_cli_version.as_deref())
        && i64::try_from(command.request_interval_ms).is_ok();
    if valid {
        Ok(())
@@ -126,3 +129,7 @@ fn validate_settings(command: &ReplaceRuntimeSettings) -> Result<(), AdminError>
        Err(AdminError::invalid("运行时设置不满足约束"))
    }
 }
+
+fn valid_client_version(value: Option<&str>) -> bool {
+    value.is_none_or(|value| CodexClientVersion::parse(value).is_ok())
+}
@@ -3,7 +3,7 @@
 use std::sync::Arc;

 use async_trait::async_trait;
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::runtime::SnapshotControl;

 use crate::{
    model::{
@@ -10,7 +10,7 @@ use gateway_admin::{
    },
    ports::backup::{BackupRepository, DatabaseDumpPort, DumpRequest},
 };
-use gateway_core::engine::CancellationToken;
+use gateway_core::lifecycle::CancellationToken;

 use super::support::{
    DUMP_CONTENT, FakeBackupRepository, FakeDumpPort, FakeObjectStore, backup_id,
@@ -1,7 +1,7 @@
 use std::str::FromStr as _;

 use chrono::{TimeDelta, Utc};
-use gateway_core::engine::credential::OpaqueProviderData;
+use gateway_core::account::OpaqueProviderData;

 use gateway_admin::{
    model::{
@@ -1,4 +1,4 @@
-//! 备份领域模型（model/backup.rs）的纯逻辑测试。
+//! 备份领域模型（model/backup）的纯逻辑测试。

 use chrono::{TimeZone as _, Utc};
 use secrecy::SecretString;
@@ -1,3 +1,4 @@
 //! 模型模块测试：镜像 src/model/ 中带逻辑的模块。

 mod backup;
+mod provider_credentials;
@@ -0,0 +1,134 @@
+use gateway_admin::model::provider_credentials::{
+    AuthorizationMutationTarget, AuthorizationOwnerBinding, PendingAuthorizationMutation,
+    ProviderQuota, ProviderQuotaWindow, ProviderQuotaWindowRole, QuotaLocalUsageAttribution,
+};
+use gateway_admin::model::{MutationActor, MutationContext};
+use gateway_core::account::ProviderAccountId;
+use gateway_core::routing::ProviderKind;
+use serde_json::{Value, json};
+
+#[test]
+fn dashboard_quota_should_preserve_unknown_and_actual_window_facts() {
+    let mut quota = ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: Vec::new(),
+        limit_reached: false,
+        provider_data: None,
+    };
+    assert!(quota.representative_window().is_none());
+    assert!(quota.representative_used_percent().is_none());
+
+    let rolling = ProviderQuotaWindow {
+        key: "provider_rolling".to_owned(),
+        group: "requests".to_owned(),
+        label: "Provider rolling window".to_owned(),
+        limit_id: None,
+        limit_name: None,
+        role: Some(ProviderQuotaWindowRole::Primary),
+        local_usage_attribution: QuotaLocalUsageAttribution::AccountWide,
+        window_seconds: Some(86_400),
+        used_percent: None,
+        reset_at: None,
+        limit_reached: false,
+        local_usage: None,
+        provider_data: None,
+    };
+    quota.windows.push(rolling.clone());
+    assert_eq!(quota.representative_window(), Some(&rolling));
+    assert!(quota.representative_used_percent().is_none());
+
+    quota.windows[0].used_percent = Some(99.6);
+    quota.apply_limit_reached_display();
+    let actual = quota.representative_window().expect("actual window");
+    assert_eq!(actual.used_percent, Some(99.6));
+    assert!(
+        !actual.limit_reached,
+        "display rounding cannot exhaust quota"
+    );
+    assert_eq!(actual.window_seconds, Some(86_400));
+    assert_eq!(actual.reset_at, None);
+
+    quota.windows.insert(
+        0,
+        ProviderQuotaWindow {
+            key: "model_specific".to_owned(),
+            used_percent: Some(100.0),
+            local_usage_attribution: QuotaLocalUsageAttribution::Unavailable,
+            ..rolling
+        },
+    );
+    assert_eq!(
+        quota
+            .representative_window()
+            .map(|window| window.key.as_str()),
+        Some("provider_rolling")
+    );
+}
+
+#[test]
+fn pending_mutation_v1_should_round_trip_all_targets_and_owners() {
+    for provider in ["openai", "xai"] {
+        for target in [
+            AuthorizationMutationTarget::Create {
+                name: "account".to_owned(),
+            },
+            AuthorizationMutationTarget::Reauthorize {
+                account_id: ProviderAccountId::new("acct_1").expect("account id"),
+            },
+        ] {
+            for actor in [
+                MutationActor::AdminSession {
+                    admin_user_id: "admin-1".to_owned(),
+                },
+                MutationActor::AdminApiKey,
+                MutationActor::System,
+            ] {
+                let expected = PendingAuthorizationMutation::new(
+                    ProviderKind::new(provider).expect("provider"),
+                    target.clone(),
+                    AuthorizationOwnerBinding::from_context(&MutationContext {
+                        actor,
+                        request_id: "request-1".to_owned(),
+                    }),
+                );
+                assert_eq!(
+                    PendingAuthorizationMutation::from_storage_v1(Value::Object(
+                        expected.to_storage_v1()
+                    )),
+                    Ok(expected),
+                );
+            }
+        }
+    }
+}
+
+#[test]
+fn pending_mutation_v1_should_keep_existing_storage_fields_and_reject_invalid_documents() {
+    let legacy = json!({
+        "provider_kind": "openai",
+        "target": { "kind": "reauthorize", "account_id": "acct_1" },
+        "owner": { "kind": "admin_session", "admin_user_id": "admin-1" },
+        "started_request_id": "request-1"
+    });
+    let restored =
+        PendingAuthorizationMutation::from_storage_v1(legacy.clone()).expect("v1 document");
+    assert_eq!(Value::Object(restored.to_storage_v1()), legacy);
+    for (pointer, invalid) in [
+        ("/provider_kind", json!("")),
+        ("/target/account_id", json!("")),
+        ("/target/kind", json!("other")),
+        ("/owner/kind", json!("other")),
+        ("/started_request_id", json!(null)),
+    ] {
+        let mut document = legacy.clone();
+        *document.pointer_mut(pointer).expect("field") = invalid;
+        assert!(
+            PendingAuthorizationMutation::from_storage_v1(document).is_err(),
+            "{pointer}"
+        );
+    }
+    let mut document = legacy;
+    document["schema_version"] = json!(2);
+    assert!(PendingAuthorizationMutation::from_storage_v1(document).is_err());
+}
@@ -24,7 +24,7 @@ use gateway_admin::{
    },
 };
 use gateway_core::{
-    engine::credential::{AccountStatusFacts, CredentialState, QuotaState},
+    account::{AccountStatusFacts, CredentialState, QuotaState},
    routing::AccountGroupId,
 };

@@ -4,20 +4,18 @@ use async_trait::async_trait;
 use chrono::{TimeDelta, Utc};
 use futures::{StreamExt as _, future::BoxFuture};
 use gateway_core::{
-    engine::{
-        UpstreamSendState,
-        credential::{
-            AccountStatusFacts, CredentialState, OpaqueProviderData, ProviderAccountId,
-            QuotaEvidence, QuotaState, resolve_account_status,
-        },
-        probe::{
-            AccountProbe, AccountProbeError, AccountProbeErrorSource, AccountProbeRequest,
-            AccountProbeResult,
-        },
+    account::{
+        AccountStatusFacts, CredentialState, OpaqueProviderData, ProviderAccountId, QuotaEvidence,
+        QuotaState, resolve_account_status,
+    },
+    engine::probe::{
+        AccountProbe, AccountProbeError, AccountProbeErrorSource, AccountProbeRequest,
+        AccountProbeResult,
    },
    error::{ClientVisibleUpstreamError, GatewayError, GatewayErrorKind},
    operation::{GenerateRequest, Operation, ProtocolPayload},
    routing::ProviderKind,
+    upstream::UpstreamSendState,
 };

 use gateway_admin::{
@@ -74,6 +72,7 @@ pub(super) struct FakeProviderAdmin {
    import_account_ids: Mutex<Vec<String>>,
    quota_requests: Mutex<Vec<ProviderQuotaRequest>>,
    quota: Mutex<ProviderQuota>,
+    quota_refresh_account: Mutex<Option<(Arc<FakeAccountStore>, AccountRecord)>>,
    current_credential_revision: Mutex<Revision>,
    reset_credit_commands: Mutex<Vec<ConsumeProviderResetCredit>>,
 }
@@ -91,6 +90,7 @@ impl FakeProviderAdmin {
            import_account_ids: Mutex::new(vec!["acct_prepared".to_owned()]),
            quota_requests: Mutex::new(Vec::new()),
            quota: Mutex::new(empty_quota()),
+            quota_refresh_account: Mutex::new(None),
            current_credential_revision: Mutex::new(revision(1)),
            reset_credit_commands: Mutex::new(Vec::new()),
        })
@@ -348,6 +348,14 @@ impl ProviderAdmin for FakeProviderAdmin {
    ) -> Result<ProviderQuota, ProviderAdminError> {
        if request.refresh {
            self.record("provider.quota");
+            if let Some((store, account)) = self
+                .quota_refresh_account
+                .lock()
+                .expect("quota refresh account")
+                .take()
+            {
+                store.set_accounts(vec![account]);
+            }
        }
        self.quota_requests
            .lock()
@@ -798,6 +806,8 @@ impl SettingsStore for StaticSettingsStore {
            max_concurrent_per_account: 1,
            request_interval_ms: 0,
            rotation_strategy: RotationStrategy::Smart,
+            min_codex_desktop_version: None,
+            min_codex_cli_version: None,
            usage_retention_days: 30,
            ops_event_retention_days: 30,
            audit_retention_days: 30,
@@ -1098,6 +1108,47 @@ async fn accounts_refresh_should_keep_guard_through_store_commit() {
    assert_eq!(store.audit_requests(), ["refresh-request"]);
 }

+#[tokio::test]
+async fn accounts_quota_refresh_should_return_the_updated_account_status() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    let mut account = account_record("openai");
+    account.quota = QuotaState::exhausted(
+        QuotaEvidence::UsageLimitReached,
+        std::time::SystemTime::now(),
+        None,
+    );
+    let store = FakeAccountStore::with_account(account.clone(), events.clone());
+    account.quota = QuotaState::allowed(std::time::SystemTime::now());
+    *provider
+        .quota_refresh_account
+        .lock()
+        .expect("quota refresh account") = Some((store.clone(), account));
+
+    let result = accounts_service(provider, store)
+        .await
+        .accounts()
+        .quota(
+            &ProviderAccountId::new("acct_test").expect("account ID"),
+            true,
+        )
+        .await
+        .expect("refresh quota");
+
+    assert_eq!(
+        result.account.quota.access(),
+        gateway_core::account::QuotaAccessState::Allowed
+    );
+    assert_eq!(
+        result.projection.status,
+        gateway_admin::model::accounts::AccountStatus::Normal
+    );
+    assert_eq!(
+        recorded(&events),
+        ["store.load_account", "provider.quota", "store.load_account"]
+    );
+}
+
 #[tokio::test]
 async fn accounts_recover_should_commit_facts_then_return_normal_account() {
    let events = events();
@@ -1110,8 +1161,7 @@ async fn accounts_recover_should_commit_facts_then_return_normal_account() {
        std::time::SystemTime::now(),
        None,
    );
-    account.last_error_reason =
-        Some(gateway_core::engine::credential::AccountErrorReason::CredentialInvalid);
+    account.last_error_reason = Some(gateway_core::account::AccountErrorReason::CredentialInvalid);
    account.last_error_message = Some("invalid credential".to_owned());
    let store = FakeAccountStore::with_account(account, events.clone());
    let services = accounts_service(provider, store.clone()).await;
@@ -1133,7 +1183,7 @@ async fn accounts_recover_should_commit_facts_then_return_normal_account() {
    );
    assert_eq!(
        result.account.account.quota.access(),
-        gateway_core::engine::credential::QuotaAccessState::Allowed
+        gateway_core::account::QuotaAccessState::Allowed
    );
    assert_eq!(
        result.account.projection.status,
@@ -1166,7 +1216,7 @@ async fn accounts_update_should_commit_then_release_disabled_account_and_publish
                account_id: "acct_test".to_owned(),
                enabled: false,
                concurrency_limit: None,
-                weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+                weight: gateway_core::account::AccountWeight::DEFAULT,
                group_ids: Vec::new(),
            },
        )
@@ -1202,7 +1252,7 @@ async fn accounts_update_should_not_notify_provider_when_store_commit_fails() {
                account_id: "acct_test".to_owned(),
                enabled: false,
                concurrency_limit: None,
-                weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+                weight: gateway_core::account::AccountWeight::DEFAULT,
                group_ids: Vec::new(),
            },
        )
@@ -1243,7 +1293,7 @@ async fn accounts_batch_update_should_commit_once_and_notify_each_provider() {
                account_ids: vec!["acct_openai".to_owned(), "acct_xai".to_owned()],
                enabled: false,
                concurrency_limit: None,
-                weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+                weight: gateway_core::account::AccountWeight::DEFAULT,
                group_ids: Vec::new(),
            },
        )
@@ -1896,7 +1946,7 @@ pub(super) fn account_record(kind: &str) -> AccountRecord {
        next_refresh_at: Some(now + TimeDelta::minutes(30)),
        enabled: true,
        concurrency_limit: None,
-        weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+        weight: gateway_core::account::AccountWeight::DEFAULT,
        credential_state: CredentialState::Ready,
        credential_observed_at: now,
        quota: QuotaState::allowed(now.into()),
@@ -31,6 +31,7 @@ use gateway_admin::{
            BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
        },
        auth::{AdminAuditEvent, AdminSession},
+        client_distribution::CodexDesktopWindowsDownloads,
        client_keys::{
            ClientKeyListQuery, ClientKeyPage, ClientKeyRecord, ClientKeySecret, DeleteClientKey,
            NewClientKey, SetClientKeyEnabled, UpdateClientKey,
@@ -55,6 +56,7 @@ use gateway_admin::{
    },
    ports::{
        backup::BackupStorePorts,
+        client_distribution::ClientDistributionResolver,
        provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind},
        store::{
            AccountGroupStore, AccountRuntimeStore, AccountStore, AdminAccountStorePorts,
@@ -68,13 +70,12 @@ use gateway_admin::{
    },
 };
 use gateway_core::{
-    engine::{
-        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
-    },
+    account::ProviderAccountId,
+    engine::probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
    error::{GatewayError, GatewayErrorKind},
    policy::ClientApiKeyId,
-    routing::{ConfigRevision, ProviderKind, snapshot::SnapshotControl},
+    routing::{ConfigRevision, ProviderKind},
+    runtime::SnapshotControl,
 };

 pub(super) struct AdminHarness {
@@ -205,6 +206,7 @@ impl AdminHarness {
            self.providers,
            Arc::new(NoopSnapshot),
            self.probe,
+            Arc::new(NoopClientDistribution),
            self.system,
        )
        .await
@@ -213,6 +215,20 @@ impl AdminHarness {
    }
 }

+struct NoopClientDistribution;
+
+#[async_trait]
+impl ClientDistributionResolver for NoopClientDistribution {
+    async fn resolve_codex_desktop_windows(&self, _: bool) -> CodexDesktopWindowsDownloads {
+        CodexDesktopWindowsDownloads {
+            resolved_at: Utc::now(),
+            cached: false,
+            warning: None,
+            packages: Vec::new(),
+        }
+    }
+}
+
 #[derive(Default)]
 struct BootstrapAuthStore {
    password_hash: Mutex<Option<String>>,
@@ -520,13 +536,14 @@ impl ObservabilityStore for UnavailableStore {
        Err(unavailable("usage trend"))
    }

-    async fn usage_calculated_billing_facts(
+    fn usage_calculated_billing_facts(
        &self,
        _: TimeRange,
        _: UsageFilter,
-    ) -> AdminStoreResult<Vec<gateway_admin::model::observability::UsageCalculatedBillingFact>>
-    {
-        Err(unavailable("usage billing facts"))
+    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+        Box::pin(futures::stream::once(async {
+            Err(unavailable("usage billing facts"))
+        }))
    }

    async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {
@@ -2,7 +2,7 @@ use std::{
    str::FromStr as _,
    sync::{
        Arc, Mutex,
-        atomic::{AtomicUsize, Ordering},
+        atomic::{AtomicBool, AtomicUsize, Ordering},
    },
    time::Duration as StdDuration,
 };
@@ -537,10 +537,41 @@ async fn usage_records_should_enrich_provider_reported_totals_when_pricing_match
    ));
 }

+#[tokio::test]
+async fn usage_insights_should_reject_partial_costs_when_billing_stream_fails() {
+    let now = Utc::now();
+    let range = observation_range(now);
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    store.replace_calculated_billing_facts(vec![UsageCalculatedBillingFact {
+        bucket_start: quarter_hour_start(now),
+        provider_kind: "openai".to_owned(),
+        upstream_model_id: "gpt-5.5".to_owned(),
+        service_tier: None,
+        input_tokens: Some(800),
+        output_tokens: Some(200),
+        cached_tokens: Some(0),
+        cache_write_tokens: Some(0),
+        total: CurrencyCost {
+            currency: "USD".to_owned(),
+            amount: "1.25".parse().expect("cost"),
+        },
+    }]);
+    store.billing_stream_fails.store(true, Ordering::SeqCst);
+    let services = observability_services_with_calculated_billing(store).await;
+    assert!(
+        services
+            .observability()
+            .usage_insights(range, UsageFilter::default())
+            .await
+            .is_err()
+    );
+}
+
 struct FixtureObservabilityStore {
    trend: Mutex<Vec<RequestMetricPoint>>,
    overview: Mutex<UsageOverview>,
    calculated_billing_facts: Mutex<Vec<UsageCalculatedBillingFact>>,
+    billing_stream_fails: AtomicBool,
    diagnostics: Mutex<Vec<DiagnosticObservation>>,
    runtime_slots: Mutex<Option<DashboardRuntimeSlots>>,
    summary_observed_at: Mutex<Option<DateTime<Utc>>>,
@@ -561,6 +592,7 @@ impl FixtureObservabilityStore {
                providers: Vec::new(),
            }),
            calculated_billing_facts: Mutex::new(Vec::new()),
+            billing_stream_fails: AtomicBool::new(false),
            diagnostics: Mutex::new(Vec::new()),
            runtime_slots: Mutex::new(None),
            summary_observed_at: Mutex::new(None),
@@ -663,16 +695,23 @@ impl ObservabilityStore for FixtureObservabilityStore {
        Ok(self.trend.lock().expect("trend").clone())
    }

-    async fn usage_calculated_billing_facts(
+    fn usage_calculated_billing_facts(
        &self,
        _: TimeRange,
        _: UsageFilter,
-    ) -> AdminStoreResult<Vec<UsageCalculatedBillingFact>> {
-        Ok(self
+    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+        let facts = self
            .calculated_billing_facts
            .lock()
            .expect("calculated billing facts")
-            .clone())
+            .clone();
+        let error = self
+            .billing_stream_fails
+            .load(Ordering::SeqCst)
+            .then(|| Err(super::unavailable("billing stream failed")));
+        Box::pin(futures::stream::iter(
+            facts.into_iter().map(Ok).chain(error),
+        ))
    }

    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
@@ -721,6 +760,8 @@ impl SettingsStore for FixtureSettingsStore {
            max_concurrent_per_account: 1,
            request_interval_ms: 0,
            rotation_strategy: RotationStrategy::Smart,
+            min_codex_desktop_version: None,
+            min_codex_cli_version: None,
            usage_retention_days: 31,
            ops_event_retention_days: 30,
            audit_retention_days: 30,
@@ -1,6 +1,6 @@
 use std::sync::Arc;

-use gateway_core::engine::credential::ProviderAccountId;
+use gateway_core::account::ProviderAccountId;

 use gateway_admin::{
    AdminServices,
@@ -67,6 +67,8 @@ async fn settings_should_reject_zero_refresh_margin_before_store_call() {
                max_concurrent_per_account: 1,
                request_interval_ms: 0,
                rotation_strategy: RotationStrategy::Smart,
+                min_codex_desktop_version: None,
+                min_codex_cli_version: None,
                usage_retention_days: 31,
                ops_event_retention_days: 30,
                audit_retention_days: 30,
@@ -1,6 +1,6 @@
 use std::sync::Arc;

-use gateway_core::engine::credential::ProviderAccountId;
+use gateway_core::account::ProviderAccountId;

