chore: bump version to 3.0.26

Co-authored-by: Codex <noreply@openai.com>
fix(xai): restore tool replay and billing details
2026-11-08 00:05:59 +00:00 · 2026-07-29 19:44:44 +08:00 · 2026-07-29 18:28:22 +08:00 · 2026-07-29 17:43:34 +08:00 · 2026-07-29 17:36:09 +08:00 · 2026-07-29 14:49:27 +08:00
236 changed files with 20840 additions and 6303 deletions
@@ -40,7 +40,7 @@ jobs:
          } >> "$GITHUB_ENV"

      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ inputs.ref }}

@@ -76,7 +76,7 @@ jobs:
          ${{ hashFiles('trivy-results.sarif') != '' &&
              (github.event_name != 'pull_request' ||
               github.event.pull_request.head.repo.full_name == github.repository) }}
-        uses: github/codeql-action/upload-sarif@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+        uses: github/codeql-action/upload-sarif@e4fba868fa4b1b91e1fdab776edc8cfbe6e9fb81 # v4.37.3
        with:
          sarif_file: trivy-results.sarif
          category: runtime-container
@@ -61,7 +61,7 @@ jobs:
          --health-retries 10
    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ inputs.ref }}
          # PR 场景需要 base 提交做冻结清单的 append-only 比对。
@@ -152,7 +152,7 @@ jobs:
      CI: 'true'
    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ inputs.ref }}

@@ -191,7 +191,7 @@ jobs:
    timeout-minutes: 5
    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ inputs.ref }}

@@ -25,7 +25,7 @@ jobs:
      container: ${{ steps.filter.outputs.container }}
    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ github.event.pull_request.head.sha || github.sha }}
          fetch-depth: 0
@@ -41,7 +41,7 @@ jobs:

    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ github.event_name == 'workflow_dispatch' && inputs.tag || github.ref }}
          fetch-depth: 0
@@ -177,7 +177,7 @@ jobs:

    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ needs.release-info.outputs.git_sha }}

@@ -237,7 +237,7 @@ jobs:

    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ needs.release-info.outputs.git_sha }}

@@ -289,7 +289,7 @@ jobs:

    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ needs.release-info.outputs.git_sha }}

@@ -408,7 +408,7 @@ jobs:

    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ needs.release-info.outputs.git_sha }}

@@ -454,7 +454,7 @@ jobs:
        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0

      - name: Login to GHCR
-        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0 # v4.4.0
+        uses: docker/login-action@abd2ef45e78c5afb21d64d4ca52ee8550d9572c7 # v4.5.1
        with:
          registry: ${{ env.REGISTRY }}
          username: ${{ github.actor }}
@@ -508,7 +508,7 @@ jobs:

    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ needs.release-info.outputs.git_sha }}

@@ -525,7 +525,7 @@ jobs:
        uses: sigstore/cosign-installer@6f9f17788090df1f26f669e9d70d6ae9567deba6 # v4.1.2

      - name: Login to GHCR
-        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0 # v4.4.0
+        uses: docker/login-action@abd2ef45e78c5afb21d64d4ca52ee8550d9572c7 # v4.5.1
        with:
          registry: ${{ env.REGISTRY }}
          username: ${{ github.actor }}
@@ -23,7 +23,7 @@ jobs:
    timeout-minutes: 20
    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ github.event.pull_request.head.sha || github.sha }}

@@ -47,7 +47,7 @@ jobs:
    timeout-minutes: 15
    steps:
      - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          ref: ${{ github.event.pull_request.head.sha || github.sha }}

@@ -21,15 +21,16 @@

 ## 能力

-| 领域     | 实现                                                                        |
-| -------- | --------------------------------------------------------------------------- |
-| 协议     | OpenAI Responses JSON、SSE、WebSocket 与模型目录                             |
-| Provider | 固定 OpenAI、xAI 两个 Provider；各自管理 OAuth、账号、额度与模型目录          |
-| 路由     | Client Key 绑定 Provider、全局模型映射、会话亲和与同 Provider 安全 fallback   |
-| 透明边界 | OpenAI SSE 与 WebSocket 均原样转发上游字节；xAI 在 `providers/xai` 内做 Grok 与 Responses 协议转换 |
-| 延续     | OpenAI native/replay continuation；xAI 使用客户端提交的完整历史                |
-| 管理     | Client Key、账号、模型目录、设置、观测、系统更新与 OAuth                       |
-| 计量     | 模型请求 Token、费用、延迟、账号与 Provider 归因                               |
+| 领域     | 实现                                                                                                  |
+| -------- | ----------------------------------------------------------------------------------------------------- |
+| 协议     | OpenAI Responses JSON、SSE、WebSocket 与模型目录                                                       |
+| Provider | 固定 OpenAI、xAI 两个 Provider；各自管理 OAuth、账号、额度与模型目录                                    |
+| 路由     | Client Key 绑定 Provider、全局模型映射、会话亲和与同 Provider 安全 fallback                             |
+| 透明边界 | OpenAI 请求保留未知字段和字段顺序，SSE 与 WebSocket 原样转发业务字节；xAI 在 Provider 内做协议转换          |
+| 延续     | OpenAI native/replay continuation；xAI 使用客户端提交的完整历史                                          |
+| 账号     | 导入、OAuth、credential 刷新、主动额度刷新，以及正常响应中的被动额度/状态观测                              |
+| 管理     | Client Key、账号、模型目录、设置、观测、系统更新与 OAuth                                                 |
+| 计量     | 模型请求 Token、费用、延迟、账号与 Provider 归因，并记录响应确认的实际 `service_tier`                      |

 ## 快速开始

@@ -93,6 +94,11 @@ curl -i http://127.0.0.1:8080/healthz
 3. 按需配置客户端模型到上游模型的全局映射；未命中映射的模型名原样透传。
 4. 创建 `sk_...` Client Key，绑定 `openai` 或 `xai`，并设置速率与并发限制。

+OpenAI 账号导入和首次 OAuth 创建在 credential 提交后会立即尝试一次额度观测；额度接口临时失败不会
+回滚已提交的账号。Free、K12 等套餐共用同一套额度与状态转换逻辑，套餐字段只作为账号事实并隔离
+对应的模型目录 cache。credential 刷新、额度刷新和正常请求中的被动额度观测是三条独立链路，详见
+[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。

@@ -145,7 +151,7 @@ curl http://127.0.0.1:8080/v1/responses \
 ## 运维

 ```bash
-# 升级
+# 实例升级
 docker compose -f deploy/compose.yaml pull codex-proxy-rs
 docker compose -f deploy/compose.yaml up -d --no-build

@@ -179,7 +185,8 @@ release/publish <version>
 ```

 脚本会更新 `release/version.yaml`、创建约定提交与带注释的 `v<version>` tag，并原子推送分支和 tag。
-不要手工修改版本后单独打 tag。
+不要手工修改版本后单独打 tag。该脚本只发布仓库版本和触发 Release 构建，不会登录服务器，也不会
+改变任何运行实例；源码提交、仓库发版和实例升级是三个独立状态。

 ## 文档

@@ -142,7 +142,7 @@ checksum = "c7c24de15d275a1ecfd47a380fb4d5ec9bfe0933f309ed5e705b775596a3574d"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -208,7 +208,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "31b698c5f9a010f6573133b09e0de5408834d0c82f8d7475a89fc1867a71cd90"
 dependencies = [
 "axum-core",
- "base64",
+ "base64 0.22.1",
 "bytes",
 "form_urlencoded",
 "futures-util",
@@ -275,6 +275,12 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"

+[[package]]
+name = "base64"
+version = "0.23.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b25655df2c3cdd83c5e5b293b88acd880332b2ddadd7c30ac43144fdc0033da9"
+
 [[package]]
 name = "base64ct"
 version = "1.8.3"
@@ -444,7 +450,7 @@ dependencies = [
 "provider-openai",
 "provider-xai",
 "serde",
- "syn 2.0.118",
+ "syn 3.0.3",
 "tempfile",
 "thiserror",
 "tokio",
@@ -669,7 +675,7 @@ dependencies = [
 "aead",
 "blake2",
 "crypto_secretbox",
- "curve25519-dalek",
+ "curve25519-dalek 4.1.3",
 "salsa20",
 "subtle",
 "zeroize",
@@ -708,8 +714,23 @@ dependencies = [
 "cfg-if",
 "cpufeatures 0.2.17",
 "curve25519-dalek-derive",
- "digest 0.10.7",
- "fiat-crypto",
+ "fiat-crypto 0.2.9",
+ "rustc_version",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "curve25519-dalek"
+version = "5.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b5eed333089e2e1c1ac8c6c0398e5e2497b4c9926ca6d0365ed1e099afa5bc23"
+dependencies = [
+ "cfg-if",
+ "cpufeatures 0.3.0",
+ "curve25519-dalek-derive",
+ "digest 0.11.3",
+ "fiat-crypto 0.3.0",
 "rustc_version",
 "subtle",
 "zeroize",
@@ -723,7 +744,7 @@ checksum = "f46882e17999c6cc590af592290432be3bce0428cb0d5f8b6715e4dc7b383eb3"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -761,6 +782,16 @@ dependencies = [
 "zeroize",
 ]

+[[package]]
+name = "der"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a69dedd701da44b0536442edf09c81a64b0ab97a7a4a5e3d1971f00027cbc63d"
+dependencies = [
+ "const-oid 0.10.2",
+ "zeroize",
+]
+
 [[package]]
 name = "deranged"
 version = "0.5.8"
@@ -799,7 +830,7 @@ checksum = "1ac70aa55017e108007fbaf5aa0f54b021c98f92ff8af59d42eda9da96e3dd4f"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -829,34 +860,35 @@ version = "0.16.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ee27f32b5c5292967d2d4a9d7f1e0b0aed2c15daded5a60300e4abb9d8020bca"
 dependencies = [
- "der",
+ "der 0.7.10",
 "digest 0.10.7",
 "elliptic-curve",
 "rfc6979",
- "signature",
- "spki",
+ "signature 2.2.0",
+ "spki 0.7.3",
 ]

 [[package]]
 name = "ed25519"
-version = "2.2.3"
+version = "3.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "115531babc129696a58c64a4fef0a8bf9e9698629fb97e9e40767d235cfbcd53"
+checksum = "29fcf32e6c73d1079f83ab4d782de2d81620346a5f38c6237a86a22f8368980a"
 dependencies = [
- "pkcs8",
- "signature",
+ "pkcs8 0.11.0",
+ "signature 3.0.0",
 ]

 [[package]]
 name = "ed25519-dalek"
-version = "2.2.0"
+version = "3.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "70e796c081cee67dc755e1a36a0a172b897fab85fc3f6bc48307991f64e4eca9"
+checksum = "6ebaa1a2bf1290ab3bfe5a7b771d050ebffab2711c19a81691c683a5144a25de"
 dependencies = [
- "curve25519-dalek",
+ "curve25519-dalek 5.0.0",
 "ed25519",
 "serde",
- "sha2 0.10.9",
+ "sha2 0.11.0",
+ "signature 3.0.0",
 "subtle",
 "zeroize",
 ]
@@ -883,7 +915,7 @@ dependencies = [
 "generic-array",
 "group",
 "pem-rfc7468",
- "pkcs8",
+ "pkcs8 0.10.2",
 "rand_core 0.6.4",
 "sec1",
 "subtle",
@@ -968,6 +1000,12 @@ version = "0.2.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "28dea519a9695b9977216879a3ebfddf92f1c08c05d984f8996aecd6ecdc811d"

+[[package]]
+name = "fiat-crypto"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "64cd1e32ddd350061ae6edb1b082d7c54915b5c672c389143b9a63403a109f24"
+
 [[package]]
 name = "filetime"
 version = "0.2.29"
@@ -1100,7 +1138,7 @@ checksum = "2d6d3cde68c518367be28956066ddfef33813991b77a55005a69dae04bf3b10b"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -1144,7 +1182,7 @@ version = "0.0.0"
 dependencies = [
 "argon2",
 "async-trait",
- "base64",
+ "base64 0.23.0",
 "chrono",
 "futures",
 "gateway-core",
@@ -1156,6 +1194,7 @@ dependencies = [
 "subtle",
 "thiserror",
 "tokio",
+ "tracing",
 "uuid",
 ]

@@ -1165,7 +1204,7 @@ version = "0.1.0"
 dependencies = [
 "async-trait",
 "axum",
- "base64",
+ "base64 0.23.0",
 "bytes",
 "chrono",
 "futures",
@@ -1176,6 +1215,7 @@ dependencies = [
 "serde_json",
 "thiserror",
 "tokio",
+ "tokio-tungstenite 0.29.0",
 "tower",
 "tower-http 0.7.0",
 "tracing",
@@ -1194,6 +1234,7 @@ dependencies = [
 "serde",
 "serde_json",
 "thiserror",
+ "tracing",
 "uuid",
 ]

@@ -1371,7 +1412,7 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b3314d5adb5d94bcdf56771f2e50dbbc80bb4bdf88967526706205ac9eff24eb"
 dependencies = [
- "base64",
+ "base64 0.22.1",
 "bytes",
 "headers-core",
 "http",
@@ -1538,7 +1579,7 @@ version = "0.1.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0"
 dependencies = [
- "base64",
+ "base64 0.22.1",
 "bytes",
 "futures-channel",
 "futures-util",
@@ -1736,19 +1777,20 @@ dependencies = [