 use gateway_admin::{
    AdminServices,
@@ -0,0 +1,488 @@
+//! Provider-owned 凭据请求、命令转换与敏感材料校验。
+
+use super::*;
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(super) enum AccountProvider {
+    OpenAi,
+    Xai,
+}
+
+impl AccountProvider {
+    fn parse(value: &str) -> Result<Self, WireValidationError> {
+        match value.trim() {
+            "openai" => Ok(Self::OpenAi),
+            "xai" => Ok(Self::Xai),
+            _ => Err(WireValidationError::new("provider")),
+        }
+    }
+}
+
+/// Provider-owned 账号导入请求；公共 API 不解释 `data` 内部字段。
+#[derive(Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountImportRequest {
+    pub provider: String,
+    pub data: Value,
+}
+
+impl AccountImportRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        AccountProvider::parse(&self.provider)?;
+        if !self.data.is_object()
+            || serde_json::to_vec(&self.data)
+                .map_or(true, |encoded| encoded.len() > MAX_IMPORT_DATA_BYTES)
+        {
+            return Err(WireValidationError::new("data"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, ImportCredentials), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        Ok((
+            provider,
+            ImportCredentials {
+                context,
+                document: provider_document(self.data, "data")?,
+            },
+        ))
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct StartAccountAuthorizationRequest {
+    pub provider: String,
+    pub name: String,
+    pub account_id: Option<String>,
+}
+
+impl StartAccountAuthorizationRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        AccountProvider::parse(&self.provider)?;
+        require_text(&self.name, MAX_NAME_BYTES, "name")?;
+        if let Some(account_id) = self.account_id.as_deref() {
+            require_account_id(account_id, "accountId")?;
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, StartAuthorization), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        let reauthorization = self
+            .account_id
+            .map(ProviderAccountId::new)
+            .transpose()
+            .map_err(|_| WireValidationError::new("accountId"))?;
+        Ok((
+            provider,
+            StartAuthorization {
+                context,
+                name: self.name,
+                reauthorization,
+            },
+        ))
+    }
+}
+
+#[derive(Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct CompleteAccountAuthorizationRequest {
+    pub provider: String,
+    pub flow_id: String,
+    pub callback_url: String,
+}
+
+impl CompleteAccountAuthorizationRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        let provider = AccountProvider::parse(&self.provider)?;
+        match provider {
+            AccountProvider::OpenAi => {
+                if !URL_SAFE_NO_PAD
+                    .decode(&self.flow_id)
+                    .is_ok_and(|decoded| decoded.len() == 32)
+                {
+                    return Err(WireValidationError::new("flowId"));
+                }
+            }
+            AccountProvider::Xai => require_wire_id(&self.flow_id, "flowId")?,
+        }
+        require_text(&self.callback_url, MAX_CALLBACK_URL_BYTES, "callbackUrl")
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, CompleteAuthorization), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        Ok((
+            provider,
+            CompleteAuthorization {
+                context,
+                flow_id: self.flow_id,
+                callback_url: self.callback_url,
+            },
+        ))
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct UpdateAccountRequest {
+    pub account_id: String,
+    pub enabled: bool,
+    #[serde(deserialize_with = "deserialize_required_nullable")]
+    pub concurrency_limit: Option<u64>,
+    pub weight: u64,
+    pub group_ids: Vec<String>,
+}
+
+impl UpdateAccountRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        parse_concurrency_limit(self.concurrency_limit)?;
+        parse_account_weight(self.weight)?;
+        validate_wire_group_ids(&self.group_ids)?;
+        Ok(())
+    }
+
+    pub(super) fn into_command(self) -> Result<UpdateAccount, WireValidationError> {
+        self.validate()?;
+        Ok(UpdateAccount {
+            account_id: self.account_id,
+            enabled: self.enabled,
+            concurrency_limit: parse_concurrency_limit(self.concurrency_limit)?,
+            weight: parse_account_weight(self.weight)?,
+            group_ids: validate_wire_group_ids(&self.group_ids)?,
+        })
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UpdatedAccountData {
+    pub account_id: String,
+    pub config_revision: u64,
+}
+
+impl From<AccountUpdateResult> for UpdatedAccountData {
+    fn from(result: AccountUpdateResult) -> Self {
+        Self {
+            account_id: result.account_id.to_string(),
+            config_revision: result.config_revision.get(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountDeletionRequest {
+    pub provider: String,
+    pub account_ids: Vec<String>,
+}
+
+impl AccountDeletionRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        AccountProvider::parse(&self.provider)?;
+        if self.account_ids.is_empty() || self.account_ids.len() > MAX_ACCOUNT_DELETE_BATCH {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        let mut unique = BTreeSet::new();
+        for account_id in &self.account_ids {
+            require_account_id(account_id, "accountIds")?;
+            if !unique.insert(account_id.as_str()) {
+                return Err(WireValidationError::new("accountIds"));
+            }
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, CredentialDeletion), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        Ok((
+            provider,
+            CredentialDeletion {
+                context,
+                account_ids: self
+                    .account_ids
+                    .into_iter()
+                    .map(ProviderAccountId::new)
+                    .collect::<Result<Vec<_>, _>>()
+                    .map_err(|_| WireValidationError::new("accountIds"))?,
+            },
+        ))
+    }
+}
+
+#[derive(Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct RotateAccountRequest {
+    pub provider: String,
+    pub account_id: String,
+    pub access_token: String,
+    pub refresh_token: Option<String>,
+    pub id_token: Option<String>,
+}
+
+impl RotateAccountRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        if AccountProvider::parse(&self.provider)? != AccountProvider::OpenAi {
+            return Err(WireValidationError::new("provider"));
+        }
+        require_account_id(&self.account_id, "accountId")?;
+        validate_oauth_material(
+            &self.access_token,
+            self.refresh_token.as_deref(),
+            self.id_token.as_deref(),
+        )
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<RotateCredential, WireValidationError> {
+        self.validate()?;
+        let mut material = Map::new();
+        material.insert("access_token".to_owned(), Value::String(self.access_token));
+        material.insert(
+            "refresh_token".to_owned(),
+            self.refresh_token.map_or(Value::Null, Value::String),
+        );
+        material.insert(
+            "id_token".to_owned(),
+            self.id_token.map_or(Value::Null, Value::String),
+        );
+        Ok(RotateCredential {
+            mutation: CredentialMutation {
+                context,
+                account_id: ProviderAccountId::new(self.account_id)
+                    .map_err(|_| WireValidationError::new("accountId"))?,
+            },
+            provider_material: ProviderDocument::new(OpaqueProviderData::new(material)),
+        })
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountImportData {
+    pub imported_count: usize,
+    pub account_ids: Vec<String>,
+}
+
+impl AccountImportData {
+    pub fn from_result(result: CredentialImportResult) -> Self {
+        let account_ids = result
+            .credential_ids
+            .into_iter()
+            .map(|account_id| account_id.to_string())
+            .collect::<Vec<_>>();
+        Self {
+            imported_count: account_ids.len(),
+            account_ids,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountAuthorizationData {
+    pub flow_id: String,
+    pub authorization_url: String,
+    pub expires_at: DateTime<Utc>,
+}
+
+impl From<AuthorizationStarted> for AccountAuthorizationData {
+    fn from(started: AuthorizationStarted) -> Self {
+        Self {
+            flow_id: started.flow_id,
+            authorization_url: started.authorization_url,
+            expires_at: started.expires_at,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountMutationData {
+    pub account_id: String,
+}
+
+impl From<CredentialMutationResult> for AccountMutationData {
+    fn from(result: CredentialMutationResult) -> Self {
+        Self {
+            account_id: result.account_id.to_string(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountDeletionData {
+    pub deleted_count: usize,
+    pub account_ids: Vec<String>,
+}
+
+impl From<CredentialDeletionResult> for AccountDeletionData {
+    fn from(result: CredentialDeletionResult) -> Self {
+        let account_ids = result
+            .account_ids
+            .into_iter()
+            .map(|account_id| account_id.to_string())
+            .collect::<Vec<_>>();
+        Self {
+            deleted_count: account_ids.len(),
+            account_ids,
+        }
+    }
+}
+
+pub(super) fn require_account_id(
+    value: &str,
+    field: &'static str,
+) -> Result<(), WireValidationError> {
+    if value.trim().is_empty()
+        || value.len() > 128
+        || value.chars().any(char::is_control)
+        || !value.starts_with("acct_")
+    {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
+pub(super) fn parse_concurrency_limit(
+    value: Option<u64>,
+) -> Result<Option<AccountConcurrencyLimit>, WireValidationError> {
+    value
+        .map(|value| {
+            u32::try_from(value)
+                .ok()
+                .and_then(AccountConcurrencyLimit::new)
+                .ok_or_else(|| WireValidationError::new("concurrencyLimit"))
+        })
+        .transpose()
+}
+
+pub(super) fn deserialize_required_nullable<'de, D>(
+    deserializer: D,
+) -> Result<Option<u64>, D::Error>
+where
+    D: Deserializer<'de>,
+{
+    Option::<u64>::deserialize(deserializer)
+}
+
+pub(super) fn parse_account_weight(value: u64) -> Result<AccountWeight, WireValidationError> {
+    u16::try_from(value)
+        .ok()
+        .and_then(AccountWeight::new)
+        .ok_or_else(|| WireValidationError::new("weight"))
+}
+
+pub(super) fn validate_wire_group_ids(
+    values: &[String],
+) -> Result<Vec<AccountGroupId>, WireValidationError> {
+    if values.len() > MAX_ACCOUNT_GROUP_BATCH
+        || values.iter().collect::<BTreeSet<_>>().len() != values.len()
+    {
+        return Err(WireValidationError::new("groupIds"));
+    }
+    values
+        .iter()
+        .cloned()
+        .map(|value| AccountGroupId::new(value).map_err(|_| WireValidationError::new("groupIds")))
+        .collect()
+}
+
+fn provider_document(
+    value: Value,
+    field: &'static str,
+) -> Result<ProviderDocument, WireValidationError> {
+    match value {
+        Value::Object(document) => Ok(ProviderDocument::new(OpaqueProviderData::new(document))),
+        _ => Err(WireValidationError::new(field)),
+    }
+}
+
+fn require_wire_id(value: &str, field: &'static str) -> Result<(), WireValidationError> {
+    require_text(value, MAX_ID_BYTES, field)?;
+    if value.starts_with("__")
+        || !value
+            .bytes()
+            .all(|byte| byte.is_ascii_alphanumeric() || matches!(byte, b'_' | b'-' | b'.' | b':'))
+    {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
+fn require_text(
+    value: &str,
+    max_bytes: usize,
+    field: &'static str,
+) -> Result<(), WireValidationError> {
+    if value.trim().is_empty() || value.len() > max_bytes || value.chars().any(char::is_control) {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
+fn validate_oauth_material(
+    access_token: &str,
+    refresh_token: Option<&str>,
+    id_token: Option<&str>,
+) -> Result<(), WireValidationError> {
+    if access_token.len() > MAX_ACCESS_TOKEN_BYTES
+        || !valid_visible_ascii(access_token)
+        || !valid_compact_jwt_shape(access_token)
+    {
+        return Err(WireValidationError::new("accessToken"));
+    }
+    if refresh_token.is_some_and(|token| {
+        token.len() > MAX_REFRESH_TOKEN_BYTES
+            || !valid_visible_ascii(token)
+            || token == access_token
+    }) {
+        return Err(WireValidationError::new("refreshToken"));
+    }
+    if id_token.is_some_and(|token| {
+        token.len() > MAX_ID_TOKEN_BYTES
+            || !valid_visible_ascii(token)
+            || !valid_compact_jwt_shape(token)
+    }) {
+        return Err(WireValidationError::new("idToken"));
+    }
+    Ok(())
+}
+
+fn valid_compact_jwt_shape(value: &str) -> bool {
+    let mut segments = value.split('.');
+    matches!(
+        (segments.next(), segments.next(), segments.next(), segments.next()),
+        (Some(header), Some(payload), Some(signature), None)
+            if !header.is_empty() && !payload.is_empty() && !signature.is_empty()
+    )
+}
+
+fn valid_visible_ascii(value: &str) -> bool {
+    !value.is_empty() && value.bytes().all(|byte| (0x21..=0x7e).contains(&byte))
+}
+
+pub(super) fn provider_document_value(document: ProviderDocument) -> Value {
+    Value::Object(document.into_provider_data().into_inner())
+}
@@ -0,0 +1,573 @@
+//! 账号管理路由与 HTTP handler 编排。
+
+use super::*;
+
+/// 构造统一账号管理路由。
+pub fn router<S>() -> Router<S>
+where
+    S: AdminSessionState + Clone + Send + Sync + 'static,
+{
+    Router::new()
+        .route("/api/admin/accounts", get(list_accounts::<S>))
+        .route("/api/admin/accounts/detail", get(account_detail::<S>))
+        .route("/api/admin/accounts/export", get(export_accounts::<S>))
+        .route("/api/admin/accounts/import", post(import_accounts::<S>))
+        .route("/api/admin/accounts/refresh", post(refresh_account::<S>))
+        .route("/api/admin/accounts/recover", post(recover_account::<S>))
+        .route("/api/admin/accounts/rotate", post(rotate_account::<S>))
+        .route("/api/admin/accounts/update", post(update_account::<S>))
+        .route("/api/admin/accounts/delete", post(delete_accounts::<S>))
+        .route(
+            "/api/admin/accounts/batch-update",
+            post(batch_update_accounts::<S>),
+        )
+        .route("/api/admin/accounts/quota", get(account_quota::<S>))
+        .route(
+            "/api/admin/accounts/profile-statistics",
+            get(account_profile_statistics::<S>),
+        )
+        .route(
+            "/api/admin/accounts/profile-avatar",
+            get(account_profile_avatar::<S>),
+        )
+        .route(
+            "/api/admin/accounts/reset-credits",
+            get(account_reset_credits::<S>).post(consume_account_reset_credit::<S>),
+        )
+        .route(
+            "/api/admin/accounts/quota/refresh",
+            post(refresh_account_quota::<S>),
+        )
+        .route("/api/admin/accounts/models", get(account_models::<S>))
+        .route(
+            "/api/admin/accounts/models/refresh",
+            post(refresh_account_models::<S>),
+        )
+        .route(
+            "/api/admin/accounts/connection-test",
+            get(test_account_connection::<S>),
+        )
+        .route(
+            "/api/admin/accounts/oauth/start",
+            post(start_account_authorization::<S>),
+        )
+        .route(
+            "/api/admin/accounts/oauth/complete",
+            post(complete_account_authorization::<S>),
+        )
+}
+
+async fn batch_update_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<BatchUpdateAccountsRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .batch_update(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(BatchUpdatedAccountsData::from(result)),
+    ))
+}
+
+async fn list_accounts<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<ListQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = query.validate().map_err(map_wire_error)?;
+    let page = command.page;
+    let page_size = command.page_size.get();
+    let result = state
+        .admin_services()
+        .accounts()
+        .list(command)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_page_data(result, page, page_size, Utc::now());
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_detail<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .quota(&account_id, false)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountQuotaData {
+        account: account_view(result, Utc::now()),
+    };
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn export_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountExportQuery>,
+) -> Result<Response, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let ids = query.into_ids().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .export(&auth.context().mutation_context(), ids)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountExportData::from_result(result);
+    let mut response = AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)).into_response();
+    response
+        .headers_mut()
+        .insert(header::CACHE_CONTROL, HeaderValue::from_static("no-store"));
+    Ok(response)
+}
+
+async fn import_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountImportRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => {
+            state
+                .admin_services()
+                .openai()
+                .import_document(command)
+                .await
+        }
+        AccountProvider::Xai => state.admin_services().xai().import_document(command).await,
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::CREATED,
+        AdminEnvelope::ok(AccountImportData::from_result(result)),
+    ))
+}
+
+async fn start_account_authorization<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<StartAccountAuthorizationRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => {
+            state
+                .admin_services()
+                .openai()
+                .start_authorization(command)
+                .await
+        }
+        AccountProvider::Xai => {
+            state
+                .admin_services()
+                .xai()
+                .start_authorization(command)
+                .await
+        }
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::CREATED,
+        AdminEnvelope::ok(AccountAuthorizationData::from(result)),
+    ))
+}
+
+async fn complete_account_authorization<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<CompleteAccountAuthorizationRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => {
+            state
+                .admin_services()
+                .openai()
+                .complete_authorization(command)
+                .await
+        }
+        AccountProvider::Xai => {
+            state
+                .admin_services()
+                .xai()
+                .complete_authorization(command)
+                .await
+        }
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::CREATED,
+        AdminEnvelope::ok(AccountMutationData::from(result)),
+    ))
+}
+
+async fn rotate_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<RotateAccountRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .openai()
+        .rotate(command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountMutationData::from(result)),
+    ))
+}
+
+async fn update_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<UpdateAccountRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .update(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(UpdatedAccountData::from(result)),
+    ))
+}
+
+async fn delete_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountDeletionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => state.admin_services().openai().delete(command).await,
+        AccountProvider::Xai => state.admin_services().xai().delete(command).await,
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountDeletionData::from(result)),
+    ))
+}
+
+async fn refresh_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountRefreshRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .refresh(&auth.context().mutation_context(), account_id)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_refresh_data(result, Utc::now());
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn recover_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountActionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .recover(&auth.context().mutation_context(), account_id)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_refresh_data(result, Utc::now());
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_quota<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .quota(&account_id, false)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountQuotaData {
+        account: account_view(result, Utc::now()),
+    };
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_profile_statistics<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .profile_statistics(&account_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountProfileStatisticsData::from(result)),
+    ))
+}
+
+async fn account_profile_avatar<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountProfileAvatarQuery>,
+) -> Result<Response, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let avatar = state
+        .admin_services()
+        .accounts()
+        .profile_avatar(&account_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(profile_avatar_response(avatar))
+}
+
+/// 将 Provider 头像流投影为受保护的同源 HTTP 响应。
+#[must_use]
+pub fn profile_avatar_response(avatar: ProviderProfileAvatar) -> Response {
+    let ProviderProfileAvatar {
+        content_type,
+        content_length,
+        etag,
+        body,
+    } = avatar;
+    let mut response = Response::new(Body::from_stream(body));
+    *response.status_mut() = StatusCode::OK;
+    let headers = response.headers_mut();
+    headers.insert(
+        header::CONTENT_TYPE,
+        content_type
+            .and_then(|value| HeaderValue::from_str(&value).ok())
+            .unwrap_or_else(|| HeaderValue::from_static("application/octet-stream")),
+    );
+    if let Some(value) =
+        content_length.and_then(|length| HeaderValue::from_str(&length.to_string()).ok())
+    {
+        headers.insert(header::CONTENT_LENGTH, value);
+    }
+    if let Some(value) = etag.and_then(|value| HeaderValue::from_str(&value).ok()) {
+        headers.insert(header::ETAG, value);
+    }
+    headers.insert(
+        header::CACHE_CONTROL,
+        HeaderValue::from_static("private, max-age=3600"),
+    );
+    headers.insert(
+        HeaderName::from_static("x-content-type-options"),
+        HeaderValue::from_static("nosniff"),
+    );
+    headers.insert(
+        HeaderName::from_static("cross-origin-resource-policy"),
+        HeaderValue::from_static("same-origin"),
+    );
+    headers.insert(
+        HeaderName::from_static("content-security-policy"),
+        HeaderValue::from_static("sandbox; default-src 'none'"),
+    );
+    response
+}
+
+async fn refresh_account_quota<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountActionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .quota(&account_id, true)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountQuotaData {
+        account: account_view(result, Utc::now()),
+    };
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_reset_credits<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .reset_credits(&auth.context().mutation_context(), account_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountResetCreditsData::from(result)),
+    ))
+}
+
+async fn consume_account_reset_credit<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountResetCreditConsumeRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .consume_reset_credit(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountResetCreditResultData::from(result)),
+    ))
+}
+
+async fn account_models<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .models(&account_id, false)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_models_data(result);
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn refresh_account_models<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountActionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .models(&account_id, true)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_models_data(result);
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn test_account_connection<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountTestQuery>,
+) -> Result<Sse<impl Stream<Item = Result<Event, Infallible>>>, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (account_id, upstream_model) = query.into_command().map_err(map_wire_error)?;
+    let stream = state
+        .admin_services()
+        .accounts()
+        .test_connection(account_id, upstream_model)
+        .await
+        .map_err(map_service_error)?
+        .map(|event| {
+            let event = AccountConnectionTestEvent::from(event);
+            let data = serde_json::to_string(&event.data).unwrap_or_else(|_| "{}".to_owned());
+            Ok(Event::default().data(data))
+        });
+    Ok(Sse::new(stream).keep_alive(KeepAlive::default()))
+}
@@ -0,0 +1,81 @@
+//! 管理端账号目录的 HTTP 合同、凭据动作、路由处理与安全响应投影。
+
+use std::{collections::BTreeSet, convert::Infallible, fmt};
+
+use axum::{
+    Router,
+    body::Body,
+    extract::State,
+    http::{HeaderName, HeaderValue, StatusCode, header},
+    response::{
+        IntoResponse, Response,
+        sse::{Event, KeepAlive, Sse},
+    },
+    routing::{get, post},
+};
+use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
+use chrono::{DateTime, FixedOffset, Utc};
+use futures::{Stream, StreamExt as _};
+use gateway_admin::model::{
+    AdminError as AdminServiceError, PageSize,
+    accounts::{
+        AccountConcurrencyLimit, AccountConnectionTestEvent as DomainConnectionTestEvent,
+        AccountCost, AccountGroupFilter, AccountListQuery, AccountModelUsage, AccountSort,
+        AccountSortField, AccountStatus as DomainAccountStatus, AccountUpdateResult, AccountUsage,
+        AccountWeight, AccountsUpdateResult, BatchUpdateAccounts, SortDirection, UpdateAccount,
+    },
+    provider_credentials::{
+        AccountDirectoryItem, AccountDirectoryPage, AccountExportBundle, AccountRefreshResult,
+        AuthorizationStarted, CompleteAuthorization, ConsumeProviderResetCredit,
+        CredentialDeletion, CredentialDeletionResult, CredentialImportResult, CredentialMutation,
+        CredentialMutationResult, ImportCredentials, ProviderDocument, ProviderModels,
+        ProviderProfileActivityInsights, ProviderProfileAvatar, ProviderProfileDailyUsage,
+        ProviderProfileInvocation, ProviderProfileStatistics, ProviderProfileStatisticsSummary,
+        ProviderQuota, ProviderQuotaWindow, ProviderResetCredit, ProviderResetCreditResult,
+        ProviderResetCredits, RotateCredential, StartAuthorization,
+    },
+};
+use gateway_core::{
+    account::{OpaqueProviderData, ProviderAccountId},
+    routing::{AccountGroupId, ProviderKind, UpstreamModelId},
+};
+use serde::{Deserialize, Deserializer, Serialize};
+use serde_json::{Map, Value};
+use uuid::{Uuid, Version};
+
+use super::presenter::{format_compact_number, format_decimal_currency, format_number};
+use super::{
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    PageMeta, WireValidationError,
+};
+
+const DEFAULT_PAGE_SIZE: u32 = 50;
+const MAX_PAGE_SIZE: u32 = 200;
+const MAX_SEARCH_BYTES: usize = 256;
+const MAX_ID_BYTES: usize = 256;
+const MAX_NAME_BYTES: usize = 512;
+const MAX_IMPORT_DATA_BYTES: usize = 64 * 1024 * 1024;
+const MAX_ACCESS_TOKEN_BYTES: usize = 16 * 1024;
+const MAX_REFRESH_TOKEN_BYTES: usize = 64 * 1024;
+const MAX_ID_TOKEN_BYTES: usize = 16 * 1024;
+const MAX_CALLBACK_URL_BYTES: usize = 64 * 1024;
+const MAX_ACCOUNT_DELETE_BATCH: usize = 200;
+const MAX_ACCOUNT_GROUP_BATCH: usize = 1000;
+const MAX_AVATAR_VERSION_BYTES: usize = 32;
+
+mod credentials;
+mod handlers;
+mod presenter;
+mod wire;
+
+pub use credentials::*;
+pub use handlers::{profile_avatar_response, router};
+pub(super) use presenter::quota_window_view;
+pub use wire::*;
+
+use credentials::{
+    AccountProvider, deserialize_required_nullable, parse_account_weight, parse_concurrency_limit,
+    provider_document_value, require_account_id, validate_wire_group_ids,
+};
+use presenter::*;
+use wire::BatchUpdatedAccountsData;
@@ -0,0 +1,417 @@
+//! Admin 领域结果到安全 HTTP wire 的展示投影。
+
+use super::*;
+
+pub(super) fn account_page_data(
+    result: AccountDirectoryPage,
+    page: u32,
+    page_size: u16,
+    now: DateTime<Utc>,
+) -> AccountPageData {
+    let total_pages = if result.total == 0 {
+        0
+    } else {
+        u32::try_from(result.total.div_ceil(u64::from(page_size))).unwrap_or(u32::MAX)
+    };
+    AccountPageData {
+        items: result
+            .items
+            .into_iter()
+            .map(|item| account_view(item, now))
+            .collect(),
+        page: PageMeta::new(page, u32::from(page_size), result.total, total_pages),
+        summary: AccountSummaryView {
+            total: result.summary.total,
+            normal: result.summary.normal,
+            quota_exhausted: result.summary.quota_exhausted,
+            rate_limited: result.summary.rate_limited,
+            disabled: result.summary.disabled,
+            error: result.summary.error,
+        },
+    }
+}
+
+pub(super) fn account_refresh_data(
+    result: AccountRefreshResult,
+    now: DateTime<Utc>,
+) -> AccountRefreshData {
+    AccountRefreshData {
+        account: account_view(result.account, now),
+    }
+}
+
+pub(super) fn account_models_data(result: ProviderModels) -> AccountModelsData {
+    AccountModelsData {
+        models: result
+            .models
+            .into_iter()
+            .map(|model| {
+                let id = model.id.to_string();
+                AccountModelView {
+                    label: id.clone(),
+                    id,
+                }
+            })
+            .collect(),
+    }
+}
+
+pub(super) fn account_view(item: AccountDirectoryItem, now: DateTime<Utc>) -> AccountView {
+    let AccountDirectoryItem {
+        account,
+        projection,
+        usage,
+        quota,
+    } = item;
+    let status = projection.status.as_str().to_owned();
+    let rate_limited_until = projection.rate_limited_until.map(DateTime::<Utc>::from);
+    let expires_at = account.access_token_expires_at.as_ref().map(china_rfc3339);
+    let added_at = china_rfc3339(&account.created_at);
+    let updated_at = china_rfc3339(&account.updated_at);
+    let (quota, refresh_token_expires_at) = account_quota_view(quota, rate_limited_until, now);
+    AccountView {
+        id: account.id.clone(),
+        name: account.name,
+        provider: account.provider_kind.to_string(),
+        groups: account
+            .groups
+            .into_iter()
+            .map(|group| AccountGroupRefView {
+                id: group.id.to_string(),
+                name: group.name,
+                color: group.color.as_str().to_owned(),
+                enabled: group.enabled,
+            })
+            .collect(),
+        resource_ref: account.id,
+        email: account.email,
+        account_id: account.upstream_account_id,
+        user_id: account.upstream_user_id,
+        label: None,
+        plan_type: account.plan_type,
+        authentication_kind: account.authentication_kind,
+        has_refresh_token: account.has_refresh_token,
+        status,
+        error_reason: projection
+            .error_reason
+            .map(|reason| reason.as_str().to_owned()),
+        error_message: projection.error_message,
+        enabled: account.enabled,
+        concurrency_limit: account.concurrency_limit.map(|limit| limit.get()),
+        weight: account.weight.get(),
+        access_token_expires_at: expires_at,
+        access_token_expires_at_display: account
+            .access_token_expires_at
+            .as_ref()
+            .map(china_datetime),
+        refresh_token_expires_at,
+        next_refresh_at: account.next_refresh_at.map(|value| china_rfc3339(&value)),
+        added_at,
+        added_at_display: china_datetime(&account.created_at),
+        updated_at,
+        updated_at_display: china_datetime(&account.updated_at),
+        quota,
+        usage: account_usage_view(usage, now),
+    }
+}
+
+pub(super) fn account_quota_view(
+    mut quota: ProviderQuota,
+    rate_limited_until: Option<DateTime<Utc>>,
+    now: DateTime<Utc>,
+) -> (AccountQuotaView, Option<String>) {
+    quota.apply_limit_reached_display();
+    let refresh_token_expires_at = quota
+        .refresh_token_expires_at
+        .map(|value| china_rfc3339(&value));
+    let refreshed_at_display = quota
+        .observed_at
+        .map_or_else(|| "—".to_owned(), |value| relative_time(value, now));
+    let windows = quota.windows.into_iter().map(quota_window_view).collect();
+    let rate_limited_until = rate_limited_until.map(|until| china_datetime(&until));
+    (
+        AccountQuotaView {
+            refreshed_at_display,
+            limit_reached: quota.limit_reached,
+            rate_limited_until,
+            windows,
+        },
+        refresh_token_expires_at,
+    )
+}
+
+pub(crate) fn quota_window_view(window: ProviderQuotaWindow) -> AccountQuotaWindowView {
+    let ProviderQuotaWindow {
+        key,
+        group,
+        label,
+        limit_id,
+        limit_name,
+        role,
+        local_usage_attribution: _,
+        window_seconds,
+        used_percent,
+        reset_at,
+        limit_reached,
+        local_usage,
+        provider_data: _,
+    } = window;
+    let label_display = limit_name
+        .as_ref()
+        .map_or_else(|| label.clone(), |name| format!("{name} · {label}"));
+    AccountQuotaWindowView {
+        label_display,
+        window_label_display: label,
+        key,
+        group,
+        limit_id,
+        limit_name,
+        role: role.map(|value| value.as_str().to_owned()),
+        window_seconds,
+        used_percent,
+        used_percent_display: used_percent
+            .map_or_else(|| "—".to_owned(), |value| format!("{value:.1}%")),
+        limit_reached,
+        local_usage: local_usage.as_ref().map(quota_local_usage),
+        reset_at_display: reset_at.map_or_else(|| "—".to_owned(), |value| china_datetime(&value)),
+    }
+}
+
+pub(super) fn quota_local_usage(usage: &AccountUsage) -> Value {
+    let total_tokens = usage.total_tokens.unwrap_or_default();
+    serde_json::json!({
+        "requestCount": usage.request_count,
+        "requestCountDisplay": format_number(usage.request_count),
+        "inputTokens": usage.input_tokens.unwrap_or_default(),
+        "inputTokensDisplay": display_optional_tokens(usage.input_tokens),
+        "outputTokens": usage.output_tokens.unwrap_or_default(),
+        "outputTokensDisplay": display_optional_tokens(usage.output_tokens),
+        "cachedTokens": usage.cached_tokens.unwrap_or_default(),
+        "cachedTokensDisplay": display_optional_tokens(usage.cached_tokens),
+        "imageInputTokens": usage.image_input_tokens.unwrap_or_default(),
+        "imageInputTokensDisplay": display_optional_tokens(usage.image_input_tokens),
+        "imageOutputTokens": usage.image_output_tokens.unwrap_or_default(),
+        "imageOutputTokensDisplay": display_optional_tokens(usage.image_output_tokens),
+        "imageRequestCount": usage.image_request_count,
+        "imageRequestFailedCount": usage.image_request_failed_count,
+        "totalTokens": total_tokens,
+        "totalTokensDisplay": format_compact_number(total_tokens),
+        "requestBuckets": usage.request_buckets.iter().map(|bucket| serde_json::json!({
+            "bucketStart": bucket.bucket_start,
+            "requestCount": bucket.request_count,
+        })).collect::<Vec<_>>(),
+    })
+}
+
+pub(super) fn account_usage_view(
+    usage: Option<AccountUsage>,
+    now: DateTime<Utc>,
+) -> AccountUsageView {
+    let Some(usage) = usage else {
+        return empty_account_usage();
+    };
+    let known_count = usage
+        .cost_coverage
+        .provider_reported_count
+        .saturating_add(usage.cost_coverage.calculated_count);
+    let cost_estimate_status = if known_count == 0 {
+        "unknown"
+    } else if usage.cost_coverage.unavailable_count > 0 {
+        "partial"
+    } else {
+        "known"
+    };
+    AccountUsageView {
+        request_count: Some(usage.request_count),
+        request_count_display: format_number(usage.request_count),
+        input_tokens: usage.input_tokens,
+        input_tokens_display: display_optional_tokens(usage.input_tokens),
+        output_tokens: usage.output_tokens,
+        output_tokens_display: display_optional_tokens(usage.output_tokens),
+        cached_tokens: usage.cached_tokens,
+        cached_tokens_display: display_optional_tokens(usage.cached_tokens),
+        reasoning_tokens: usage.reasoning_tokens,
+        reasoning_tokens_display: display_optional_tokens(usage.reasoning_tokens),
+        image_input_tokens: usage.image_input_tokens,
+        image_input_tokens_display: display_optional_tokens(usage.image_input_tokens),
+        image_output_tokens: usage.image_output_tokens,
+        image_output_tokens_display: display_optional_tokens(usage.image_output_tokens),
+        image_request_count: Some(usage.image_request_count),
+        image_request_count_display: format_number(usage.image_request_count),
+        image_request_failed_count: Some(usage.image_request_failed_count),
+        image_request_failed_count_display: format_number(usage.image_request_failed_count),
+        total_tokens: usage.total_tokens,
+        total_tokens_display: display_optional_tokens(usage.total_tokens),
+        created_tokens: usage.cache_write_tokens,
+        created_tokens_display: display_optional_tokens(usage.cache_write_tokens),
+        read_tokens: usage.cached_tokens,
+        read_tokens_display: display_optional_tokens(usage.cached_tokens),
+        last_used_at: usage.last_used_at.map(|value| china_rfc3339(&value)),
+        last_used_at_display: usage
+            .last_used_at
+            .map_or_else(|| "—".to_owned(), |value| relative_time(value, now)),
+        cost_estimate_status: cost_estimate_status.to_owned(),
+        known_cost_count: Some(known_count),
+        partial_cost_count: Some(u64::from(cost_estimate_status == "partial")),
+        unknown_cost_count: Some(usage.cost_coverage.unavailable_count),
+        costs: usage.costs.iter().map(account_currency_cost_view).collect(),
+        models: usage
+            .models
+            .into_iter()
+            .map(|model| account_model_usage_view(model, now))
+            .collect(),
+    }
+}
+
+pub(super) fn account_model_usage_view(
+    usage: AccountModelUsage,
+    now: DateTime<Utc>,
+) -> ModelUsageView {
+    let known_count = usage
+        .cost_coverage
+        .provider_reported_count
+        .saturating_add(usage.cost_coverage.calculated_count);
+    let cost_estimate_status = if known_count == 0 {
+        "unknown"
+    } else if usage.cost_coverage.unavailable_count > 0 {
+        "partial"
+    } else {
+        "known"
+    };
+    let usd = usage
+        .costs
+        .iter()
+        .find(|cost| cost.currency.eq_ignore_ascii_case("USD"));
+    ModelUsageView {
+        model: usage.model,
+        request_count: usage.request_count,
+        request_count_display: format_number(usage.request_count),
+        success_rate: (usage.request_count > 0)
+            .then(|| usage.success_count as f64 * 100.0 / usage.request_count as f64),
+        success_rate_display: if usage.request_count == 0 {
+            "—".to_owned()
+        } else {
+            format!(
+                "{:.1}%",
+                usage.success_count as f64 * 100.0 / usage.request_count as f64
+            )
+        },
+        input_tokens: usage.input_tokens,
+        input_tokens_display: display_optional_tokens(usage.input_tokens),
+        output_tokens: usage.output_tokens,
+        output_tokens_display: display_optional_tokens(usage.output_tokens),
+        cached_tokens: usage.cached_tokens,
+        cached_tokens_display: display_optional_tokens(usage.cached_tokens),
+        image_input_tokens: usage.image_input_tokens,
+        image_input_tokens_display: display_optional_tokens(usage.image_input_tokens),
+        image_output_tokens: usage.image_output_tokens,
+        image_output_tokens_display: display_optional_tokens(usage.image_output_tokens),
+        image_request_count: usage.image_request_count,
+        image_request_count_display: format_number(usage.image_request_count),
+        image_request_failed_count: usage.image_request_failed_count,
+        image_request_failed_count_display: format_number(usage.image_request_failed_count),
+        total_tokens: usage.total_tokens,
+        total_tokens_display: display_optional_tokens(usage.total_tokens),
+        billing_amount_usd: usd.map(|cost| cost.amount.as_str().to_owned()),
+        billing_amount_usd_display: usd.map_or_else(
+            || "—".to_owned(),
+            |cost| format_decimal_currency(cost.amount.as_str(), "USD"),
+        ),
+        cost_estimate_status: cost_estimate_status.to_owned(),
+        known_cost_count: known_count,
+        partial_cost_count: u64::from(cost_estimate_status == "partial"),
+        unknown_cost_count: usage.cost_coverage.unavailable_count,
+        costs: usage.costs.iter().map(account_currency_cost_view).collect(),
+        last_used_at: china_rfc3339(&usage.last_used_at),
+        last_used_at_display: relative_time(usage.last_used_at, now),
+    }
+}
+
+pub(super) fn account_currency_cost_view(cost: &AccountCost) -> CurrencyCostView {
+    CurrencyCostView {
+        currency: cost.currency.clone(),
+        estimated_amount: cost.amount.as_str().to_owned(),
+        estimated_amount_display: format_decimal_currency(cost.amount.as_str(), &cost.currency),
+    }
+}
+
+pub(super) fn display_optional_tokens(value: Option<u64>) -> String {
+    value.map_or_else(|| "—".to_owned(), format_compact_number)
+}
+
+pub(super) fn empty_account_usage() -> AccountUsageView {
+    AccountUsageView {
+        request_count: None,
+        request_count_display: "—".to_owned(),
+        input_tokens: None,
+        input_tokens_display: "—".to_owned(),
+        output_tokens: None,
+        output_tokens_display: "—".to_owned(),
+        cached_tokens: None,
+        cached_tokens_display: "—".to_owned(),
+        reasoning_tokens: None,
+        reasoning_tokens_display: "—".to_owned(),
+        image_input_tokens: None,
+        image_input_tokens_display: "—".to_owned(),
+        image_output_tokens: None,
+        image_output_tokens_display: "—".to_owned(),
+        image_request_count: None,
+        image_request_count_display: "—".to_owned(),
+        image_request_failed_count: None,
+        image_request_failed_count_display: "—".to_owned(),
+        total_tokens: None,
+        total_tokens_display: "—".to_owned(),
+        created_tokens: None,
+        created_tokens_display: "—".to_owned(),
+        read_tokens: None,
+        read_tokens_display: "—".to_owned(),
+        last_used_at: None,
+        last_used_at_display: "—".to_owned(),
+        cost_estimate_status: "unavailable".to_owned(),
+        known_cost_count: None,
+        partial_cost_count: None,
+        unknown_cost_count: None,
+        costs: Vec::new(),
+        models: Vec::new(),
+    }
+}
+
+pub(super) fn relative_time(value: DateTime<Utc>, now: DateTime<Utc>) -> String {
+    let elapsed = now.signed_duration_since(value);
+    if elapsed.num_seconds() < 0 {
+        return china_datetime(&value);
+    }
+    if elapsed.num_seconds() < 60 {
+        return "刚刚".to_owned();
+    }
+    if elapsed.num_minutes() < 60 {
+        return format!("{} 分钟前", elapsed.num_minutes());
+    }
+    if elapsed.num_hours() < 24 {
+        return format!("{} 小时前", elapsed.num_hours());
+    }
+    format!("{} 天前", elapsed.num_days())
+}
+
+pub(super) fn china_offset() -> FixedOffset {
+    FixedOffset::east_opt(8 * 60 * 60).expect("UTC+8 is a valid fixed offset")
+}
+
+pub(super) fn china_rfc3339(value: &DateTime<Utc>) -> String {
+    value.with_timezone(&china_offset()).to_rfc3339()
+}
+
+pub(super) fn china_datetime(value: &DateTime<Utc>) -> String {
+    value
+        .with_timezone(&china_offset())
+        .format("%Y-%m-%d %H:%M:%S")
+        .to_string()
+}
+
+pub(super) fn map_wire_error(error: WireValidationError) -> AdminError {
+    AdminError::bad_request(format!("{} 字段不合法", error.field()))
+}
+
+pub(super) fn map_service_error(error: AdminServiceError) -> AdminError {
+    super::super::wire::map_admin_service_error(error)
+}
@@ -0,0 +1,840 @@
+//! 账号管理请求、响应与查询 wire contract。
+
+use super::*;
+
+/// 账号列表查询参数。
+#[derive(Debug, Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct ListQuery {
+    pub page: Option<u32>,
+    pub page_size: Option<u32>,
+    pub provider: Option<String>,
+    pub group_id: Option<String>,
+    pub search: Option<String>,
+    pub status: Option<String>,
+    pub sort_by: Option<String>,
+    pub sort_direction: Option<String>,
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct BatchUpdateAccountsRequest {
+    pub account_ids: Vec<String>,
+    pub enabled: bool,
+    #[serde(deserialize_with = "deserialize_required_nullable")]
+    pub concurrency_limit: Option<u64>,
+    pub weight: u64,
+    pub group_ids: Vec<String>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub(super) struct BatchUpdatedAccountsData {
+    account_ids: Vec<String>,
+    config_revision: u64,
+}
+
+impl From<AccountsUpdateResult> for BatchUpdatedAccountsData {
+    fn from(result: AccountsUpdateResult) -> Self {
+        Self {
+            account_ids: result
+                .account_ids
+                .into_iter()
+                .map(|id| id.to_string())
+                .collect(),
+            config_revision: result.config_revision.get(),
+        }
+    }
+}
+
+impl BatchUpdateAccountsRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        if self.account_ids.is_empty()
+            || self.account_ids.len() > MAX_ACCOUNT_GROUP_BATCH
+            || self
+                .account_ids
+                .iter()
+                .any(|id| require_account_id(id, "accountIds").is_err())
+            || self.account_ids.iter().collect::<BTreeSet<_>>().len() != self.account_ids.len()
+        {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        validate_wire_group_ids(&self.group_ids)?;
+        parse_concurrency_limit(self.concurrency_limit)?;
+        parse_account_weight(self.weight)?;
+        Ok(())
+    }
+
+    pub(super) fn into_command(self) -> Result<BatchUpdateAccounts, WireValidationError> {
+        self.validate()?;
+        Ok(BatchUpdateAccounts {
+            account_ids: self.account_ids,
+            enabled: self.enabled,
+            concurrency_limit: parse_concurrency_limit(self.concurrency_limit)?,
+            weight: parse_account_weight(self.weight)?,
+            group_ids: validate_wire_group_ids(&self.group_ids)?,
+        })
+    }
+}
+
+impl ListQuery {
+    /// 解析并校验全部 wire 字段，生成 Admin 查询命令。
+    pub fn validate(self) -> Result<AccountListQuery, WireValidationError> {
+        let page = self.page.unwrap_or(1);
+        if page == 0 {
+            return Err(WireValidationError::new("page"));
+        }
+        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
+        if page_size == 0 || page_size > MAX_PAGE_SIZE {
+            return Err(WireValidationError::new("pageSize"));
+        }
+        let provider_kind = parse_provider(self.provider.as_deref().unwrap_or("all"))?;
+        let group_filter = match self.group_id.as_deref().map(str::trim) {
+            None | Some("") => None,
+            Some("ungrouped") => Some(AccountGroupFilter::Ungrouped),
+            Some(value) => Some(AccountGroupFilter::Group(
+                AccountGroupId::new(value.to_owned())
+                    .map_err(|_| WireValidationError::new("groupId"))?,
+            )),
+        };
+        let search = self
+            .search
+            .map(|value| value.trim().to_owned())
+            .filter(|value| !value.is_empty());
+        if search.as_deref().is_some_and(|value| {
+            value.len() > MAX_SEARCH_BYTES || value.chars().any(char::is_control)
+        }) {
+            return Err(WireValidationError::new("search"));
+        }
+        let status = match self.status.as_deref().map(str::trim) {
+            None | Some("") => None,
+            Some(value) => Some(
+                DomainAccountStatus::parse(&value.to_ascii_lowercase())
+                    .ok_or_else(|| WireValidationError::new("status"))?,
+            ),
+        };
+        let sort = match (self.sort_by.as_deref(), self.sort_direction.as_deref()) {
+            (None, None) => None,
+            (Some(field), Some(direction)) => Some(AccountSort {
+                field: parse_sort_field(field).ok_or_else(|| WireValidationError::new("sortBy"))?,
+                direction: parse_sort_direction(direction)
+                    .ok_or_else(|| WireValidationError::new("sortDirection"))?,
+            }),
+            _ => return Err(WireValidationError::new("sort")),
+        };
+        Ok(AccountListQuery {
+            page,
+            page_size: PageSize::new(
+                u16::try_from(page_size).map_err(|_| WireValidationError::new("pageSize"))?,
+            )
+            .map_err(|_| WireValidationError::new("pageSize"))?,
+            provider_kind,
+            group_filter,
+            search,
+            status,
+            sort,
+        })
+    }
+}
+
+fn parse_provider(value: &str) -> Result<Option<ProviderKind>, WireValidationError> {
+    let value = value.trim();
+    if value.is_empty() || value.eq_ignore_ascii_case("all") {
+        return Ok(None);
+    }
+    ProviderKind::new(value.to_owned())
+        .map(Some)
+        .map_err(|_| WireValidationError::new("provider"))
+}
+
+fn parse_sort_field(value: &str) -> Option<AccountSortField> {
+    match value.trim() {
+        "email" => Some(AccountSortField::Email),
+        "status" => Some(AccountSortField::Status),
+        "planType" => Some(AccountSortField::PlanType),
+        "usage" => Some(AccountSortField::Usage),
+        "lastUsedAt" => Some(AccountSortField::LastUsedAt),
+        "expiresAt" => Some(AccountSortField::ExpiresAt),
+        _ => None,
+    }
+}
+
+fn parse_sort_direction(value: &str) -> Option<SortDirection> {
+    match value.trim().to_ascii_lowercase().as_str() {
+        "asc" => Some(SortDirection::Asc),
+        "desc" => Some(SortDirection::Desc),
+        _ => None,
+    }
+}
+
+/// 账号列表响应数据。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountPageData {
+    pub items: Vec<AccountView>,
+    pub page: PageMeta,
+    pub summary: AccountSummaryView,
+}
+
+/// 账号概览计数。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountSummaryView {
+    pub total: u64,
+    pub normal: u64,
+    pub quota_exhausted: u64,
+    pub rate_limited: u64,
+    pub disabled: u64,
+    pub error: u64,
+}
+
+/// 一条安全账号视图。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountView {
+    pub id: String,
+    pub name: String,
+    pub provider: String,
+    pub groups: Vec<AccountGroupRefView>,
+    pub resource_ref: String,
+    pub email: Option<String>,
+    pub account_id: Option<String>,
+    pub user_id: Option<String>,
+    pub label: Option<String>,
+    pub plan_type: Option<String>,
+    pub authentication_kind: String,
+    pub has_refresh_token: bool,
+    pub status: String,
+    /// `status == "error"` 时的具体原因；其余状态为 `null`。
+    pub error_reason: Option<String>,
+    /// 最近一次失败的上游错误描述；仅错误状态存在。
+    pub error_message: Option<String>,
+    pub enabled: bool,
+    pub concurrency_limit: Option<u32>,
+    pub weight: u16,
+    pub access_token_expires_at: Option<String>,
+    pub access_token_expires_at_display: Option<String>,
+    pub refresh_token_expires_at: Option<String>,
+    pub next_refresh_at: Option<String>,
+    pub added_at: String,
+    pub added_at_display: String,
+    pub updated_at: String,
+    pub updated_at_display: String,
+    pub quota: AccountQuotaView,
+    pub usage: AccountUsageView,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountGroupRefView {
+    pub id: String,
+    pub name: String,
+    pub color: String,
+    pub enabled: bool,
+}
+
+/// Provider quota 安全视图。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountQuotaView {
+    pub refreshed_at_display: String,
+    pub limit_reached: bool,
+    /// 429 临时限流（Redis 冷却）到期时间展示；非限流中为 `null`。
+    pub rate_limited_until: Option<String>,
+    pub windows: Vec<AccountQuotaWindowView>,
+}
+
+/// 一个 quota 时间窗口。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountQuotaWindowView {
+    pub key: String,
+    pub group: String,
+    pub limit_id: Option<String>,
+    pub limit_name: Option<String>,
+    pub role: Option<String>,
+    pub window_seconds: Option<u64>,
+    pub label_display: String,
+    pub window_label_display: String,
+    pub used_percent: Option<f64>,
+    pub used_percent_display: String,
+    pub limit_reached: bool,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub local_usage: Option<serde_json::Value>,
+    pub reset_at_display: String,
+}
+
+/// 账号观测用量。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountUsageView {
+    pub request_count: Option<u64>,
+    pub request_count_display: String,
+    pub input_tokens: Option<u64>,
+    pub input_tokens_display: String,
+    pub output_tokens: Option<u64>,
+    pub output_tokens_display: String,
+    pub cached_tokens: Option<u64>,
+    pub cached_tokens_display: String,
+    pub reasoning_tokens: Option<u64>,
+    pub reasoning_tokens_display: String,
+    pub image_input_tokens: Option<u64>,
+    pub image_input_tokens_display: String,
+    pub image_output_tokens: Option<u64>,
+    pub image_output_tokens_display: String,
+    pub image_request_count: Option<u64>,
+    pub image_request_count_display: String,
+    pub image_request_failed_count: Option<u64>,
+    pub image_request_failed_count_display: String,
+    pub total_tokens: Option<u64>,
+    pub total_tokens_display: String,
+    pub created_tokens: Option<u64>,
+    pub created_tokens_display: String,
+    pub read_tokens: Option<u64>,
+    pub read_tokens_display: String,
+    pub last_used_at: Option<String>,
+    pub last_used_at_display: String,
+    pub cost_estimate_status: String,
+    pub known_cost_count: Option<u64>,
+    pub partial_cost_count: Option<u64>,
+    pub unknown_cost_count: Option<u64>,
+    pub costs: Vec<CurrencyCostView>,
+    pub models: Vec<ModelUsageView>,
+}
+
+/// 凭据在单个上游模型上的观测用量。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct ModelUsageView {
+    pub model: String,
+    pub request_count: u64,
+    pub request_count_display: String,
+    pub success_rate: Option<f64>,
+    pub success_rate_display: String,
+    pub input_tokens: Option<u64>,
+    pub input_tokens_display: String,
+    pub output_tokens: Option<u64>,
+    pub output_tokens_display: String,
+    pub cached_tokens: Option<u64>,
+    pub cached_tokens_display: String,
+    pub image_input_tokens: Option<u64>,
+    pub image_input_tokens_display: String,
+    pub image_output_tokens: Option<u64>,
+    pub image_output_tokens_display: String,
+    pub image_request_count: u64,
+    pub image_request_count_display: String,
+    pub image_request_failed_count: u64,
+    pub image_request_failed_count_display: String,
+    pub total_tokens: Option<u64>,
+    pub total_tokens_display: String,
+    pub billing_amount_usd: Option<String>,
+    pub billing_amount_usd_display: String,
+    pub cost_estimate_status: String,
+    pub known_cost_count: u64,
+    pub partial_cost_count: u64,
+    pub unknown_cost_count: u64,
+    pub costs: Vec<CurrencyCostView>,
+    pub last_used_at: String,
+    pub last_used_at_display: String,
+}
+
+/// 单一货币的可查询成本。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct CurrencyCostView {
+    pub currency: String,
+    pub estimated_amount: String,
+    pub estimated_amount_display: String,
+}
+
+/// 账号详情类 GET 的固定 ID query。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountIdQuery {
+    pub account_id: String,
+}
+
+impl AccountIdQuery {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")
+    }
+
+    pub(super) fn into_id(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 头像 GET 的固定 query；`version` 只参与浏览器缓存键，不进入上游请求。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountProfileAvatarQuery {
+    pub account_id: String,
+    pub version: Option<String>,
+}
+
+impl AccountProfileAvatarQuery {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        if self.version.as_deref().is_some_and(|version| {
+            version.is_empty()
+                || version.len() > MAX_AVATAR_VERSION_BYTES
+                || !version.bytes().all(|byte| byte.is_ascii_alphanumeric())
+        }) {
+            return Err(WireValidationError::new("version"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_id(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 敏感导出的固定 query；IDs 使用逗号分隔，禁止隐式导出全部账号。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountExportQuery {
+    pub account_ids: String,
+    pub confirm: String,
+}
+
+impl AccountExportQuery {
+    pub fn into_ids(self) -> Result<Vec<ProviderAccountId>, WireValidationError> {
+        if self.confirm != "export_sensitive_accounts" {
+            return Err(WireValidationError::new("confirm"));
+        }
+        let ids = self
+            .account_ids
+            .split(',')
+            .map(str::trim)
+            .filter(|id| !id.is_empty())
+            .map(ToOwned::to_owned)
+            .collect::<Vec<_>>();
+        if ids.is_empty()
+            || ids.len() > 200
+            || ids
+                .iter()
+                .any(|id| require_account_id(id, "accountIds").is_err())
+        {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        let unique = ids.iter().collect::<BTreeSet<_>>();
+        if unique.len() != ids.len() {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        ids.into_iter()
+            .map(|id| {
+                ProviderAccountId::new(id).map_err(|_| WireValidationError::new("accountIds"))
+            })
+            .collect()
+    }
+}
+
+/// 账号运行期动作。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountActionRequest {
+    pub account_id: String,
+}
+
+impl AccountActionRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")
+    }
+
+    pub(super) fn into_id(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 主动额度重置卡消费请求。幂等键由 UI 生成并在不确定重试时复用，与官方一致。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountResetCreditConsumeRequest {
+    pub account_id: String,
+    #[serde(default)]
+    pub credit_id: Option<String>,
+    pub redeem_request_id: String,
+}
+
+impl AccountResetCreditConsumeRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        if self.credit_id.as_deref().is_some_and(|value| {
+            let value = value.trim();
+            value.is_empty() || value.len() > 512 || value.chars().any(char::is_control)
+        }) {
+            return Err(WireValidationError::new("creditId"));
+        }
+        let value = self.redeem_request_id.trim();
+        let redeem_request_id =
+            Uuid::parse_str(value).map_err(|_| WireValidationError::new("redeemRequestId"))?;
+        if redeem_request_id.get_version() != Some(Version::Random)
+            || redeem_request_id.hyphenated().to_string() != value
+        {
+            return Err(WireValidationError::new("redeemRequestId"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(self) -> Result<ConsumeProviderResetCredit, WireValidationError> {
+        self.validate()?;
+        Ok(ConsumeProviderResetCredit {
+            account_id: ProviderAccountId::new(self.account_id)
+                .map_err(|_| WireValidationError::new("accountId"))?,
+            credit_id: self.credit_id.map(|value| value.trim().to_owned()),
+            redeem_request_id: Uuid::parse_str(&self.redeem_request_id)
+                .map_err(|_| WireValidationError::new("redeemRequestId"))?,
+        })
+    }
+}
+
+/// 手工 OAuth 刷新会变更持久 credential。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountRefreshRequest {
+    pub account_id: String,
+}
+
+impl AccountRefreshRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")
+    }
+
+    pub(super) fn into_command(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 连接测试 query；测试仍经唯一 Core/Provider 模型请求路径执行。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountTestQuery {
+    pub account_id: String,
+    pub model_id: String,
+}
+
+impl AccountTestQuery {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        if self.model_id.trim().is_empty() || self.model_id.chars().any(char::is_control) {
+            return Err(WireValidationError::new("modelId"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+    ) -> Result<(ProviderAccountId, UpstreamModelId), WireValidationError> {
+        self.validate()?;
+        Ok((
+            ProviderAccountId::new(self.account_id)
+                .map_err(|_| WireValidationError::new("accountId"))?,
+            UpstreamModelId::new(self.model_id).map_err(|_| WireValidationError::new("modelId"))?,
+        ))
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AccountModelView {
+    pub id: String,
+    pub label: String,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AccountModelsData {
+    pub models: Vec<AccountModelView>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountRefreshData {
+    pub account: AccountView,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AccountQuotaData {
+    pub account: AccountView,
+}
+
+/// Provider 官方个人资料统计响应。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileStatisticsData {
+    pub display_name: Option<String>,
+    pub username: Option<String>,
+    pub image_url: Option<String>,
+    pub has_stats_error: bool,
+    pub summary: AccountProfileStatisticsSummaryView,
+    pub daily_usage: Option<Vec<AccountProfileDailyUsageView>>,
+    pub activity_insights: AccountProfileActivityInsightsView,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileStatisticsSummaryView {
+    pub total_text_tokens: Option<u64>,
+    pub peak_tokens: Option<u64>,
+    pub longest_task_duration_ms: Option<u64>,
+    pub current_streak_days: Option<u64>,
+    pub longest_streak_days: Option<u64>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileDailyUsageView {
+    pub date: String,
+    pub tokens: u64,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileActivityInsightsView {
+    pub fast_mode_percent: Option<f64>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_effort_percent: Option<f64>,
+    pub skills_explored: Option<u64>,
+    pub total_skills_used: Option<u64>,
+    pub total_threads: Option<u64>,
+    pub invocations: Option<Vec<AccountProfileInvocationView>>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileInvocationView {
+    #[serde(rename = "type")]
+    pub invocation_type: String,
+    pub plugin_id: Option<String>,
+    pub plugin_name: Option<String>,
+    pub skill_id: Option<String>,
+    pub skill_name: Option<String>,
+    pub usage_count: Option<u64>,
+}
+
+impl From<ProviderProfileStatistics> for AccountProfileStatisticsData {
+    fn from(statistics: ProviderProfileStatistics) -> Self {
+        Self {
+            display_name: statistics.display_name,
+            username: statistics.username,
+            image_url: statistics.image_url,
+            has_stats_error: statistics.has_stats_error,
+            summary: profile_statistics_summary_view(statistics.summary),
+            daily_usage: statistics
+                .daily_usage
+                .map(|daily| daily.into_iter().map(profile_daily_usage_view).collect()),
+            activity_insights: profile_activity_insights_view(statistics.activity_insights),
+        }
+    }
+}
+
+const fn profile_statistics_summary_view(
+    summary: ProviderProfileStatisticsSummary,
+) -> AccountProfileStatisticsSummaryView {
+    AccountProfileStatisticsSummaryView {
+        total_text_tokens: summary.total_text_tokens,
+        peak_tokens: summary.peak_tokens,
+        longest_task_duration_ms: summary.longest_task_duration_ms,
+        current_streak_days: summary.current_streak_days,
+        longest_streak_days: summary.longest_streak_days,
+    }
+}
+
+fn profile_daily_usage_view(daily: ProviderProfileDailyUsage) -> AccountProfileDailyUsageView {
+    AccountProfileDailyUsageView {
+        date: daily.date.to_string(),
+        tokens: daily.tokens,
+    }
+}
+
+fn profile_activity_insights_view(
+    insights: ProviderProfileActivityInsights,
+) -> AccountProfileActivityInsightsView {
+    AccountProfileActivityInsightsView {
+        fast_mode_percent: insights.fast_mode_percent,
+        reasoning_effort: insights.reasoning_effort,
+        reasoning_effort_percent: insights.reasoning_effort_percent,
+        skills_explored: insights.skills_explored,
+        total_skills_used: insights.total_skills_used,
+        total_threads: insights.total_threads,
+        invocations: insights.invocations.map(|invocations| {
+            invocations
+                .into_iter()
+                .map(profile_invocation_view)
+                .collect()
+        }),
+    }
+}
+
+fn profile_invocation_view(invocation: ProviderProfileInvocation) -> AccountProfileInvocationView {
+    AccountProfileInvocationView {
+        invocation_type: invocation.invocation_type,
+        plugin_id: invocation.plugin_id,
+        plugin_name: invocation.plugin_name,
+        skill_id: invocation.skill_id,
+        skill_name: invocation.skill_name,
+        usage_count: invocation.usage_count,
+    }
+}
+
+/// 主动额度重置卡列表响应。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountResetCreditsData {
+    pub available_count: u64,
+    pub credits: Vec<AccountResetCreditView>,
+}
+
+/// 一张安全主动额度重置卡视图。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountResetCreditView {
+    pub id: String,
+    pub status: Option<String>,
+    pub title: Option<String>,
+    pub expires_at: Option<String>,
+    pub reset_type: Option<String>,
+}
+
+/// 主动额度重置卡消费响应。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountResetCreditResultData {
+    pub code: String,
+    pub credit: Option<AccountResetCreditView>,
+}
+
+impl From<ProviderResetCredit> for AccountResetCreditView {
+    fn from(credit: ProviderResetCredit) -> Self {
+        Self {
+            id: credit.id,
+            status: credit.status,
+            title: credit.title,
+            expires_at: credit.expires_at.map(|value| value.to_rfc3339()),
+            reset_type: credit.reset_type,
+        }
+    }
+}
+
+impl From<ProviderResetCredits> for AccountResetCreditsData {
+    fn from(credits: ProviderResetCredits) -> Self {
+        Self {
+            available_count: credits.available_count,
+            credits: credits
+                .credits
+                .into_iter()
+                .map(AccountResetCreditView::from)
+                .collect(),
+        }
+    }
+}
+
+impl From<ProviderResetCreditResult> for AccountResetCreditResultData {
+    fn from(result: ProviderResetCreditResult) -> Self {
+        Self {
+            code: result.code,
+            credit: result.credit.map(AccountResetCreditView::from),
+        }
+    }
+}
+
+/// Provider-owned 明文导出文档；Debug 永远不输出内部 JSON。
+#[derive(Serialize)]
+#[serde(transparent)]
+pub struct AccountExportData(Value);
+
+impl AccountExportData {
+    #[must_use]
+    pub const fn new(value: Value) -> Self {
+        Self(value)
+    }
+
+    pub(super) fn from_result(bundle: AccountExportBundle) -> Self {
+        let documents = bundle
+            .documents
+            .into_iter()
+            .map(|document| {
+                serde_json::json!({
+                    "provider": document.provider_kind.to_string(),
+                    "document": provider_document_value(document.document),
+                })
+            })
+            .collect::<Vec<_>>();
+        Self::new(serde_json::json!({
+            "exportedAt": bundle.exported_at.to_rfc3339(),
+            "documents": documents,
+        }))
+    }
+}
+
+impl fmt::Debug for AccountExportData {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter.write_str("AccountExportData(<redacted>)")
+    }
+}
+
+pub struct AccountConnectionTestEvent {
+    pub data: Value,
+}
+
+impl From<DomainConnectionTestEvent> for AccountConnectionTestEvent {
+    fn from(event: DomainConnectionTestEvent) -> Self {
+        let data = match event {
+            DomainConnectionTestEvent::Started { model } => serde_json::json!({
+                "type": "test_start",
+                "model": model,
+                "text": "正在连接上游 Responses"
+            }),
+            DomainConnectionTestEvent::Request {
+                model,
+                input_text,
+                stream,
+                store,
+            } => serde_json::json!({
+                "type": "request",
+                "payload": {
+                    "model": model,
+                    "input": [{
+                        "role": "user",
+                        "content": [{ "type": "input_text", "text": input_text }]
+                    }],
+                    "stream": stream,
+                    "store": store
+                }
+            }),
+            DomainConnectionTestEvent::Content { text } => {
+                serde_json::json!({ "type": "content", "text": text })
+            }
+            DomainConnectionTestEvent::Completed => serde_json::json!({
+                "type": "test_complete",
+                "success": true
+            }),
+            DomainConnectionTestEvent::Failed {
+                source,
+                gateway_error_code,
+                send_state,
+                message,
+                provider_error_code,
+                provider_error_type,
+                upstream_status,
+                upstream_content_type,
+                upstream_body,
+            } => serde_json::json!({
+                "type": "error",
+                "source": source.as_str(),
+                "gatewayErrorCode": gateway_error_code.as_str(),
+                "sendState": send_state.map(gateway_core::upstream::UpstreamSendState::as_str),
+                "error": message,
+                "providerErrorCode": provider_error_code,
+                "providerErrorType": provider_error_type,
+                "upstreamStatus": upstream_status,
+                "upstreamContentType": upstream_content_type,
+                "upstreamBody": upstream_body
+            }),
+        };
+        Self { data }
+    }
+}
@@ -505,6 +505,8 @@ pub(crate) fn usage_attempt_view(attempt: domain::UsageAttempt) -> UsageAttemptV

 pub(crate) fn usage_detail_view(detail: domain::UsageDetail) -> UsageRecordDetailView {
    UsageRecordDetailView {
+        trace: detail.trace,
+        related_requests: detail.related_requests,
        request: usage_record_view(detail.request),
        attempts: detail
            .attempts
@@ -558,8 +560,8 @@ pub(crate) fn ops_error_view(error: domain::OpsError) -> OpsErrorView {
        transport: error.upstream_transport,
        attempt_index: error.attempt_index,
        failure_class: error.failure_kind,
+        upstream_send_state: error.upstream_send_state,
        provider_error_code: error.provider_error_code,
-        occurrence_count: error.occurrence_count,
        response_id: error.client_response_id,
        upstream_request_id: error.upstream_request_id,
        latency_ms: error.latency_ms,
@@ -571,11 +573,24 @@ pub(crate) fn ops_error_view(error: domain::OpsError) -> OpsErrorView {
        subagent_kind: error.subagent_kind,
        compact: error.compact,
        message: error.message,
+        raw_upstream_error: error.raw_upstream_error,
        metadata: OpsErrorMetadataView {
            source: error.source,
            component: error.component,
            attempt_id: None,
            account_label,
+            continuation_affinity_hash: error.continuation_affinity_hash,
+            continuation_previous_response_id_hash: error.continuation_previous_response_id_hash,
+            continuation_unavailable_reason: error.continuation_unavailable_reason,
+            upstream_connection_id: error.upstream_connection_id,
+            upstream_connection_exit_reason: error.upstream_connection_exit_reason,
+            upstream_connection_age_ms: error.upstream_connection_age_ms,
+            upstream_connection_idle_ms: error.upstream_connection_idle_ms,
+            recovery_request_id: error.recovery_request_id,
+            recovered_at: error.recovered_at,
+            recovery_attempt_count: error.recovery_attempt_count,
+            recovery_retry_delay_ms: error.recovery_retry_delay_ms,
+            recovery_total_latency_ms: error.recovery_total_latency_ms,
        },
        created_at: error.occurred_at,
        created_at_display: china_datetime(&error.occurred_at),
@@ -850,6 +865,28 @@ pub(crate) fn dashboard_view(
    } = observation;
    let mut account_usage_views = Vec::with_capacity(account_usage.len());
    for credential in account_usage {
+        let local_requests = credential
+            .quota_window
+            .as_ref()
+            .filter(|window| window.used_percent.is_none())
+            .and_then(|window| window.local_usage.as_ref())
+            .map(|usage| usage.request_count);
+        let (metric_label, metric_value) = match local_requests {
+            Some(count) => (
+                "次数".to_owned(),
+                if count > 0 {
+                    format_compact_number(count)
+                } else {
+                    "—".to_owned()
+                },
+            ),
+            None => (
+                "今日 Token".to_owned(),
+                credential
+                    .total_tokens
+                    .map_or_else(|| "—".to_owned(), format_compact_number),
+            ),
+        };
        account_usage_views.push(DashboardAccountUsageView {
            id: credential.account_id.clone(),
            provider: credential.provider_kind.clone(),
@@ -872,6 +909,11 @@ pub(crate) fn dashboard_view(
                })
                .collect(),
            quota_used_percent: credential.quota_used_percent,
+            usage_window: credential
+                .quota_window
+                .map(crate::admin::accounts::quota_window_view),
+            metric_label,
+            metric_value,
            last_used: relative_time(credential.last_used_at, range.end),
        });
    }
@@ -107,14 +107,12 @@ pub struct OpsQuery {
    pub provider: Option<String>,
    pub request_id: Option<String>,
    pub account_id: Option<String>,
-    pub route: Option<String>,
    pub model: Option<String>,
    pub status_code: Option<i64>,
    pub client_status_code: Option<i64>,
    pub upstream_status_code: Option<i64>,
    pub transport: Option<String>,
    pub attempt_index: Option<i64>,
-    pub failure_class: Option<String>,
    pub response_id: Option<String>,
    pub upstream_request_id: Option<String>,
    pub search: Option<String>,
@@ -352,13 +350,11 @@ pub(crate) fn ops_command(query: &OpsQuery) -> Result<domain::OpsErrorQuery, Wir
            provider_kind: non_empty(query.provider.clone()),
            provider_account_ref: non_empty(query.account_id.clone()),
            operation: non_empty(query.kind.clone()),
-            endpoint: non_empty(query.route.clone()),
            model: non_empty(query.model.clone()),
            transport: non_empty(query.transport.clone()),
            attempt_index: parse_attempt_index(query.attempt_index)?,
            response_id: non_empty(query.response_id.clone()),
            upstream_request_id: non_empty(query.upstream_request_id.clone()),
-            failure_kind: non_empty(query.failure_class.clone()),
            status_code,
            search: non_empty(query.search.clone()),
        },
@@ -247,6 +247,8 @@ pub struct UsageAttemptView {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageRecordDetailView {
+    pub trace: Option<serde_json::Value>,
+    pub related_requests: Vec<serde_json::Value>,
    #[serde(flatten)]
    pub request: UsageRecordView,
    pub attempts: Vec<UsageAttemptView>,
@@ -375,6 +377,9 @@ pub struct DashboardAccountUsageView {
    pub request_count: u64,
    pub request_buckets: Vec<DashboardAccountRequestBucketView>,
    pub quota_used_percent: Option<f64>,
+    pub usage_window: Option<crate::admin::accounts::AccountQuotaWindowView>,
+    pub metric_label: String,
+    pub metric_value: String,
    pub last_used: String,
 }

@@ -776,8 +781,8 @@ pub struct OpsErrorView {
    pub transport: Option<String>,
    pub attempt_index: Option<u32>,
    pub failure_class: String,
+    pub upstream_send_state: Option<String>,
    pub provider_error_code: Option<String>,
-    pub occurrence_count: u32,
    pub response_id: Option<String>,
    pub upstream_request_id: Option<String>,
    pub latency_ms: Option<u64>,
@@ -789,6 +794,8 @@ pub struct OpsErrorView {
    pub subagent_kind: Option<String>,
    pub compact: Option<bool>,
    pub message: String,
+    /// 上游错误正文或 WebSocket close/error frame 原文；不做脱敏。
+    pub raw_upstream_error: Option<String>,
    pub metadata: OpsErrorMetadataView,
    pub created_at: DateTime<Utc>,
    pub created_at_display: String,
@@ -802,4 +809,16 @@ pub struct OpsErrorMetadataView {
    pub component: String,
    pub attempt_id: Option<String>,
    pub account_label: Option<String>,
+    pub continuation_affinity_hash: Option<String>,
+    pub continuation_previous_response_id_hash: Option<String>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_id: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub upstream_connection_age_ms: Option<u64>,
+    pub upstream_connection_idle_ms: Option<u64>,
+    pub recovery_request_id: Option<String>,
+    pub recovered_at: Option<DateTime<Utc>>,
+    pub recovery_attempt_count: u32,
+    pub recovery_retry_delay_ms: Option<u64>,
+    pub recovery_total_latency_ms: Option<u64>,
 }
@@ -3,7 +3,7 @@
 //! 当前 wire 仍保留 display 字段；统一由本模块提供，避免 accounts/observability
 //! 各自维护格式化规则。

-use gateway_core::accounting::Decimal;
+use gateway_core::metering::Decimal;

 /// 千分位格式化。
 #[must_use]
@@ -10,14 +10,18 @@ use axum::{
    routing::{get, post},
 };
 use chrono::{DateTime, Utc};
+use gateway_admin::model::client_distribution::{
+    ClientDownloadPackage, CodexDesktopWindowsDownloads,
+};
 use gateway_admin::model::settings::{
    ModelMappings as DomainModelMappings, ReplaceRuntimeSettings, RotationStrategy, RuntimeSettings,
 };
+use gateway_core::policy::CodexClientVersion;
 use gateway_core::routing::{PublicModelId, UpstreamModelId};
 use serde::{Deserialize, Serialize};

 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminResponse, AdminSessionState,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
    WireValidationError, wire::map_admin_service_error,
 };

@@ -34,6 +38,8 @@ pub struct RuntimeSettingsView {
    pub max_concurrent_per_account: u64,
    pub request_interval_ms: u64,
    pub rotation_strategy: String,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
    pub usage_retention_days: u64,
    pub ops_event_retention_days: u64,
    pub audit_retention_days: u64,
@@ -50,6 +56,8 @@ pub struct UpdateRuntimeSettingsRequest {
    pub max_concurrent_per_account: u64,
    pub request_interval_ms: u64,
    pub rotation_strategy: String,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
    pub usage_retention_days: u64,
    pub ops_event_retention_days: u64,
    pub audit_retention_days: u64,
@@ -75,6 +83,14 @@ impl UpdateRuntimeSettingsRequest {
        if RotationStrategy::parse(&self.rotation_strategy).is_none() {
            return Err(WireValidationError::new("rotationStrategy"));
        }
+        validate_optional_client_version(
+            self.min_codex_desktop_version.as_deref(),
+            "minCodexDesktopVersion",
+        )?;
+        validate_optional_client_version(
+            self.min_codex_cli_version.as_deref(),
+            "minCodexCliVersion",
+        )?;
        Ok(())
    }

@@ -90,6 +106,8 @@ impl UpdateRuntimeSettingsRequest {
            request_interval_ms: self.request_interval_ms,
            rotation_strategy: RotationStrategy::parse(&self.rotation_strategy)
                .ok_or_else(|| WireValidationError::new("rotationStrategy"))?,
+            min_codex_desktop_version: self.min_codex_desktop_version,
+            min_codex_cli_version: self.min_codex_cli_version,
            usage_retention_days: u32::try_from(self.usage_retention_days)
                .map_err(|_| WireValidationError::new("settingsUsageRetentionOverflow"))?,
            ops_event_retention_days: u32::try_from(self.ops_event_retention_days)
@@ -109,6 +127,8 @@ impl From<RuntimeSettings> for RuntimeSettingsView {
            max_concurrent_per_account: u64::from(settings.max_concurrent_per_account),
            request_interval_ms: settings.request_interval_ms,
            rotation_strategy: settings.rotation_strategy.as_str().to_owned(),
+            min_codex_desktop_version: settings.min_codex_desktop_version,
+            min_codex_cli_version: settings.min_codex_cli_version,
            usage_retention_days: u64::from(settings.usage_retention_days),
            ops_event_retention_days: u64::from(settings.ops_event_retention_days),
            audit_retention_days: u64::from(settings.audit_retention_days),
@@ -145,6 +165,58 @@ pub struct DeletedAdminApiKey {
    pub message: &'static str,
 }

+#[derive(Debug, Clone, Copy, Default, Deserialize)]
+#[serde(default, deny_unknown_fields)]
+struct ClientDownloadsQuery {
+    refresh: bool,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct ClientDownloadPackageView {
+    architecture: String,
+    source: String,
+    version: Option<String>,
+    file_name: String,
+    size_bytes: Option<u64>,
+    download_url: String,
+    expires_at: Option<DateTime<Utc>>,
+}
+
+impl From<ClientDownloadPackage> for ClientDownloadPackageView {
+    fn from(package: ClientDownloadPackage) -> Self {
+        Self {
+            architecture: package.architecture.as_str().to_owned(),
+            source: package.source.as_str().to_owned(),
+            version: package.version,
+            file_name: package.file_name,
+            size_bytes: package.size_bytes,
+            download_url: package.download_url,
+            expires_at: package.expires_at,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct CodexDesktopWindowsDownloadsView {
+    resolved_at: DateTime<Utc>,
+    cached: bool,
+    warning: Option<String>,
+    packages: Vec<ClientDownloadPackageView>,
+}
+
+impl From<CodexDesktopWindowsDownloads> for CodexDesktopWindowsDownloadsView {
+    fn from(downloads: CodexDesktopWindowsDownloads) -> Self {
+        Self {
+            resolved_at: downloads.resolved_at,
+            cached: downloads.cached,
+            warning: downloads.warning,
+            packages: downloads.packages.into_iter().map(Into::into).collect(),
+        }
+    }
+}
+
 impl Default for DeletedAdminApiKey {
    fn default() -> Self {
        Self {
@@ -161,6 +233,10 @@ where
    Router::new()
        .route("/api/admin/settings", get(settings::<S>))
        .route("/api/admin/settings/update", post(update_settings::<S>))
+        .route(
+            "/api/admin/settings/client-downloads/codex-desktop/windows",
+            get(codex_desktop_windows_downloads::<S>),
+        )
        .route(
            "/api/admin/settings/admin-api-key",
            get(admin_api_key_status::<S>),
@@ -175,6 +251,25 @@ where
        )
 }

+async fn codex_desktop_windows_downloads<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<ClientDownloadsQuery>,
+) -> impl IntoResponse
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let downloads = state
+        .admin_services()
+        .client_distribution()
+        .codex_desktop_windows(query.refresh)
+        .await;
+    AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(CodexDesktopWindowsDownloadsView::from(downloads)),
+    )
+}
+
 async fn settings<S>(
    _auth: AdminAuth,
    State(state): State<S>,
@@ -322,6 +417,16 @@ fn valid_model_name(value: &str, max_len: usize) -> bool {
        && !value.bytes().any(|byte| byte.is_ascii_control())
 }