 [[package]]
 name = "jsonwebtoken"
-version = "10.3.0"
+version = "11.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0529410abe238729a60b108898784df8984c87f6054c9c4fcacc47e4803c1ce1"
+checksum = "881733cbc631fc9e472e24447ce32a64bedf2da498d6d8570b08edc87de71f65"
 dependencies = [
 "aws-lc-rs",
- "base64",
+ "base64 0.22.1",
 "getrandom 0.2.17",
 "js-sys",
 "pem",
 "serde",
 "serde_json",
- "signature",
+ "signature 2.2.0",
 "simple_asn1",
+ "zeroize",
 ]

 [[package]]
@@ -2015,7 +2057,7 @@ version = "3.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1d30c53c26bc5b31a98cd02d20f25a7c8567146caf63ed593a9d87b2775291be"
 dependencies = [
- "base64",
+ "base64 0.22.1",
 "serde_core",
 ]

@@ -2046,8 +2088,18 @@ version = "0.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f950b2377845cebe5cf8b5165cb3cc1a5e0fa5cfa3e1f7f55707d8fd82e0a7b7"
 dependencies = [
- "der",
- "spki",
+ "der 0.7.10",
+ "spki 0.7.3",
+]
+
+[[package]]
+name = "pkcs8"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "451913da69c775a56034ea8d9003d27ee8948e12443eae7c038ba100a4f21cb7"
+dependencies = [
+ "der 0.8.1",
+ "spki 0.8.0",
 ]

 [[package]]
@@ -2115,7 +2167,7 @@ version = "0.0.0"
 dependencies = [
 "async-stream",
 "async-trait",
- "base64",
+ "base64 0.23.0",
 "bytes",
 "chrono",
 "cookie",
@@ -2125,7 +2177,7 @@ dependencies = [
 "gateway-admin",
 "gateway-core",
 "gateway-protocol",
- "getrandom 0.3.4",
+ "getrandom 0.4.3",
 "hex",
 "jsonwebtoken",
 "reqwest",
@@ -2157,14 +2209,14 @@ version = "0.0.0"
 dependencies = [
 "async-stream",
 "async-trait",
- "base64",
+ "base64 0.23.0",
 "bytes",
 "chrono",
 "futures",
 "gateway-admin",
 "gateway-core",
 "gateway-protocol",
- "getrandom 0.3.4",
+ "getrandom 0.4.3",
 "jsonwebtoken",
 "p256",
 "reqwest",
@@ -2409,7 +2461,7 @@ version = "0.12.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
 dependencies = [
- "base64",
+ "base64 0.22.1",
 "bytes",
 "cookie",
 "cookie_store",
@@ -2598,9 +2650,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3e97a565f76233a6003f9f5c54be1d9c5bdfa3eccfb189469f11ec4901c47dc"
 dependencies = [
 "base16ct",
- "der",
+ "der 0.7.10",
 "generic-array",
- "pkcs8",
+ "pkcs8 0.10.2",
 "subtle",
 "zeroize",
 ]
@@ -2796,6 +2848,12 @@ dependencies = [
 "rand_core 0.6.4",
 ]

+[[package]]
+name = "signature"
+version = "3.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d567dcbaf0049cb8ac2608a76cd95ff9e4412e1899d389ee400918ca7537f5"
+
 [[package]]
 name = "simd-adler32"
 version = "0.3.9"
@@ -2855,7 +2913,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d91ed6c858b01f942cd56b37a94b3e0a1798290327d1236e4d9cf4eaca44d29d"
 dependencies = [
 "base64ct",
- "der",
+ "der 0.7.10",
+]
+
+[[package]]
+name = "spki"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d9efca8738c78ee9484207732f728b1ef517bbb1833d6fc0879ca898a522f6f"
+dependencies = [
+ "base64ct",
+ "der 0.8.1",
 ]

 [[package]]
@@ -2877,7 +2945,7 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "05b44e85bf579a8eeb4ceaa77a3a523baf2bf0e9bac7e40f405d537b5d2d5ccb"
 dependencies = [
- "base64",
+ "base64 0.22.1",
 "bytes",
 "cfg-if",
 "chrono",
@@ -2918,7 +2986,7 @@ dependencies = [
 "quote",
 "sqlx-core",
 "sqlx-macros-core",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -2941,7 +3009,7 @@ dependencies = [
 "sqlx-mysql",
 "sqlx-postgres",
 "sqlx-sqlite",
- "syn 2.0.118",
+ "syn 2.0.119",
 "thiserror",
 "tokio",
 "url",
@@ -2981,7 +3049,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "87a2bdd6e83f6b3ea525ca9fee568030508b58355a43d0b2c1674d5f79dcd65e"
 dependencies = [
 "atoi",
- "base64",
+ "base64 0.22.1",
 "bitflags",
 "byteorder",
 "chrono",
@@ -3066,9 +3134,9 @@ checksum = "a7973cce6668464ea31f176d85b13c7ab3bba2cb3b77a2ed26abd7801688010a"

 [[package]]
 name = "syn"
-version = "2.0.118"
+version = "2.0.119"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1b9ae57f904213ebb649ce6895b8a66c66f0203b9319718f69a5612a065b1422"
+checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -3103,7 +3171,7 @@ checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -3124,7 +3192,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
 "fastrand",
- "getrandom 0.3.4",
+ "getrandom 0.4.3",
 "once_cell",
 "rustix",
 "windows-sys 0.61.2",
@@ -3238,7 +3306,7 @@ checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -3414,7 +3482,7 @@ checksum = "7490cfa5ec963746568740651ac6781f701c9c5ea257c58e057f3ba8cf69e8da"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -3691,7 +3759,7 @@ dependencies = [
 "bumpalo",
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 "wasm-bindgen-shared",
 ]

@@ -3773,7 +3841,7 @@ checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -3784,7 +3852,7 @@ checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -3909,7 +3977,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "08db1edfb05d9b3c1542e521aea074442088292f00b5f28e435c714a98f85031"
 dependencies = [
 "assert-json-diff",
- "base64",
+ "base64 0.22.1",
 "deadpool",
 "futures",
 "http",
@@ -3983,7 +4051,7 @@ checksum = "de844c262c8848816172cef550288e7dc6c7b7814b4ee56b3e1553f275f1858e"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 "synstructure",
 ]

@@ -4004,7 +4072,7 @@ checksum = "e2e817b7b52d0c7358d3246da9d69935ebb18116b2b102b4230dac079b4862f5"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -4024,7 +4092,7 @@ checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 "synstructure",
 ]

@@ -4045,7 +4113,7 @@ checksum = "3c50655cbb0fe3fc43170059e702f1ce5e19b84cec58dc87b037a09935c2f328"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -4078,7 +4146,7 @@ checksum = "625dc425cab0dca6dc3c3319506e6593dcb08a9f387ea3b284dbd52a92c40555"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 2.0.118",
+ "syn 2.0.119",
 ]

 [[package]]
@@ -25,7 +25,7 @@ tokio = { version = "1.52.3", default-features = false, features = ["rt-multi-th

 [dev-dependencies]
 config = { version = "0.15.23", default-features = false, features = ["yaml"] }
-syn = { version = "2.0.118", features = ["full"] }
+syn = { version = "3.0.3", features = ["full"] }
 tempfile = "3.27.0"

 [lints]
@@ -14,7 +14,7 @@ path = "tests/main.rs"
 [dependencies]
 argon2 = "0.5.3"
 async-trait = "0.1.89"
-base64 = "0.22.1"
+base64 = "0.23.0"
 chrono = "0.4.45"
 futures = "0.3.32"
 gateway-core = { path = "../gateway-core" }
@@ -24,10 +24,11 @@ serde = { version = "1.0.228", features = ["derive"] }
 secrecy = { version = "0.10.3", features = ["serde"] }
 subtle = "2.6.1"
 thiserror = "2.0.18"
+tracing = "0.1.44"
 uuid = { version = "1.23.3", features = ["v7"] }

 [dev-dependencies]
-serde_json = { version = "1.0.150", features = ["preserve_order"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt"] }

 [lints]
@@ -9,17 +9,8 @@ use gateway_core::routing::ProviderKind;

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

-/// Provider 账号当前可用性。
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum AccountAvailability {
-    Unknown,
-    Ready,
-    Cooldown,
-    QuotaExhausted,
-    Expired,
-    Banned,
-    Invalid,
-}
+/// Provider 账号当前可用性；权威定义与字符串编解码在 gateway-core，此处仅复用。
+pub use gateway_core::engine::credential::AccountAvailability;

 /// 管理页使用的归一化账号状态。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -189,7 +180,6 @@ pub struct AccountSummary {
 /// 账号启停写入命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct SetAccountEnabled {
-    pub expected_config_revision: Revision,
    pub account_id: String,
    pub enabled: bool,
 }
@@ -197,7 +187,6 @@ pub struct SetAccountEnabled {
 /// 账号批量删除命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DeleteAccounts {
-    pub expected_config_revision: Revision,
    pub account_ids: Vec<String>,
 }

@@ -223,6 +212,9 @@ pub enum AccountConnectionTestEvent {
        message: String,
        provider_error_code: Option<String>,
        provider_error_type: Option<String>,
+        upstream_status: Option<u16>,
+        upstream_content_type: Option<String>,
+        upstream_body: Option<String>,
        account_status: AccountStatus,
    },
 }
@@ -141,7 +141,6 @@ impl fmt::Debug for ClientKeySecret {
 /// API 提交的 Client Key 创建命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CreateClientKey {
-    pub expected_config_revision: Revision,
    pub name: String,
    pub label: Option<String>,
    pub provider_kind: ProviderKind,
@@ -151,7 +150,6 @@ pub struct CreateClientKey {
 /// 管理用例生成 ID 与明文后的持久化命令。
 #[derive(Clone, PartialEq, Eq)]
 pub struct NewClientKey {
-    pub expected_config_revision: Revision,
    pub id: ClientApiKeyId,
    pub name: String,
    pub label: Option<String>,
@@ -175,7 +173,6 @@ impl fmt::Debug for NewClientKey {
 /// 修改 Client Key 的公开策略字段。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UpdateClientKey {
-    pub expected_config_revision: Revision,
    pub id: ClientApiKeyId,
    pub name: String,
    pub label: Option<String>,
@@ -186,7 +183,6 @@ pub struct UpdateClientKey {
 /// 修改 Client Key 启用状态。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct SetClientKeyEnabled {
-    pub expected_config_revision: Revision,
    pub id: ClientApiKeyId,
    pub enabled: bool,
 }
@@ -194,7 +190,6 @@ pub struct SetClientKeyEnabled {
 /// 删除 Client Key。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DeleteClientKey {
-    pub expected_config_revision: Revision,
    pub id: ClientApiKeyId,
 }

@@ -330,6 +330,7 @@ pub struct LatencyPercentiles {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ProviderBillingInput {
    pub upstream_model_id: String,
+    pub service_tier: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
    pub cached_tokens: Option<u64>,
@@ -345,6 +346,7 @@ pub struct UsageCalculatedBillingFact {
    pub bucket_start: DateTime<Utc>,
    pub provider_kind: String,
    pub upstream_model_id: String,
+    pub service_tier: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
    pub cached_tokens: Option<u64>,
@@ -574,6 +576,7 @@ pub struct UsageRecord {
    pub upstream_transport: Option<String>,
    pub http_version: Option<String>,
    pub websocket_pool: Option<String>,
+    pub service_tier: Option<String>,
    /// Provider 已筛选的专有观测 JSON；管理领域保持不透明。
    pub provider_metadata_json: Option<String>,
    pub attempt_count: u32,
@@ -2,14 +2,15 @@

 use std::fmt;

+use async_trait::async_trait;
 use chrono::{DateTime, Utc};
 use gateway_core::{
-    engine::credential::{OpaqueProviderData, ProviderAccountId},
+    engine::credential::{OpaqueProviderData, ProviderAccountId, ProviderAccountIdentity},
    routing::{ProviderKind, UpstreamModelId},
 };

 use super::{
-    MutationActor, MutationContext, PageSize, Revision,
+    AdminError, MutationActor, MutationContext, PageSize, Revision,
    accounts::{AccountAvailability, AccountRecord, AccountStatus, AccountSummary, AccountUsage},
 };

@@ -101,7 +102,6 @@ pub struct CredentialDetails {
 /// Provider 正式文档批量导入命令。
 pub struct ImportCredentials {
    pub context: MutationContext,
-    pub expected_config_revision: Revision,
    pub document: ProviderDocument,
 }

@@ -110,7 +110,6 @@ impl fmt::Debug for ImportCredentials {
        formatter
            .debug_struct("ImportCredentials")
            .field("context", &self.context)
-            .field("expected_config_revision", &self.expected_config_revision)
            .field("document", &self.document)
            .finish()
    }
@@ -169,17 +168,9 @@ pub struct PreparedCredentialImport {
 /// Admin 交给 Store 的导入事务命令。
 #[derive(Debug, Clone, PartialEq)]
 pub struct CredentialImportCommit {
-    pub expected_config_revision: Revision,
    pub prepared: PreparedCredentialImport,
 }

-/// 可选的重新授权目标。
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct ReauthorizationTarget {
-    pub account_id: ProviderAccountId,
-    pub credential_revision: Revision,
-}
-
 /// OAuth pending owner 的中立身份；不编码具体 Provider 的 Redis key 或 JSON。
 #[derive(Clone, PartialEq, Eq)]
 pub enum AuthorizationOwner {
@@ -240,21 +231,18 @@ impl fmt::Debug for AuthorizationOwnerBinding {
 }

 /// OAuth 完成时应创建新账号还是 CAS 更新既有 credential。
+///
+/// 重新授权只绑定稳定的账号身份：credential revision 由服务端在临近写入时读取，
+/// 长流程期间的后台刷新不得让恢复操作失效。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum AuthorizationMutationTarget {
-    Create {
-        name: String,
-    },
-    Reauthorize {
-        account_id: ProviderAccountId,
-        expected_credential_revision: Revision,
-    },
+    Create { name: String },
+    Reauthorize { account_id: ProviderAccountId },
 }

 /// 必须完整进入 Provider opaque pending payload、并在 complete 后原样恢复的事务信封。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct PendingAuthorizationMutation {
-    expected_config_revision: Revision,
    provider_kind: ProviderKind,
    target: AuthorizationMutationTarget,
    owner_binding: AuthorizationOwnerBinding,
@@ -263,24 +251,17 @@ pub struct PendingAuthorizationMutation {
 impl PendingAuthorizationMutation {
    #[must_use]
    pub const fn new(
-        expected_config_revision: Revision,
        provider_kind: ProviderKind,
        target: AuthorizationMutationTarget,
        owner_binding: AuthorizationOwnerBinding,
    ) -> Self {
        Self {
-            expected_config_revision,
            provider_kind,
            target,
            owner_binding,
        }
    }

-    #[must_use]
-    pub const fn expected_config_revision(&self) -> Revision {
-        self.expected_config_revision
-    }
-
    #[must_use]
    pub const fn provider_kind(&self) -> &ProviderKind {
        &self.provider_kind
@@ -301,9 +282,8 @@ impl PendingAuthorizationMutation {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct StartAuthorization {
    pub context: MutationContext,
-    pub expected_config_revision: Revision,
    pub name: String,
-    pub reauthorization: Option<ReauthorizationTarget>,
+    pub reauthorization: Option<ProviderAccountId>,
 }

 /// OAuth 流程启动结果。
@@ -322,6 +302,20 @@ pub trait CredentialCommitGuard: Send + 'static {
    fn finish(self: Box<Self>);
 }

+/// OAuth pending claim 在 Store 事务结果确定后执行的显式结算动作。
+///
+/// OAuth provider 必须在 credential 准备阶段持有 claim：Store 提交成功后消费 flow，提交或
+/// 校验失败后释放 flow。异步结算不能依赖 `Drop`，否则请求提前返回会让同一授权流无谓地
+/// 进入短暂的不可重试状态。
+#[async_trait]
+pub trait AuthorizationCommitGuard: Send + 'static {
+    /// Store 已提交 OAuth credential 后消费对应的一次性 flow。
+    async fn commit(self: Box<Self>) -> Result<(), AdminError>;
+
+    /// Store 未提交 OAuth credential 时释放 claim，允许同一 flow 重试。
+    async fn abort(self: Box<Self>) -> Result<(), AdminError>;
+}
+
 /// OAuth complete 后由 Provider 返回的准备结果；Store 仍是唯一提交者。
 pub enum PreparedAuthorizationCredential {
    Create(PreparedCredentialCreate),
@@ -332,6 +326,7 @@ pub enum PreparedAuthorizationCredential {
 pub struct PreparedAuthorizationCommit {
    pub pending: PendingAuthorizationMutation,
    pub credential: PreparedAuthorizationCredential,
+    authorization_guard: Option<Box<dyn AuthorizationCommitGuard>>,
 }

 impl fmt::Debug for PreparedAuthorizationCommit {
@@ -358,9 +353,37 @@ pub struct AuthorizationCommit {
    pub credential: AuthorizationCredentialCommit,
 }

+/// OAuth 准备结果拆解后的 Store 命令与两个结算 guard。
+///
+/// Store 成功时先结束 credential guard，再消费 OAuth claim；失败时丢弃 credential guard 并
+/// 释放 OAuth claim，使同一授权流可以重试。
+pub(crate) struct AuthorizationCommitSettlement {
+    pub(crate) command: AuthorizationCommit,
+    pub(crate) credential_guard: Option<Box<dyn CredentialCommitGuard>>,
+    pub(crate) authorization_guard: Option<Box<dyn AuthorizationCommitGuard>>,
+}
+
 impl PreparedAuthorizationCommit {
    #[must_use]
-    pub fn into_commit(self) -> (AuthorizationCommit, Option<Box<dyn CredentialCommitGuard>>) {
+    pub fn new(
+        pending: PendingAuthorizationMutation,
+        credential: PreparedAuthorizationCredential,
+    ) -> Self {
+        Self {
+            pending,
+            credential,
+            authorization_guard: None,
+        }
+    }
+
+    /// 让 OAuth claim 覆盖准备完成到 Store 事务结算之间的全部窗口。
+    #[must_use]
+    pub fn with_authorization_guard(mut self, guard: Box<dyn AuthorizationCommitGuard>) -> Self {
+        self.authorization_guard = Some(guard);
+        self
+    }
+
+    pub(crate) fn into_commit(self) -> AuthorizationCommitSettlement {
        let (credential, guard) = match self.credential {
            PreparedAuthorizationCredential::Create(credential) => {
                (AuthorizationCredentialCommit::Create(credential), None)
@@ -373,13 +396,27 @@ impl PreparedAuthorizationCommit {
                )
            }
        };
-        (
-            AuthorizationCommit {
+        AuthorizationCommitSettlement {
+            command: AuthorizationCommit {
                pending: self.pending,
                credential,
            },
-            guard,
-        )
+            credential_guard: guard,
+            authorization_guard: self.authorization_guard,
+        }
+    }
+
+    pub(crate) async fn abort(self) -> Result<(), AdminError> {
+        let AuthorizationCommitSettlement {
+            credential_guard,
+            authorization_guard,
+            ..
+        } = self.into_commit();
+        drop(credential_guard);
+        if let Some(guard) = authorization_guard {
+            guard.abort().await?;
+        }
+        Ok(())
    }
 }

@@ -406,7 +443,6 @@ impl fmt::Debug for CompleteAuthorization {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CredentialMutation {
    pub context: MutationContext,
-    pub expected_config_revision: Revision,
    pub account_id: ProviderAccountId,
 }

@@ -422,7 +458,6 @@ pub struct CredentialMutationResult {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CredentialDeletion {
    pub context: MutationContext,
-    pub expected_config_revision: Revision,
    pub account_ids: Vec<ProviderAccountId>,
 }

@@ -436,14 +471,12 @@ pub struct CredentialDeletionResult {
 /// Provider-owned token 轮换命令。
 pub struct RotateCredential {
    pub mutation: CredentialMutation,
-    pub expected_credential_revision: Revision,
    pub provider_material: ProviderDocument,
 }

 /// Provider 校验手工轮换材料时所需的非事务输入。
 pub struct PrepareCredentialRotation {
    pub account: AccountRecord,
-    pub expected_credential_revision: Revision,
    pub provider_material: ProviderDocument,
 }

@@ -452,10 +485,6 @@ impl fmt::Debug for PrepareCredentialRotation {
        formatter
            .debug_struct("PrepareCredentialRotation")
            .field("account", &self.account)
-            .field(
-                "expected_credential_revision",
-                &self.expected_credential_revision,
-            )
            .field("provider_material", &self.provider_material)
            .finish()
    }
@@ -467,6 +496,7 @@ pub struct PreparedCredentialRotationFacts {
    pub account_id: ProviderAccountId,
    pub provider_kind: ProviderKind,
    pub expected_credential_revision: Revision,
+    pub replacement_identity: Option<ProviderAccountIdentity>,
    pub name: String,
    pub email: Option<String>,
    pub plan_type: Option<String>,
@@ -520,7 +550,6 @@ impl fmt::Debug for PreparedCredentialRotation {
 /// Admin 交给 Store 的轮换或 refresh 事务命令。
 #[derive(Debug, Clone, PartialEq)]
 pub struct CredentialRotationCommit {
-    pub expected_config_revision: Revision,
    pub prepared: PreparedCredentialRotationFacts,
 }

@@ -529,10 +558,6 @@ impl fmt::Debug for RotateCredential {
        formatter
            .debug_struct("RotateCredential")
            .field("mutation", &self.mutation)
-            .field(
-                "expected_credential_revision",
-                &self.expected_credential_revision,
-            )
            .field("provider_material", &self.provider_material)
            .finish()
    }
@@ -39,7 +39,6 @@ pub struct RuntimeSettings {
 /// 原子替换运行设置的命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ReplaceRuntimeSettings {
-    pub expected_config_revision: Revision,
    pub model_mappings: ModelMappings,
    pub refresh_margin_seconds: u64,
    pub refresh_concurrency: u32,
@@ -64,6 +64,12 @@ pub trait ProviderAdmin: Send + Sync {
    /// 成功之后，不参与事务成败，也不得恢复或改写已经提交的账号状态。
    async fn account_unavailable(&self, account_id: &ProviderAccountId);

+    /// 账号资格事实已经由控制面提交，失效 Provider 持有的可重建派生状态。
+    ///
+    /// 该通知发生在 Store 事务成功之后、下一份 RuntimeSnapshot 编译之前；通知
+    /// 不参与已提交事务成败。没有账号派生状态的 Provider 可使用默认空实现。
+    async fn account_facts_changed(&self, _account_ids: &[ProviderAccountId]) {}
+
    /// 生成一次连接测试所需的 Provider-owned operation；Core 负责实际执行与落账。
    fn connection_test_operation(
        &self,
@@ -179,7 +179,7 @@ pub trait AuthStore: Send + Sync {
    async fn append_audit_event(&self, event: AdminAuditEvent) -> AdminStoreResult<()>;
 }

-/// Client API Key 管理及其 revision CAS 写入。
+/// Client API Key 管理写入。
 #[async_trait]
 pub trait ClientKeyStore: Send + Sync {
    async fn list_client_keys(&self, query: ClientKeyListQuery) -> AdminStoreResult<ClientKeyPage>;
@@ -265,7 +265,7 @@ pub trait ObservabilityStore: Send + Sync {
    async fn list_ops_errors(&self, query: OpsErrorQuery) -> AdminStoreResult<OpsErrorPage>;
 }

-/// Runtime settings 与管理员 API Key 的 revision CAS 写入。
+/// Runtime settings 与管理员 API Key 写入。
 #[async_trait]
 pub trait SettingsStore: Send + Sync {
    async fn load_runtime_settings(&self) -> AdminStoreResult<RuntimeSettings>;
@@ -280,14 +280,12 @@ pub trait SettingsStore: Send + Sync {

    async fn replace_admin_api_key(
        &self,
-        expected_config_revision: Revision,
        key: AdminApiKey,
        context: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation>;

    async fn delete_admin_api_key(
        &self,
-        expected_config_revision: Revision,
        context: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation>;
 }
@@ -15,7 +15,7 @@ use gateway_core::{

 use crate::{
    model::{
-        AdminError, MutationContext, Revision,
+        AdminError, MutationContext,
        accounts::{
            AccountConnectionTestEvent, AccountConnectionTestEventStream, AccountListQuery,
            AccountRecord, AccountStatus, AccountUsageWindowQuery,
@@ -54,7 +54,6 @@ pub trait AccountsService: Send + Sync {
    async fn refresh(
        &self,
        context: &MutationContext,
-        expected_config_revision: Revision,
        account_id: ProviderAccountId,
    ) -> Result<AccountRefreshResult, AdminError>;