+fn validate_optional_client_version(
+    value: Option<&str>,
+    field: &'static str,
+) -> Result<(), WireValidationError> {
+    if value.is_some_and(|value| CodexClientVersion::parse(value).is_err()) {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
 fn map_wire_error(error: WireValidationError) -> AdminError {
    let message = match error.field() {
        "settingsRefreshConcurrencyOverflow" => "refreshConcurrency 不合法".to_owned(),
@@ -329,6 +434,8 @@ fn map_wire_error(error: WireValidationError) -> AdminError {
        "settingsUsageRetentionOverflow" => "usageRetentionDays 不合法".to_owned(),
        "settingsOpsRetentionOverflow" => "opsEventRetentionDays 不合法".to_owned(),
        "settingsAuditRetentionOverflow" => "auditRetentionDays 不合法".to_owned(),
+        "minCodexDesktopVersion" => "Codex Desktop 最低版本格式不合法".to_owned(),
+        "minCodexCliVersion" => "Codex CLI 最低版本格式不合法".to_owned(),
        field => format!("{field} 字段不合法"),
    };
    AdminError::bad_request(message)
@@ -180,13 +180,16 @@ pub fn initialize(
                "request",
                request_id = %request_id,
                method = %request.method().as_str(),
-                uri = %request
-                    .uri()
-                    .path_and_query()
-                    .map(axum::http::uri::PathAndQuery::as_str)
-                    .unwrap_or_default(),
+                uri = %request.uri().path(),
            )
        }
+    })
+    .on_request(|_request: &Request<_>, _span: &tracing::Span| {
+        tracing::info!(target: "request_trace", stage = "http.received", "HTTP request received");
+    })
+    .on_response(|response: &axum::http::Response<_>, latency: Duration, _span: &tracing::Span| {
+        tracing::info!(target: "request_trace", stage = "http.response", status = response.status().as_u16(),
+            headers_ms = latency.as_millis(), "HTTP response headers ready");
    });
    let router = router
        .layer(PropagateRequestIdLayer::new(request_id_header.clone()))
@@ -5,9 +5,13 @@ use axum::{
    response::{IntoResponse, Response},
 };
 use gateway_core::engine::execution::AuthenticatedClient;
+use gateway_core::policy::{ClientVersionRejection, CodexClientKind, CodexClientVersion};

 use super::{
-    error::{missing_client_api_key_response, runtime_unavailable_response},
+    error::{
+        client_version_rejection_response, missing_client_api_key_response,
+        runtime_unavailable_response,
+    },
    service::OpenAiService,
 };

@@ -26,6 +30,44 @@ pub enum ClientApiKeyAuthError {
    RuntimeUnavailable,
 }

+/// Client API Key 或最低版本准入失败。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum ClientAccessError {
+    Authentication(ClientApiKeyAuthError),
+    Version(ClientVersionRejection),
+}
+
+impl From<ClientApiKeyAuthError> for ClientAccessError {
+    fn from(error: ClientApiKeyAuthError) -> Self {
+        Self::Authentication(error)
+    }
+}
+
+impl From<ClientVersionRejection> for ClientAccessError {
+    fn from(error: ClientVersionRejection) -> Self {
+        Self::Version(error)
+    }
+}
+
+/// 从有界请求头中识别出的客户端及其可选合法版本。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct IdentifiedCodexClient {
+    kind: CodexClientKind,
+    version: Option<CodexClientVersion>,
+}
+
+impl IdentifiedCodexClient {
+    #[must_use]
+    pub const fn kind(&self) -> CodexClientKind {
+        self.kind
+    }
+
+    #[must_use]
+    pub const fn version(&self) -> Option<&CodexClientVersion> {
+        self.version.as_ref()
+    }
+}
+
 impl ClientApiKeyAuthError {
    /// 返回可用于日志和指标的稳定失败原因。
    #[must_use]
@@ -67,19 +109,121 @@ pub fn bearer_client_api_key(headers: &HeaderMap) -> Result<&str, ClientApiKeyAu
 pub(crate) fn authenticate_client(
    service: &OpenAiService,
    headers: &HeaderMap,
-) -> Result<AuthenticatedClient, ClientApiKeyAuthError> {
-    bearer_client_api_key(headers).and_then(|key| service.authenticate(key))
+) -> Result<AuthenticatedClient, ClientAccessError> {
+    let key = bearer_client_api_key(headers)?;
+    let client = service.authenticate(key)?;
+    if let Some(identified) = identify_codex_client(headers) {
+        client
+            .snapshot()
+            .min_codex_client_versions()
+            .enforce(identified.kind(), identified.version())?;
+    }
+    Ok(client)
 }

-pub(crate) fn authentication_error_response(error: ClientApiKeyAuthError) -> Response {
-    log_client_api_key_auth_failure(error);
-    if error == ClientApiKeyAuthError::RuntimeUnavailable {
-        runtime_unavailable_response().into_response()
-    } else {
-        missing_client_api_key_response().into_response()
+pub(crate) fn client_access_error_response(error: ClientAccessError) -> Response {
+    match error {
+        ClientAccessError::Authentication(error) => {
+            log_client_api_key_auth_failure(error);
+            if error == ClientApiKeyAuthError::RuntimeUnavailable {
+                runtime_unavailable_response().into_response()
+            } else {
+                missing_client_api_key_response().into_response()
+            }
+        }
+        ClientAccessError::Version(error) => {
+            tracing::info!(
+                client = error.kind().as_str(),
+                current_version = error.current().map(ToString::to_string),
+                min_version = %error.min(),
+                "Codex client version requirement rejected request"
+            );
+            client_version_rejection_response(&error).into_response()
+        }
    }
 }

+/// Desktop 优先于其内嵌的 CLI/Core 标记；未知客户端保持兼容并返回 `None`。
+#[must_use]
+pub fn identify_codex_client(headers: &HeaderMap) -> Option<IdentifiedCodexClient> {
+    const MAXIMUM_HEADER_LENGTH: usize = 4096;
+
+    let originator = bounded_ascii_header(headers, "originator", MAXIMUM_HEADER_LENGTH);
+    let user_agent = bounded_ascii_header(headers, "user-agent", MAXIMUM_HEADER_LENGTH);
+    let is_desktop = originator.is_some_and(|value| value.eq_ignore_ascii_case("Codex Desktop"))
+        || user_agent.is_some_and(|value| contains_ascii_case_insensitive(value, "Codex Desktop"));
+    if is_desktop {
+        let explicit_version = bounded_ascii_header(headers, "version", MAXIMUM_HEADER_LENGTH);
+        let version = match explicit_version {
+            Some(value) => CodexClientVersion::parse(value).ok(),
+            None => user_agent
+                .and_then(desktop_version_from_user_agent)
+                .and_then(|value| CodexClientVersion::parse(value).ok()),
+        };
+        return Some(IdentifiedCodexClient {
+            kind: CodexClientKind::Desktop,
+            version,
+        });
+    }
+
+    let user_agent = user_agent?;
+    for product in user_agent.split(|character: char| {
+        character.is_ascii_whitespace() || matches!(character, '(' | ')' | ';' | ',' | '[' | ']')
+    }) {
+        for prefix in ["codex_cli_rs", "codex-cli"] {
+            if product.eq_ignore_ascii_case(prefix) {
+                return Some(IdentifiedCodexClient {
+                    kind: CodexClientKind::Cli,
+                    version: None,
+                });
+            }
+            let Some((name, version)) = product.split_once('/') else {
+                continue;
+            };
+            if name.eq_ignore_ascii_case(prefix) {
+                return Some(IdentifiedCodexClient {
+                    kind: CodexClientKind::Cli,
+                    version: CodexClientVersion::parse(version).ok(),
+                });
+            }
+        }
+    }
+    None
+}
+
+fn bounded_ascii_header<'a>(
+    headers: &'a HeaderMap,
+    name: &'static str,
+    maximum_length: usize,
+) -> Option<&'a str> {
+    let value = headers.get(name)?.to_str().ok()?;
+    if !value.is_ascii() {
+        return None;
+    }
+    Some(&value[..value.len().min(maximum_length)])
+}
+
+fn desktop_version_from_user_agent(user_agent: &str) -> Option<&str> {
+    let marker = "Codex Desktop;";
+    let start = find_ascii_case_insensitive(user_agent, marker)? + marker.len();
+    let version = user_agent[start..]
+        .trim_start()
+        .split([')', ' ', ';', ','])
+        .next()?;
+    (!version.is_empty()).then_some(version)
+}
+
+fn contains_ascii_case_insensitive(haystack: &str, needle: &str) -> bool {
+    find_ascii_case_insensitive(haystack, needle).is_some()
+}
+
+fn find_ascii_case_insensitive(haystack: &str, needle: &str) -> Option<usize> {
+    haystack
+        .as_bytes()
+        .windows(needle.len())
+        .position(|window| window.eq_ignore_ascii_case(needle.as_bytes()))
+}
+
 fn log_client_api_key_auth_failure(error: ClientApiKeyAuthError) {
    match error {
        ClientApiKeyAuthError::RuntimeUnavailable => {
@@ -9,6 +9,7 @@ use axum::{
 use gateway_core::{
    engine::EngineError,
    error::{GatewayError, GatewayErrorKind},
+    policy::{ClientVersionRejection, CodexClientKind},
 };
 use serde_json::{Value, json};

@@ -58,6 +59,47 @@ pub fn runtime_unavailable_response() -> (StatusCode, Json<Value>) {
    )
 }

+/// 已识别 Codex 客户端不满足最低版本要求。
+pub fn client_version_rejection_response(
+    rejection: &ClientVersionRejection,
+) -> (StatusCode, Json<Value>) {
+    let client_label = match rejection.kind() {
+        CodexClientKind::Desktop => "Codex Desktop",
+        CodexClientKind::Cli => "Codex CLI",
+    };
+    let (message, code, current_version) = match rejection.current() {
+        Some(current) => (
+            format!(
+                "{client_label} {current} is below the minimum required version {}. Upgrade {client_label} and retry.",
+                rejection.min()
+            ),
+            "client_version_too_old",
+            Some(current.to_string()),
+        ),
+        None => (
+            format!(
+                "A valid {client_label} version is required. Upgrade to version {} or newer and retry.",
+                rejection.min()
+            ),
+            "client_version_unavailable",
+            None,
+        ),
+    };
+    (
+        StatusCode::UPGRADE_REQUIRED,
+        Json(json!({
+            "error": {
+                "message": message,
+                "type": "invalid_request_error",
+                "code": code,
+                "client": rejection.kind().as_str(),
+                "current_version": current_version,
+                "min_version": rejection.min().to_string()
+            }
+        })),
+    )
+}
+
 /// 对外模型不存在。
 pub fn model_not_found_response() -> (StatusCode, Json<Value>) {
    openai_error_response(
@@ -3,22 +3,21 @@
 use std::net::SocketAddr;

 use axum::{
-    body::{Body, Bytes},
+    body::Bytes,
    extract::{Extension, State, connect_info::ConnectInfo},
-    http::{HeaderMap, HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
-    response::{IntoResponse, Response},
+    http::HeaderMap,
+    response::Response,
 };
-use gateway_core::engine::execution::StartedExecution;
 use gateway_core::error::{GatewayError, GatewayErrorKind};
-use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
 use gateway_core::operation::{ImageRequest, ImageRequestKind, Operation, RawJsonPayload};
-use serde_json::{Map, Value};
+use serde_json::Value;

 use crate::ApiState;
 use crate::openai::{
-    auth::{authenticate_client, authentication_error_response},
-    error::{engine_error_response, gateway_error_response, protocol_error_response},
-    responses::{PendingExecution, ProtocolError, ProtocolErrorBody, request_client_context},
+    auth::{authenticate_client, client_access_error_response},
+    error::gateway_error_response,
+    provider_endpoint::collect_raw_json_response,
+    responses::{OpenAiRequestHeaders, request_client_context},
 };

 const OPENAI_PROTOCOL: &str = "openai";
@@ -71,7 +70,7 @@ async fn handle_image_request(
    let service = state.openai();
    let client = match authenticate_client(service, &headers) {
        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
    };
    let (client_ip, user_agent) = request_client_context(
        &headers,
@@ -82,13 +81,13 @@ async fn handle_image_request(
        Err(error) => return gateway_error_response(&error),
    };
    let started = match service
-        .start_image(client, operation, client_ip, user_agent, endpoint)
+        .start_provider_endpoint(client, operation, client_ip, user_agent, endpoint)
        .await
    {
        Ok(started) => started,
        Err(error) => return gateway_error_response(&error),
    };
-    collect_image_response(started).await
+    collect_raw_json_response(started).await
 }

 fn image_operation(
@@ -96,7 +95,7 @@ fn image_operation(
    headers: &HeaderMap,
    kind: ImageRequestKind,
 ) -> Result<Operation, GatewayError> {
-    let mut context = Map::new();
+    let mut context = OpenAiRequestHeaders::from_headers(headers).session_context();
    if let Some(turn_id) = headers
        .get("x-codex-image-turn-id")
        .and_then(|value| value.to_str().ok())
@@ -118,116 +117,3 @@ fn image_operation(
        kind, payload,
    )))
 }
-
-async fn collect_image_response(started: StartedExecution) -> Response {
-    let mut execution = PendingExecution::new(started.session);
-    let Some(session) = execution.session_mut() else {
-        return invalid_upstream_response();
-    };
-    let events = match session.collect_uncommitted().await {
-        Ok(events) => events,
-        Err(error) => {
-            let response = engine_error_response(&error);
-            return execution.record_response_status(response).await;
-        }
-    };
-    let body = match raw_json_body(events) {
-        Some(body) => body,
-        None => {
-            let response = invalid_upstream_response();
-            let response = execution.record_response_status(response).await;
-            execution.cancel_and_finalize().await;
-            return response;
-        }
-    };
-    let status = session
-        .response_status_code()
-        .and_then(|status| StatusCode::from_u16(status).ok())
-        .filter(StatusCode::is_success)
-        .unwrap_or(StatusCode::OK);
-    let response_headers = session.response_headers().to_vec();
-    let response = json_body_response(body, status, &response_headers);
-    let Some(session) = execution.session_mut() else {
-        return invalid_upstream_response();
-    };
-    if let Err(error) = session.commit_downstream(Some(status.as_u16())).await {
-        execution.cancel_and_finalize().await;
-        let response = engine_error_response(&error);
-        return execution.record_response_status(response).await;
-    }
-    if !session.is_finalized() {
-        execution.cancel_and_finalize().await;
-        return invalid_upstream_response();
-    }
-    execution.disarm();
-    response
-}
-
-fn raw_json_body(events: Vec<ProviderEvent>) -> Option<Bytes> {
-    let mut body = None;
-    for event in events {
-        let (_, wire) = event.into_parts();
-        let Some(wire) = wire.filter(|wire| wire.protocol() == "openai") else {
-            continue;
-        };
-        let Some(raw) = wire.into_raw_json_body() else {
-            continue;
-        };
-        if body.replace(raw).is_some() {
-            return None;
-        }
-    }
-    body
-}
-
-fn json_body_response(
-    body: Bytes,
-    status: StatusCode,
-    response_headers: &[ProviderResponseHeader],
-) -> Response {
-    let mut response = Response::new(Body::from(body));
-    *response.status_mut() = status;
-    response
-        .headers_mut()
-        .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
-    apply_response_headers(response, response_headers)
-}
-
-fn apply_response_headers(
-    mut response: Response,
-    response_headers: &[ProviderResponseHeader],
-) -> Response {
-    let connection_options =
-        crate::openai::responses::response_connection_options(response_headers);
-    for header in response_headers {
-        if !crate::openai::responses::response_header_is_forwardable(
-            header.name(),
-            &connection_options,
-        ) {
-            continue;
-        }
-        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
-            continue;
-        };
-        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
-            continue;
-        };
-        response.headers_mut().append(name, value);
-    }
-    response
-}
-
-fn invalid_upstream_response() -> Response {
-    protocol_error_response(
-        StatusCode::BAD_GATEWAY,
-        ProtocolErrorBody {
-            error: ProtocolError {
-                kind: "server_error",
-                code: "invalid_upstream_response",
-                message: "The gateway could not forward the upstream image response.".to_owned(),
-                param: None,
-            },
-        },
-    )
-    .into_response()
-}
@@ -4,6 +4,8 @@ pub mod auth;
 pub mod error;
 pub mod images;
 pub mod models;
+mod provider_endpoint;
 pub mod responses;
 pub mod router;
+pub mod search;
 pub(crate) mod service;
@@ -13,7 +13,7 @@ use serde_json::{Value, json};
 use crate::ApiState;

 use super::{
-    auth::{authenticate_client, authentication_error_response},
+    auth::{authenticate_client, client_access_error_response},
    error::model_not_found_response,
 };

@@ -34,7 +34,7 @@ pub(crate) async fn models(
    let service = state.openai();
    let client = match authenticate_client(service, &headers) {
        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
    };

    if query
@@ -81,7 +81,7 @@ pub(crate) async fn model_detail(
    let service = state.openai();
    let client = match authenticate_client(service, &headers) {
        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
    };
    let Ok(public_model) = PublicModelId::new(model_id) else {
        return model_not_found_response().into_response();
@@ -97,50 +97,6 @@ pub(crate) async fn model_detail(
        .into_response()
 }

-/// `GET /v1/models/catalog`。
-///
-/// 新架构的目录由 core 按客户端 Provider 范围裁剪；这里不读取或重建任一
-/// Provider 的 wire catalog，只恢复 Codex 客户端依赖的稳定展示合同。
-pub(crate) async fn model_catalog(State(state): State<ApiState>, headers: HeaderMap) -> Response {
-    let service = state.openai();
-    let client = match authenticate_client(service, &headers) {
-        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
-    };
-    let models = service
-        .public_models(&client)
-        .into_iter()
-        .map(|model| catalog_model_json(model.as_str()))
-        .collect::<Vec<_>>();
-
-    (StatusCode::OK, Json(models)).into_response()
-}
-
-/// `GET /v1/models/{model_id}/info`。
-pub(crate) async fn model_info(
-    State(state): State<ApiState>,
-    headers: HeaderMap,
-    Path(model_id): Path<String>,
-) -> Response {
-    let service = state.openai();
-    let client = match authenticate_client(service, &headers) {
-        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
-    };
-    let Ok(public_model) = PublicModelId::new(model_id) else {
-        return model_not_found_response().into_response();
-    };
-    if !service.contains_public_model(&client, &public_model) {
-        return model_not_found_response().into_response();
-    }
-
-    (
-        StatusCode::OK,
-        Json(catalog_model_json(public_model.as_str())),
-    )
-        .into_response()
-}
-
 fn openai_model_json(id: &str) -> Value {
    json!({
        "id": id,
@@ -150,22 +106,6 @@ fn openai_model_json(id: &str) -> Value {
    })
 }

-fn catalog_model_json(id: &str) -> Value {
-    json!({
-        "id": id,
-        "displayName": id,
-        "description": "",
-        "isDefault": false,
-        "supportedReasoningEfforts": [],
-        "defaultReasoningEffort": "",
-        "inputModalities": ["text"],
-        "outputModalities": ["text"],
-        "supportsPersonality": false,
-        "upgrade": Value::Null,
-        "source": "gateway",
-    })
-}
-
 fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
    let id = profile.model().as_str();
    let presentation = profile.presentation();
@@ -0,0 +1,124 @@
+//! OpenAI Provider 原生非流式 JSON 端点的公共交付边界。
+
+use axum::{
+    body::{Body, Bytes},
+    http::{HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
+    response::{IntoResponse, Response},
+};
+use gateway_core::engine::execution::StartedExecution;
+use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
+
+use super::{
+    error::{engine_error_response, protocol_error_response},
+    responses::{PendingExecution, ProtocolError, ProtocolErrorBody},
+};
+
+/// 收集一个 Provider 原生 JSON 响应，并在 Core commit 后按原始 bytes 交付。
+pub(super) async fn collect_raw_json_response(started: StartedExecution) -> Response {
+    let mut execution = PendingExecution::new(started.session);
+    let Some(session) = execution.session_mut() else {
+        return invalid_upstream_response();
+    };
+    let events = match session.collect_uncommitted().await {
+        Ok(events) => events,
+        Err(error) => {
+            let response = engine_error_response(&error);
+            return execution.record_response_status(response).await;
+        }
+    };
+    let body = match raw_json_body(events) {
+        Some(body) => body,
+        None => {
+            let response = invalid_upstream_response();
+            let response = execution.record_response_status(response).await;
+            execution.cancel_and_finalize().await;
+            return response;
+        }
+    };
+    let status = session
+        .response_status_code()
+        .and_then(|status| StatusCode::from_u16(status).ok())
+        .filter(StatusCode::is_success)
+        .unwrap_or(StatusCode::OK);
+    let response_headers = session.response_headers().to_vec();
+    let response = json_body_response(body, status, &response_headers);
+    let Some(session) = execution.session_mut() else {
+        return invalid_upstream_response();
+    };
+    if let Err(error) = session.commit_downstream(Some(status.as_u16())).await {
+        execution.cancel_and_finalize().await;
+        let response = engine_error_response(&error);
+        return execution.record_response_status(response).await;
+    }
+    if !session.is_finalized() {
+        execution.cancel_and_finalize().await;
+        return invalid_upstream_response();
+    }
+    execution.disarm();
+    response
+}
+
+fn raw_json_body(events: Vec<ProviderEvent>) -> Option<Bytes> {
+    let mut body = None;
+    for event in events {
+        let (_, wire) = event.into_parts();
+        let Some(wire) = wire.filter(|wire| wire.protocol() == "openai") else {
+            continue;
+        };
+        let Some(raw) = wire.into_raw_json_body() else {
+            continue;
+        };
+        if body.replace(raw).is_some() {
+            return None;
+        }
+    }
+    body
+}
+
+fn json_body_response(
+    body: Bytes,
+    status: StatusCode,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    let mut response = Response::new(Body::from(body));
+    *response.status_mut() = status;
+    response
+        .headers_mut()
+        .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
+    apply_response_headers(response, response_headers)
+}
+
+fn apply_response_headers(
+    mut response: Response,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    let connection_options = super::responses::response_connection_options(response_headers);
+    for header in response_headers {
+        if !super::responses::response_header_is_forwardable(header.name(), &connection_options) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+            continue;
+        };
+        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
+            continue;
+        };
+        response.headers_mut().append(name, value);
+    }
+    response
+}
+
+fn invalid_upstream_response() -> Response {
+    protocol_error_response(
+        StatusCode::BAD_GATEWAY,
+        ProtocolErrorBody {
+            error: ProtocolError {
+                kind: "server_error",
+                code: "invalid_upstream_response",
+                message: "The gateway could not forward the upstream JSON response.".to_owned(),
+                param: None,
+            },
+        },
+    )
+    .into_response()
+}
@@ -3,6 +3,7 @@
 use std::collections::VecDeque;
 use std::convert::Infallible;
 use std::net::{IpAddr, SocketAddr};
+use std::time::Duration;

 use axum::{
    body::{Body, Bytes},
@@ -13,9 +14,10 @@ use axum::{
    },
    response::{IntoResponse, Response},
 };
-use futures::stream;
-use gateway_core::engine::CommitRequirement;
+use futures::{StreamExt, stream};
+use gateway_core::diagnostics::TraceContext;
 use gateway_core::engine::execution::{ClientTransport, ExecutionSession, StartedExecution};
+use gateway_core::engine::{CommitRequirement, EngineError};
 use gateway_core::error::{GatewayError, GatewayErrorKind};
 use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
 use gateway_core::lifecycle::ConnectionGuard;
@@ -23,7 +25,7 @@ use gateway_protocol::openai::sse::{DONE_SSE_FRAME, response_failed_sse_event_wi

 use crate::ApiState;
 use crate::openai::{
-    auth::{authenticate_client, authentication_error_response},
+    auth::{authenticate_client, client_access_error_response},
    error::{
        engine_error_response, gateway_error_contract, gateway_error_from_engine,
        gateway_error_response, protocol_error_response, runtime_unavailable_response,
@@ -32,46 +34,25 @@ use crate::openai::{

 use super::{
    OpenAiResponsesEncoder, ProtocolErrorBody, ResponseEncodeError,
-    request::{decode_request_with_headers, decode_review_request_with_headers},
+    request::decode_request_with_headers,
 };

+const SSE_KEEPALIVE_INTERVAL: Duration = Duration::from_secs(15);
+
 /// `POST /v1/responses`。
 pub(crate) async fn responses(
    State(state): State<ApiState>,
    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    ingress_id: Option<Extension<tower_http::request_id::RequestId>>,
    headers: HeaderMap,
    body: Bytes,
-) -> Response {
-    handle_responses(state, connect_info, headers, body, false).await
-}
-
-/// `POST /v1/responses/review`。
-pub(crate) async fn review_responses(
-    State(state): State<ApiState>,
-    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
-    headers: HeaderMap,
-    body: Bytes,
-) -> Response {
-    handle_responses(state, connect_info, headers, body, true).await
-}
-
-async fn handle_responses(
-    state: ApiState,
-    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
-    headers: HeaderMap,
-    body: Bytes,
-    review: bool,
 ) -> Response {
    let service = state.openai();
    let client = match authenticate_client(service, &headers) {
        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
    };
-    let decoded = match if review {
-        decode_review_request_with_headers(&body, &headers)
-    } else {
-        decode_request_with_headers(&body, &headers)
-    } {
+    let decoded = match decode_request_with_headers(&body, &headers) {
        Ok(decoded) => decoded,
        Err(error) => {
            return protocol_error_response(StatusCode::BAD_REQUEST, error.protocol_body());
@@ -100,26 +81,32 @@ async fn handle_responses(
            } else {
                ClientTransport::HttpJson
            },
-            if review {
-                "/v1/responses/review"
-            } else {
-                "/v1/responses"
-            },
+            "/v1/responses",
        )
        .await
    {
        Ok(started) => started,
        Err(error) => return gateway_error_response(&error),
    };
+    let trace = started.session.trace();
+    trace.headers("client.request", serde_json::json!({
+        "ingressRequestId": ingress_id.as_ref().and_then(|Extension(id)| id.header_value().to_str().ok()),
+    }), headers.iter().map(|(name, value)| (name.as_str(), value.as_bytes())));
+    trace.capture("client.request.body", &body);
+    let request_id_header = HeaderValue::from_str(started.request_id.as_str()).ok();
    let StartedExecution {
        stream, session, ..
    } = started;
-    if stream {
+    let mut response = if stream {
        stream_execution_response(session, connection_guard).await
    } else {
        drop(connection_guard);
        collect_execution_response(session).await
+    };
+    if let Some(id) = request_id_header {
+        response.headers_mut().insert("x-gateway-request-id", id);
    }
+    response
 }

 /// 从 socket 与标准转发头提取旧 Usage 页面使用的诊断事实。
@@ -180,7 +167,8 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
    let events = match session.collect_uncommitted().await {
        Ok(events) => events,
        Err(error) => {
-            let response = engine_error_response(&error);
+            let response_headers = session.response_headers().to_vec();
+            let response = engine_error_response_with_headers(&error, &response_headers);
            return execution.record_response_status(response).await;
        }
    };
@@ -196,6 +184,11 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
        }
    };
    let response_headers = session.response_headers().to_vec();
+    session.trace().record(
+        "downstream.encoded",
+        serde_json::json!({"transport": "http_json", "bytes": encoded.len()}),
+    );
+    session.trace().dump("downstream.body", &encoded);
    let response = json_body_response(encoded, &response_headers);

    let Some(session) = execution.session_mut() else {
@@ -206,7 +199,7 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
        .await
    {
        execution.cancel_and_finalize().await;
-        let response = engine_error_response(&error);
+        let response = engine_error_response_with_headers(&error, &response_headers);
        return execution.record_response_status(response).await;
    }
    if !session.is_finalized() {
@@ -274,6 +267,13 @@ fn apply_response_headers(
    response
 }

+fn engine_error_response_with_headers(
+    error: &EngineError,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    apply_response_headers(engine_error_response(error), response_headers)
+}
+
 /// 编码首个 SSE frame 后提交下游，再持续驱动同一执行会话。
 pub async fn stream_execution_response(
    session: Box<dyn ExecutionSession>,
@@ -295,7 +295,8 @@ pub async fn stream_execution_response(
            return response;
        }
        Err(error) => {
-            let response = engine_error_response(&error);
+            let response_headers = session.response_headers().to_vec();
+            let response = engine_error_response_with_headers(&error, &response_headers);
            return execution.record_response_status(response).await;
        }
    };
@@ -327,7 +328,7 @@ pub async fn stream_execution_response(
        .await
    {
        execution.cancel_and_finalize().await;
-        let response = engine_error_response(&error);
+        let response = engine_error_response_with_headers(&error, &response_headers);
        return execution.record_response_status(response).await;
    }
    let Some(session) = execution.into_session() else {
@@ -337,9 +338,11 @@ pub async fn stream_execution_response(
    if state.encoder.is_completed() {
        state.finish_completed(Vec::new()).await;
    }
-    let body = Body::from_stream(stream::unfold(state, |mut state| async move {
+    let output = Box::pin(stream::unfold(state, |mut state| async move {
        loop {
            if let Some(chunk) = state.pending.pop_front() {
+                state.trace.dump("downstream.chunk", &chunk);
+                state.handed_off_bytes += chunk.len() as u64;
                return Some((Ok::<Bytes, Infallible>(chunk), state));
            }
            if state.output_finished {
@@ -348,19 +351,35 @@ pub async fn stream_execution_response(
            state.advance().await;
        }
    }));
+    // 保活只轮询已固定的输出 stream；不能取消并重建 advance/next_event future，
+    // 否则一次心跳就可能丢失正在等待的上游事件或执行终态清理。
+    let body = Body::from_stream(stream::unfold(output, |mut output| async move {
+        let chunk = tokio::select! {
+            biased;
+            chunk = output.next() => chunk?,
+            () = tokio::time::sleep(SSE_KEEPALIVE_INTERVAL) => {
+                Ok(Bytes::from_static(b": keep-alive\n\n"))
+            }
+        };
+        Some((chunk, output))
+    }));
    event_stream_response(body, &response_headers)
 }

 fn event_stream_response(body: Body, response_headers: &[ProviderResponseHeader]) -> Response {
-    let mut response = Response::new(body);
+    let mut response = apply_response_headers(Response::new(body), response_headers);
    *response.status_mut() = StatusCode::OK;
    response
        .headers_mut()
        .insert(CONTENT_TYPE, HeaderValue::from_static("text/event-stream"));
+    response.headers_mut().insert(
+        CACHE_CONTROL,
+        HeaderValue::from_static("no-cache, no-transform"),
+    );
    response
        .headers_mut()
-        .insert(CACHE_CONTROL, HeaderValue::from_static("no-cache"));
-    apply_response_headers(response, response_headers)
+        .insert("x-accel-buffering", HeaderValue::from_static("no"));
+    response
 }

 fn internal_gateway_response(message: &'static str) -> Response {
@@ -422,12 +441,18 @@ impl Drop for PendingExecution {
        if session.is_finalized() {
            return;
        }
+        session.trace().record(
+            "downstream.cancelled",
+            serde_json::json!({"reason": "response_guard_dropped"}),
+        );
        session.cancel();
        detach_finalize(session);
    }
 }

 struct ResponsesStreamState {
+    trace: TraceContext,
+    handed_off_bytes: u64,
    session: Option<Box<dyn ExecutionSession>>,
    encoder: OpenAiResponsesEncoder,
    pending: VecDeque<Bytes>,
@@ -444,6 +469,8 @@ impl ResponsesStreamState {
        connection_guard: Option<Box<dyn ConnectionGuard>>,
    ) -> Self {
        Self {
+            trace: session.trace(),
+            handed_off_bytes: 0,
            session: Some(session),
            encoder,
            pending: initial_frames.into_iter().collect(),
@@ -599,6 +626,11 @@ impl ResponsesStreamState {

 impl Drop for ResponsesStreamState {
    fn drop(&mut self) {
+        self.trace.record("downstream.body.closed", serde_json::json!({
+            "handedOffBytes": self.handed_off_bytes,
+            "pendingChunks": self.pending.len(),
+            "outputFinished": self.output_finished, "executionTerminal": self.execution_terminal,
+        }));
        if self.execution_terminal {
            return;
        }
@@ -4,12 +4,12 @@ mod error;
 mod http;
 mod request;
 mod response;
-mod websocket;
+pub mod websocket;

 pub use error::{ProtocolError, ProtocolErrorBody, RequestDecodeError, ResponseEncodeError};
+pub(crate) use http::responses;
 pub(super) use http::{PendingExecution, request_client_context};
 pub use http::{collect_execution_response, stream_execution_response};
-pub(crate) use http::{responses, review_responses};
 pub use request::{
    ContinuationIntent, DecodedResponsesRequest, OpenAiRequestHeaders, ResponsesRequestMetadata,
    decode_request_with_headers,
@@ -13,9 +13,19 @@ use serde_json::{Map, Value};
 use super::error::RequestDecodeError;

 const OPENAI_PROTOCOL: &str = "openai";
-const REVIEW_SUBAGENT: &str = "review";
 const OPENAI_SUBAGENT_KEY: &str = "x-openai-subagent";
+const CODEX_TURN_METADATA_KEY: &str = "x-codex-turn-metadata";
 const PASSTHROUGH_HEADERS_CONTEXT_KEY: &str = "opaque_request_headers";
+const DOWNSTREAM_WEBSOCKET_CONNECTION_ID_CONTEXT_KEY: &str = "downstream_websocket_connection_id";
+
+/// Responses 请求进入共享解码内核时的下游传输来源。
+#[derive(Clone, Copy)]
+pub(super) enum RequestDecodeSource {
+    /// 单次 HTTP 请求，请求头与正文属于同一请求。
+    Http,
+    /// 复用连接上的 WebSocket `response.create` 帧。
+    WebSocketFrame,
+}