@@ -354,7 +353,6 @@ impl AccountsService for DefaultAccountsService {
    async fn refresh(
        &self,
        context: &MutationContext,
-        expected_config_revision: Revision,
        account_id: ProviderAccountId,
    ) -> Result<AccountRefreshResult, AdminError> {
        let (account, provider) = self.provider_for_account(&account_id).await?;
@@ -367,12 +365,14 @@ impl AccountsService for DefaultAccountsService {
        validate_prepared_rotation(&account, &prepared, "provider credential refresh")?;
        let result = commit_credential_refresh(
            self.accounts.as_ref(),
-            expected_config_revision,
            prepared,
            context,
            "provider credential refresh",
        )
        .await?;
+        provider
+            .account_facts_changed(std::slice::from_ref(&result.account_id))
+            .await;
        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
        let account = self.load_directory_item(&result.account_id, false).await?;
        Ok(AccountRefreshResult {
@@ -452,12 +452,33 @@ impl AccountsService for DefaultAccountsService {
                        account_status: status,
                    }))
                    .collect(),
-                Err(error) => vec![AccountConnectionTestEvent::Failed {
-                    message: error.client_message().to_owned(),
-                    provider_error_code: error.client_error_code().map(ToOwned::to_owned),
-                    provider_error_type: error.client_error_type().map(ToOwned::to_owned),
-                    account_status: status,
-                }],
+                Err(error) => {
+                    let upstream_status = error
+                        .upstream_response()
+                        .map(gateway_core::engine::probe::AccountProbeUpstreamResponse::status);
+                    let upstream_content_type = error
+                        .upstream_response()
+                        .and_then(|response| response.content_type())
+                        .and_then(|value| std::str::from_utf8(value).ok())
+                        .map(ToOwned::to_owned);
+                    let upstream_body = error
+                        .upstream_response()
+                        .map(|response| String::from_utf8_lossy(response.body()).into_owned());
+                    let message = upstream_body
+                        .as_deref()
+                        .filter(|body| !body.is_empty())
+                        .unwrap_or_else(|| error.client_message())
+                        .to_owned();
+                    vec![AccountConnectionTestEvent::Failed {
+                        message,
+                        provider_error_code: error.client_error_code().map(ToOwned::to_owned),
+                        provider_error_type: error.client_error_type().map(ToOwned::to_owned),
+                        upstream_status,
+                        upstream_content_type,
+                        upstream_body,
+                        account_status: status,
+                    }]
+                }
            }
        })
        .flat_map(futures::stream::iter);
@@ -468,22 +489,25 @@ impl AccountsService for DefaultAccountsService {
 fn account_status(account: &AccountRecord, now: chrono::DateTime<Utc>) -> AccountStatus {
    if !account.enabled {
        AccountStatus::Disabled
+    } else if account.availability == crate::model::accounts::AccountAvailability::Banned {
+        AccountStatus::Banned
+    } else if account.availability == crate::model::accounts::AccountAvailability::QuotaExhausted
+        || (account.availability == crate::model::accounts::AccountAvailability::Cooldown
+            && account.availability_reason.as_deref() == Some("usage_limit_exhausted")
+            && account.cooldown_until.is_none_or(|until| until > now))
+    {
+        AccountStatus::QuotaExhausted
+    } else if matches!(
+        account.availability,
+        crate::model::accounts::AccountAvailability::Expired
+            | crate::model::accounts::AccountAvailability::Invalid
+    ) || account
+        .access_token_expires_at
+        .is_some_and(|expires_at| expires_at <= now)
+    {
+        AccountStatus::Expired
    } else {
-        match account.availability {
-            crate::model::accounts::AccountAvailability::Banned => AccountStatus::Banned,
-            crate::model::accounts::AccountAvailability::QuotaExhausted => {
-                AccountStatus::QuotaExhausted
-            }
-            crate::model::accounts::AccountAvailability::Expired
-            | crate::model::accounts::AccountAvailability::Invalid => AccountStatus::Expired,
-            _ if account
-                .access_token_expires_at
-                .is_some_and(|expires_at| expires_at <= now) =>
-            {
-                AccountStatus::Expired
-            }
-            _ => AccountStatus::Active,
-        }
+        AccountStatus::Active
    }
 }

@@ -94,7 +94,6 @@ impl ClientKeyService for DefaultClientKeyService {
            .store
            .create_client_key(
                NewClientKey {
-                    expected_config_revision: command.expected_config_revision,
                    id,
                    name: command.name,
                    label: command.label,
@@ -90,17 +90,10 @@ async fn pending_authorization(
    resource: &'static str,
 ) -> Result<PendingAuthorizationMutation, AdminError> {
    let target = match &command.reauthorization {
-        Some(target) => {
-            let details =
-                required_credential(accounts, provider_kind, &target.account_id, resource).await?;
-            if details.credential.credential_revision != target.credential_revision {
-                return Err(AdminError::conflict(format!(
-                    "{resource} reauthorization target is stale"
-                )));
-            }
+        Some(account_id) => {
+            required_credential(accounts, provider_kind, account_id, resource).await?;
            AuthorizationMutationTarget::Reauthorize {
-                account_id: target.account_id.clone(),
-                expected_credential_revision: target.credential_revision,
+                account_id: account_id.clone(),
            }
        }
        None => AuthorizationMutationTarget::Create {
@@ -108,7 +101,6 @@ async fn pending_authorization(
        },
    };
    Ok(PendingAuthorizationMutation::new(
-        command.expected_config_revision,
        provider_kind.clone(),
        target,
        crate::model::provider_credentials::AuthorizationOwnerBinding::from_context(
@@ -143,7 +135,6 @@ fn validate_prepared_rotation(
    let facts = prepared.facts();
    if facts.account_id.as_str() != account.id.as_str()
        || facts.provider_kind != account.provider_kind
-        || facts.expected_credential_revision != account.credential_revision
    {
        return Err(AdminError::conflict(format!(
            "{resource} prepared facts do not match the current credential"
@@ -152,18 +143,27 @@ fn validate_prepared_rotation(
    Ok(())
 }

-fn validate_authorization_commit(
+async fn validate_authorization_commit(
    provider_kind: &ProviderKind,
    context: &MutationContext,
-    prepared: &PreparedAuthorizationCommit,
+    prepared: PreparedAuthorizationCommit,
    resource: &'static str,
-) -> Result<(), AdminError> {
+) -> Result<PreparedAuthorizationCommit, AdminError> {
    if prepared.pending.provider_kind() != provider_kind
        || !prepared.pending.owner_binding().matches_context(context)
    {
-        return Err(AdminError::conflict(format!(
+        let validation_error = AdminError::conflict(format!(
            "{resource} pending authorization binding is invalid"
-        )));
+        ));
+        if let Err(error) = prepared.abort().await {
+            tracing::warn!(
+                resource,
+                settlement_error = %error,
+                "OAuth authorization claim release failed after preparation validation"
+            );
+            return Err(error);
+        }
+        return Err(validation_error);
    }
    let matches_target = match (prepared.pending.target(), &prepared.credential) {
        (
@@ -171,25 +171,29 @@ fn validate_authorization_commit(
            PreparedAuthorizationCredential::Create(credential),
        ) => credential.provider_kind == *provider_kind,
        (
-            AuthorizationMutationTarget::Reauthorize {
-                account_id,
-                expected_credential_revision,
-            },
+            AuthorizationMutationTarget::Reauthorize { account_id },
            PreparedAuthorizationCredential::Reauthorize(credential),
        ) => {
            let facts = credential.facts();
-            facts.provider_kind == *provider_kind
-                && facts.account_id == *account_id
-                && facts.expected_credential_revision == *expected_credential_revision
+            facts.provider_kind == *provider_kind && facts.account_id == *account_id
        }
        _ => false,
    };
    if !matches_target {
-        return Err(AdminError::conflict(format!(
+        let validation_error = AdminError::conflict(format!(
            "{resource} prepared credential does not match its pending target"
-        )));
+        ));
+        if let Err(error) = prepared.abort().await {
+            tracing::warn!(
+                resource,
+                settlement_error = %error,
+                "OAuth authorization claim release failed after preparation validation"
+            );
+            return Err(error);
+        }
+        return Err(validation_error);
    }
-    Ok(())
+    Ok(prepared)
 }

 async fn commit_authorization(
@@ -198,16 +202,34 @@ async fn commit_authorization(
    context: &MutationContext,
    resource: &'static str,
 ) -> Result<CredentialMutationResult, AdminError> {
-    let (command, guard) = prepared.into_commit();
+    let crate::model::provider_credentials::AuthorizationCommitSettlement {
+        command,
+        credential_guard,
+        authorization_guard,
+    } = prepared.into_commit();
    match accounts.commit_authorization(command, context).await {
        Ok(result) => {
-            if let Some(guard) = guard {
+            if let Some(guard) = credential_guard {
                guard.finish();
            }
+            if let Some(guard) = authorization_guard {
+                guard.commit().await?;
+            }
            Ok(result)
        }
        Err(error) => {
-            drop(guard);
+            drop(credential_guard);
+            if let Some(guard) = authorization_guard
+                && let Err(settlement_error) = guard.abort().await
+            {
+                tracing::warn!(
+                    resource,
+                    store_error = %error,
+                    settlement_error = %settlement_error,
+                    "OAuth authorization claim release failed after Store commit failure"
+                );
+                return Err(settlement_error);
+            }
            Err(map_store_error(error, resource))
        }
    }
@@ -215,20 +237,13 @@ async fn commit_authorization(

 async fn commit_credential_rotation(
    accounts: &dyn AccountStore,
-    expected_config_revision: crate::model::Revision,
    prepared: PreparedCredentialRotation,
    context: &MutationContext,
    resource: &'static str,
 ) -> Result<CredentialMutationResult, AdminError> {
    let (facts, guard) = prepared.into_parts();
    match accounts
-        .commit_credential_rotation(
-            CredentialRotationCommit {
-                expected_config_revision,
-                prepared: facts,
-            },
-            context,
-        )
+        .commit_credential_rotation(CredentialRotationCommit { prepared: facts }, context)
        .await
    {
        Ok(result) => {
@@ -244,20 +259,13 @@ async fn commit_credential_rotation(

 async fn commit_credential_refresh(
    accounts: &dyn AccountStore,
-    expected_config_revision: crate::model::Revision,
    prepared: PreparedCredentialRotation,
    context: &MutationContext,
    resource: &'static str,
 ) -> Result<CredentialMutationResult, AdminError> {
    let (facts, guard) = prepared.into_parts();
    match accounts
-        .commit_credential_refresh(
-            CredentialRotationCommit {
-                expected_config_revision,
-                prepared: facts,
-            },
-            context,
-        )
+        .commit_credential_refresh(CredentialRotationCommit { prepared: facts }, context)
        .await
    {
        Ok(result) => {
@@ -289,7 +297,6 @@ async fn set_credential_enabled(
    let revision = accounts
        .set_account_enabled(
            SetAccountEnabled {
-                expected_config_revision: command.expected_config_revision,
                account_id: account_id.as_str().to_owned(),
                enabled,
            },
@@ -300,6 +307,9 @@ async fn set_credential_enabled(
    if !enabled {
        provider.account_unavailable(&account_id).await;
    }
+    provider
+        .account_facts_changed(std::slice::from_ref(&account_id))
+        .await;
    Ok(CredentialMutationResult {
        config_revision: revision,
        account_id,
@@ -320,7 +330,6 @@ async fn delete_credentials(
    let revision = accounts
        .delete_accounts(
            DeleteAccounts {
-                expected_config_revision: command.expected_config_revision,
                account_ids: account_ids
                    .iter()
                    .map(|account_id| account_id.as_str().to_owned())
@@ -333,6 +342,7 @@ async fn delete_credentials(
    for account_id in &account_ids {
        provider.account_unavailable(account_id).await;
    }
+    provider.account_facts_changed(&account_ids).await;
    Ok(CredentialDeletionResult {
        config_revision: revision,
        account_ids,
@@ -428,6 +428,7 @@ fn recover_standard_costs(
        };
        let input = ProviderBillingInput {
            upstream_model_id: fact.upstream_model_id,
+            service_tier: fact.service_tier,
            input_tokens: fact.input_tokens,
            output_tokens: fact.output_tokens,
            cached_tokens: fact.cached_tokens,
@@ -491,14 +492,14 @@ impl DefaultObservabilityService {
        }
    }

-    /// 逐条尽力把 calculated 总额升级为完整分解；单条脏数据（非法 Provider kind
-    /// 或费用规则失败）只保留该条已存的总额，不影响整页返回。
+    /// 逐条尽力把可校验的总额升级为完整分解；单条脏数据（非法 Provider kind、
+    /// 不支持的来源或费用规则失败）只保留该条已存的总额，不影响整页返回。
    fn enrich_billing(&self, records: &mut [crate::model::observability::UsageRecord]) {
        for record in records {
            let Some(UsageBilling::Total { source, total }) = record.billing.as_ref() else {
                continue;
            };
-            if source != "calculated" {
+            if !matches!(source.as_str(), "calculated" | "provider_reported") {
                continue;
            }
            let (Some(provider), Some(upstream_model_id)) = (
@@ -512,6 +513,7 @@ impl DefaultObservabilityService {
            };
            let input = ProviderBillingInput {
                upstream_model_id: upstream_model_id.clone(),
+                service_tier: record.service_tier.clone(),
                input_tokens: record.input_tokens,
                output_tokens: record.output_tokens,
                cached_tokens: record.cached_tokens,
@@ -83,6 +83,27 @@ impl DefaultOpenAiService {
            snapshot,
        }
    }
+
+    async fn observe_initial_quotas(&self, account_ids: &[ProviderAccountId], request_id: &str) {
+        for account_id in account_ids {
+            if let Err(error) = self
+                .provider
+                .quota(ProviderQuotaRequest {
+                    account_id: account_id.clone(),
+                    refresh: true,
+                    rolling_usage: None,
+                })
+                .await
+            {
+                tracing::warn!(
+                    request_id,
+                    account_id = %account_id.as_str(),
+                    quota_error = ?error.kind(),
+                    "OpenAI initial quota observation failed"
+                );
+            }
+        }
+    }
 }

 #[async_trait]
@@ -112,7 +133,6 @@ impl OpenAiService for DefaultOpenAiService {
        command: ImportCredentials,
    ) -> Result<CredentialImportResult, AdminError> {
        let context = command.context;
-        let expected_config_revision = command.expected_config_revision;
        let prepared = self
            .provider
            .prepare_import(PrepareCredentialImport {
@@ -127,27 +147,16 @@ impl OpenAiService for DefaultOpenAiService {
        )?;
        let result = self
            .accounts
-            .commit_credential_import(
-                CredentialImportCommit {
-                    expected_config_revision,
-                    prepared,
-                },
-                &context,
-            )
+            .commit_credential_import(CredentialImportCommit { prepared }, &context)
            .await
            .map_err(|error| map_store_error(error, "OpenAI credential import"))?;
+        self.provider
+            .account_facts_changed(&result.credential_ids)
+            .await;
        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
-        // 导入已经提交，额度属于可重建观察事实；单个账号查询失败由周期任务重试。
-        for account_id in &result.credential_ids {
-            let _ = self
-                .provider
-                .quota(ProviderQuotaRequest {
-                    account_id: account_id.clone(),
-                    refresh: true,
-                    rolling_usage: None,
-                })
-                .await;
-        }
+        // 导入完成后立即做一次观察；失败不回滚已经提交的 credential。
+        self.observe_initial_quotas(&result.credential_ids, &context.request_id)
+            .await;
        Ok(result)
    }

@@ -178,12 +187,13 @@ impl OpenAiService for DefaultOpenAiService {
            .complete_authorization(command)
            .await
            .map_err(|error| map_provider_error(error, "OpenAI authorization"))?;
-        validate_authorization_commit(
+        let prepared = validate_authorization_commit(
            self.provider.provider_kind(),
            &context,
-            &prepared,
+            prepared,
            "OpenAI authorization",
-        )?;
+        )
+        .await?;
        let result = commit_authorization(
            self.accounts.as_ref(),
            prepared,
@@ -191,7 +201,15 @@ impl OpenAiService for DefaultOpenAiService {
            "OpenAI authorization",
        )
        .await?;
+        self.provider
+            .account_facts_changed(std::slice::from_ref(&result.account_id))
+            .await;
        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
+        self.observe_initial_quotas(
+            std::slice::from_ref(&result.account_id),
+            &context.request_id,
+        )
+        .await;
        Ok(result)
    }

@@ -200,7 +218,6 @@ impl OpenAiService for DefaultOpenAiService {
        command: RotateCredential,
    ) -> Result<CredentialMutationResult, AdminError> {
        let context = command.mutation.context;
-        let expected_config_revision = command.mutation.expected_config_revision;
        let account_id = command.mutation.account_id;
        let details = required_credential(
            self.accounts.as_ref(),
@@ -209,17 +226,11 @@ impl OpenAiService for DefaultOpenAiService {
            "OpenAI credential rotation",
        )
        .await?;
-        if details.credential.credential_revision != command.expected_credential_revision {
-            return Err(AdminError::conflict(
-                "OpenAI credential rotation revision is stale",
-            ));
-        }
        let account = details.credential;
        let prepared = self
            .provider
            .prepare_rotation(PrepareCredentialRotation {
                account: account.clone(),
-                expected_credential_revision: command.expected_credential_revision,
                provider_material: command.provider_material,
            })
            .await
@@ -227,12 +238,14 @@ impl OpenAiService for DefaultOpenAiService {
        validate_prepared_rotation(&account, &prepared, "OpenAI credential rotation")?;
        let result = commit_credential_rotation(
            self.accounts.as_ref(),
-            expected_config_revision,
            prepared,
            &context,
            "OpenAI credential rotation",
        )
        .await?;
+        self.provider
+            .account_facts_changed(std::slice::from_ref(&result.account_id))
+            .await;
        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
        Ok(result)
    }
@@ -86,13 +86,12 @@ impl SettingsService for DefaultSettingsService {
        &self,
        context: &MutationContext,
    ) -> Result<RegeneratedAdminApiKey, AdminError> {
-        let settings = self.load().await?;
        let mut bytes = [0_u8; 32];
        OsRng.fill_bytes(&mut bytes);
        let key = AdminApiKey::new(format!("admin-{}", hex::encode(bytes)));
        let mutation = self
            .store
-            .replace_admin_api_key(settings.config_revision, key.clone(), context)
+            .replace_admin_api_key(key.clone(), context)
            .await
            .map_err(|error| map_store_error(error, "administrator API key"))?;
        publish_committed(self.snapshot.as_ref(), mutation.config_revision).await?;
@@ -103,10 +102,9 @@ impl SettingsService for DefaultSettingsService {
        &self,
        context: &MutationContext,
    ) -> Result<AdminApiKeyMutation, AdminError> {
-        let settings = self.load().await?;
        let mutation = self
            .store
-            .delete_admin_api_key(settings.config_revision, context)
+            .delete_admin_api_key(context)
            .await
            .map_err(|error| map_store_error(error, "administrator API key"))?;
        publish_committed(self.snapshot.as_ref(), mutation.config_revision).await?;
@@ -89,7 +89,6 @@ impl XaiService for DefaultXaiService {
        command: ImportCredentials,
    ) -> Result<CredentialImportResult, AdminError> {
        let context = command.context;
-        let expected_config_revision = command.expected_config_revision;
        let prepared = self
            .provider
            .prepare_import(PrepareCredentialImport {
@@ -104,13 +103,7 @@ impl XaiService for DefaultXaiService {
        )?;
        let result = self
            .accounts
-            .commit_credential_import(
-                CredentialImportCommit {
-                    expected_config_revision,
-                    prepared,
-                },
-                &context,
-            )
+            .commit_credential_import(CredentialImportCommit { prepared }, &context)
            .await
            .map_err(|error| map_store_error(error, "xAI credential import"))?;
        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
@@ -155,12 +148,13 @@ impl XaiService for DefaultXaiService {
            .complete_authorization(command)
            .await
            .map_err(|error| map_provider_error(error, "xAI authorization"))?;
-        validate_authorization_commit(
+        let prepared = validate_authorization_commit(
            self.provider.provider_kind(),
            &context,
-            &prepared,
+            prepared,
            "xAI authorization",
-        )?;
+        )
+        .await?;
        let result = commit_authorization(
            self.accounts.as_ref(),
            prepared,
@@ -6,7 +6,7 @@ use futures::{StreamExt as _, future::BoxFuture};
 use gateway_core::{
    engine::{
        credential::{OpaqueProviderData, ProviderAccountId},
-        probe::{AccountProbe, AccountProbeRequest, AccountProbeResult},
+        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
    },
    error::{ClientVisibleUpstreamError, GatewayError, GatewayErrorKind},
    operation::{GenerateRequest, Operation, ProtocolPayload},
@@ -16,7 +16,7 @@ use gateway_core::{
 use gateway_admin::{
    AdminServices,
    model::{
-        MutationContext, Revision,
+        AdminError, MutationContext, Revision,
        accounts::{
            AccountAvailability, AccountConnectionTestEvent, AccountListQuery, AccountPage,
            AccountRecord, AccountSummary, AccountUsage, AccountUsageWindowQuery,
@@ -24,12 +24,12 @@ use gateway_admin::{
        },
        observability::TimeRange,
        provider_credentials::{
-            AuthorizationCommit, AuthorizationCredentialCommit, AuthorizationMutationTarget,
-            AuthorizationStarted, CompleteAuthorization, CredentialCommitGuard, CredentialDetails,
-            CredentialImportCommit, CredentialImportResult, CredentialListQuery,
-            CredentialMutationResult, CredentialPage, CredentialRotationCommit,
-            PendingAuthorizationMutation, PrepareCredentialImport, PrepareCredentialRefresh,
-            PrepareCredentialRotation, PreparedAuthorizationCommit,
+            AuthorizationCommit, AuthorizationCommitGuard, AuthorizationCredentialCommit,
+            AuthorizationMutationTarget, AuthorizationStarted, CompleteAuthorization,
+            CredentialCommitGuard, CredentialDetails, CredentialImportCommit,
+            CredentialImportResult, CredentialListQuery, CredentialMutationResult, CredentialPage,
+            CredentialRotationCommit, PendingAuthorizationMutation, PrepareCredentialImport,
+            PrepareCredentialRefresh, PrepareCredentialRotation, PreparedAuthorizationCommit,
            PreparedAuthorizationCredential, PreparedCredentialCreate, PreparedCredentialImport,
            PreparedCredentialRotation, PreparedCredentialRotationFacts, ProviderDocument,
            ProviderExport, ProviderExportCredentialInput, ProviderModels, ProviderQuota,
@@ -58,11 +58,13 @@ pub(super) struct FakeProviderAdmin {
    events: EventLog,
    failure: Mutex<Option<ProviderAdminErrorKind>>,
    quota_failure: Mutex<Option<ProviderAdminErrorKind>>,
-    pending: Mutex<Option<PendingAuthorizationMutation>>,
+    pending: Arc<Mutex<Option<PendingAuthorizationMutation>>>,
+    retry_authorization_after_abort: Mutex<bool>,
    export_inputs: Mutex<Vec<ProviderExportCredentialInput>>,
    import_account_ids: Mutex<Vec<String>>,
    quota_requests: Mutex<Vec<ProviderQuotaRequest>>,
    quota: Mutex<ProviderQuota>,
+    current_credential_revision: Mutex<Revision>,
 }

 impl FakeProviderAdmin {
@@ -72,11 +74,13 @@ impl FakeProviderAdmin {
            events,
            failure: Mutex::new(None),
            quota_failure: Mutex::new(None),
-            pending: Mutex::new(None),
+            pending: Arc::new(Mutex::new(None)),
+            retry_authorization_after_abort: Mutex::new(false),
            export_inputs: Mutex::new(Vec::new()),
            import_account_ids: Mutex::new(vec!["acct_prepared".to_owned()]),
            quota_requests: Mutex::new(Vec::new()),
            quota: Mutex::new(empty_quota()),
+            current_credential_revision: Mutex::new(revision(1)),
        })
    }

@@ -113,6 +117,20 @@ impl FakeProviderAdmin {
        self.pending.lock().expect("pending authorization").clone()
    }

+    pub(super) fn retry_authorization_after_abort(&self) {
+        *self
+            .retry_authorization_after_abort
+            .lock()
+            .expect("authorization retry") = true;
+    }
+
+    pub(super) fn set_current_credential_revision(&self, revision: Revision) {
+        *self
+            .current_credential_revision
+            .lock()
+            .expect("current credential revision") = revision;
+    }
+
    fn export_inputs(&self) -> Vec<ProviderExportCredentialInput> {
        self.export_inputs.lock().expect("export inputs").clone()
    }
@@ -133,7 +151,11 @@ impl FakeProviderAdmin {
            PreparedCredentialRotationFacts {
                account_id: ProviderAccountId::new(account.id.clone()).expect("account ID"),
                provider_kind: account.provider_kind.clone(),
-                expected_credential_revision: account.credential_revision,
+                expected_credential_revision: *self
+                    .current_credential_revision
+                    .lock()
+                    .expect("current credential revision"),
+                replacement_identity: None,
                name: account.name.clone(),
                email: account.email.clone(),
                plan_type: account.plan_type.clone(),
@@ -159,6 +181,10 @@ impl ProviderAdmin for FakeProviderAdmin {
        self.record("provider.account_unavailable");
    }

+    async fn account_facts_changed(&self, _: &[ProviderAccountId]) {
+        self.record("provider.account_facts_changed");
+    }
+
    fn connection_test_operation(
        &self,
        model: &gateway_core::routing::UpstreamModelId,
@@ -246,23 +272,31 @@ impl ProviderAdmin for FakeProviderAdmin {
        if !pending.owner_binding().matches_context(&command.context) {
            return Err(ProviderAdminError::new(ProviderAdminErrorKind::NotFound));
        }
+        let retry_pending = (*self
+            .retry_authorization_after_abort
+            .lock()
+            .expect("authorization retry"))
+        .then(|| pending.clone());
        let credential = match pending.target() {
            AuthorizationMutationTarget::Create { name } => {
                PreparedAuthorizationCredential::Create(prepared_create(self.kind.clone(), name))
            }
-            AuthorizationMutationTarget::Reauthorize {
-                account_id,
-                expected_credential_revision,
-            } => {
+            AuthorizationMutationTarget::Reauthorize { account_id } => {
                let mut account = account_record(self.kind.as_str());
                account.id = account_id.as_str().to_owned();
-                account.credential_revision = *expected_credential_revision;
                PreparedAuthorizationCredential::Reauthorize(self.prepared_rotation(&account))
            }
        };
-        Ok(PreparedAuthorizationCommit {
-            pending,
-            credential,
+        let prepared = PreparedAuthorizationCommit::new(pending, credential);
+        Ok(match retry_pending {
+            Some(pending) => {
+                prepared.with_authorization_guard(Box::new(RetryableAuthorizationGuard::new(
+                    self.events.clone(),
+                    Arc::clone(&self.pending),
+                    pending,
+                )))
+            }
+            None => prepared,
        })
    }