 #[derive(Clone, Default)]
 pub struct OpenAiRequestHeaders {
@@ -26,6 +36,7 @@ pub struct OpenAiRequestHeaders {
    include_timing_metrics: Option<String>,
    codex_window_id: Option<String>,
    parent_thread_id: Option<String>,
+    downstream_websocket_connection_id: Option<String>,

    conversation_id: Option<String>,
    session_id: Option<String>,
@@ -51,6 +62,7 @@ impl OpenAiRequestHeaders {
            include_timing_metrics: header_string(headers, "x-responsesapi-include-timing-metrics"),
            codex_window_id: header_string(headers, "x-codex-window-id"),
            parent_thread_id: header_string(headers, "x-codex-parent-thread-id"),
+            downstream_websocket_connection_id: None,
            conversation_id: header_string(headers, "conversation-id")
                .or_else(|| header_string(headers, "conversation_id")),
            session_id: header_string(headers, "session-id")
@@ -65,16 +77,43 @@ impl OpenAiRequestHeaders {
        }
    }

-    fn apply_subagent(&self, body: &mut Map<String, Value>, forced_subagent: Option<&str>) {
-        if let Some(subagent) = forced_subagent.or(self.subagent.as_deref()) {
+    /// 绑定代理为当前下游 WebSocket 分配的连接身份。
+    #[must_use]
+    pub(super) fn with_downstream_websocket_connection_id(
+        mut self,
+        connection_id: impl Into<String>,
+    ) -> Self {
+        self.downstream_websocket_connection_id = Some(connection_id.into());
+        self
+    }
+
+    fn apply_subagent(&self, body: &mut Map<String, Value>) {
+        if let Some(subagent) = self.subagent.as_deref() {
            inject_subagent_metadata(body, subagent);
        }
    }

-    fn protocol_context(&self, use_websocket: Option<bool>) -> Map<String, Value> {
+    /// 独立端点只消费会话身份与 turn metadata，不携带 Responses 的连接状态。
+    pub(crate) fn session_context(&self) -> Map<String, Value> {
+        let mut context = Map::new();
+        insert_protocol_context(&mut context, "session_id", self.session_id.as_ref());
+        insert_protocol_context(&mut context, "thread_id", self.thread_id.as_ref());
+        insert_protocol_context(&mut context, "turn_metadata", self.turn_metadata.as_ref());
+        context
+    }
+
+    fn protocol_context(
+        &self,
+        use_websocket: Option<bool>,
+        frame_turn_metadata: Option<&String>,
+    ) -> Map<String, Value> {
        let mut context = Map::new();
        insert_protocol_context(&mut context, "turn_state", self.turn_state.as_ref());
-        insert_protocol_context(&mut context, "turn_metadata", self.turn_metadata.as_ref());
+        insert_protocol_context(
+            &mut context,
+            "turn_metadata",
+            frame_turn_metadata.or(self.turn_metadata.as_ref()),
+        );
        insert_protocol_context(&mut context, "beta_features", self.beta_features.as_ref());
        insert_protocol_context(&mut context, "version", self.version.as_ref());
        insert_protocol_context(
@@ -92,6 +131,11 @@ impl OpenAiRequestHeaders {
            "parent_thread_id",
            self.parent_thread_id.as_ref(),
        );
+        insert_protocol_context(
+            &mut context,
+            DOWNSTREAM_WEBSOCKET_CONNECTION_ID_CONTEXT_KEY,
+            self.downstream_websocket_connection_id.as_ref(),
+        );
        insert_protocol_context(
            &mut context,
            "conversation_id",
@@ -283,20 +327,11 @@ pub fn decode_request_with_headers(
    body: &[u8],
    headers: &HeaderMap,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
-    decode_request_inner(body, false, &OpenAiRequestHeaders::from_headers(headers))
-}
-
-/// 解码 `POST /v1/responses/review` 请求并冻结 review subagent 语义。
-pub(super) fn decode_review_request_with_headers(
-    body: &[u8],
-    headers: &HeaderMap,
-) -> Result<DecodedResponsesRequest, RequestDecodeError> {
-    decode_request_inner(body, true, &OpenAiRequestHeaders::from_headers(headers))
+    decode_request_inner(body, &OpenAiRequestHeaders::from_headers(headers))
 }

 pub(super) fn decode_request_inner(
    body: &[u8],
-    review: bool,
    request_headers: &OpenAiRequestHeaders,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
    let value =
@@ -304,14 +339,14 @@ pub(super) fn decode_request_inner(
    let Value::Object(object) = value else {
        return Err(RequestDecodeError::ExpectedObject);
    };
-    decode_request_object(object, review, request_headers)
+    decode_request_object(object, request_headers, RequestDecodeSource::Http)
 }

-/// 解码已解析的顶层 object；WebSocket 帧解码复用此内核，避免序列化往返。
+/// 解码已解析的顶层 object；按下游传输来源恢复连接级协议上下文。
 pub(super) fn decode_request_object(
    mut object: Map<String, Value>,
-    review: bool,
    request_headers: &OpenAiRequestHeaders,
+    source: RequestDecodeSource,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
    // 仅消费已识别的本地 transport 开关；未知同名值保留给未来上游协议。
    let use_websocket = object.get("use_websocket").and_then(Value::as_bool);
@@ -340,8 +375,12 @@ pub(super) fn decode_request_object(
        .map(|response_id| ContinuationIntent::PreviousResponseId(response_id.to_owned()))
        .unwrap_or(ContinuationIntent::None);

-    request_headers.apply_subagent(&mut object, review.then_some(REVIEW_SUBAGENT));
-    let protocol_context = request_headers.protocol_context(use_websocket);
+    request_headers.apply_subagent(&mut object);
+    let frame_turn_metadata = match source {
+        RequestDecodeSource::Http => None,
+        RequestDecodeSource::WebSocketFrame => frame_turn_metadata(&object),
+    };
+    let protocol_context = request_headers.protocol_context(use_websocket, frame_turn_metadata);

    let payload = ProtocolPayload::json_object(OPENAI_PROTOCOL, object)
        .map_err(|_| RequestDecodeError::CanonicalContract {
@@ -362,6 +401,16 @@ pub(super) fn decode_request_object(
    })
 }

+fn frame_turn_metadata(body: &Map<String, Value>) -> Option<&String> {
+    body.get("client_metadata")
+        .and_then(Value::as_object)
+        .and_then(|metadata| metadata.get(CODEX_TURN_METADATA_KEY))
+        .and_then(|value| match value {
+            Value::String(value) if !value.trim().is_empty() => Some(value),
+            _ => None,
+        })
+}
+
 fn inject_subagent_metadata(body: &mut Map<String, Value>, subagent: &str) {
    let metadata = body
        .entry("client_metadata".to_owned())
@@ -443,6 +492,8 @@ fn passthrough_header_name(name: &str, connection_headers: &[String]) -> bool {
            // 下游鉴权和账号 cookie 绝不能成为上游账号身份。
            | "authorization"
            | "x-api-key"
+            // Codex 的服务端托管认证标记只用于客户端能力判断，不代表上游身份。
+            | "x-openai-actor-authorization"
            | "cookie"
            | "cookie2"
            | "chatgpt-account-id"
@@ -11,7 +11,7 @@ use std::{

 use axum::extract::ws::{CloseFrame, Message, WebSocket, close_code};
 use futures::{Sink, SinkExt, Stream, StreamExt};
-use gateway_core::engine::CancellationToken;
+use gateway_core::lifecycle::CancellationToken;
 use thiserror::Error;
 use tokio::{
    sync::{mpsc, oneshot},
@@ -24,21 +24,23 @@ const INBOUND_EVENT_BUFFER: usize = 32;
 const DOWNSTREAM_WRITE_TIMEOUT: Duration = Duration::from_secs(5 * 60);
 const CONNECTION_MAX_AGE: Duration = Duration::from_secs(60 * 60);

+/// WebSocket pump 的写入与生命周期预算。
 #[derive(Clone, Copy)]
-pub(super) struct ConnectionConfig {
-    pub(super) write_timeout: Duration,
-    pub(super) max_age: Duration,
+pub struct ConnectionConfig {
+    write_timeout: Duration,
+    max_age: Duration,
 }

 impl ConnectionConfig {
-    pub(super) const PRODUCTION: Self = Self {
+    /// 生产环境固定预算。
+    pub const PRODUCTION: Self = Self {
        write_timeout: DOWNSTREAM_WRITE_TIMEOUT,
        max_age: CONNECTION_MAX_AGE,
    };
 }

 /// 业务层可观察的客户端输入；Ping/Pong 始终由 pump 消费。
-pub(super) enum ConnectionEvent {
+pub enum ConnectionEvent {
    Text(String),
    Binary,
    Expired,
@@ -47,7 +49,7 @@ pub(super) enum ConnectionEvent {

 /// 下游写入阶段；名称刻意使用 write，而不是暗示客户端已消费的 delivery。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub(super) enum FramePhase {
+pub enum FramePhase {
    Metadata,
    First,
    Data,
@@ -85,21 +87,26 @@ impl FramePhase {
    }
 }

+/// 一次下游写入的请求归属与协议阶段。
 #[derive(Clone)]
-pub(super) struct WriteContext {
+pub struct WriteContext {
    request_id: Option<Arc<str>>,
    phase: FramePhase,
 }

 impl WriteContext {
-    pub(super) fn request(request_id: &Arc<str>, phase: FramePhase) -> Self {
+    /// 创建归属于某个请求的写入上下文。
+    #[must_use]
+    pub fn request(request_id: &Arc<str>, phase: FramePhase) -> Self {
        Self {
            request_id: Some(Arc::clone(request_id)),
            phase,
        }
    }

-    pub(super) const fn connection(phase: FramePhase) -> Self {
+    /// 创建连接级写入上下文。
+    #[must_use]
+    pub const fn connection(phase: FramePhase) -> Self {
        Self {
            request_id: None,
            phase,
@@ -107,8 +114,9 @@ impl WriteContext {
    }
 }

+/// WebSocket pump 停止的稳定原因。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub(super) enum PumpExitReason {
+pub enum PumpExitReason {
    ClientClose,
    PeerEof,
    ReadError,
@@ -140,8 +148,9 @@ impl PumpExitReason {
    }
 }

+/// 下游 WebSocket 写入失败。
 #[derive(Debug, Error)]
-pub(super) enum ConnectionWriteError {
+pub enum ConnectionWriteError {
    #[error("downstream WebSocket pump is closed")]
    Closed,
    #[error("downstream WebSocket write timed out after {timeout:?}")]
@@ -179,12 +188,14 @@ impl ConnectionStats {
    }
 }

-pub(super) struct ResponsesWebSocketConnection {
+/// 协调层持有的单 owner WebSocket 连接句柄。
+pub struct ResponsesWebSocketConnection {
    connection_id: Arc<str>,
    opened_at: Instant,
    expired: Arc<AtomicBool>,
    commands: Option<mpsc::Sender<ConnectionCommand>>,
    incoming: mpsc::Receiver<ConnectionEvent>,
+    exited: oneshot::Receiver<PumpExitReason>,
    pump_task: Option<JoinHandle<()>>,
    stats: Arc<ConnectionStats>,
    config: ConnectionConfig,
@@ -209,7 +220,9 @@ impl ResponsesWebSocketConnection {
        &self.connection_id
    }

-    pub(super) fn is_expired(&self) -> bool {
+    /// 返回连接是否已经达到生命周期上限。
+    #[must_use]
+    pub fn is_expired(&self) -> bool {
        self.expired.load(Ordering::Acquire)
    }

@@ -217,8 +230,18 @@ impl ResponsesWebSocketConnection {
        self.opened_at.elapsed()
    }

-    pub(super) async fn next_event(&mut self) -> Option<ConnectionEvent> {
-        let event = self.incoming.recv().await;
+    /// 等待下一个需要业务层处理的客户端事件。
+    pub async fn next_event(&mut self) -> Option<ConnectionEvent> {
+        if let Some(reason) = self.exit_reason {
+            return Some(ConnectionEvent::Exited(reason));
+        }
+        let event = tokio::select! {
+            biased;
+            reason = &mut self.exited => {
+                Some(ConnectionEvent::Exited(reason.unwrap_or(PumpExitReason::PumpStopped)))
+            }
+            event = self.incoming.recv() => event,
+        };
        if let Some(ConnectionEvent::Exited(reason)) = event.as_ref() {
            self.exit_reason.get_or_insert(*reason);
        } else if event.is_none() {
@@ -227,7 +250,24 @@ impl ResponsesWebSocketConnection {
        event
    }

-    pub(super) async fn send_text(
+    /// 等待连接退出，不消费留给后续串行请求的业务帧。
+    pub async fn wait_for_exit(&mut self) -> PumpExitReason {
+        if let Some(reason) = self.exit_reason {
+            return reason;
+        }
+        let reason = (&mut self.exited)
+            .await
+            .unwrap_or(PumpExitReason::PumpStopped);
+        self.exit_reason = Some(reason);
+        reason
+    }
+
+    /// 串行写入文本帧，并等待 pump 确认 transport 写入结果。
+    ///
+    /// # Errors
+    ///
+    /// pump 已关闭、写入超时或 transport 失败时返回稳定错误。
+    pub async fn send_text(
        &mut self,
        payload: String,
        context: WriteContext,
@@ -391,7 +431,8 @@ impl Drop for ResponsesWebSocketConnection {
    }
 }

-pub(super) fn spawn_connection<S, E>(
+/// 为一个 socket 启动单 owner pump，并返回协调层句柄。
+pub fn spawn_connection<S, E>(
    socket: S,
    connection_id: Arc<str>,
    cancellation: CancellationToken,
@@ -406,10 +447,12 @@ where
    let stats = Arc::new(ConnectionStats::default());
    let (command_tx, command_rx) = mpsc::channel(OUTBOUND_COMMAND_BUFFER);
    let (incoming_tx, incoming_rx) = mpsc::channel(INBOUND_EVENT_BUFFER);
+    let (exit_tx, exit_rx) = oneshot::channel();
    let pump_task = tokio::spawn(run_pump(
        socket,
        command_rx,
        incoming_tx,
+        exit_tx,
        Arc::clone(&connection_id),
        cancellation,
        opened_at,
@@ -423,6 +466,7 @@ where
        expired,
        commands: Some(command_tx),
        incoming: incoming_rx,
+        exited: exit_rx,
        pump_task: Some(pump_task),
        stats,
        config,
@@ -435,6 +479,7 @@ async fn run_pump<S, E>(
    mut socket: S,
    mut commands: mpsc::Receiver<ConnectionCommand>,
    incoming: mpsc::Sender<ConnectionEvent>,
+    exited: oneshot::Sender<PumpExitReason>,
    connection_id: Arc<str>,
    cancellation: CancellationToken,
    opened_at: Instant,
@@ -455,8 +500,13 @@ async fn run_pump<S, E>(
            () = &mut deadline, if !deadline_elapsed => {
                deadline_elapsed = true;
                expired.store(true, Ordering::Release);
-                if let Err(reason) = emit_incoming(&incoming, ConnectionEvent::Expired) {
-                    break reason;
+                // 满队列本身已能唤醒空闲协调层；到期标志仍阻止启动下一轮。
+                // 不能因无法追加 Expired 通知而中断正在收尾的响应。
+                match incoming.try_send(ConnectionEvent::Expired) {
+                    Ok(()) | Err(mpsc::error::TrySendError::Full(_)) => {}
+                    Err(mpsc::error::TrySendError::Closed(_)) => {
+                        break PumpExitReason::CoordinatorDropped;
+                    }
                }
            }
            command = commands.recv() => {
@@ -531,7 +581,8 @@ async fn run_pump<S, E>(
            },
        }
    };
-    let _ = incoming.try_send(ConnectionEvent::Exited(reason));
+    // 退出不能排在待执行请求之后，也不能因业务队列已满而丢失。
+    let _ = exited.send(reason);
    tracing::debug!(
        websocket_connection_id = %connection_id,
        pump_exit_reason = reason.as_str(),
@@ -13,12 +13,10 @@ use crate::openai::error::{gateway_error_contract, gateway_error_from_engine};

 use super::{
    super::{DecodedResponsesRequest, OpenAiResponsesEncoder, PendingExecution, ProtocolErrorBody},
-    connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext},
+    connection::{FramePhase, ResponsesWebSocketConnection, WriteContext},
    protocol::{error_event, response_metadata_event},
 };

-const ACTIVE_RESPONSE_VIOLATION: &str = "Only one response.create may be active per connection";
-
 #[derive(Clone, Copy, PartialEq, Eq)]
 pub(super) enum ForwardOutcome {
    Continue,
@@ -66,29 +64,20 @@ pub(super) async fn forward_execution(
        );
        return send_gateway_error(connection, &error, &request_id).await;
    }
-    let first = loop {
-        match next_active_input(connection, &mut execution).await {
-            ActiveInput::Event(Ok(Some(event))) => break event,
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended before its first event",
-                );
-                return send_gateway_error(connection, &error, &request_id).await;
-            }
-            ActiveInput::Event(Err(error)) => {
-                let error = gateway_error_from_engine(&error);
-                return send_gateway_error(connection, &error, &request_id).await;
-            }
-            ActiveInput::Control => continue,
-            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
-            ActiveInput::ProtocolViolation => {
-                connection
-                    .close_policy(ACTIVE_RESPONSE_VIOLATION, Some(&request_id))
-                    .await;
-                return ForwardOutcome::Disconnect;
-            }
+    let first = match next_active_input(connection, &mut execution).await {
+        ActiveInput::Event(Ok(Some(event))) => event,
+        ActiveInput::Event(Ok(None)) => {
+            let error = GatewayError::new(
+                GatewayErrorKind::Internal,
+                "gateway response ended before its first event",
+            );
+            return send_gateway_error(connection, &error, &request_id).await;
        }
+        ActiveInput::Event(Err(error)) => {
+            return send_initial_engine_error(connection, &mut execution, &error, &request_id)
+                .await;
+        }
+        ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
    };
    let requirement = first.commit_requirement();
    let mut first = first.into_provider_events();
@@ -259,18 +248,35 @@ pub(super) async fn forward_execution(
                let error = gateway_error_from_engine(&error);
                return send_gateway_error(connection, &error, &request_id).await;
            }
-            ActiveInput::Control => {}
            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
-            ActiveInput::ProtocolViolation => {
-                connection
-                    .close_policy(ACTIVE_RESPONSE_VIOLATION, Some(&request_id))
-                    .await;
-                return ForwardOutcome::Disconnect;
-            }
        }
    }
 }

+async fn send_initial_engine_error(
+    connection: &mut ResponsesWebSocketConnection,
+    execution: &mut PendingExecution,
+    error: &EngineError,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let response_headers = execution
+        .session_mut()
+        .map(|session| session.response_headers().to_vec())
+        .unwrap_or_default();
+    if !response_headers.is_empty()
+        && !send_metadata(
+            connection,
+            request_id,
+            response_metadata_event(request_id, &response_headers),
+        )
+        .await
+    {
+        return ForwardOutcome::Disconnect;
+    }
+    let error = gateway_error_from_engine(error);
+    send_gateway_error(connection, &error, request_id).await
+}
+
 fn commit_connection_replay(
    replay: &mut ConnectionReplaySnapshot,
    encoder: &OpenAiResponsesEncoder,
@@ -286,50 +292,39 @@ async fn confirm_completed_execution(
    execution: &mut PendingExecution,
    request_id: &Arc<str>,
 ) -> Result<(), ForwardOutcome> {
-    loop {
-        match next_active_input(connection, execution).await {
-            ActiveInput::Event(Ok(None))
-                if execution
-                    .session_mut()
-                    .is_some_and(|session| session.is_finalized()) =>
-            {
-                return Ok(());
-            }
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response was not finalized after its terminal event",
-                );
-                return Err(send_gateway_error(connection, &error, request_id).await);
-            }
-            ActiveInput::Event(Ok(Some(_))) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response continued after its terminal event",
-                );
-                return Err(send_gateway_error(connection, &error, request_id).await);
-            }
-            ActiveInput::Event(Err(error)) => {
-                let error = gateway_error_from_engine(&error);
-                return Err(send_gateway_error(connection, &error, request_id).await);
-            }
-            ActiveInput::Control => {}
-            ActiveInput::Disconnect => return Err(ForwardOutcome::Disconnect),
-            ActiveInput::ProtocolViolation => {
-                connection
-                    .close_policy(ACTIVE_RESPONSE_VIOLATION, Some(request_id))
-                    .await;
-                return Err(ForwardOutcome::Disconnect);
-            }
+    match next_active_input(connection, execution).await {
+        ActiveInput::Event(Ok(None))
+            if execution
+                .session_mut()
+                .is_some_and(|session| session.is_finalized()) =>
+        {
+            Ok(())
        }
+        ActiveInput::Event(Ok(None)) => {
+            let error = GatewayError::new(
+                GatewayErrorKind::Internal,
+                "gateway response was not finalized after its terminal event",
+            );
+            Err(send_gateway_error(connection, &error, request_id).await)
+        }
+        ActiveInput::Event(Ok(Some(_))) => {
+            let error = GatewayError::new(
+                GatewayErrorKind::Internal,
+                "gateway response continued after its terminal event",
+            );
+            Err(send_gateway_error(connection, &error, request_id).await)
+        }
+        ActiveInput::Event(Err(error)) => {
+            let error = gateway_error_from_engine(&error);
+            Err(send_gateway_error(connection, &error, request_id).await)
+        }
+        ActiveInput::Disconnect => Err(ForwardOutcome::Disconnect),
    }
 }

 enum ActiveInput {
    Event(Result<Option<CoordinatedEvent>, EngineError>),
-    Control,
    Disconnect,
-    ProtocolViolation,
 }

 async fn next_active_input(
@@ -339,15 +334,17 @@ async fn next_active_input(
    let Some(session) = execution.session_mut() else {
        return ActiveInput::Disconnect;
    };
+    // 与 Codex stream_request 的连接锁一致：本轮结束前不消费下一条请求。
+    // pump 继续接收有界业务帧和处理 Ping/Pong；退出通过独立通知取消本轮。
    tokio::select! {
-        event = session.next_event() => ActiveInput::Event(event),
-        message = connection.next_event() => match message {
-            Some(ConnectionEvent::Expired) => ActiveInput::Control,
-            Some(ConnectionEvent::Text(_) | ConnectionEvent::Binary) => {
-                ActiveInput::ProtocolViolation
-            }
-            Some(ConnectionEvent::Exited(_)) | None => ActiveInput::Disconnect,
+        biased;
+        _ = connection.wait_for_exit() => {
+            session.trace().record("downstream.cancelled", serde_json::json!({
+                "reason": "websocket_connection_exit", "connectionId": connection.id(),
+            }));
+            ActiveInput::Disconnect
        },
+        event = session.next_event() => ActiveInput::Event(event),
    }
 }

@@ -459,6 +456,7 @@ fn log_terminal_write_success(
    provider_terminal_to_write: std::time::Duration,
 ) {
    tracing::info!(
+        target: "request_trace", stage = "downstream.terminal.written",
        websocket_connection_id = connection.id(),
        request_id = %request_id,
        provider_terminal_to_terminal_write_ms = provider_terminal_to_write.as_millis(),
@@ -473,6 +471,7 @@ fn log_terminal_write_failure(
    provider_terminal_to_write: std::time::Duration,
 ) {
    tracing::info!(
+        target: "request_trace", stage = "downstream.terminal.write_failed",
        websocket_connection_id = connection.id(),
        request_id = %request_id,
        provider_terminal_to_terminal_write_ms = provider_terminal_to_write.as_millis(),
@@ -1,6 +1,6 @@
 //! OpenAI Responses WebSocket 的升级、连接与串行 session 编排。

-mod connection;
+pub mod connection;
 mod forward;
 mod protocol;

@@ -19,6 +19,7 @@ use axum::{
    response::{IntoResponse, Response},
 };
 use gateway_core::{
+    diagnostics::{TraceContext, diagnostic_json},
    engine::execution::{AuthenticatedClient, ClientTransport},
    lifecycle::{ConnectionGuard, ConnectionLifecycle},
 };
@@ -26,7 +27,7 @@ use gateway_core::{
 use crate::{
    ApiState,
    openai::{
-        auth::{authenticate_client, authentication_error_response},
+        auth::{authenticate_client, client_access_error_response},
        error::runtime_unavailable_response,
        service::OpenAiService,
    },
@@ -54,18 +55,20 @@ pub(crate) async fn responses_websocket(
    let service = state.openai().clone();
    let client = match authenticate_client(&service, &headers) {
        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
    };
    let (client_ip, user_agent) = request_client_context(
        &headers,
        connect_info.map(|Extension(ConnectInfo(address))| address),
    );
+    let request_headers = OpenAiRequestHeaders::from_headers(&headers);
    ResponsesWebSocketAdapter::new(service).upgrade_with_client_context(
        websocket,
        client,
        client_ip,
        user_agent,
-        OpenAiRequestHeaders::from_headers(&headers),
+        request_headers,
+        headers,
    )
 }

@@ -89,15 +92,24 @@ impl ResponsesWebSocketAdapter {
        client_ip: Option<IpAddr>,
        user_agent: Option<String>,
        request_headers: OpenAiRequestHeaders,
+        raw_headers: HeaderMap,
    ) -> Response {
        let connection_guard = match self.service.try_register_connection() {
            Ok(guard) => guard,
            Err(_) => return runtime_unavailable_response().into_response(),
        };
+        let connection_id = self.service.next_request_id().replacen("req_", "ws_", 1);
+        TraceContext::new(&connection_id).headers(
+            "client.connection.headers",
+            serde_json::json!({"transport": "websocket", "method": "GET", "path": "/v1/responses"}),
+            raw_headers
+                .iter()
+                .map(|(name, value)| (name.as_str(), value.as_bytes())),
+        );
        let session = ResponsesWebSocketSession {
            service: self.service.clone(),
            client,
-            connection_id: self.service.next_request_id().replacen("req_", "ws_", 1),
+            connection_id,
            client_ip,
            user_agent,
            request_headers,
@@ -143,6 +155,8 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
    );
    let _connection_guard = connection_guard;
    let cancellation = lifecycle.cancellation();
+    let request_headers =
+        request_headers.with_downstream_websocket_connection_id(connection_id.clone());
    let mut connection = ResponsesWebSocketConnection::new(socket, connection_id, cancellation);
    let mut request_count = 0_u64;
    let mut replay = ConnectionReplaySnapshot::default();
@@ -172,11 +186,12 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
        let decoded = match decode_response_create_with_context(&payload, &request_headers) {
            Ok(decoded) => decoded.with_client_context(client_ip, user_agent.clone()),
            Err(error) => {
-                tracing::info!(
-                    websocket_connection_id = connection.id(),
-                    request_id = %correlation_id,
-                    error = %error,
-                    "Responses WebSocket request rejected"
+                trace_rejected_request(
+                    &correlation_id,
+                    connection.id(),
+                    &payload,
+                    "decode",
+                    &error.to_string(),
                );
                if send_protocol_error(
                    &mut connection,
@@ -195,6 +210,13 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
        let decoded = replay.prepare(decoded);
        // deadline 与 Text 可能同时就绪；在任何上游执行开始前再次封住该竞争窗口。
        if connection.is_expired() {
+            trace_rejected_request(
+                &correlation_id,
+                connection.id(),
+                &payload,
+                "connection_expired",
+                "",
+            );
            expire_connection(&mut connection).await;
            break;
        }
@@ -209,6 +231,13 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
        {
            Ok(started) => started,
            Err(error) => {
+                trace_rejected_request(
+                    &correlation_id,
+                    connection.id(),
+                    &payload,
+                    "start",
+                    &error.to_string(),
+                );
                if send_gateway_error(&mut connection, &error, &correlation_id).await
                    == ForwardOutcome::Disconnect
                {
@@ -217,6 +246,14 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
                continue;
            }
        };
+        started.session.trace().record("client.connection", serde_json::json!({
+            "transport": "websocket", "connectionId": connection.id(), "correlationId": correlation_id,
+            "requestIndex": request_count,
+        }));
+        started
+            .session
+            .trace()
+            .capture("client.request.body", payload.as_bytes());

        if forward_execution(&mut connection, started, &mut replay).await
            == ForwardOutcome::Disconnect
@@ -232,6 +269,28 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
    connection.log_summary(request_count);
 }

+// 尚未建立模型请求的拒绝也保留原文入口，用返回给客户端的 correlation ID 检索。
+fn trace_rejected_request(
+    correlation_id: &str,
+    connection_id: &str,
+    payload: &str,
+    phase: &'static str,
+    error: &str,
+) {
+    let trace = TraceContext::new(correlation_id);
+    trace.record(
+        "client.connection",
+        serde_json::json!({"connectionId": connection_id}),
+    );
+    trace.capture("client.request.body", payload.as_bytes());
+    trace.record(
+        "client.request.rejected",
+        serde_json::json!({
+            "phase": phase, "detail": diagnostic_json(&serde_json::json!({"message": error})),
+        }),
+    );
+}
+
 async fn expire_connection(connection: &mut ResponsesWebSocketConnection) {
    if connection
        .send_text(
@@ -6,7 +6,8 @@ use serde_json::{Map, Value, json};
 use thiserror::Error;

 use super::super::{
-    DecodedResponsesRequest, ProtocolErrorBody, RequestDecodeError, request::OpenAiRequestHeaders,
+    DecodedResponsesRequest, ProtocolErrorBody, RequestDecodeError,
+    request::{OpenAiRequestHeaders, RequestDecodeSource},
 };

 /// 使用连接级请求头和 Provider 上下文解码官方 `response.create` 文本帧。
@@ -40,8 +41,12 @@ fn decode_response_create_inner(
    if matches!(body.get("stream"), Some(value) if value.as_bool() != Some(true)) {
        return Err(ResponseCreateFrameError::StreamingRequired);
    }
-    super::super::request::decode_request_object(body, false, request_headers)
-        .map_err(ResponseCreateFrameError::Request)
+    super::super::request::decode_request_object(
+        body,
+        request_headers,
+        RequestDecodeSource::WebSocketFrame,
+    )
+    .map_err(ResponseCreateFrameError::Request)
 }

 /// `response.create` 帧的稳定安全错误。
@@ -8,8 +8,9 @@ use axum::{

 use super::{
    images::{image_edits, image_generations},
-    models::{model_catalog, model_detail, model_info, models},
-    responses::{responses, responses_websocket, review_responses},
+    models::{model_detail, models},
+    responses::{responses, responses_websocket},
+    search::standalone_search,
 };

 use crate::ApiState;
@@ -19,11 +20,9 @@ pub(crate) fn router() -> Router<ApiState> {
    Router::new()
        .route("/v1/images/generations", post(image_generations))
        .route("/v1/images/edits", post(image_edits))
+        .route("/v1/alpha/search", post(standalone_search))
        .route("/v1/responses", get(responses_websocket).post(responses))
-        .route("/v1/responses/review", post(review_responses))
        .route("/v1/models", get(models))
-        .route("/v1/models/catalog", get(model_catalog))
-        .route("/v1/models/{model_id}/info", get(model_info))
        // 官方 OpenAI 模型详情合同使用 path ID；它不属于 Admin API 约束。
        .route("/v1/models/{model_id}", get(model_detail))
        // OpenAI 数据面正文属于客户端/上游协议；代理不能用私有大小上限提前拒绝
@@ -0,0 +1,67 @@
+//! Codex standalone search 非流式 HTTP adapter。
+
+use std::net::SocketAddr;
+
+use axum::{
+    body::Bytes,
+    extract::{Extension, State, connect_info::ConnectInfo},
+    http::HeaderMap,
+    response::Response,
+};
+use gateway_core::error::{GatewayError, GatewayErrorKind};
+use gateway_core::operation::{Operation, RawJsonPayload, StandaloneSearchRequest};
+
+use crate::ApiState;
+use crate::openai::{
+    auth::{authenticate_client, client_access_error_response},
+    error::gateway_error_response,
+    provider_endpoint::collect_raw_json_response,
+    responses::{OpenAiRequestHeaders, request_client_context},
+};
+
+const OPENAI_PROTOCOL: &str = "openai";
+
+/// `POST /v1/alpha/search`。
+pub(crate) async fn standalone_search(
+    State(state): State<ApiState>,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    let service = state.openai();
+    let client = match authenticate_client(service, &headers) {
+        Ok(client) => client,
+        Err(error) => return client_access_error_response(error),
+    };
+    let (client_ip, user_agent) = request_client_context(
+        &headers,
+        connect_info.map(|Extension(ConnectInfo(address))| address),
+    );
+    let operation = match search_operation(body, &headers) {
+        Ok(operation) => operation,
+        Err(error) => return gateway_error_response(&error),
+    };
+    let started = match service
+        .start_provider_endpoint(client, operation, client_ip, user_agent, "/v1/alpha/search")
+        .await
+    {
+        Ok(started) => started,
+        Err(error) => return gateway_error_response(&error),
+    };
+    collect_raw_json_response(started).await
+}
+
+fn search_operation(body: Bytes, headers: &HeaderMap) -> Result<Operation, GatewayError> {
+    let context = OpenAiRequestHeaders::from_headers(headers).session_context();
+    let payload = RawJsonPayload::new(OPENAI_PROTOCOL, body)
+        .map_err(|_| {
+            GatewayError::new(
+                GatewayErrorKind::Internal,
+                "OpenAI protocol identifier is invalid",
+            )
+        })?
+        .with_context(context);
+    Ok(Operation::Search(StandaloneSearchRequest::from_raw_json(
+        payload,
+    )))
+}
@@ -0,0 +1,5 @@
+//! Codex standalone search HTTP adapter。
+
+mod http;
+
+pub(crate) use http::standalone_search;
@@ -106,7 +106,7 @@ impl OpenAiService {
            .await
    }

-    pub(crate) async fn start_image(
+    pub(crate) async fn start_provider_endpoint(
        &self,
        client: AuthenticatedClient,
        operation: gateway_core::operation::Operation,
@@ -348,6 +348,8 @@ mod response {
            output_tokens_display: "-".to_owned(),
            cached_tokens: None,
            cached_tokens_display: "-".to_owned(),
+            reasoning_tokens: None,
+            reasoning_tokens_display: "-".to_owned(),
            image_input_tokens: None,
            image_input_tokens_display: "-".to_owned(),
            image_output_tokens: None,
@@ -374,6 +376,8 @@ mod response {
        let value = serde_json::to_value(view).expect("serialize account usage");
        assert!(value["inputTokens"].is_null());
        assert!(value["totalTokens"].is_null());
+        assert!(value["reasoningTokens"].is_null());
+        assert_eq!(value["reasoningTokensDisplay"], "-");
        assert_eq!(value["createdTokensDisplay"], "-");
    }

@@ -404,10 +408,8 @@ mod actions {
        RotateAccountRequest, StartAccountAuthorizationRequest,
    };
    use gateway_core::{
-        engine::{
-            UpstreamSendState, credential::ProviderAccountId, probe::AccountProbeErrorSource,
-        },
-        error::GatewayErrorKind,
+        account::ProviderAccountId, engine::probe::AccountProbeErrorSource,
+        error::GatewayErrorKind, upstream::UpstreamSendState,
    };
    use serde_json::json;

@@ -25,6 +25,10 @@ use gateway_admin::{
            AccountsUpdateResult, BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
        },
        auth::{AdminAuditEvent, AdminSession},
+        client_distribution::{
+            ClientArchitecture, ClientDownloadPackage, ClientDownloadSource,
+            CodexDesktopWindowsDownloads,
+        },
        client_keys::{
            ClientKeyListQuery, ClientKeyPage, ClientKeyRecord, ClientKeySecret, DeleteClientKey,
            NewClientKey, SetClientKeyEnabled, UpdateClientKey,
@@ -50,6 +54,7 @@ use gateway_admin::{
        system::{SystemOperationAccepted, SystemUpdateDetail, SystemUpdateStatus, SystemVersion},
    },
    ports::{
+        client_distribution::ClientDistributionResolver,
        provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind},
        store::{
            AccountGroupStore, AccountRuntimeStore, AccountStore, AdminAccountStorePorts,
@@ -64,14 +69,11 @@ use gateway_admin::{
 };
 use gateway_api::admin::AdminSessionState;
 use gateway_core::{
-    engine::{
-        credential::{AccountStatusFacts, CredentialState, ProviderAccountId, QuotaState},
-        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
-    },
+    account::{AccountStatusFacts, CredentialState, ProviderAccountId, QuotaState},
+    engine::probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
    policy::{ClientApiKeyId, RateLimits},
-    routing::{
-        ConfigRevision, ProviderKind, PublicModelId, UpstreamModelId, snapshot::SnapshotControl,
-    },
+    routing::{ConfigRevision, ProviderKind, PublicModelId, UpstreamModelId},
+    runtime::SnapshotControl,
 };

 mod account_groups;
@@ -143,6 +145,7 @@ impl AdminTestFixture {
            providers,
            Arc::new(NoopSnapshot),
            Arc::new(NoopProbe),
+            Arc::new(StaticClientDistribution),
            system,
        )
        .await
@@ -165,6 +168,30 @@ impl AdminTestFixture {
    }
 }

+struct StaticClientDistribution;
+
+#[async_trait]
+impl ClientDistributionResolver for StaticClientDistribution {
+    async fn resolve_codex_desktop_windows(&self, _: bool) -> CodexDesktopWindowsDownloads {
+        CodexDesktopWindowsDownloads {
+            resolved_at: Utc::now(),
+            cached: false,
+            warning: None,
+            packages: vec![ClientDownloadPackage {
+                architecture: ClientArchitecture::X64,
+                source: ClientDownloadSource::MicrosoftStore,
+                version: Some("26.825.6671.0".to_owned()),
+                file_name: "OpenAI.Codex_26.825.6671.0_x64__2p2nqsd0c76g0.msix".to_owned(),
+                size_bytes: Some(744_250_000),
+                download_url:
+                    "https://dl.delivery.mp.microsoft.com/filestreamingservice/files/test"
+                        .to_owned(),
+                expires_at: Some(Utc::now() + Duration::hours(1)),
+            }],
+        }
+    }
+}
+
 #[derive(Clone)]
 pub(super) struct AdminTestState(AdminServices);

@@ -319,6 +346,8 @@ impl SettingsStore for MemorySettingsStore {
            max_concurrent_per_account: command.max_concurrent_per_account,
            request_interval_ms: command.request_interval_ms,
            rotation_strategy: command.rotation_strategy,
+            min_codex_desktop_version: command.min_codex_desktop_version,
+            min_codex_cli_version: command.min_codex_cli_version,
            usage_retention_days: command.usage_retention_days,
            ops_event_retention_days: command.ops_event_retention_days,
            audit_retention_days: command.audit_retention_days,
@@ -846,13 +875,14 @@ impl ObservabilityStore for UnusedStore {
        Err(unavailable("usage trend"))
    }

-    async fn usage_calculated_billing_facts(
+    fn usage_calculated_billing_facts(
        &self,
        _: TimeRange,
        _: UsageFilter,
-    ) -> AdminStoreResult<Vec<gateway_admin::model::observability::UsageCalculatedBillingFact>>
-    {
-        Err(unavailable("usage billing facts"))
+    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+        Box::pin(futures::stream::once(async {
+            Err(unavailable("usage billing facts"))
+        }))
    }

    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
@@ -1073,6 +1103,8 @@ fn test_runtime_settings() -> RuntimeSettings {
        max_concurrent_per_account: 3,
        request_interval_ms: 50,
        rotation_strategy: RotationStrategy::Smart,
+        min_codex_desktop_version: None,
+        min_codex_cli_version: None,
        usage_retention_days: 31,
        ops_event_retention_days: 30,
        audit_retention_days: 90,
@@ -49,6 +49,12 @@ fn ops_query_should_reject_page_size_above_terminal_limit() {
    assert_eq!(query.validate_pagination().unwrap_err().field(), "pageSize");
 }

+#[test]
+fn ops_query_should_reject_removed_filters() {
+    assert!(serde_json::from_value::<OpsQuery>(json!({"route": "/v1/responses"})).is_err());
+    assert!(serde_json::from_value::<OpsQuery>(json!({"failureClass": "rate_limited"})).is_err());
+}
+
 #[test]
 fn diagnostics_query_should_keep_wire_dimension_name() {
    let query: DiagnosticsQuery =
@@ -71,6 +71,9 @@ fn dashboard_account_usage_should_keep_daily_request_timeline() {
            request_count: 3,
        }],
        quota_used_percent: None,
+        usage_window: None,
+        metric_label: "次数".to_owned(),
+        metric_value: "3".to_owned(),
        last_used: "刚刚".to_owned(),
    })
    .expect("dashboard account usage");
@@ -426,6 +429,8 @@ async fn usage_detail_should_keep_attempt_snapshot_contract() {
        .lock()
        .expect("usage detail")
        .replace(UsageDetail {
+            trace: None,
+            related_requests: Vec::new(),
            request: usage_record_with_account(
                "req_detail",
                "acct_snap_a",
@@ -552,6 +557,7 @@ async fn ops_errors_should_keep_account_label_and_authentication_contract() {
            upstream_model_id: Some("upstream-err".to_owned()),
            upstream_transport: Some("http_sse".to_owned()),
            failure_kind: "upstream_error".to_owned(),
+            upstream_send_state: Some("sent".to_owned()),
            client_status_code: Some(502),
            upstream_status_code: Some(502),
            provider_error_code: Some("upstream".to_owned()),
@@ -559,7 +565,9 @@ async fn ops_errors_should_keep_account_label_and_authentication_contract() {
            upstream_request_id: None,
            latency_ms: Some(90),
            message: "snapshot error".to_owned(),
-            occurrence_count: 1,
+            raw_upstream_error: Some(
+                r#"{"error":{"code":"upstream","message":"raw upstream marker"}}"#.to_owned(),
+            ),
            client_ip: Some("203.0.113.8".to_owned()),
            user_agent: Some("codex-cli/0.144.0".to_owned()),
            reasoning_effort: Some("medium".to_owned()),
@@ -567,6 +575,18 @@ async fn ops_errors_should_keep_account_label_and_authentication_contract() {
            request_kind: Some("root".to_owned()),
            subagent_kind: None,
            compact: Some(false),
+            continuation_affinity_hash: Some("affinity-hash".to_owned()),
+            continuation_previous_response_id_hash: Some("response-hash".to_owned()),
+            continuation_unavailable_reason: Some("reused_connection_lost".to_owned()),
+            upstream_connection_id: Some("connection-id".to_owned()),
+            upstream_connection_exit_reason: Some("tcp_reset".to_owned()),
+            upstream_connection_age_ms: Some(12_000),
+            upstream_connection_idle_ms: Some(4_000),
+            recovery_request_id: None,
+            recovered_at: None,
+            recovery_attempt_count: 0,
+            recovery_retry_delay_ms: None,
+            recovery_total_latency_ms: None,
            occurred_at: Utc::now(),
            stable_sort_id: "model_request:req_err".to_owned(),
        });
@@ -601,6 +621,11 @@ async fn ops_errors_should_keep_account_label_and_authentication_contract() {
            "clientIp": value["data"]["items"][0]["clientIp"],
            "userAgent": value["data"]["items"][0]["userAgent"],
            "providerErrorCode": value["data"]["items"][0]["providerErrorCode"],
+            "upstreamSendState": value["data"]["items"][0]["upstreamSendState"],
+            "rawUpstreamError": value["data"]["items"][0]["rawUpstreamError"],
+            "continuationUnavailableReason": value["data"]["items"][0]["metadata"]["continuationUnavailableReason"],
+            "upstreamConnectionExitReason": value["data"]["items"][0]["metadata"]["upstreamConnectionExitReason"],
+            "upstreamConnectionAgeMs": value["data"]["items"][0]["metadata"]["upstreamConnectionAgeMs"],
        }),
        serde_json::json!({
            "provider": "openai",
@@ -615,6 +640,11 @@ async fn ops_errors_should_keep_account_label_and_authentication_contract() {
            "clientIp": "203.0.113.8",
            "userAgent": "codex-cli/0.144.0",
            "providerErrorCode": "upstream",
+            "upstreamSendState": "sent",
+            "rawUpstreamError": "{\"error\":{\"code\":\"upstream\",\"message\":\"raw upstream marker\"}}",
+            "continuationUnavailableReason": "reused_connection_lost",
+            "upstreamConnectionExitReason": "tcp_reset",
+            "upstreamConnectionAgeMs": 12000,
        })
    );
 }
@@ -46,6 +46,8 @@ fn update_body() -> Value {
        "maxConcurrentPerAccount": 5,
        "requestIntervalMs": 25,
        "rotationStrategy": "round_robin",
+        "minCodexDesktopVersion": "26.825.6671",
+        "minCodexCliVersion": "0.40.0",
        "usageRetentionDays": 32,
        "opsEventRetentionDays": 31,
        "auditRetentionDays": 91
@@ -62,6 +64,19 @@ fn settings_request_should_reject_unknown_rotation_strategy() {
    assert_eq!(request.validate().unwrap_err().field(), "rotationStrategy");
 }

+#[test]
+fn settings_request_should_reject_non_semver_client_min() {
+    let mut body = update_body();
+    body["minCodexCliVersion"] = json!("v0.40.0");
+    let request: UpdateRuntimeSettingsRequest =
+        serde_json::from_value(body).expect("decode settings");
+
+    assert_eq!(
+        request.validate().unwrap_err().field(),
+        "minCodexCliVersion"
+    );
+}
+
 #[test]
 fn settings_response_should_cover_the_full_runtime_settings_contract() {
    use std::collections::BTreeMap;
@@ -70,7 +85,7 @@ fn settings_response_should_cover_the_full_runtime_settings_contract() {
    use gateway_admin::model::Revision;
    use gateway_admin::model::settings::RuntimeSettings;
    use gateway_api::admin::settings::RuntimeSettingsView;
-    use gateway_core::engine::credential::RotationStrategy;
+    use gateway_core::account::RotationStrategy;
    use gateway_core::routing::{PublicModelId, UpstreamModelId};

    let settings = RuntimeSettings {
@@ -90,6 +105,8 @@ fn settings_response_should_cover_the_full_runtime_settings_contract() {
        max_concurrent_per_account: 5,
        request_interval_ms: 25,
        rotation_strategy: RotationStrategy::RoundRobin,
+        min_codex_desktop_version: Some("26.825.6671".to_owned()),
+        min_codex_cli_version: Some("0.40.0".to_owned()),
        usage_retention_days: 32,
        ops_event_retention_days: 31,
        audit_retention_days: 91,
@@ -112,6 +129,8 @@ fn settings_response_should_cover_the_full_runtime_settings_contract() {
            "maxConcurrentPerAccount": 5,
            "requestIntervalMs": 25,
            "rotationStrategy": "round_robin",
+            "minCodexDesktopVersion": "26.825.6671",
+            "minCodexCliVersion": "0.40.0",
            "usageRetentionDays": 32,
            "opsEventRetentionDays": 31,
            "auditRetentionDays": 91,
@@ -127,7 +146,7 @@ fn settings_request_and_response_fields_should_stay_in_lockstep() {
    use gateway_admin::model::Revision;
    use gateway_admin::model::settings::RuntimeSettings;
    use gateway_api::admin::settings::RuntimeSettingsView;
-    use gateway_core::engine::credential::RotationStrategy;
+    use gateway_core::account::RotationStrategy;
    use gateway_core::routing::{PublicModelId, UpstreamModelId};

    let request: UpdateRuntimeSettingsRequest =
@@ -159,6 +178,8 @@ fn settings_request_and_response_fields_should_stay_in_lockstep() {
        request_interval_ms: request.request_interval_ms,
        rotation_strategy: RotationStrategy::parse(&request.rotation_strategy)
            .expect("fixture rotation strategy"),
+        min_codex_desktop_version: request.min_codex_desktop_version,
+        min_codex_cli_version: request.min_codex_cli_version,
        usage_retention_days: u32::try_from(request.usage_retention_days).expect("u32"),
        ops_event_retention_days: u32::try_from(request.ops_event_retention_days).expect("u32"),
        audit_retention_days: u32::try_from(request.audit_retention_days).expect("u32"),
@@ -234,6 +255,31 @@ async fn settings_post_should_replace_global_model_mappings() {
    assert_eq!(data["modelMappings"]["grok-latest"], "grok-4.5");
 }

+#[tokio::test]
+async fn client_downloads_should_return_validated_direct_links() {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let response = app(fixture.state())
+        .oneshot(request(
+            Method::GET,
+            "/api/admin/settings/client-downloads/codex-desktop/windows?refresh=true",
+            None,
+        ))
+        .await
+        .expect("client downloads response");
+
+    assert_eq!(response.status(), StatusCode::OK);
+    let data = response_json(response).await["data"].clone();
+    assert_eq!(data["packages"][0]["architecture"], "x64");
+    assert_eq!(data["packages"][0]["source"], "microsoft_store");
+    assert_eq!(data["packages"][0]["version"], "26.825.6671.0");
+    assert!(
+        data["packages"][0]["downloadUrl"]
+            .as_str()
+            .is_some_and(|url| url.starts_with("https://dl.delivery.mp.microsoft.com/"))
+    );
+}
+
 #[test]
 fn settings_request_should_reject_invalid_model_mapping_name() {
    let mut body = update_body();
@@ -34,7 +34,11 @@ fn source_tree_should_match_frozen_machine_manifest() {
    actual.sort();
    let mut expected = vec![
        "src/admin/account_groups.rs",
-        "src/admin/accounts.rs",
+        "src/admin/accounts/credentials.rs",
+        "src/admin/accounts/handlers.rs",
+        "src/admin/accounts/mod.rs",
+        "src/admin/accounts/presenter.rs",
+        "src/admin/accounts/wire.rs",
        "src/admin/auth.rs",
        "src/admin/backups.rs",
        "src/admin/client_keys.rs",
@@ -57,6 +61,7 @@ fn source_tree_should_match_frozen_machine_manifest() {
        "src/openai/images/mod.rs",
        "src/openai/mod.rs",
        "src/openai/models.rs",
+        "src/openai/provider_endpoint.rs",
        "src/openai/responses/error.rs",
        "src/openai/responses/http.rs",
        "src/openai/responses/mod.rs",
@@ -67,6 +72,8 @@ fn source_tree_should_match_frozen_machine_manifest() {
        "src/openai/responses/websocket/mod.rs",
        "src/openai/responses/websocket/protocol.rs",
        "src/openai/router.rs",
+        "src/openai/search/http.rs",
+        "src/openai/search/mod.rs",
        "src/openai/service.rs",
    ];
    expected.sort_unstable();
@@ -81,7 +88,7 @@ fn test_tree_should_match_frozen_rust_mirror() {
    actual.sort();
    let mut expected = vec![
        "tests/admin/account_groups.rs",
-        "tests/admin/accounts.rs",
+        "tests/admin/accounts/mod.rs",
        "tests/admin/auth.rs",
        "tests/admin/client_keys.rs",
        "tests/admin/errors.rs",
@@ -97,15 +104,17 @@ fn test_tree_should_match_frozen_rust_mirror() {
        "tests/main.rs",
        "tests/openai/auth.rs",
        "tests/openai/error.rs",
-        "tests/openai/images.rs",
+        "tests/openai/images/mod.rs",
        "tests/openai/mod.rs",
        "tests/openai/models.rs",
+        "tests/openai/provider_endpoint.rs",
        "tests/openai/responses/http.rs",
        "tests/openai/responses/mod.rs",
        "tests/openai/responses/websocket/connection.rs",
        "tests/openai/responses/websocket/mod.rs",
        "tests/openai/responses/websocket/protocol.rs",
        "tests/openai/router.rs",
+        "tests/openai/search/mod.rs",
    ];
    expected.sort_unstable();

@@ -1,6 +1,9 @@
 use axum::http::{HeaderMap, HeaderValue, header::AUTHORIZATION};

-use gateway_api::openai::auth::{ClientApiKeyAuthError, bearer_client_api_key};
+use gateway_api::openai::auth::{
+    ClientApiKeyAuthError, bearer_client_api_key, identify_codex_client,
+};
+use gateway_core::policy::CodexClientKind;

 #[test]
 fn bearer_client_api_key_should_reject_missing_authorization() {
@@ -10,6 +13,32 @@ fn bearer_client_api_key_should_reject_missing_authorization() {
    );
 }

+#[test]
+fn actor_authorization_marker_should_not_replace_client_api_key() {
+    let mut headers = HeaderMap::new();
+    headers.insert(
+        "x-openai-actor-authorization",
+        HeaderValue::from_static("proxy-managed"),
+    );
+
+    assert_eq!(
+        bearer_client_api_key(&headers),
+        Err(ClientApiKeyAuthError::MissingAuthorization)
+    );
+}
+
+#[test]
+fn actor_authorization_marker_should_preserve_existing_bearer_authentication() {
+    let mut headers = HeaderMap::new();
+    headers.insert(
+        "x-openai-actor-authorization",
+        HeaderValue::from_static("proxy-managed"),
+    );
+    headers.insert(AUTHORIZATION, HeaderValue::from_static("Bearer sk_client"));
+
+    assert_eq!(bearer_client_api_key(&headers), Ok("sk_client"));
+}
+
 #[test]
 fn bearer_client_api_key_should_reject_non_utf8_authorization() {
    let mut headers = HeaderMap::new();
@@ -88,3 +117,48 @@ fn client_auth_failure_reasons_should_be_stable_and_secret_free() {
        ]
    );
 }
+
+#[test]
+fn desktop_headers_should_take_precedence_over_embedded_cli_marker() {
+    let mut headers = HeaderMap::new();
+    headers.insert("originator", HeaderValue::from_static("Codex Desktop"));
+    headers.insert("version", HeaderValue::from_static("26.825.6671"));
+    headers.insert(
+        "user-agent",
+        HeaderValue::from_static("codex_cli_rs/0.39.0 terminal (Codex Desktop; 26.1.0)"),
+    );
+
+    let identified = identify_codex_client(&headers).expect("recognized desktop");
+
+    assert_eq!(identified.kind(), CodexClientKind::Desktop);
+    assert_eq!(
+        identified.version().map(ToString::to_string).as_deref(),
+        Some("26.825.6671")
+    );
+}
+
+#[test]
+fn cli_user_agent_should_expose_semver_or_recognized_missing_version() {
+    let mut headers = HeaderMap::new();
+    headers.insert(
+        "user-agent",
+        HeaderValue::from_static("codex_cli_rs/0.39.0 (Linux; x86_64)"),
+    );
+    let identified = identify_codex_client(&headers).expect("recognized CLI");
+    assert_eq!(identified.kind(), CodexClientKind::Cli);
+    assert_eq!(
+        identified.version().map(ToString::to_string).as_deref(),
+        Some("0.39.0")
+    );
+
+    headers.insert(
+        "user-agent",
+        HeaderValue::from_static("codex-cli/not-a-version"),
+    );
+    assert!(
+        identify_codex_client(&headers)
+            .expect("recognized invalid CLI")
+            .version()
+            .is_none()
+    );
+}
@@ -1,9 +1,10 @@
 use axum::{body::to_bytes, http::StatusCode};
-use gateway_core::engine::{EngineError, UpstreamSendState};
+use gateway_core::engine::EngineError;
 use gateway_core::error::{
    ClientVisibleUpstreamError, GatewayError, GatewayErrorKind, ProviderError, ProviderErrorKind,
    StoreError, StoreErrorKind,
 };
+use gateway_core::upstream::UpstreamSendState;

 use gateway_api::openai::error::{
    gateway_error_contract, gateway_error_from_engine, gateway_error_response,
@@ -397,3 +398,38 @@ async fn gateway_error_response_should_expose_only_structured_client_visible_ups
        })
    );
 }
+
+#[tokio::test]
+async fn continuation_recovery_should_preserve_the_official_retry_signal() {
+    let error = GatewayError::from_provider(
+        &ProviderError::new(
+            ProviderErrorKind::ContinuationRecoveryRequired,
+            UpstreamSendState::NotSent,
+        )
+        .with_client_visible_upstream_error(ClientVisibleUpstreamError::new(
+            "Previous response was not found. Retrying the full request.",
+            Some("previous_response_not_found".to_owned()),
+            Some("invalid_request_error".to_owned()),
+        )),
+    );
+
+    let response = gateway_error_response(&error);
+    let status = response.status();
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read continuation recovery response");
+    let body: serde_json::Value =
+        serde_json::from_slice(&body).expect("continuation recovery JSON");
+
+    assert_eq!(status, StatusCode::BAD_REQUEST);
+    assert_eq!(
+        body,
+        serde_json::json!({
+            "error": {
+                "message": "Previous response was not found. Retrying the full request.",
+                "type": "invalid_request_error",
+                "code": "previous_response_not_found"
+            }
+        })
+    );
+}
@@ -10,7 +10,6 @@ use axum::{
 };
 use bytes::Bytes;
 use futures::future::BoxFuture;
-use gateway_core::engine::UpstreamSendState;
 use gateway_core::engine::execution::{
    AuthenticatedClient, ClientAuthenticationError, ClientTransport, ExecutionService,
    ExecutionSession, StartExecution, StartProviderExecution, StartedExecution,
@@ -22,6 +21,7 @@ use gateway_core::error::{
 use gateway_core::event::{ProtocolWireEvent, ProviderEvent, ProviderResponseHeader};
 use gateway_core::operation::{ImageRequestKind, Operation};
 use gateway_core::routing::PublicModelId;
+use gateway_core::upstream::UpstreamSendState;
 use serde_json::{Value, json};
 use tower::ServiceExt;

@@ -260,6 +260,8 @@ async fn image_routes_should_not_decode_bodies_and_should_preserve_both_directio
                    .header(AUTHORIZATION, "Bearer sk_images_test")
                    .header("content-type", "application/json")
                    .header("x-codex-image-turn-id", "turn_image_route")
+                    .header("session-id", "root-image-session")
+                    .header("thread-id", "child-image-thread")
                    .body(Body::from(body.to_vec()))
                    .expect("image request"),
            )
@@ -286,7 +288,7 @@ async fn image_routes_should_not_decode_bodies_and_should_preserve_both_directio
        assert_eq!(captured.body.as_ref(), *body);
        assert_eq!(
            captured.context,
-            json!({"image_turn_id": "turn_image_route"})
+            json!({"image_turn_id": "turn_image_route", "session_id": "root-image-session", "thread_id": "child-image-thread"})
        );
    }
    assert_eq!(
@@ -2,8 +2,10 @@ mod auth;
 mod error;
 mod images;
 mod models;
+mod provider_endpoint;
 mod responses;
 mod router;
+mod search;

 use std::collections::{BTreeMap, BTreeSet};
 use std::num::NonZeroU32;
@@ -12,6 +14,7 @@ use std::time::{Duration, SystemTime};

 use async_trait::async_trait;
 use futures::future::BoxFuture;
+use gateway_core::account::{AccountSelectionPolicy, ProviderAccountId, RotationStrategy};
 use gateway_core::engine::admission::{
    ClientAdmissionDecision, ClientAdmissionError, ClientAdmissionPort, ClientAdmissionRecovery,
    ClientAdmissionRequest, ClientAdmissionRestoreResult,
@@ -19,9 +22,6 @@ use gateway_core::engine::admission::{
 use gateway_core::engine::continuation::{
    NativeContinuationPin, NativeContinuationPort, NativeContinuationStoreError, PreviousResponseId,
 };
-use gateway_core::engine::credential::{
-    AccountSelectionPolicy, ProviderAccountId, RotationStrategy,
-};
 use gateway_core::engine::execution::{
    AuthenticatedClient, ClientApiKeyUsageSink, DefaultExecutionService, ExecutionService,
    ProviderCircuitDecision, ProviderCircuitError, ProviderCircuitPort,
@@ -29,17 +29,21 @@ use gateway_core::engine::execution::{
 use gateway_core::engine::provider::ProviderRegistry;
 use gateway_core::engine::{
    AttemptRecord, ExecutionStore, IntermediateFailure, ModelRequestFinalization, ModelRequestId,
-    NewModelRequest, RecoveryReport, UpstreamSendState,
+    NewModelRequest, RecoveryReport,
 };
 use gateway_core::error::StoreError;
 use gateway_core::health::{WorkerHealthSnapshot, WorkerHealthSource};
 use gateway_core::lifecycle::{ConnectionDraining, ConnectionGuard, ConnectionLifecycle};
-use gateway_core::policy::{ClientApiKeyId, ClientPolicy, PlaintextClientApiKey, RateLimits};
-use gateway_core::routing::snapshot::RuntimeSnapshotHandle;
+use gateway_core::policy::{
+    ClientApiKeyId, ClientPolicy, CodexClientMinVersions, CodexClientVersion,
+    PlaintextClientApiKey, RateLimits,
+};
 use gateway_core::routing::{
    ClientRoutingScope, ConfigRevision, FrozenAccountScope, ModelCapabilities, ProviderKind,
    ProviderModel, RuntimeAccount, RuntimeAccountDirectory, RuntimeSnapshot, UpstreamModelId,
 };
+use gateway_core::runtime::RuntimeSnapshotHandle;
+use gateway_core::upstream::UpstreamSendState;

 pub(super) async fn api_router(execution: Arc<dyn ExecutionService>) -> axum::Router {
    api_router_with_origins(execution, Vec::new()).await
@@ -109,6 +113,30 @@ pub(super) fn authenticated_client_for_provider(
        .expect("authenticated client")
 }

+pub(super) fn authenticated_client_with_min_versions(
+    plaintext: &str,
+    desktop: Option<&str>,
+    cli: Option<&str>,
+) -> AuthenticatedClient {
+    let snapshot =
+        snapshot(plaintext, "openai").with_min_codex_client_versions(CodexClientMinVersions::new(
+            desktop.map(|version| CodexClientVersion::parse(version).expect("Desktop min version")),
+            cli.map(|version| CodexClientVersion::parse(version).expect("CLI min version")),
+        ));
+    let source = DefaultExecutionService::new(
+        RuntimeSnapshotHandle::new(snapshot),
+        Arc::new(UnusedExecutionStore),
+        ProviderRegistry::default(),
+        Arc::new(UnusedAdmissions),
+        Arc::new(UnusedCircuits),
+        Arc::new(UnusedContinuation),
+        Arc::new(IgnoredClientApiKeyUsage),
+    );
+    source
+        .authenticate(plaintext)
+        .expect("authenticated client")
+}
+
 struct IgnoredClientApiKeyUsage;

 impl ClientApiKeyUsageSink for IgnoredClientApiKeyUsage {
@@ -160,7 +188,7 @@ fn snapshot(plaintext: &str, provider_name: &str) -> RuntimeSnapshot {

 #[derive(Default)]
 struct TestLifecycle {
-    cancellation: gateway_core::engine::CancellationToken,
+    cancellation: gateway_core::lifecycle::CancellationToken,
 }

 struct TestConnectionGuard;
@@ -172,7 +200,7 @@ impl ConnectionLifecycle for TestLifecycle {
        Ok(Box::new(TestConnectionGuard))
    }

-    fn cancellation(&self) -> gateway_core::engine::CancellationToken {
+    fn cancellation(&self) -> gateway_core::lifecycle::CancellationToken {
        self.cancellation.clone()
    }

@@ -15,7 +15,7 @@ use gateway_core::routing::{
 };
 use tower::ServiceExt;

-use super::{api_router, authenticated_client};
+use super::{api_router, authenticated_client, authenticated_client_with_min_versions};

 pub(super) struct ModelsExecution {
    client: AuthenticatedClient,
@@ -36,6 +36,24 @@ impl ModelsExecution {
            profiles: true,
        })
    }
+
+    fn with_cli_min() -> Arc<Self> {
+        Arc::new(Self {
+            client: authenticated_client_with_min_versions("sk_models_test", None, Some("0.40.0")),
+            profiles: false,
+        })
+    }
+
+    fn with_desktop_min() -> Arc<Self> {
+        Arc::new(Self {
+            client: authenticated_client_with_min_versions(
+                "sk_models_test",
+                Some("26.825.51511"),
+                None,
+            ),
+            profiles: false,
+        })
+    }
 }

 impl ExecutionService for ModelsExecution {
@@ -144,6 +162,111 @@ async fn models_should_encode_the_service_visible_catalog() {
    );
 }