@@ -342,18 +376,20 @@ pub(super) struct FakeAccountStore {
    account: AccountRecord,
    fail_commit: Mutex<bool>,
    audit_requests: Mutex<Vec<String>>,
-    authorization_revision: Mutex<Option<Revision>>,
    quota_window_usage: Mutex<Vec<AccountUsageWindowResult>>,
 }

 impl FakeAccountStore {
    pub(super) fn new(kind: &str, events: EventLog) -> Arc<Self> {
+        Self::with_account(account_record(kind), events)
+    }
+
+    fn with_account(account: AccountRecord, events: EventLog) -> Arc<Self> {
        Arc::new(Self {
            events,
-            account: account_record(kind),
+            account,
            fail_commit: Mutex::new(false),
            audit_requests: Mutex::new(Vec::new()),
-            authorization_revision: Mutex::new(None),
            quota_window_usage: Mutex::new(Vec::new()),
        })
    }
@@ -366,13 +402,6 @@ impl FakeAccountStore {
        self.audit_requests.lock().expect("audit requests").clone()
    }

-    pub(super) fn authorization_revision(&self) -> Option<Revision> {
-        *self
-            .authorization_revision
-            .lock()
-            .expect("authorization revision")
-    }
-
    pub(super) fn set_quota_window_usage(&self, usage: Vec<AccountUsageWindowResult>) {
        *self.quota_window_usage.lock().expect("quota window usage") = usage;
    }
@@ -519,10 +548,6 @@ impl AccountStore for FakeAccountStore {
    ) -> AdminStoreResult<CredentialMutationResult> {
        self.record("store.commit_authorization");
        self.record_context(context);
-        *self
-            .authorization_revision
-            .lock()
-            .expect("authorization revision") = Some(command.pending.expected_config_revision());
        self.require_commit()?;
        let (account_id, credential_revision) = match command.credential {
            AuthorizationCredentialCommit::Create(credential) => (credential.account_id, None),
@@ -627,7 +652,6 @@ impl SettingsStore for StaticSettingsStore {

    async fn replace_admin_api_key(
        &self,
-        _: Revision,
        _: AdminApiKey,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -636,7 +660,6 @@ impl SettingsStore for StaticSettingsStore {

    async fn delete_admin_api_key(
        &self,
-        _: Revision,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
        Err(store_unavailable())
@@ -675,6 +698,51 @@ impl Drop for RecordingGuard {
    }
 }

+struct RetryableAuthorizationGuard {
+    events: EventLog,
+    pending: Arc<Mutex<Option<PendingAuthorizationMutation>>>,
+    authorization: PendingAuthorizationMutation,
+}
+
+impl RetryableAuthorizationGuard {
+    fn new(
+        events: EventLog,
+        pending: Arc<Mutex<Option<PendingAuthorizationMutation>>>,
+        authorization: PendingAuthorizationMutation,
+    ) -> Self {
+        Self {
+            events,
+            pending,
+            authorization,
+        }
+    }
+}
+
+#[async_trait]
+impl AuthorizationCommitGuard for RetryableAuthorizationGuard {
+    async fn commit(self: Box<Self>) -> Result<(), AdminError> {
+        self.events
+            .lock()
+            .expect("authorization guard events")
+            .push("authorization_guard.commit");
+        Ok(())
+    }
+
+    async fn abort(self: Box<Self>) -> Result<(), AdminError> {
+        let Self {
+            events,
+            pending,
+            authorization,
+        } = *self;
+        *pending.lock().expect("pending authorization") = Some(authorization);
+        events
+            .lock()
+            .expect("authorization guard events")
+            .push("authorization_guard.abort");
+        Ok(())
+    }
+}
+
 #[test]
 fn provider_registry_should_resolve_custom_kind_without_central_match() {
    let provider = FakeProviderAdmin::new("custom-provider", events());
@@ -701,9 +769,11 @@ fn provider_registry_should_reject_duplicate_kind() {
 }

 #[tokio::test]
-async fn connection_test_should_preserve_safe_provider_error_details() {
+async fn connection_test_should_probe_unavailable_account() {
    let provider = FakeProviderAdmin::new("xai", events());
-    let store = FakeAccountStore::new("xai", events());
+    let mut account = account_record("xai");
+    account.availability = AccountAvailability::QuotaExhausted;
+    let store = FakeAccountStore::with_account(account, events());
    let services =
        accounts_service_with_probe(provider, store, Arc::new(FailingAccountProbe)).await;

@@ -724,6 +794,7 @@ async fn connection_test_should_preserve_safe_provider_error_details() {
            message,
            provider_error_code: Some(code),
            provider_error_type: Some(error_type),
+            account_status: gateway_admin::model::accounts::AccountStatus::QuotaExhausted,
            ..
        }) if message == "included usage exhausted"
            && code == "usage_exhausted"
@@ -731,6 +802,35 @@ async fn connection_test_should_preserve_safe_provider_error_details() {
    ));
 }

+#[tokio::test]
+async fn connection_test_should_preserve_disabled_account_status() {
+    let provider = FakeProviderAdmin::new("xai", events());
+    let mut account = account_record("xai");
+    account.enabled = false;
+    let store = FakeAccountStore::with_account(account, events());
+    let services =
+        accounts_service_with_probe(provider, store, Arc::new(FailingAccountProbe)).await;
+
+    let events = services
+        .accounts()
+        .test_connection(
+            ProviderAccountId::new("acct_test").expect("account ID"),
+            gateway_core::routing::UpstreamModelId::new("grok-4.5").expect("model"),
+        )
+        .await
+        .expect("connection test stream")
+        .collect::<Vec<_>>()
+        .await;
+
+    assert!(matches!(
+        events.last(),
+        Some(AccountConnectionTestEvent::Failed {
+            account_status: gateway_admin::model::accounts::AccountStatus::Disabled,
+            ..
+        })
+    ));
+}
+
 #[tokio::test]
 async fn accounts_export_should_pass_store_loaded_timestamps_and_material_to_provider() {
    let provider = FakeProviderAdmin::new("openai", events());
@@ -769,7 +869,6 @@ async fn accounts_refresh_should_keep_guard_through_store_commit() {
        .accounts()
        .refresh(
            &context("refresh-request"),
-            revision(1),
            ProviderAccountId::new("acct_test").expect("account ID"),
        )
        .await
@@ -788,6 +887,7 @@ async fn accounts_refresh_should_keep_guard_through_store_commit() {
            "provider.prepare_refresh",
            "store.commit_refresh",
            "guard.finish",
+            "provider.account_facts_changed",
            "store.load_account",
        ]
    );
@@ -822,6 +922,36 @@ async fn accounts_list_should_return_complete_directory_semantics() {
    );
 }

+#[tokio::test]
+async fn accounts_list_should_prefer_usage_limit_exhaustion_over_stale_token_expiry() {
+    let provider = FakeProviderAdmin::new("openai", events());
+    let mut account = account_record("openai");
+    account.availability = AccountAvailability::Cooldown;
+    account.availability_reason = Some("usage_limit_exhausted".to_owned());
+    account.cooldown_until = Some(Utc::now() + TimeDelta::minutes(5));
+    account.access_token_expires_at = Some(Utc::now() - TimeDelta::minutes(5));
+    let store = FakeAccountStore::with_account(account, events());
+
+    let page = accounts_service(provider, store)
+        .await
+        .accounts()
+        .list(AccountListQuery {
+            page: 1,
+            page_size: gateway_admin::model::PageSize::new(20).expect("page size"),
+            provider_kind: None,
+            search: None,
+            status: None,
+            sort: None,
+        })
+        .await
+        .expect("usage-limited account directory");
+
+    assert_eq!(
+        page.items.first().expect("account item").status,
+        gateway_admin::model::accounts::AccountStatus::QuotaExhausted,
+    );
+}
+
 #[tokio::test]
 async fn accounts_list_should_attach_local_usage_to_quota_windows() {
    let provider = FakeProviderAdmin::new("openai", events());
@@ -882,7 +1012,6 @@ async fn accounts_refresh_provider_failure_should_not_call_store_commit() {
        .accounts()
        .refresh(
            &context("refresh-provider-error"),
-            revision(1),
            ProviderAccountId::new("acct_test").expect("account ID"),
        )
        .await
@@ -895,7 +1024,7 @@ async fn accounts_refresh_provider_failure_should_not_call_store_commit() {
 }

 #[tokio::test]
-async fn accounts_refresh_store_failure_should_drop_guard_after_cas_attempt() {
+async fn accounts_refresh_store_failure_should_drop_guard_after_commit_attempt() {
    let events = events();
    let provider = FakeProviderAdmin::new("openai", events.clone());
    let store = FakeAccountStore::new("openai", events.clone());
@@ -906,11 +1035,10 @@ async fn accounts_refresh_store_failure_should_drop_guard_after_cas_attempt() {
        .accounts()
        .refresh(
            &context("refresh-store-error"),
-            revision(1),
            ProviderAccountId::new("acct_test").expect("account ID"),
        )
        .await
-        .expect_err("Store CAS must fail");
+        .expect_err("Store commit must fail");

    assert_eq!(
        recorded(&events),
@@ -1039,7 +1167,7 @@ fn prepared_create_with_id(

 fn rotation_result(command: CredentialRotationCommit) -> CredentialMutationResult {
    CredentialMutationResult {
-        config_revision: revision(command.expected_config_revision.get() + 1),
+        config_revision: revision(2),
        account_id: command.prepared.account_id,
        credential_revision: Some(revision(
            command.prepared.expected_credential_revision.get() + 1,
@@ -1074,7 +1202,7 @@ impl AccountProbe for SuccessfulAccountProbe {
    fn probe(
        &self,
        _: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>> {
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
        Box::pin(async {
            Ok(AccountProbeResult {
                text: vec!["OK".to_owned()],
@@ -1089,19 +1217,19 @@ impl AccountProbe for FailingAccountProbe {
    fn probe(
        &self,
        _: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>> {
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
        Box::pin(async {
            let detail = ClientVisibleUpstreamError::new(
                "included usage exhausted",
                Some("usage_exhausted".to_owned()),
                Some("invalid_request_error".to_owned()),
-            )
-            .expect("safe provider error");
+            );
            Err(GatewayError::new(
                GatewayErrorKind::RateLimited,
                "upstream capacity is temporarily unavailable",
            )
-            .with_client_visible_upstream_error(detail))
+            .with_client_visible_upstream_error(detail)
+            .into())
        })
    }
 }
@@ -60,7 +60,7 @@ use gateway_admin::{
 use gateway_core::{
    engine::{
        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeRequest, AccountProbeResult},
+        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
    },
    error::{GatewayError, GatewayErrorKind},
    policy::ClientApiKeyId,
@@ -449,7 +449,6 @@ impl SettingsStore for UnavailableStore {

    async fn replace_admin_api_key(
        &self,
-        _: Revision,
        _: AdminApiKey,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -458,7 +457,6 @@ impl SettingsStore for UnavailableStore {

    async fn delete_admin_api_key(
        &self,
-        _: Revision,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
        Err(unavailable("admin API key"))
@@ -649,12 +647,13 @@ impl AccountProbe for UnavailableProbe {
    fn probe(
        &self,
        _: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>> {
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
        Box::pin(async {
            Err(GatewayError::new(
                GatewayErrorKind::Internal,
                "test account probe is unavailable",
-            ))
+            )
+            .into())
        })
    }
 }
@@ -249,6 +249,7 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
        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),
@@ -326,9 +327,19 @@ async fn usage_records_should_tolerate_records_that_fail_billing_enrichment() {
    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
    let invalid_kind = "x".repeat(65);
    store.replace_usage_records(vec![
-        calculated_total_record("request_invalid_kind", Some(&invalid_kind), now),
-        calculated_total_record("request_unregistered_kind", Some("anthropic"), now),
-        calculated_total_record("request_enriched", Some("openai"), now),
+        total_record(
+            "request_invalid_kind",
+            Some(&invalid_kind),
+            "calculated",
+            now,
+        ),
+        total_record(
+            "request_unregistered_kind",
+            Some("anthropic"),
+            "calculated",
+            now,
+        ),
+        total_record("request_enriched", Some("openai"), "calculated", now),
    ]);
    let services = observability_services_with_calculated_billing(store).await;

@@ -353,6 +364,30 @@ async fn usage_records_should_tolerate_records_that_fail_billing_enrichment() {
    );
 }

+#[tokio::test]
+async fn usage_records_should_enrich_provider_reported_totals_when_pricing_matches() {
+    let now = Utc::now();
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
+    store.replace_usage_records(vec![total_record(
+        "request_provider_reported",
+        Some("openai"),
+        "provider_reported",
+        now,
+    )]);
+    let services = observability_services_with_calculated_billing(store).await;
+
+    let page = services
+        .observability()
+        .usage_records(usage_query(now))
+        .await
+        .expect("usage records");
+
+    assert!(matches!(
+        page.items[0].billing,
+        Some(UsageBilling::Calculated(_))
+    ));
+}
+
 struct FixtureObservabilityStore {
    trend: Mutex<Vec<RequestMetricPoint>>,
    overview: Mutex<UsageOverview>,
@@ -518,7 +553,6 @@ impl SettingsStore for FixtureSettingsStore {

    async fn replace_admin_api_key(
        &self,
-        _: Revision,
        _: AdminApiKey,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -527,7 +561,6 @@ impl SettingsStore for FixtureSettingsStore {

    async fn delete_admin_api_key(
        &self,
-        _: Revision,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
        Err(super::unavailable("admin API key"))
@@ -568,9 +601,10 @@ fn usage_query(now: DateTime<Utc>) -> UsageQuery {
    }
 }