+#[tokio::test]
+async fn models_should_reject_recognized_cli_below_configured_min() {
+    let request = Request::get("/v1/models")
+        .header(AUTHORIZATION, "Bearer sk_models_test")
+        .header("user-agent", "codex_cli_rs/0.39.0 (Linux; x86_64)")
+        .body(Body::empty())
+        .expect("build models request");
+    let response = api_router(ModelsExecution::with_cli_min())
+        .await
+        .oneshot(request)
+        .await
+        .expect("list models response");
+
+    assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read version rejection body");
+    let value: serde_json::Value = serde_json::from_slice(&body).expect("version rejection JSON");
+    assert_eq!(value["error"]["code"], "client_version_too_old");
+    assert_eq!(value["error"]["client"], "codex_cli");
+    assert_eq!(value["error"]["current_version"], "0.39.0");
+    assert_eq!(value["error"]["min_version"], "0.40.0");
+}
+
+#[tokio::test]
+async fn models_should_reject_recognized_cli_with_invalid_version() {
+    let request = Request::get("/v1/models")
+        .header(AUTHORIZATION, "Bearer sk_models_test")
+        .header("user-agent", "codex-cli/not-a-version")
+        .body(Body::empty())
+        .expect("build models request");
+    let response = api_router(ModelsExecution::with_cli_min())
+        .await
+        .oneshot(request)
+        .await
+        .expect("list models response");
+
+    assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read version rejection body");
+    let value: serde_json::Value = serde_json::from_slice(&body).expect("version rejection JSON");
+    assert_eq!(value["error"]["code"], "client_version_unavailable");
+    assert!(value["error"]["current_version"].is_null());
+    assert_eq!(value["error"]["min_version"], "0.40.0");
+}
+
+#[tokio::test]
+async fn models_should_reject_desktop_below_its_configured_min() {
+    let request = Request::get("/v1/models")
+        .header(AUTHORIZATION, "Bearer sk_models_test")
+        .header("originator", "Codex Desktop")
+        .header("version", "26.825.50000")
+        .header("user-agent", "codex_cli_rs/99.0.0 (Codex Desktop)")
+        .body(Body::empty())
+        .expect("build models request");
+    let response = api_router(ModelsExecution::with_desktop_min())
+        .await
+        .oneshot(request)
+        .await
+        .expect("list models response");
+
+    assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read version rejection body");
+    let value: serde_json::Value = serde_json::from_slice(&body).expect("version rejection JSON");
+    assert_eq!(value["error"]["code"], "client_version_too_old");
+    assert_eq!(value["error"]["client"], "codex_desktop");
+    assert_eq!(value["error"]["current_version"], "26.825.50000");
+    assert_eq!(value["error"]["min_version"], "26.825.51511");
+}
+
+#[tokio::test]
+async fn models_should_allow_cli_at_its_configured_min() {
+    let request = Request::get("/v1/models")
+        .header(AUTHORIZATION, "Bearer sk_models_test")
+        .header("user-agent", "codex_cli_rs/0.40.0 (Linux; x86_64)")
+        .body(Body::empty())
+        .expect("build models request");
+    let response = api_router(ModelsExecution::with_cli_min())
+        .await
+        .oneshot(request)
+        .await
+        .expect("list models response");
+
+    assert_eq!(response.status(), StatusCode::OK);
+}
+
+#[tokio::test]
+async fn models_should_leave_unknown_clients_unrestricted() {
+    let request = Request::get("/v1/models")
+        .header(AUTHORIZATION, "Bearer sk_models_test")
+        .header("user-agent", "curl/8.14.1")
+        .body(Body::empty())
+        .expect("build models request");
+    let response = api_router(ModelsExecution::with_cli_min())
+        .await
+        .oneshot(request)
+        .await
+        .expect("list models response");
+
+    assert_eq!(response.status(), StatusCode::OK);
+}
+
 #[tokio::test]
 async fn models_should_encode_provider_profiles_for_current_codex_clients() {
    let response = api_router(ModelsExecution::with_profiles())
@@ -261,51 +384,12 @@ async fn model_detail_should_hide_unknown_models() {
 }

 #[tokio::test]
-async fn model_catalog_should_keep_the_codex_catalog_contract() {
-    let response = api_router(ModelsExecution::new())
-        .await
-        .oneshot(authorized_request("/v1/models/catalog"))
-        .await
-        .expect("catalog response");
-
-    assert_eq!(response.status(), StatusCode::OK);
-    let body = to_bytes(response.into_body(), usize::MAX)
-        .await
-        .expect("read catalog body");
-    let value: serde_json::Value = serde_json::from_slice(&body).expect("catalog JSON");
-    assert_eq!(value[0]["id"], "model-a");
-    assert_eq!(value[0]["displayName"], "model-a");
-    assert_eq!(value[0]["source"], "gateway");
-}
-
-#[tokio::test]
-async fn model_info_should_return_a_single_visible_catalog_entry() {
-    let response = api_router(ModelsExecution::new())
-        .await
-        .oneshot(authorized_request("/v1/models/model-a/info"))
-        .await
-        .expect("model info response");
-
-    assert_eq!(response.status(), StatusCode::OK);
-}
-
-#[tokio::test]
-async fn model_info_should_hide_unknown_models() {
-    let response = api_router(ModelsExecution::new())
-        .await
-        .oneshot(authorized_request("/v1/models/model-private/info"))
-        .await
-        .expect("missing model info response");
-
-    assert_eq!(response.status(), StatusCode::NOT_FOUND);
-}
-
-#[tokio::test]
-async fn models_should_require_a_valid_bearer_client_key() {
-    let response = api_router(ModelsExecution::new())
+async fn models_should_authenticate_before_applying_the_version_gate() {
+    let response = api_router(ModelsExecution::with_cli_min())
        .await
        .oneshot(
            Request::get("/v1/models")
+                .header("user-agent", "codex_cli_rs/0.1.0 (Linux; x86_64)")
                .body(Body::empty())
                .expect("build unauthenticated request"),
        )
@@ -0,0 +1,107 @@
+use std::sync::{Arc, Mutex, atomic::AtomicBool, atomic::Ordering};
+
+use bytes::Bytes;
+use futures::future::BoxFuture;
+use gateway_core::engine::execution::ExecutionSession;
+use gateway_core::engine::{CoordinatedEvent, EngineError};
+use gateway_core::error::ProviderError;
+use gateway_core::event::{ProtocolWireEvent, ProviderEvent, ProviderResponseHeader};
+
+pub(super) struct BufferedJsonSession {
+    body: Option<Bytes>,
+    response_headers: Vec<ProviderResponseHeader>,
+    response_status: Option<u16>,
+    committed_statuses: Arc<Mutex<Vec<u16>>>,
+    finalized: AtomicBool,
+    failure: Option<ProviderError>,
+}
+
+impl BufferedJsonSession {
+    pub(super) fn success(
+        body: Bytes,
+        response_status: u16,
+        response_headers: Vec<ProviderResponseHeader>,
+        committed_statuses: Arc<Mutex<Vec<u16>>>,
+    ) -> Self {
+        Self {
+            body: Some(body),
+            response_headers,
+            response_status: Some(response_status),
+            committed_statuses,
+            finalized: AtomicBool::new(false),
+            failure: None,
+        }
+    }
+
+    pub(super) fn failure(error: ProviderError) -> Self {
+        Self {
+            body: None,
+            response_headers: Vec::new(),
+            response_status: None,
+            committed_statuses: Arc::new(Mutex::new(Vec::new())),
+            finalized: AtomicBool::new(false),
+            failure: Some(error),
+        }
+    }
+}
+
+impl ExecutionSession for BufferedJsonSession {
+    fn next_event(&mut self) -> BoxFuture<'_, Result<Option<CoordinatedEvent>, EngineError>> {
+        Box::pin(async { unreachable!("buffered JSON delivery does not stream") })
+    }
+
+    fn collect_uncommitted(&mut self) -> BoxFuture<'_, Result<Vec<ProviderEvent>, EngineError>> {
+        Box::pin(async move {
+            if let Some(error) = self.failure.take() {
+                return Err(EngineError::Provider(error));
+            }
+            Ok(vec![ProviderEvent::wire(
+                ProtocolWireEvent::raw_json(
+                    "openai",
+                    self.body.take().expect("single buffered JSON response"),
+                )
+                .expect("OpenAI protocol"),
+            )])
+        })
+    }
+
+    fn response_headers(&self) -> &[ProviderResponseHeader] {
+        &self.response_headers
+    }
+
+    fn response_status_code(&self) -> Option<u16> {
+        self.response_status
+    }
+
+    fn commit_downstream(
+        &mut self,
+        client_status_code: Option<u16>,
+    ) -> BoxFuture<'_, Result<(), EngineError>> {
+        Box::pin(async move {
+            self.committed_statuses
+                .lock()
+                .expect("committed status lock")
+                .push(client_status_code.expect("buffered JSON response status"));
+            self.finalized.store(true, Ordering::Release);
+            Ok(())
+        })
+    }
+
+    fn record_client_status(&mut self, _: u16) -> BoxFuture<'_, Result<(), EngineError>> {
+        Box::pin(async { Ok(()) })
+    }
+
+    fn is_finalized(&self) -> bool {
+        self.finalized.load(Ordering::Acquire)
+    }
+
+    fn cancel(&self) {
+        self.finalized.store(true, Ordering::Release);
+    }
+
+    fn detach_finalize(self: Box<Self>) -> BoxFuture<'static, ()> {
+        Box::pin(async move {
+            self.finalized.store(true, Ordering::Release);
+        })
+    }
+}
@@ -4,6 +4,7 @@ use std::sync::{
    Arc, Mutex,
    atomic::{AtomicBool, Ordering},
 };
+use std::time::Duration;

 use axum::{
    body::{Body, to_bytes},
@@ -14,12 +15,13 @@ use axum::{
    },
 };
 use bytes::Bytes;
+use futures::StreamExt;
 use futures::future::{BoxFuture, pending};
 use gateway_core::engine::execution::{
    AuthenticatedClient, ClientAuthenticationError, ExecutionService, ExecutionSession,
    StartExecution, StartProviderExecution, StartedExecution,
 };
-use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError, UpstreamSendState};
+use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError};
 use gateway_core::error::{
    ClientVisibleUpstreamError, ClientVisibleUpstreamResponse, GatewayError, GatewayErrorKind,
    ProviderError, ProviderErrorKind,
@@ -30,12 +32,13 @@ use gateway_core::event::{
 };
 use gateway_core::operation::{Operation, OperationKind};
 use gateway_core::routing::PublicModelId;
+use gateway_core::upstream::UpstreamSendState;
 use serde_json::{Value, json};

 use gateway_api::openai::responses::{collect_execution_response, stream_execution_response};
 use tower::ServiceExt;

-use crate::openai::{api_router, authenticated_client, authenticated_client_for_provider};
+use crate::openai::{api_router, authenticated_client_for_provider};

 #[derive(Default)]
 struct Trace {
@@ -78,6 +81,7 @@ impl Trace {

 enum NextStep {
    Event(CoordinatedEvent),
+    DelayedEvent(Duration, CoordinatedEvent),
    Error(EngineError),
    FinalizeCancelled,
    FinalizeSuccess,
@@ -279,6 +283,12 @@ impl ExecutionSession for FakeSession {
                    self.trace.push("next_event");
                    Ok(Some(event))
                }
+                NextStep::DelayedEvent(delay, event) => {
+                    self.trace.push("wait_event");
+                    tokio::time::sleep(delay).await;
+                    self.trace.push("next_event");
+                    Ok(Some(event))
+                }
                NextStep::Error(error) => {
                    self.trace.push("next_error");
                    self.finalized = true;
@@ -688,92 +698,6 @@ async fn xai_private_headers_should_not_enter_openai_request_facts() {
    assert!(captured.prompt_cache_key.is_none());
 }

-#[tokio::test]
-async fn review_route_should_inject_review_subagent_and_record_its_endpoint() {
-    let observed = Arc::new(Mutex::new(None));
-    let execution = Arc::new(ContextCaptureExecution {
-        observed: Arc::clone(&observed),
-        client: authenticated_client("sk_context_test"),
-    });
-    let request = Request::post("/v1/responses/review")
-        .header(AUTHORIZATION, "Bearer sk_context_test")
-        .header("x-openai-subagent", "compact")
-        .body(Body::from(
-            json!({
-                "model": "smart-code",
-                "input": "review this",
-                "client_metadata": {"existing": "preserved"}
-            })
-            .to_string(),
-        ))
-        .expect("review request");
-
-    let response = api_router(execution)
-        .await
-        .oneshot(request)
-        .await
-        .expect("review response");
-    let captured = observed
-        .lock()
-        .expect("review capture lock")
-        .clone()
-        .expect("captured review request");
-
-    assert_eq!(response.status(), StatusCode::INTERNAL_SERVER_ERROR);
-    assert_eq!(captured.endpoint, "/v1/responses/review");
-    assert_eq!(
-        captured
-            .client_metadata
-            .as_ref()
-            .and_then(|metadata| metadata.get("x-openai-subagent")),
-        Some(&json!("review"))
-    );
-    assert_eq!(
-        captured
-            .client_metadata
-            .as_ref()
-            .and_then(|metadata| metadata.get("existing")),
-        Some(&json!("preserved"))
-    );
-}
-
-#[tokio::test]
-async fn review_route_should_not_replace_non_object_client_metadata() {
-    let observed = Arc::new(Mutex::new(None));
-    let execution = Arc::new(ContextCaptureExecution {
-        observed: Arc::clone(&observed),
-        client: authenticated_client("sk_context_test"),
-    });
-    let request = Request::post("/v1/responses/review")
-        .header(AUTHORIZATION, "Bearer sk_context_test")
-        .body(Body::from(
-            json!({
-                "model": "smart-code",
-                "input": "review this",
-                "client_metadata": ["opaque", "client", "value"]
-            })
-            .to_string(),
-        ))
-        .expect("review request");
-
-    let response = api_router(execution)
-        .await
-        .oneshot(request)
-        .await
-        .expect("review response");
-    let captured = observed
-        .lock()
-        .expect("review capture lock")
-        .clone()
-        .expect("captured review request");
-
-    assert_eq!(response.status(), StatusCode::INTERNAL_SERVER_ERROR);
-    assert_eq!(
-        captured.client_metadata,
-        Some(json!(["opaque", "client", "value"]))
-    );
-}
-
 #[tokio::test]
 async fn streaming_encodes_first_frame_before_commit_and_http_delivery() {
    let trace = Arc::new(Trace::default());
@@ -794,6 +718,154 @@ async fn streaming_encodes_first_frame_before_commit_and_http_delivery() {
    std::mem::forget(response);
 }

+#[tokio::test(start_paused = true)]
+async fn streaming_should_keep_alive_during_silent_compaction_without_restarting_execution() {
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::Event(delivery(started(), CommitRequirement::CommitBeforeDelivery)),
+            NextStep::DelayedEvent(
+                Duration::from_secs(240),
+                delivery(completed(), CommitRequirement::AlreadyCommitted),
+            ),
+            NextStep::FinalizeSuccess,
+        ],
+    );
+    let response = stream_execution_response(Box::new(session), None).await;
+    let mut body = response.into_body().into_data_stream();
+    let first = body.next().await.expect("first frame").expect("body bytes");
+    assert!(String::from_utf8_lossy(&first).contains("response.created"));
+    let start = tokio::time::Instant::now();
+
+    for heartbeat in 1..16 {
+        let chunk = tokio::time::timeout(Duration::from_secs(20), body.next())
+            .await
+            .expect("silent upstream must not leave the downstream idle")
+            .expect("heartbeat frame")
+            .expect("heartbeat bytes");
+        assert_eq!(chunk, Bytes::from_static(b": keep-alive\n\n"));
+        assert_eq!(start.elapsed(), Duration::from_secs(15 * heartbeat));
+    }
+
+    let terminal = body
+        .next()
+        .await
+        .expect("terminal frame")
+        .expect("body bytes");
+    assert!(String::from_utf8_lossy(&terminal).contains("response.completed"));
+    assert_eq!(start.elapsed(), Duration::from_secs(240));
+    assert_eq!(
+        body.next().await.expect("done frame").expect("body bytes"),
+        Bytes::from_static(b"data: [DONE]\n\n")
+    );
+    assert!(body.next().await.is_none());
+    assert_eq!(
+        trace.snapshot(),
+        vec![
+            "next_event",
+            "commit",
+            "wait_event",
+            "next_event",
+            "next_end"
+        ]
+    );
+    assert!(!trace.is_cancelled());
+}
+
+#[tokio::test(start_paused = true)]
+async fn dropping_stream_during_keepalive_should_cancel_and_finalize_execution() {
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::Event(delivery(started(), CommitRequirement::CommitBeforeDelivery)),
+            NextStep::DelayedEvent(
+                Duration::from_secs(240),
+                delivery(completed(), CommitRequirement::AlreadyCommitted),
+            ),
+            NextStep::FinalizeCancelled,
+        ],
+    );
+    let response = stream_execution_response(Box::new(session), None).await;
+    let mut body = response.into_body().into_data_stream();
+    let _ = body.next().await.expect("first frame").expect("body bytes");
+    let heartbeat = tokio::time::timeout(Duration::from_secs(20), body.next())
+        .await
+        .expect("heartbeat before client disconnect")
+        .expect("heartbeat frame")
+        .expect("heartbeat bytes");
+    assert_eq!(heartbeat, Bytes::from_static(b": keep-alive\n\n"));
+
+    drop(body);
+    tokio::task::yield_now().await;
+
+    assert!(trace.is_cancelled());
+    assert_eq!(
+        trace.snapshot(),
+        vec!["next_event", "commit", "wait_event", "cancel_finalize"]
+    );
+}
+
+#[tokio::test(start_paused = true)]
+async fn streaming_keepalive_should_wait_for_first_event_before_committing_http_status() {
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::DelayedEvent(
+                Duration::from_secs(45),
+                delivery(started(), CommitRequirement::CommitBeforeDelivery),
+            ),
+            NextStep::FinalizeCancelled,
+        ],
+    );
+    let response = tokio::spawn(stream_execution_response(Box::new(session), None));
+    tokio::task::yield_now().await;
+    tokio::time::advance(Duration::from_secs(30)).await;
+
+    assert!(!response.is_finished());
+    assert!(trace.client_statuses().is_empty());
+    let response = response.await.expect("response task");
+    assert_eq!(response.status(), StatusCode::OK);
+    assert_eq!(trace.snapshot(), vec!["wait_event", "next_event", "commit"]);
+}
+
+#[tokio::test]
+async fn streaming_response_should_disable_proxy_buffering_and_cache_transformation() {
+    let session = FakeSession::streaming(
+        Arc::new(Trace::default()),
+        vec![
+            NextStep::Event(delivery(started(), CommitRequirement::CommitBeforeDelivery)),
+            NextStep::FinalizeCancelled,
+        ],
+    )
+    .with_response_headers(vec![
+        ProviderResponseHeader::new("x-accel-buffering", Bytes::from_static(b"yes")),
+        ProviderResponseHeader::new("cache-control", Bytes::from_static(b"public, max-age=60")),
+    ]);
+
+    let response = stream_execution_response(Box::new(session), None).await;
+
+    assert_eq!(response.headers()["x-accel-buffering"], "no");
+    assert_eq!(
+        response.headers()["cache-control"],
+        "no-cache, no-transform"
+    );
+    assert_eq!(
+        response
+            .headers()
+            .get_all("x-accel-buffering")
+            .iter()
+            .count(),
+        1
+    );
+    assert_eq!(
+        response.headers().get_all("cache-control").iter().count(),
+        1
+    );
+}
+
 #[tokio::test]
 async fn streaming_response_should_append_ordinary_headers_and_skip_unrepresentable_or_sensitive_ones()
 {
@@ -978,6 +1050,41 @@ async fn streaming_rate_limit_before_first_frame_should_persist_the_returned_429
    assert_eq!(trace.client_statuses(), vec![429]);
 }

+#[tokio::test]
+async fn streaming_failure_before_first_frame_should_return_safe_observed_headers() {
+    let trace = Arc::new(Trace::default());
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![NextStep::Error(EngineError::Provider(ProviderError::new(
+            ProviderErrorKind::Unavailable,
+            UpstreamSendState::Ambiguous,
+        )))],
+    )
+    .with_response_headers(vec![
+        ProviderResponseHeader::new(
+            "x-codex-turn-state",
+            Bytes::from_static(b"turn-state-before-close"),
+        ),
+        ProviderResponseHeader::new(
+            "authorization",
+            Bytes::from_static(b"must-not-cross-boundary"),
+        ),
+    ]);
+
+    let response = stream_execution_response(Box::new(session), None).await;
+
+    assert_eq!(response.status(), StatusCode::BAD_GATEWAY);
+    assert_eq!(
+        response
+            .headers()
+            .get("x-codex-turn-state")
+            .and_then(|value| value.to_str().ok()),
+        Some("turn-state-before-close")
+    );
+    assert!(response.headers().get("authorization").is_none());
+    assert_eq!(trace.client_statuses(), vec![502]);
+}
+
 #[tokio::test]
 async fn streaming_upstream_http_failure_before_first_frame_should_preserve_raw_response() {
    let trace = Arc::new(Trace::default());
@@ -1064,11 +1171,29 @@ async fn buffered_upstream_http_failure_should_preserve_raw_response() {
            raw_body.clone(),
        ));
    let session = FakeSession::buffered(Arc::clone(&trace), vec![started(), completed()])
-        .with_collect_error(EngineError::Provider(error));
+        .with_collect_error(EngineError::Provider(error))
+        .with_response_headers(vec![
+            ProviderResponseHeader::new(
+                "x-codex-turn-state",
+                Bytes::from_static(b"turn-state-before-close"),
+            ),
+            ProviderResponseHeader::new(
+                "authorization",
+                Bytes::from_static(b"must-not-cross-boundary"),
+            ),
+        ]);

    let response = collect_execution_response(Box::new(session)).await;

    assert_eq!(response.status(), StatusCode::SERVICE_UNAVAILABLE);
+    assert_eq!(
+        response
+            .headers()
+            .get("x-codex-turn-state")
+            .and_then(|value| value.to_str().ok()),
+        Some("turn-state-before-close")
+    );
+    assert!(response.headers().get("authorization").is_none());
    assert_eq!(
        to_bytes(response.into_body(), usize::MAX)
            .await
@@ -196,7 +196,13 @@ fn decoder_should_preserve_connection_metadata_outside_the_openai_wire_body() {
        HeaderValue::from_static("{\"kind\":\"review\"}"),
    );
    headers.insert("conversation-id", HeaderValue::from_static("conversation"));
-    let body = json!({"model": "smart-code", "input": "hello"});
+    let body = json!({
+        "model": "smart-code",
+        "input": "hello",
+        "client_metadata": {
+            "x-codex-turn-metadata": "{\"kind\":\"turn\"}"
+        }
+    });

    let decoded = decode_request_with_headers(body.to_string().as_bytes(), &headers)
        .expect("request should decode");
@@ -275,6 +281,10 @@ fn decoder_should_preserve_ordinary_request_headers_as_opaque_multivalues() {
    headers.insert("content-length", HeaderValue::from_static("999"));
    headers.insert("authorization", HeaderValue::from_static("Bearer client"));
    headers.insert("x-api-key", HeaderValue::from_static("client-key"));
+    headers.insert(
+        "x-openai-actor-authorization",
+        HeaderValue::from_static("proxy-managed"),
+    );
    headers.insert("cookie", HeaderValue::from_static("client=cookie"));
    headers.insert(
        "chatgpt-account-id",
@@ -342,6 +352,7 @@ fn decoder_should_preserve_ordinary_request_headers_as_opaque_multivalues() {
        "content-length",
        "authorization",
        "x-api-key",
+        "x-openai-actor-authorization",
        "cookie",
        "chatgpt-account-id",
        "chatgpt-project-id",
@@ -2,8 +2,8 @@ use std::{
    fmt,
    pin::Pin,
    sync::{
-        Arc,
-        atomic::{AtomicBool, Ordering},
+        Arc, Mutex,
+        atomic::{AtomicBool, AtomicUsize, Ordering},
    },
    task::{Context, Poll},
    time::{Duration, SystemTime},
@@ -16,7 +16,7 @@ use axum::{
 use futures::{Sink, SinkExt, Stream, StreamExt, future::BoxFuture};
 use gateway_core::{
    engine::{
-        CancellationToken, CommitRequirement, CoordinatedEvent, EngineError,
+        CommitRequirement, CoordinatedEvent, EngineError,
        execution::{
            AuthenticatedClient, ClientAuthenticationError, ExecutionService, ExecutionSession,
            StartExecution, StartProviderExecution, StartedExecution,
@@ -24,6 +24,8 @@ use gateway_core::{
    },
    error::GatewayError,
    event::{GatewayEvent, ProtocolWireEvent, ProviderEvent, ProviderResponseHeader, ResponseMeta},
+    lifecycle::CancellationToken,
+    operation::Operation,
    routing::PublicModelId,
 };
 use serde_json::{Value, json};
@@ -31,7 +33,7 @@ use tokio::sync::mpsc::{
    UnboundedReceiver, UnboundedSender, error::TryRecvError, unbounded_channel,
 };
 use tokio_tungstenite::{
-    connect_async,
+    MaybeTlsStream, WebSocketStream, connect_async,
    tungstenite::{
        Message as ClientMessage, client::IntoClientRequest, protocol::frame::coding::CloseCode,
    },
@@ -43,27 +45,33 @@ use crate::openai::{api_router, authenticated_client};
 #[derive(Default)]
 struct CrossingLimitTrace {
    release_terminal: tokio::sync::Notify,
-    started_emitted: AtomicBool,
-    terminal_emitted: AtomicBool,
+    starts: AtomicUsize,
+    inputs: Mutex<Vec<Value>>,
+    cancelled: AtomicBool,
+    cancellation_observed: tokio::sync::Notify,
    finalized: AtomicBool,
 }

 struct CrossingLimitSession {
    trace: Arc<CrossingLimitTrace>,
+    started_emitted: bool,
+    terminal_emitted: bool,
+    finalized: bool,
 }

 impl ExecutionSession for CrossingLimitSession {
    fn next_event(&mut self) -> BoxFuture<'_, Result<Option<CoordinatedEvent>, EngineError>> {
        Box::pin(async move {
-            if !self.trace.started_emitted.swap(true, Ordering::AcqRel) {
+            if !self.started_emitted {
+                self.started_emitted = true;
                return Ok(Some(crossing_limit_started_batch()));
            }
-            if !self.trace.terminal_emitted.load(Ordering::Acquire) {
+            if !self.terminal_emitted {
                self.trace.release_terminal.notified().await;
-                if !self.trace.terminal_emitted.swap(true, Ordering::AcqRel) {
-                    return Ok(Some(crossing_limit_terminal_batch()));
-                }
+                self.terminal_emitted = true;
+                return Ok(Some(crossing_limit_terminal_batch()));
            }
+            self.finalized = true;
            self.trace.finalized.store(true, Ordering::Release);
            Ok(None)
        })
@@ -86,10 +94,13 @@ impl ExecutionSession for CrossingLimitSession {
    }

    fn is_finalized(&self) -> bool {
-        self.trace.finalized.load(Ordering::Acquire)
+        self.finalized
    }

-    fn cancel(&self) {}
+    fn cancel(&self) {
+        self.trace.cancelled.store(true, Ordering::Release);
+        self.trace.cancellation_observed.notify_one();
+    }

    fn detach_finalize(self: Box<Self>) -> BoxFuture<'static, ()> {
        Box::pin(async move {
@@ -126,6 +137,14 @@ impl ExecutionService for CrossingLimitExecution {
        request: StartExecution,
    ) -> BoxFuture<'_, Result<StartedExecution, GatewayError>> {
        Box::pin(async move {
+            self.trace.starts.fetch_add(1, Ordering::AcqRel);
+            if let Operation::Generate(generate) = &request.operation {
+                self.trace
+                    .inputs
+                    .lock()
+                    .expect("input trace lock")
+                    .push(generate.protocol_payload().body()["input"].clone());
+            }
            Ok(StartedExecution {
                request_id: gateway_core::engine::ModelRequestId::new("req_ws_crossing_limit")
                    .expect("request id"),
@@ -133,6 +152,9 @@ impl ExecutionService for CrossingLimitExecution {
                stream: request.metadata.stream,
                session: Box::new(CrossingLimitSession {
                    trace: Arc::clone(&self.trace),
+                    started_emitted: false,
+                    terminal_emitted: false,
+                    finalized: false,
                }),
            })
        })
@@ -190,17 +212,8 @@ fn crossing_limit_terminal_batch() -> CoordinatedEvent {
        .expect("terminal WebSocket batch")
 }

-// 连接 runtime 没有正式公共 API；镜像测试直接编译该私有模块，以测试 socket pump，
-// 不把测试钩子暴露给 gateway-api 的消费者。
-#[expect(
-    dead_code,
-    reason = "the mirrored test only exercises pump-facing seams"
-)]
-#[path = "../../../../src/openai/responses/websocket/connection.rs"]
-mod connection_under_test;
-
-use connection_under_test::{
-    ConnectionConfig, ConnectionEvent, ConnectionWriteError, FramePhase,
+use gateway_api::openai::responses::websocket::connection::{
+    ConnectionConfig, ConnectionEvent, ConnectionWriteError, FramePhase, PumpExitReason,
    ResponsesWebSocketConnection, WriteContext, spawn_connection,
 };

@@ -263,12 +276,14 @@ struct PumpHarness {
    incoming: UnboundedSender<Result<Message, TestSocketError>>,
    written: UnboundedReceiver<Message>,
    dropped: Arc<AtomicBool>,
+    cancellation: CancellationToken,
 }

 fn test_connection(stall_writes: bool) -> PumpHarness {
    let (incoming_tx, incoming_rx) = unbounded_channel();
    let (written_tx, written_rx) = unbounded_channel();
    let dropped = Arc::new(AtomicBool::new(false));
+    let cancellation = CancellationToken::new();
    let socket = TestSocket {
        incoming: incoming_rx,
        written: written_tx,
@@ -278,7 +293,7 @@ fn test_connection(stall_writes: bool) -> PumpHarness {
    let connection = spawn_connection(
        socket,
        Arc::from("ws_test"),
-        CancellationToken::new(),
+        cancellation.clone(),
        ConnectionConfig::PRODUCTION,
    );
    PumpHarness {
@@ -286,6 +301,7 @@ fn test_connection(stall_writes: bool) -> PumpHarness {
        incoming: incoming_tx,
        written: written_rx,
        dropped,
+        cancellation,
    }
 }

@@ -324,6 +340,110 @@ async fn pump_consumes_pong_without_forwarding_a_business_event() {
    assert!(result.is_err(), "Pong unexpectedly reached the coordinator");
 }

+#[tokio::test(start_paused = true)]
+async fn waiting_for_exit_should_preserve_queued_business_frames() {
+    let PumpHarness {
+        mut connection,
+        incoming,
+        ..
+    } = test_connection(false);
+    for payload in ["first", "second"] {
+        incoming
+            .send(Ok(Message::Text(payload.into())))
+            .expect("queue text");
+    }
+
+    assert!(
+        tokio::time::timeout(Duration::from_secs(1), connection.wait_for_exit())
+            .await
+            .is_err()
+    );
+    for expected in ["first", "second"] {
+        assert!(
+            matches!(connection.next_event().await, Some(ConnectionEvent::Text(payload)) if payload == expected)
+        );
+    }
+}
+
+#[tokio::test]
+async fn client_close_should_take_priority_over_queued_business_frames() {
+    let PumpHarness {
+        mut connection,
+        incoming,
+        ..
+    } = test_connection(false);
+    incoming
+        .send(Ok(Message::Text("queued".into())))
+        .expect("queue text");
+    incoming
+        .send(Ok(Message::Close(None)))
+        .expect("close socket");
+
+    assert_eq!(
+        tokio::time::timeout(Duration::from_secs(1), connection.wait_for_exit())
+            .await
+            .expect("observe close"),
+        PumpExitReason::ClientClose
+    );
+    assert!(matches!(
+        connection.next_event().await,
+        Some(ConnectionEvent::Exited(PumpExitReason::ClientClose))
+    ));
+}
+
+#[tokio::test]
+async fn full_business_queue_should_not_block_lifecycle_shutdown() {
+    let PumpHarness {
+        mut connection,
+        incoming,
+        mut written,
+        cancellation,
+        ..
+    } = test_connection(false);
+    for _ in 0..32 {
+        incoming
+            .send(Ok(Message::Text("queued".into())))
+            .expect("queue text");
+    }
+    incoming
+        .send(Ok(Message::Ping(vec![1].into())))
+        .expect("send Ping after queue fills");
+    assert!(matches!(written.recv().await, Some(Message::Pong(_))));
+    cancellation.cancel();
+
+    assert_eq!(
+        tokio::time::timeout(Duration::from_secs(1), connection.wait_for_exit())
+            .await
+            .expect("observe shutdown"),
+        PumpExitReason::LifecycleShutdown
+    );
+}
+
+#[tokio::test]
+async fn inbound_overload_should_close_without_executing_queued_frames() {
+    let PumpHarness {
+        mut connection,
+        incoming,
+        ..
+    } = test_connection(false);
+    for _ in 0..33 {
+        incoming
+            .send(Ok(Message::Text("queued".into())))
+            .expect("queue text");
+    }
+
+    assert_eq!(
+        tokio::time::timeout(Duration::from_secs(1), connection.wait_for_exit())
+            .await
+            .expect("observe overload"),
+        PumpExitReason::InboundOverload
+    );
+    assert!(matches!(
+        connection.next_event().await,
+        Some(ConnectionEvent::Exited(PumpExitReason::InboundOverload))
+    ));
+}
+
 #[tokio::test(start_paused = true)]
 async fn pump_does_not_emit_an_active_ping() {
    let PumpHarness {
@@ -379,6 +499,7 @@ async fn stalled_write_times_out_at_three_hundred_seconds_and_aborts_the_pump()
        incoming: _incoming,
        written: _written,
        dropped,
+        ..
    } = test_connection(true);
    let request_id = Arc::<str>::from("req_test");

@@ -421,6 +542,7 @@ async fn dropping_the_connection_aborts_and_drops_the_socket_owner() {
        incoming: _incoming,
        written: _written,
        dropped,
+        ..
    } = test_connection(false);

    drop(connection);
@@ -436,6 +558,7 @@ async fn idle_connection_reaches_the_official_limit_without_starting_an_executio
        client: authenticated_client("sk_ws_atomic"),
        trace: Arc::clone(&trace),
        response_headers: Vec::new(),
+        fail_before_first_event: false,
    });
    let app = api_router(execution).await;
    let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
@@ -547,6 +670,27 @@ async fn active_response_crossing_the_limit_writes_terminal_before_the_limit_err
        }
    }