-fn calculated_total_record(
+fn total_record(
    id: &str,
    provider_kind: Option<&str>,
+    source: &str,
    now: DateTime<Utc>,
 ) -> UsageRecord {
    UsageRecord {
@@ -591,6 +625,7 @@ fn calculated_total_record(
        upstream_transport: None,
        http_version: None,
        websocket_pool: None,
+        service_tier: None,
        provider_metadata_json: None,
        attempt_count: 1,
        upstream_send_state: "sent".to_owned(),
@@ -613,11 +648,11 @@ fn calculated_total_record(
        image_input_tokens: None,
        image_output_tokens: None,
        total_tokens: Some(1_000),
-        cost_source: "calculated".to_owned(),
+        cost_source: source.to_owned(),
        cost_amount: None,
        cost_currency: None,
        billing: Some(UsageBilling::Total {
-            source: "calculated".to_owned(),
+            source: source.to_owned(),
            total: CurrencyCost {
                currency: "USD".to_owned(),
                amount: gateway_admin::model::observability::DecimalAmount::from_str("1.25")
@@ -6,7 +6,7 @@ use gateway_admin::{
    AdminServices,
    model::provider_credentials::{
        AuthorizationMutationTarget, CompleteAuthorization, CredentialDeletion, CredentialMutation,
-        ImportCredentials, ProviderQuotaRequest, ReauthorizationTarget, StartAuthorization,
+        ImportCredentials, ProviderQuotaRequest, StartAuthorization,
    },
    ports::provider::ProviderAdminErrorKind,
 };
@@ -30,7 +30,11 @@ async fn openai_enable_should_use_scoped_store_without_provider_mutation() {

    assert_eq!(
        recorded(&events),
-        ["store.credential_details", "store.set_enabled"]
+        [
+            "store.credential_details",
+            "store.set_enabled",
+            "provider.account_facts_changed",
+        ]
    );
    assert_eq!(store.audit_requests(), ["request-openai"]);
 }
@@ -54,6 +58,7 @@ async fn openai_disable_should_commit_then_release_provider_resources() {
            "store.credential_details",
            "store.set_enabled",
            "provider.account_unavailable",
+            "provider.account_facts_changed",
        ]
    );
    assert_eq!(store.audit_requests(), ["request-openai"]);
@@ -78,6 +83,7 @@ async fn openai_delete_should_commit_then_release_provider_resources() {
            "store.credential_details",
            "store.delete",
            "provider.account_unavailable",
+            "provider.account_facts_changed",
        ]
    );
    assert_eq!(store.audit_requests(), ["request-openai"]);
@@ -114,7 +120,6 @@ async fn openai_import_should_prepare_before_atomic_store_commit() {
        .openai()
        .import_document(ImportCredentials {
            context: context("import-openai"),
-            expected_config_revision: revision(1),
            document: document(),
        })
        .await
@@ -125,6 +130,7 @@ async fn openai_import_should_prepare_before_atomic_store_commit() {
        [
            "provider.prepare_import",
            "store.commit_import",
+            "provider.account_facts_changed",
            "provider.quota",
        ]
    );
@@ -151,7 +157,6 @@ async fn openai_import_should_refresh_quota_for_every_imported_account() {
        .openai()
        .import_document(ImportCredentials {
            context: context("import-openai-batch"),
-            expected_config_revision: revision(1),
            document: document(),
        })
        .await
@@ -193,7 +198,6 @@ async fn openai_import_should_remain_successful_when_quota_refresh_fails() {
        .openai()
        .import_document(ImportCredentials {
            context: context("import-openai-quota-failure"),
-            expected_config_revision: revision(1),
            document: document(),
        })
        .await
@@ -206,6 +210,135 @@ async fn openai_import_should_remain_successful_when_quota_refresh_fails() {
    assert_eq!(provider.quota_requests().len(), 1);
 }

+#[tokio::test]
+async fn openai_authorization_create_should_observe_initial_quota() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    let store = FakeAccountStore::new("openai", events.clone());
+    let services = service(provider.clone(), store.clone()).await;
+
+    services
+        .openai()
+        .start_authorization(StartAuthorization {
+            context: context("oauth-start-openai-create"),
+            name: "new OpenAI credential".to_owned(),
+            reauthorization: None,
+        })
+        .await
+        .expect("start authorization");
+    services
+        .openai()
+        .complete_authorization(CompleteAuthorization {
+            context: context("oauth-start-openai-create"),
+            flow_id: "flow-test".to_owned(),
+            callback_url: "http://localhost/callback?code=test&state=test".to_owned(),
+        })
+        .await
+        .expect("complete authorization");
+
+    assert_eq!(
+        recorded(&events),
+        [
+            "provider.start_authorization",
+            "provider.complete_authorization",
+            "store.commit_authorization",
+            "provider.account_facts_changed",
+            "provider.quota",
+        ]
+    );
+    assert_eq!(
+        provider.quota_requests(),
+        [ProviderQuotaRequest {
+            account_id: ProviderAccountId::new("acct_prepared").expect("account ID"),
+            refresh: true,
+            rolling_usage: None,
+        }]
+    );
+    assert_eq!(store.audit_requests(), ["oauth-start-openai-create"]);
+}
+
+#[tokio::test]
+async fn openai_authorization_create_should_remain_successful_when_initial_quota_fails() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    provider.fail_next_quota(ProviderAdminErrorKind::Unavailable);
+    let store = FakeAccountStore::new("openai", events);
+    let services = service(provider.clone(), store).await;
+
+    services
+        .openai()
+        .start_authorization(StartAuthorization {
+            context: context("oauth-start-openai-quota-failure"),
+            name: "new OpenAI credential".to_owned(),
+            reauthorization: None,
+        })
+        .await
+        .expect("start authorization");
+    let result = services
+        .openai()
+        .complete_authorization(CompleteAuthorization {
+            context: context("oauth-start-openai-quota-failure"),
+            flow_id: "flow-test".to_owned(),
+            callback_url: "http://localhost/callback?code=test&state=test".to_owned(),
+        })
+        .await
+        .expect("quota observation must not fail authorization");
+
+    assert_eq!(result.account_id.as_str(), "acct_prepared");
+    assert_eq!(provider.quota_requests().len(), 1);
+}
+
+#[tokio::test]
+async fn openai_authorization_store_failure_should_release_claim_for_retry() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    provider.retry_authorization_after_abort();
+    let store = FakeAccountStore::new("openai", events.clone());
+    store.fail_next_commit();
+    let services = service(provider.clone(), store).await;
+    let command = || CompleteAuthorization {
+        context: context("oauth-store-retry"),
+        flow_id: "flow-test".to_owned(),
+        callback_url: "http://localhost/callback?code=test&state=test".to_owned(),
+    };
+
+    services
+        .openai()
+        .start_authorization(StartAuthorization {
+            context: context("oauth-store-retry"),
+            name: "new OpenAI credential".to_owned(),
+            reauthorization: None,
+        })
+        .await
+        .expect("start authorization");
+    services
+        .openai()
+        .complete_authorization(command())
+        .await
+        .expect_err("Store commit must fail");
+    services
+        .openai()
+        .complete_authorization(command())
+        .await
+        .expect("released claim must permit retry");
+
+    assert_eq!(
+        recorded(&events),
+        [
+            "provider.start_authorization",
+            "provider.complete_authorization",
+            "store.commit_authorization",
+            "authorization_guard.abort",
+            "provider.complete_authorization",
+            "store.commit_authorization",
+            "authorization_guard.commit",
+            "provider.account_facts_changed",
+            "provider.quota",
+        ]
+    );
+    assert!(provider.pending().is_none());
+}
+
 #[tokio::test]
 async fn openai_import_provider_error_should_not_touch_store_transaction() {
    let events = events();
@@ -218,7 +351,6 @@ async fn openai_import_provider_error_should_not_touch_store_transaction() {
        .openai()
        .import_document(ImportCredentials {
            context: context("import-openai-error"),
-            expected_config_revision: revision(1),
            document: document(),
        })
        .await
@@ -228,7 +360,7 @@ async fn openai_import_provider_error_should_not_touch_store_transaction() {
 }

 #[tokio::test]
-async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_through_commit() {
+async fn openai_reauthorization_should_commit_after_credential_revision_advances() {
    let events = events();
    let provider = FakeProviderAdmin::new("openai", events.clone());
    let store = FakeAccountStore::new("openai", events.clone());
@@ -237,18 +369,13 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
        .openai()
        .start_authorization(StartAuthorization {
            context: context("oauth-start-openai"),
-            expected_config_revision: revision(7),
            name: "reauthorize".to_owned(),
-            reauthorization: Some(ReauthorizationTarget {
-                account_id: ProviderAccountId::new("acct_test").expect("account ID"),
-                credential_revision: revision(1),
-            }),
+            reauthorization: Some(ProviderAccountId::new("acct_test").expect("account ID")),
        })
        .await
        .expect("start reauthorization");

    let pending = provider.pending().expect("pending envelope");
-    assert_eq!(pending.expected_config_revision(), revision(7));
    assert_eq!(pending.provider_kind().as_str(), "openai");
    assert_eq!(
        pending.owner_binding().started_request_id(),
@@ -256,15 +383,14 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
    );
    assert!(matches!(
        pending.target(),
-        AuthorizationMutationTarget::Reauthorize {
-            account_id,
-            expected_credential_revision,
-        } if account_id.as_str() == "acct_test"
-            && *expected_credential_revision == revision(1)
+        AuthorizationMutationTarget::Reauthorize { account_id }
+            if account_id.as_str() == "acct_test"
    ));
    assert!(!format!("{pending:?}").contains("admin-test"));

-    services
+    provider.set_current_credential_revision(revision(2));
+
+    let result = services
        .openai()
        .complete_authorization(CompleteAuthorization {
            context: context("oauth-complete-openai"),
@@ -274,6 +400,8 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
        .await
        .expect("complete reauthorization");

+    assert_eq!(result.credential_revision, Some(revision(3)));
+
    assert_eq!(
        recorded(&events),
        [
@@ -282,9 +410,11 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
            "provider.complete_authorization",
            "store.commit_authorization",
            "guard.finish",
+            "provider.account_facts_changed",
+            "provider.quota",
        ]
    );
-    assert_eq!(store.authorization_revision(), Some(revision(7)));
+    assert_eq!(provider.quota_requests().len(), 1);
    assert_eq!(store.audit_requests(), ["oauth-complete-openai"]);
 }

@@ -299,7 +429,6 @@ async fn service(provider: Arc<FakeProviderAdmin>, store: Arc<FakeAccountStore>)
 fn mutation(account_id: &str) -> CredentialMutation {
    CredentialMutation {
        context: context("request-openai"),
-        expected_config_revision: revision(1),
        account_id: ProviderAccountId::new(account_id).expect("account ID"),
    }
 }
@@ -307,7 +436,6 @@ fn mutation(account_id: &str) -> CredentialMutation {
 fn deletion(account_id: &str) -> CredentialDeletion {
    CredentialDeletion {
        context: context("request-openai"),
-        expected_config_revision: revision(1),
        account_ids: vec![ProviderAccountId::new(account_id).expect("account ID")],
    }
 }
@@ -2,7 +2,7 @@ use async_trait::async_trait;

 use gateway_admin::{
    model::{
-        AdminErrorKind, MutationContext, Revision,
+        AdminErrorKind, MutationContext,
        settings::{
            AdminApiKey, AdminApiKeyMutation, ReplaceRuntimeSettings, RotationStrategy,
            RuntimeSettings,
@@ -33,7 +33,6 @@ impl SettingsStore for UnusedSettingsStore {

    async fn replace_admin_api_key(
        &self,
-        _: Revision,
        _: AdminApiKey,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -42,7 +41,6 @@ impl SettingsStore for UnusedSettingsStore {

    async fn delete_admin_api_key(
        &self,
-        _: Revision,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
        Err(unused())
@@ -63,7 +61,6 @@ async fn settings_should_reject_zero_refresh_margin_before_store_call() {
                request_id: "request-settings".to_owned(),
            },
            ReplaceRuntimeSettings {
-                expected_config_revision: Revision::new(1).expect("revision"),
                model_mappings: Default::default(),
                refresh_margin_seconds: 0,
                refresh_concurrency: 1,
@@ -8,9 +8,7 @@ use gateway_admin::{
    ports::provider::ProviderAdminErrorKind,
 };

-use super::accounts::{
-    FakeAccountStore, FakeProviderAdmin, context, document, events, recorded, revision,
-};
+use super::accounts::{FakeAccountStore, FakeProviderAdmin, context, document, events, recorded};