+    for _ in 0..32 {
+        socket
+            .send(ClientMessage::Text(
+                json!({"type": "response.create", "model": "model-a", "input": "queued after limit"})
+                    .to_string()
+                    .into(),
+            ))
+            .await
+            .expect("fill request queue before expiry");
+    }
+    socket
+        .send(ClientMessage::Ping(vec![1].into()))
+        .await
+        .expect("send Ping after queued request");
+    let pong = tokio::time::timeout(Duration::from_secs(1), socket.next())
+        .await
+        .expect("Pong timeout")
+        .expect("connection remains open")
+        .expect("valid frame");
+    assert!(matches!(pong, ClientMessage::Pong(_)));
+
    tokio::time::pause();
    tokio::time::advance(Duration::from_secs(60 * 60)).await;
    tokio::task::yield_now().await;
@@ -575,15 +719,21 @@ async fn active_response_crossing_the_limit_writes_terminal_before_the_limit_err

    assert_eq!(event_types, ["response.completed", "error"]);
    assert!(trace.finalized.load(Ordering::Acquire));
+    assert_eq!(trace.starts.load(Ordering::Acquire), 1);
    server.abort();
 }

-#[tokio::test]
-async fn second_text_frame_during_an_active_response_keeps_the_single_response_contract() {
+type TestClientSocket = WebSocketStream<MaybeTlsStream<tokio::net::TcpStream>>;
+
+async fn start_active_response() -> (
+    Arc<CrossingLimitTrace>,
+    TestClientSocket,
+    tokio::task::JoinHandle<()>,
+) {
    let trace = Arc::new(CrossingLimitTrace::default());
    let execution = Arc::new(CrossingLimitExecution {
        client: authenticated_client("sk_ws_crossing_limit"),
-        trace,
+        trace: Arc::clone(&trace),
    });
    let app = api_router(execution).await;
    let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
@@ -615,7 +765,7 @@ async fn second_text_frame_during_an_active_response_keeps_the_single_response_c
        .into(),
    );
    socket
-        .send(response_create.clone())
+        .send(response_create)
        .await
        .expect("send first response.create");
    loop {
@@ -633,19 +783,169 @@ async fn second_text_frame_during_an_active_response_keeps_the_single_response_c
        }
    }

+    (trace, socket, server)
+}
+
+#[tokio::test]
+async fn requests_received_during_an_active_response_should_execute_in_order() {
+    let (trace, mut socket, server) = start_active_response().await;
+    for input in ["second", "third"] {
+        socket
+            .send(ClientMessage::Text(
+                json!({"type": "response.create", "model": "model-a", "input": input})
+                    .to_string()
+                    .into(),
+            ))
+            .await
+            .expect("send queued response.create");
+    }
    socket
-        .send(response_create)
+        .send(ClientMessage::Ping(vec![1, 2, 3].into()))
        .await
-        .expect("send overlapping response.create");
+        .expect("send Ping after queued requests");
+    let message = tokio::time::timeout(Duration::from_secs(2), socket.next())
+        .await
+        .expect("Pong timeout while response is active")
+        .expect("WebSocket remains open")
+        .expect("valid WebSocket frame");
+    assert!(matches!(message, ClientMessage::Pong(_)));
+    assert_eq!(trace.starts.load(Ordering::Acquire), 1);
+
+    for completed_count in 1..=3 {
+        trace.release_terminal.notify_one();
+        let expected_types = if completed_count < 3 {
+            vec![
+                "response.completed",
+                "response.metadata",
+                "response.created",
+            ]
+        } else {
+            vec!["response.completed"]
+        };
+        let mut event_types = Vec::new();
+        for _ in &expected_types {
+            let message = tokio::time::timeout(Duration::from_secs(2), socket.next())
+                .await
+                .expect("serial response timeout")
+                .expect("WebSocket remains open")
+                .expect("valid WebSocket frame");
+            let ClientMessage::Text(text) = message else {
+                panic!("unexpected frame during serial execution: {message:?}");
+            };
+            let event: Value = serde_json::from_str(&text).expect("response event JSON");
+            event_types.push(event["type"].as_str().expect("event type").to_owned());
+        }
+        assert_eq!(event_types, expected_types);
+        assert_eq!(
+            trace.starts.load(Ordering::Acquire),
+            (completed_count + 1).min(3)
+        );
+    }
+    assert_eq!(
+        *trace.inputs.lock().expect("input trace lock"),
+        vec![json!("hello"), json!("second"), json!("third")]
+    );
+    assert!(!trace.cancelled.load(Ordering::Acquire));
+    socket.close(None).await.expect("close WebSocket");
+    server.abort();
+}
+
+#[tokio::test]
+async fn queued_unknown_message_should_be_rejected_before_the_next_valid_request() {
+    let (trace, mut socket, server) = start_active_response().await;
+    for payload in [
+        json!({"type": "response.future"}),
+        json!({"type": "response.create", "model": "model-a", "input": "next"}),
+    ] {
+        socket
+            .send(ClientMessage::Text(payload.to_string().into()))
+            .await
+            .expect("queue frame");
+    }
+    trace.release_terminal.notify_one();
+
+    let mut event_types = Vec::new();
+    for _ in 0..4 {
+        let message = tokio::time::timeout(Duration::from_secs(2), socket.next())
+            .await
+            .expect("response timeout")
+            .expect("connection remains open")
+            .expect("valid frame");
+        let ClientMessage::Text(text) = message else {
+            panic!("unexpected frame: {message:?}");
+        };
+        let event: Value = serde_json::from_str(&text).expect("event JSON");
+        event_types.push(event["type"].as_str().expect("event type").to_owned());
+    }
+    assert_eq!(
+        event_types,
+        [
+            "response.completed",
+            "error",
+            "response.metadata",
+            "response.created"
+        ]
+    );
+    assert_eq!(trace.starts.load(Ordering::Acquire), 2);
+    assert_eq!(
+        *trace.inputs.lock().expect("input trace lock"),
+        vec![json!("hello"), json!("next")]
+    );
+    socket.close(None).await.expect("close WebSocket");
+    server.abort();
+}
+
+#[tokio::test]
+async fn queued_binary_frame_should_be_rejected_after_the_active_response_finishes() {
+    let (trace, mut socket, server) = start_active_response().await;
+    socket
+        .send(ClientMessage::Binary(b"{}".to_vec().into()))
+        .await
+        .expect("queue binary frame");
+    trace.release_terminal.notify_one();
+
+    let message = tokio::time::timeout(Duration::from_secs(2), socket.next())
+        .await
+        .expect("terminal timeout")
+        .expect("connection remains open")
+        .expect("valid frame");
+    let ClientMessage::Text(text) = message else {
+        panic!("active response did not finish before binary rejection: {message:?}");
+    };
+    let event: Value = serde_json::from_str(&text).expect("event JSON");
+    assert_eq!(event["type"], "response.completed");
    let message = tokio::time::timeout(Duration::from_secs(2), socket.next())
        .await
        .expect("policy close timeout")
-        .expect("WebSocket returns a policy close")
-        .expect("valid WebSocket frame");
-    let ClientMessage::Close(Some(frame)) = message else {
-        panic!("overlapping response.create must close the connection");
-    };
+        .expect("connection closes")
+        .expect("valid frame");
+    assert!(
+        matches!(message, ClientMessage::Close(Some(frame)) if frame.code == CloseCode::Policy)
+    );
+    assert_eq!(trace.starts.load(Ordering::Acquire), 1);
+    server.abort();
+}

-    assert_eq!(frame.code, CloseCode::Policy);
+#[tokio::test]
+async fn client_close_should_cancel_active_execution_without_starting_queued_requests() {
+    let (trace, mut socket, server) = start_active_response().await;
+    socket
+        .send(ClientMessage::Text(
+            json!({"type": "response.create", "model": "model-a", "input": "queued"})
+                .to_string()
+                .into(),
+        ))
+        .await
+        .expect("queue request");
+    socket.close(None).await.expect("close WebSocket");
+
+    tokio::time::timeout(
+        Duration::from_secs(2),
+        trace.cancellation_observed.notified(),
+    )
+    .await
+    .expect("cancel active execution promptly");
+    assert_eq!(trace.starts.load(Ordering::Acquire), 1);
+    assert!(trace.cancelled.load(Ordering::Acquire));
    server.abort();
 }
@@ -2,29 +2,34 @@ mod connection;
 mod protocol;

 use std::sync::{
-    Arc,
+    Arc, Mutex,
    atomic::{AtomicBool, AtomicUsize, Ordering},
 };
 use std::time::{Duration, SystemTime};

 use axum::{
    body::Body,
-    http::{Request, StatusCode, header::AUTHORIZATION},
+    http::{HeaderMap, HeaderValue, Request, StatusCode, header::AUTHORIZATION},
 };
 use bytes::Bytes;
 use futures::{SinkExt, StreamExt, future::BoxFuture};
-use gateway_api::openai::responses::ResponseCreateFrameError;
+use gateway_api::openai::responses::{
+    DecodedResponsesRequest, OpenAiRequestHeaders, ResponseCreateFrameError,
+    decode_response_create_with_context,
+};
 use gateway_core::engine::execution::{
    AuthenticatedClient, ClientAuthenticationError, ExecutionService, ExecutionSession,
    StartExecution, StartProviderExecution, StartedExecution,
 };
-use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError, UpstreamSendState};
+use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError};
 use gateway_core::error::{GatewayError, ProviderError, ProviderErrorKind};
 use gateway_core::event::{
    GatewayEvent, ProtocolWireEvent, ProviderEvent, ProviderResponseHeader, ResponseMeta,
 };
 use gateway_core::operation::Operation;
 use gateway_core::routing::PublicModelId;
+use gateway_core::upstream::UpstreamSendState;
+use gateway_protocol::openai::codex_responses_request_semantics;
 use serde_json::{Value, json};
 use tokio_tungstenite::connect_async;
 use tokio_tungstenite::tungstenite::Message as ClientMessage;
@@ -34,6 +39,22 @@ use tower::ServiceExt;
 use super::decode_response_create;
 use crate::openai::{api_router, authenticated_client, models::ModelsExecution};

+fn decode_response_create_with_turn_header(
+    payload: Value,
+    opening_turn_metadata: &'static str,
+) -> DecodedResponsesRequest {
+    let mut headers = HeaderMap::new();
+    headers.insert(
+        "x-codex-turn-metadata",
+        HeaderValue::from_static(opening_turn_metadata),
+    );
+    decode_response_create_with_context(
+        &payload.to_string(),
+        &OpenAiRequestHeaders::from_headers(&headers),
+    )
+    .expect("response.create should decode")
+}
+
 #[test]
 fn response_create_should_default_to_the_websocket_streaming_contract() {
    let decoded = decode_response_create(
@@ -118,6 +139,87 @@ fn response_create_should_preserve_compaction_trigger_for_openai() {
    );
 }

+#[test]
+fn response_create_should_prefer_frame_turn_metadata_over_opening_headers() {
+    let decoded = decode_response_create_with_turn_header(
+        json!({
+            "type": "response.create",
+            "model": "smart-code",
+            "input": "hello",
+            "client_metadata": {
+                "x-codex-turn-metadata": r#"{"request_kind":"turn"}"#
+            }
+        }),
+        r#"{"request_kind":"compaction"}"#,
+    );
+    let Operation::Generate(request) = decoded.operation() else {
+        panic!("Responses must map to Generate");
+    };
+
+    let semantics = codex_responses_request_semantics(
+        request.protocol_payload().body(),
+        request.protocol_payload().context(),
+    );
+
+    assert_eq!(
+        (semantics.request_kind.as_deref(), semantics.compact),
+        (Some("turn"), false)
+    );
+}
+
+#[test]
+fn response_create_should_accept_frame_compaction_after_a_turn_opening_header() {
+    let decoded = decode_response_create_with_turn_header(
+        json!({
+            "type": "response.create",
+            "model": "smart-code",
+            "input": "hello",
+            "client_metadata": {
+                "x-codex-turn-metadata": r#"{"request_kind":"compaction"}"#
+            }
+        }),
+        r#"{"request_kind":"turn"}"#,
+    );
+    let Operation::Generate(request) = decoded.operation() else {
+        panic!("Responses must map to Generate");
+    };
+
+    let semantics = codex_responses_request_semantics(
+        request.protocol_payload().body(),
+        request.protocol_payload().context(),
+    );
+
+    assert_eq!(
+        (semantics.request_kind.as_deref(), semantics.compact),
+        (Some("compaction"), true)
+    );
+}
+
+#[test]
+fn response_create_should_fall_back_to_opening_turn_metadata_when_the_frame_omits_it() {
+    let decoded = decode_response_create_with_turn_header(
+        json!({
+            "type": "response.create",
+            "model": "smart-code",
+            "input": "hello"
+        }),
+        r#"{"request_kind":"compaction"}"#,
+    );
+    let Operation::Generate(request) = decoded.operation() else {
+        panic!("Responses must map to Generate");
+    };
+
+    let semantics = codex_responses_request_semantics(
+        request.protocol_payload().body(),
+        request.protocol_payload().context(),
+    );
+
+    assert_eq!(
+        (semantics.request_kind.as_deref(), semantics.compact),
+        (Some("compaction"), true)
+    );
+}
+
 #[test]
 fn response_create_should_reject_explicit_non_streaming_requests() {
    let error = decode_response_create(
@@ -178,17 +280,26 @@ struct AtomicFailureTrace {
    next_calls: AtomicUsize,
    committed: AtomicBool,
    finalized: AtomicBool,
+    downstream_websocket_connection_ids: Mutex<Vec<String>>,
 }

 struct AtomicFailureSession {
    trace: Arc<AtomicFailureTrace>,
    response_headers: Vec<ProviderResponseHeader>,
+    fail_before_first_event: bool,
 }

 impl ExecutionSession for AtomicFailureSession {
    fn next_event(&mut self) -> BoxFuture<'_, Result<Option<CoordinatedEvent>, EngineError>> {
        Box::pin(async move {
-            match self.trace.next_calls.fetch_add(1, Ordering::AcqRel) {
+            let next_call = self.trace.next_calls.fetch_add(1, Ordering::AcqRel);
+            if self.fail_before_first_event && next_call == 0 {
+                return Err(EngineError::Provider(ProviderError::new(
+                    ProviderErrorKind::Unavailable,
+                    UpstreamSendState::Ambiguous,
+                )));
+            }
+            match next_call {
                0 => Ok(Some(atomic_failure_batch())),
                1 => {
                    self.trace.finalized.store(true, Ordering::Release);
@@ -238,6 +349,7 @@ struct AtomicFailureExecution {
    client: AuthenticatedClient,
    trace: Arc<AtomicFailureTrace>,
    response_headers: Vec<ProviderResponseHeader>,
+    fail_before_first_event: bool,
 }

 impl ExecutionService for AtomicFailureExecution {
@@ -263,6 +375,19 @@ impl ExecutionService for AtomicFailureExecution {
        request: StartExecution,
    ) -> BoxFuture<'_, Result<StartedExecution, GatewayError>> {
        self.trace.starts.fetch_add(1, Ordering::AcqRel);
+        if let Operation::Generate(generate) = &request.operation
+            && let Some(connection_id) = generate
+                .protocol_payload()
+                .context()
+                .get("downstream_websocket_connection_id")
+                .and_then(Value::as_str)
+        {
+            self.trace
+                .downstream_websocket_connection_ids
+                .lock()
+                .expect("downstream connection trace lock")
+                .push(connection_id.to_owned());
+        }
        Box::pin(async move {
            Ok(StartedExecution {
                request_id: gateway_core::engine::ModelRequestId::new("req_ws_atomic")
@@ -272,6 +397,7 @@ impl ExecutionService for AtomicFailureExecution {
                session: Box::new(AtomicFailureSession {
                    trace: Arc::clone(&self.trace),
                    response_headers: self.response_headers.clone(),
+                    fail_before_first_event: self.fail_before_first_event,
                }),
            })
        })
@@ -337,6 +463,7 @@ async fn websocket_atomic_upstream_failure_batch_should_be_forwarded_once() {
        client: authenticated_client("sk_ws_atomic"),
        trace: Arc::clone(&trace),
        response_headers: Vec::new(),
+        fail_before_first_event: false,
    });
    let app = api_router(execution).await;
    let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
@@ -408,6 +535,14 @@ async fn websocket_atomic_upstream_failure_batch_should_be_forwarded_once() {
    assert!(trace.committed.load(Ordering::Acquire));
    assert_eq!(trace.next_calls.load(Ordering::Acquire), 2);
    assert!(trace.finalized.load(Ordering::Acquire));
+    {
+        let downstream_connection_ids = trace
+            .downstream_websocket_connection_ids
+            .lock()
+            .expect("downstream connection trace lock");
+        assert_eq!(downstream_connection_ids.len(), 1);
+        assert!(downstream_connection_ids[0].starts_with("ws_"));
+    }

    socket.close(None).await.expect("close WebSocket");
    server.abort();
@@ -438,6 +573,7 @@ async fn websocket_response_metadata_should_preserve_ordinary_headers_without_bl
            ProviderResponseHeader::new("content-type", Bytes::from_static(b"application/private")),
            ProviderResponseHeader::new("x-request-id", Bytes::from_static(b"req_upstream")),
        ],
+        fail_before_first_event: false,
    });
    let app = api_router(execution).await;
    let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
@@ -522,6 +658,91 @@ async fn websocket_response_metadata_should_preserve_ordinary_headers_without_bl
    server.abort();
 }

+#[tokio::test]
+async fn websocket_failure_before_first_event_should_return_observed_metadata_then_error() {
+    let trace = Arc::new(AtomicFailureTrace::default());
+    let execution = Arc::new(AtomicFailureExecution {
+        client: authenticated_client("sk_ws_atomic"),
+        trace: Arc::clone(&trace),
+        response_headers: vec![
+            ProviderResponseHeader::new(
+                "x-codex-turn-state",
+                Bytes::from_static(b"turn-state-before-close"),
+            ),
+            ProviderResponseHeader::new(
+                "authorization",
+                Bytes::from_static(b"must-not-cross-boundary"),
+            ),
+        ],
+        fail_before_first_event: true,
+    });
+    let app = api_router(execution).await;
+    let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
+        .await
+        .expect("bind WebSocket test server");
+    let address = listener.local_addr().expect("test server address");
+    let server = tokio::spawn(async move {
+        axum::serve(listener, app)
+            .await
+            .expect("serve WebSocket test router");
+    });
+    let mut request = format!("ws://{address}/v1/responses")
+        .into_client_request()
+        .expect("WebSocket request");
+    request.headers_mut().insert(
+        AUTHORIZATION,
+        "Bearer sk_ws_atomic".parse().expect("authorization"),
+    );
+    let (mut socket, response) = connect_async(request).await.expect("upgrade WebSocket");
+    assert_eq!(response.status(), StatusCode::SWITCHING_PROTOCOLS);
+    socket
+        .send(ClientMessage::Text(
+            json!({
+                "type": "response.create",
+                "model": "model-a",
+                "input": "hello"
+            })
+            .to_string()
+            .into(),
+        ))
+        .await
+        .expect("send response.create");
+
+    let mut messages = Vec::<Value>::new();
+    while messages.len() < 2 {
+        let message = tokio::time::timeout(Duration::from_secs(2), socket.next())
+            .await
+            .expect("WebSocket response timeout")
+            .expect("WebSocket remains open")
+            .expect("valid WebSocket frame");
+        let ClientMessage::Text(text) = message else {
+            continue;
+        };
+        messages.push(serde_json::from_str(&text).expect("JSON WebSocket event"));
+    }
+
+    assert_eq!(
+        messages
+            .iter()
+            .filter_map(|message| message.get("type").and_then(Value::as_str))
+            .collect::<Vec<_>>(),
+        vec!["response.metadata", "error"]
+    );
+    let headers = messages[0]
+        .get("headers")
+        .and_then(Value::as_object)
+        .expect("response metadata headers");
+    assert_eq!(
+        headers.get("x-codex-turn-state"),
+        Some(&json!("turn-state-before-close"))
+    );
+    assert!(!headers.contains_key("authorization"));
+    assert!(!trace.committed.load(Ordering::Acquire));
+
+    socket.close(None).await.expect("close WebSocket");
+    server.abort();
+}
+
 #[tokio::test]
 async fn websocket_response_create_should_not_have_a_private_16_mib_frame_limit() {
    let trace = Arc::new(AtomicFailureTrace::default());
@@ -529,6 +750,7 @@ async fn websocket_response_create_should_not_have_a_private_16_mib_frame_limit(
        client: authenticated_client("sk_ws_atomic"),
        trace,
        response_headers: Vec::new(),
+        fail_before_first_event: false,
    });
    let app = api_router(execution).await;
    let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
@@ -1,6 +1,6 @@
 use axum::{
    body::Body,
-    http::{Method, Request, StatusCode},
+    http::{Method, Request, StatusCode, header::AUTHORIZATION},
 };
 use tower::ServiceExt;

@@ -9,6 +9,54 @@ use super::models::ModelsExecution;

 const REMOVED_BODY_LIMIT_BYTES: usize = 16 * 1024 * 1024;

+#[tokio::test]
+async fn removed_responses_review_route_should_not_reach_the_responses_handler() {
+    let response = api_router_with_origins(ModelsExecution::new(), Vec::new())
+        .await
+        .oneshot(
+            Request::post("/v1/responses/review")
+                .header(AUTHORIZATION, "Bearer sk_models_test")
+                .body(Body::empty())
+                .expect("build removed review request"),
+        )
+        .await
+        .expect("route removed review request");
+
+    assert_eq!(response.status(), StatusCode::METHOD_NOT_ALLOWED);
+}
+
+#[tokio::test]
+async fn removed_models_catalog_extension_should_use_standard_model_lookup() {
+    let response = api_router_with_origins(ModelsExecution::new(), Vec::new())
+        .await
+        .oneshot(
+            Request::get("/v1/models/catalog")
+                .header(AUTHORIZATION, "Bearer sk_models_test")
+                .body(Body::empty())
+                .expect("build removed model catalog request"),
+        )
+        .await
+        .expect("route removed model catalog request");
+
+    assert_eq!(response.status(), StatusCode::NOT_FOUND);
+}
+
+#[tokio::test]
+async fn removed_model_info_route_should_return_not_found() {
+    let response = api_router_with_origins(ModelsExecution::new(), Vec::new())
+        .await
+        .oneshot(
+            Request::get("/v1/models/model-a/info")
+                .header(AUTHORIZATION, "Bearer sk_models_test")
+                .body(Body::empty())
+                .expect("build removed model info request"),
+        )
+        .await
+        .expect("route removed model info request");
+
+    assert_eq!(response.status(), StatusCode::NOT_FOUND);
+}
+
 #[tokio::test]
 async fn responses_body_should_accept_payload_above_the_removed_private_limit() {
    let router = api_router_with_origins(ModelsExecution::new(), Vec::new()).await;
@@ -0,0 +1,234 @@
+use std::sync::{Arc, Mutex};
+use std::time::SystemTime;
+
+use axum::{
+    body::{Body, to_bytes},
+    http::{Request, StatusCode, header::AUTHORIZATION},
+};
+use bytes::Bytes;
+use futures::future::BoxFuture;
+use gateway_core::engine::ModelRequestId;
+use gateway_core::engine::execution::{
+    AuthenticatedClient, ClientAuthenticationError, ClientTransport, ExecutionService,
+    StartExecution, StartProviderExecution, StartedExecution,
+};
+use gateway_core::error::{
+    ClientVisibleUpstreamResponse, GatewayError, GatewayErrorKind, ProviderError, ProviderErrorKind,
+};
+use gateway_core::event::ProviderResponseHeader;
+use gateway_core::operation::Operation;
+use gateway_core::routing::PublicModelId;
+use gateway_core::upstream::UpstreamSendState;
+use serde_json::{Value, json};
+use tower::ServiceExt;
+
+use super::provider_endpoint::BufferedJsonSession;
+use super::{api_router, authenticated_client};
+
+const SEARCH_RESPONSE: &[u8] = br#"{ "encrypted_output":"ciphertext", "output":"search result", "results":[{"type":"text_result","ref_id":"turn0search0","future":9007199254740993}] }"#;
+
+#[derive(Debug, Clone, PartialEq)]
+struct CapturedSearchRequest {
+    provider: String,
+    endpoint: String,
+    transport: ClientTransport,
+    body: Bytes,
+    context: Value,
+}
+
+struct SearchExecution {
+    client: AuthenticatedClient,
+    captured: Mutex<Vec<CapturedSearchRequest>>,
+    committed_statuses: Arc<Mutex<Vec<u16>>>,
+    fail_with_upstream_response: bool,
+}
+
+impl SearchExecution {
+    fn new(fail_with_upstream_response: bool) -> Arc<Self> {
+        Arc::new(Self {
+            client: authenticated_client("sk_search_test"),
+            captured: Mutex::new(Vec::new()),
+            committed_statuses: Arc::new(Mutex::new(Vec::new())),
+            fail_with_upstream_response,
+        })
+    }
+
+    fn captured(&self) -> Vec<CapturedSearchRequest> {
+        self.captured.lock().expect("capture lock").clone()
+    }
+}
+
+impl ExecutionService for SearchExecution {
+    fn authenticate(
+        &self,
+        plaintext: &str,
+    ) -> Result<AuthenticatedClient, ClientAuthenticationError> {
+        (plaintext == "sk_search_test")
+            .then(|| self.client.clone())
+            .ok_or(ClientAuthenticationError::InvalidKey)
+    }
+
+    fn public_models(&self, _: &AuthenticatedClient) -> Vec<PublicModelId> {
+        Vec::new()
+    }
+
+    fn contains_public_model(&self, _: &AuthenticatedClient, _: &PublicModelId) -> bool {
+        false
+    }
+
+    fn start(&self, _: StartExecution) -> BoxFuture<'_, Result<StartedExecution, GatewayError>> {
+        Box::pin(async {
+            Err(GatewayError::new(
+                GatewayErrorKind::Internal,
+                "search test must use provider endpoint execution",
+            ))
+        })
+    }
+
+    fn start_provider_endpoint(
+        &self,
+        request: StartProviderExecution,
+    ) -> BoxFuture<'_, Result<StartedExecution, GatewayError>> {
+        Box::pin(async move {
+            let Operation::Search(search) = &request.operation else {
+                return Err(GatewayError::new(
+                    GatewayErrorKind::Internal,
+                    "search test received a non-search operation",
+                ));
+            };
+            let payload = search.payload();
+            self.captured
+                .lock()
+                .expect("capture lock")
+                .push(CapturedSearchRequest {
+                    provider: request.provider.as_str().to_owned(),
+                    endpoint: request.metadata.endpoint,
+                    transport: request.metadata.transport,
+                    body: payload.body().clone(),
+                    context: Value::Object(payload.context().clone()),
+                });
+            let session = if self.fail_with_upstream_response {
+                BufferedJsonSession::failure(
+                    ProviderError::new(
+                        ProviderErrorKind::InvalidRequest,
+                        UpstreamSendState::Sent,
+                    )
+                    .with_status(StatusCode::UNPROCESSABLE_ENTITY.as_u16())
+                    .with_client_visible_upstream_response(
+                        ClientVisibleUpstreamResponse::new(
+                            StatusCode::UNPROCESSABLE_ENTITY.as_u16(),
+                            Some(b"application/problem+json".to_vec()),
+                            Bytes::from_static(
+                                br#"{ "error":{"message":"future search validation"}, "future":9007199254740993 }"#,
+                            ),
+                        )
+                        .with_headers(vec![ProviderResponseHeader::new(
+                            "x-future-search-error",
+                            Bytes::from_static(b"preserved"),
+                        )]),
+                    ),
+                )
+            } else {
+                BufferedJsonSession::success(
+                    Bytes::from_static(SEARCH_RESPONSE),
+                    StatusCode::CREATED.as_u16(),
+                    vec![ProviderResponseHeader::new(
+                        "x-search-rate-limit",
+                        Bytes::from_static(b"42"),
+                    )],
+                    Arc::clone(&self.committed_statuses),
+                )
+            };
+            Ok(StartedExecution {
+                request_id: ModelRequestId::new("req_search_test").expect("request ID"),
+                created_at: SystemTime::now(),
+                stream: false,
+                session: Box::new(session),
+            })
+        })
+    }
+}
+
+#[tokio::test]
+async fn search_route_should_preserve_request_and_success_response_bytes() {
+    let execution = SearchExecution::new(false);
+    let request_body = br#"{ "id":"search-session", "model":"gpt-future", "commands":{"search_query":[{"q":"private query"}]}, "future":1, "future":2 }"#;
+    let turn_metadata =
+        r#"{"session_id":"session","thread_id":"thread","turn_id":"turn","future":true}"#;
+    let response = api_router(execution.clone())
+        .await
+        .oneshot(
+            Request::post("/v1/alpha/search")
+                .header(AUTHORIZATION, "Bearer sk_search_test")
+                .header("content-type", "application/json")
+                .header("x-codex-turn-metadata", turn_metadata)
+                .header("session-id", "root-session")
+                .header("thread-id", "child-thread")
+                .body(Body::from(request_body.to_vec()))
+                .expect("search request"),
+        )
+        .await
+        .expect("search response");
+
+    assert_eq!(response.status(), StatusCode::CREATED);
+    assert_eq!(
+        response.headers().get("x-search-rate-limit"),
+        Some(&"42".parse().expect("header value"))
+    );
+    let response_body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read search response");
+    assert_eq!(response_body.as_ref(), SEARCH_RESPONSE);
+
+    let captured = execution.captured();
+    assert_eq!(captured.len(), 1);
+    assert_eq!(captured[0].provider, "openai");
+    assert_eq!(captured[0].endpoint, "/v1/alpha/search");
+    assert_eq!(captured[0].transport, ClientTransport::HttpJson);
+    assert_eq!(captured[0].body.as_ref(), request_body);
+    assert_eq!(
+        captured[0].context,
+        json!({"turn_metadata": turn_metadata, "session_id": "root-session", "thread_id": "child-thread"})
+    );
+    assert_eq!(
+        *execution
+            .committed_statuses
+            .lock()
+            .expect("committed status lock"),
+        vec![StatusCode::CREATED.as_u16()]
+    );
+}
+
+#[tokio::test]
+async fn search_route_should_return_the_exact_upstream_error_response() {
+    let response = api_router(SearchExecution::new(true))
+        .await
+        .oneshot(
+            Request::post("/v1/alpha/search")
+                .header(AUTHORIZATION, "Bearer sk_search_test")
+                .header("content-type", "application/json")
+                .body(Body::from(
+                    br#"{ "model":"gpt-future", "future_invalid":9007199254740993 }"#.to_vec(),
+                ))
+                .expect("search request"),
+        )
+        .await
+        .expect("search response");
+
+    assert_eq!(response.status(), StatusCode::UNPROCESSABLE_ENTITY);
+    assert_eq!(
+        response.headers().get("content-type"),
+        Some(&"application/problem+json".parse().expect("content type"))
+    );
+    assert_eq!(
+        response.headers().get("x-future-search-error"),
+        Some(&"preserved".parse().expect("header value"))
+    );
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read search response");
+    assert_eq!(
+        body.as_ref(),
+        br#"{ "error":{"message":"future search validation"}, "future":9007199254740993 }"#
+    );
+}
@@ -13,11 +13,14 @@ path = "tests/main.rs"

 [dependencies]
 async-trait = "0.1.89"
+base64 = "0.23.0"
 bytes = "1.11.1"
 futures = "0.3.32"
 futures-timer = "3.0.3"
 serde = { version = "1.0.228", features = ["derive"] }
 serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
+sha2 = "0.11.0"
+semver = "1.0.27"
 thiserror = "2.0.18"
 tracing = "0.1.44"
 uuid = { version = "1.23.3", features = ["v7"] }
@@ -0,0 +1,16 @@
+//! Provider credential 值对象构造错误。
+
+use thiserror::Error;
+
+/// Credential 值对象构造错误。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Error)]
+pub enum CredentialError {
+    #[error("credential revision must be greater than zero")]
+    InvalidRevision,
+    #[error("credential revision overflow")]
+    RevisionOverflow,
+    #[error("credential CAS profile belongs to a different account")]
+    ProfileAccountMismatch,
+    #[error("credential refresh schedule requires a refresh token")]
+    InvalidRefreshSchedule,
+}
@@ -0,0 +1,13 @@
+//! Provider 账号领域、持久化端口与同一 target 内的账号选择。
+
+mod error;
+mod model;
+pub mod scope;
+mod selection;
+mod store;
+
+pub use error::CredentialError;
+pub use model::*;
+pub use selection::*;
+pub(crate) use selection::{SMART_SCORE_TOLERANCE, smart_score};
+pub use store::ProviderAccountStore;
--- a/Show More
+++ b/Show More