 #[tokio::test]
 async fn xai_disable_should_commit_then_notify_the_stateless_provider() {
@@ -31,6 +29,7 @@ async fn xai_disable_should_commit_then_notify_the_stateless_provider() {
            "store.credential_details",
            "store.set_enabled",
            "provider.account_unavailable",
+            "provider.account_facts_changed",
        ]
    );
    assert_eq!(store.audit_requests(), ["request-xai"]);
@@ -47,7 +46,6 @@ async fn xai_import_should_prepare_before_atomic_store_commit() {
        .xai()
        .import_document(ImportCredentials {
            context: context("import-xai"),
-            expected_config_revision: revision(3),
            document: document(),
        })
        .await
@@ -84,7 +82,6 @@ async fn xai_import_should_refresh_quota_for_every_imported_account() {
        .xai()
        .import_document(ImportCredentials {
            context: context("import-xai-batch"),
-            expected_config_revision: revision(1),
            document: document(),
        })
        .await
@@ -119,7 +116,6 @@ async fn xai_import_should_remain_successful_when_quota_refresh_fails() {
        .xai()
        .import_document(ImportCredentials {
            context: context("import-xai-quota-failure"),
-            expected_config_revision: revision(1),
            document: document(),
        })
        .await
@@ -140,7 +136,6 @@ async fn service(provider: Arc<FakeProviderAdmin>, store: Arc<FakeAccountStore>)
 fn mutation(account_id: &str) -> CredentialMutation {
    CredentialMutation {
        context: context("request-xai"),
-        expected_config_revision: revision(1),
        account_id: ProviderAccountId::new(account_id).expect("account ID"),
    }
 }
@@ -13,7 +13,7 @@ path = "tests/main.rs"

 [dependencies]
 axum = { version = "0.8.9", default-features = false, features = ["json", "query", "ws"] }
-base64 = "0.22.1"
+base64 = "0.23.0"
 bytes = "1.11.1"
 chrono = { version = "0.4.45", features = ["serde"] }
 futures = "0.3.32"
@@ -21,7 +21,7 @@ gateway-admin = { path = "../gateway-admin" }
 gateway-core = { path = "../gateway-core" }
 gateway-protocol = { path = "../gateway-protocol" }
 serde = { version = "1.0.228", features = ["derive"] }
-serde_json = { version = "1.0.150", features = ["preserve_order"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 thiserror = "2.0.18"
 tokio = { version = "1.52.3", default-features = false, features = ["macros", "time"] }
 tower-http = { version = "0.7.0", features = ["cors", "fs", "request-id", "timeout", "trace"] }
@@ -31,7 +31,9 @@ uuid = { version = "1.23.3", features = ["v7"] }

 [dev-dependencies]
 async-trait = "0.1.89"
-tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt"] }
+axum = { version = "0.8.9", default-features = false, features = ["http1", "tokio"] }
+tokio = { version = "1.52.3", default-features = false, features = ["macros", "net", "rt-multi-thread"] }
+tokio-tungstenite = "0.29.0"
 tower = { version = "0.5.3", features = ["util"] }

 [lints]
@@ -16,18 +16,18 @@ 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, AdminErrorKind, PageSize, Revision,
+    AdminError as AdminServiceError, AdminErrorKind, PageSize,
    accounts::{
-        AccountAvailability, AccountConnectionTestEvent as DomainConnectionTestEvent, AccountCost,
-        AccountListQuery, AccountModelUsage, AccountSort, AccountSortField,
-        AccountStatus as DomainAccountStatus, AccountUsage, SortDirection,
+        AccountConnectionTestEvent as DomainConnectionTestEvent, AccountCost, AccountListQuery,
+        AccountModelUsage, AccountSort, AccountSortField, AccountStatus as DomainAccountStatus,
+        AccountUsage, SortDirection,
    },
    provider_credentials::{
        AccountDirectoryItem, AccountDirectoryPage, AccountExportBundle, AccountRefreshResult,
        AuthorizationStarted, CompleteAuthorization, CredentialDeletion, CredentialDeletionResult,
        CredentialImportResult, CredentialMutation, CredentialMutationResult, ImportCredentials,
-        ProviderDocument, ProviderModels, ProviderQuota, ProviderQuotaWindow,
-        ReauthorizationTarget, RotateCredential, StartAuthorization,
+        ProviderDocument, ProviderModels, ProviderQuota, ProviderQuotaWindow, RotateCredential,
+        StartAuthorization,
    },
 };
 use gateway_core::{
@@ -161,7 +161,6 @@ fn parse_sort_direction(value: &str) -> Option<SortDirection> {
 #[derive(Debug, Clone, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct AccountPageData {
-    pub config_revision: u64,
    pub items: Vec<AccountView>,
    pub page: PageMeta,
    pub summary: AccountSummaryView,
@@ -197,8 +196,6 @@ pub struct AccountView {
    pub token_refreshing: bool,
    pub availability: String,
    pub enabled: bool,
-    pub credential_revision: u64,
-    pub state_revision: Option<u64>,
    pub access_token_expires_at: Option<String>,
    pub access_token_expires_at_display: Option<String>,
    pub refresh_token_expires_at: Option<String>,
@@ -391,31 +388,21 @@ impl AccountActionRequest {
    }
 }

-/// 手工 OAuth 刷新会变更持久 credential，因此必须携带配置 CAS revision。
+/// 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,
-    pub expected_config_revision: u64,
 }

 impl AccountRefreshRequest {
    pub fn validate(&self) -> Result<(), WireValidationError> {
-        require_account_id(&self.account_id, "accountId")?;
-        if self.expected_config_revision == 0 {
-            return Err(WireValidationError::new("expectedConfigRevision"));
-        }
-        Ok(())
+        require_account_id(&self.account_id, "accountId")
    }

-    fn into_command(self) -> Result<(Revision, ProviderAccountId), WireValidationError> {
+    fn into_command(self) -> Result<ProviderAccountId, WireValidationError> {
        self.validate()?;
-        Ok((
-            Revision::new(self.expected_config_revision)
-                .map_err(|_| WireValidationError::new("expectedConfigRevision"))?,
-            ProviderAccountId::new(self.account_id)
-                .map_err(|_| WireValidationError::new("accountId"))?,
-        ))
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
    }
 }

@@ -460,7 +447,6 @@ pub struct AccountModelsData {
 #[derive(Debug, Clone, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct AccountRefreshData {
-    pub config_revision: u64,
    pub account: AccountView,
 }

@@ -545,12 +531,18 @@ impl From<DomainConnectionTestEvent> for AccountConnectionTestEvent {
                message,
                provider_error_code,
                provider_error_type,
+                upstream_status,
+                upstream_content_type,
+                upstream_body,
                account_status,
            } => serde_json::json!({
                "type": "error",
                "error": message,
                "providerErrorCode": provider_error_code,
                "providerErrorType": provider_error_type,
+                "upstreamStatus": upstream_status,
+                "upstreamContentType": upstream_content_type,
+                "upstreamBody": upstream_body,
                "accountStatus": account_status_name(account_status)
            }),
        };
@@ -579,14 +571,12 @@ impl AccountProvider {
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct AccountImportRequest {
    pub provider: String,
-    pub expected_config_revision: u64,
    pub data: Value,
 }

 impl AccountImportRequest {
    pub fn validate(&self) -> Result<(), WireValidationError> {
        AccountProvider::parse(&self.provider)?;
-        require_positive(self.expected_config_revision, "expectedConfigRevision")?;
        if !self.data.is_object()
            || serde_json::to_vec(&self.data)
                .map_or(true, |encoded| encoded.len() > MAX_IMPORT_DATA_BYTES)
@@ -606,10 +596,6 @@ impl AccountImportRequest {
            provider,
            ImportCredentials {
                context,
-                expected_config_revision: revision(
-                    self.expected_config_revision,
-                    "expectedConfigRevision",
-                )?,
                document: provider_document(self.data, "data")?,
            },
        ))
@@ -620,28 +606,18 @@ impl AccountImportRequest {
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct StartAccountAuthorizationRequest {
    pub provider: String,
-    pub expected_config_revision: u64,
    pub name: String,
    pub account_id: Option<String>,
-    pub expected_credential_revision: Option<u64>,
 }

 impl StartAccountAuthorizationRequest {
    pub fn validate(&self) -> Result<(), WireValidationError> {
        AccountProvider::parse(&self.provider)?;
-        require_positive(self.expected_config_revision, "expectedConfigRevision")?;
        require_text(&self.name, MAX_NAME_BYTES, "name")?;
-        match (
-            self.account_id.as_deref(),
-            self.expected_credential_revision,
-        ) {
-            (None, None) => Ok(()),
-            (Some(account_id), Some(credential_revision)) => {
-                require_account_id(account_id, "accountId")?;
-                require_positive(credential_revision, "expectedCredentialRevision")
-            }
-            _ => Err(WireValidationError::new("reauthorization")),
+        if let Some(account_id) = self.account_id.as_deref() {
+            require_account_id(account_id, "accountId")?;
        }
+        Ok(())
    }

    fn into_command(
@@ -650,23 +626,15 @@ impl StartAccountAuthorizationRequest {
    ) -> Result<(AccountProvider, StartAuthorization), WireValidationError> {
        self.validate()?;
        let provider = AccountProvider::parse(&self.provider)?;
-        let reauthorization = match (self.account_id, self.expected_credential_revision) {
-            (None, None) => None,
-            (Some(account_id), Some(credential_revision)) => Some(ReauthorizationTarget {
-                account_id: ProviderAccountId::new(account_id)
-                    .map_err(|_| WireValidationError::new("accountId"))?,
-                credential_revision: revision(credential_revision, "expectedCredentialRevision")?,
-            }),
-            _ => return Err(WireValidationError::new("reauthorization")),
-        };
+        let reauthorization = self
+            .account_id
+            .map(ProviderAccountId::new)
+            .transpose()
+            .map_err(|_| WireValidationError::new("accountId"))?;
        Ok((
            provider,
            StartAuthorization {
                context,
-                expected_config_revision: revision(
-                    self.expected_config_revision,
-                    "expectedConfigRevision",
-                )?,
                name: self.name,
                reauthorization,
            },
@@ -721,14 +689,12 @@ impl CompleteAccountAuthorizationRequest {
 pub struct AccountMutationRequest {
    pub provider: String,
    pub account_id: String,
-    pub expected_config_revision: u64,
 }

 impl AccountMutationRequest {
    pub fn validate(&self) -> Result<(), WireValidationError> {
        AccountProvider::parse(&self.provider)?;
-        require_account_id(&self.account_id, "accountId")?;
-        require_positive(self.expected_config_revision, "expectedConfigRevision")
+        require_account_id(&self.account_id, "accountId")
    }

    fn into_command(
@@ -741,10 +707,6 @@ impl AccountMutationRequest {
            provider,
            CredentialMutation {
                context,
-                expected_config_revision: revision(
-                    self.expected_config_revision,
-                    "expectedConfigRevision",
-                )?,
                account_id: ProviderAccountId::new(self.account_id)
                    .map_err(|_| WireValidationError::new("accountId"))?,
            },
@@ -757,7 +719,6 @@ impl AccountMutationRequest {
 pub struct AccountDeletionRequest {
    pub provider: String,
    pub account_ids: Vec<String>,
-    pub expected_config_revision: u64,
 }

 impl AccountDeletionRequest {
@@ -773,7 +734,7 @@ impl AccountDeletionRequest {
                return Err(WireValidationError::new("accountIds"));
            }
        }
-        require_positive(self.expected_config_revision, "expectedConfigRevision")
+        Ok(())
    }

    fn into_command(
@@ -786,10 +747,6 @@ impl AccountDeletionRequest {
            provider,
            CredentialDeletion {
                context,
-                expected_config_revision: revision(
-                    self.expected_config_revision,
-                    "expectedConfigRevision",
-                )?,
                account_ids: self
                    .account_ids
                    .into_iter()
@@ -806,8 +763,6 @@ impl AccountDeletionRequest {
 pub struct RotateAccountRequest {
    pub provider: String,
    pub account_id: String,
-    pub expected_config_revision: u64,
-    pub expected_credential_revision: u64,
    pub access_token: String,
    pub refresh_token: Option<String>,
 }
@@ -818,11 +773,6 @@ impl RotateAccountRequest {
            return Err(WireValidationError::new("provider"));
        }
        require_account_id(&self.account_id, "accountId")?;
-        require_positive(self.expected_config_revision, "expectedConfigRevision")?;
-        require_positive(
-            self.expected_credential_revision,
-            "expectedCredentialRevision",
-        )?;
        validate_oauth_material(&self.access_token, self.refresh_token.as_deref())
    }

@@ -840,17 +790,9 @@ impl RotateAccountRequest {
        Ok(RotateCredential {
            mutation: CredentialMutation {
                context,
-                expected_config_revision: revision(
-                    self.expected_config_revision,
-                    "expectedConfigRevision",
-                )?,
                account_id: ProviderAccountId::new(self.account_id)
                    .map_err(|_| WireValidationError::new("accountId"))?,
            },
-            expected_credential_revision: revision(
-                self.expected_credential_revision,
-                "expectedCredentialRevision",
-            )?,
            provider_material: ProviderDocument::new(OpaqueProviderData::new(material)),
        })
    }
@@ -859,7 +801,6 @@ impl RotateAccountRequest {
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct AccountImportData {
-    pub config_revision: u64,
    pub imported_count: usize,
    pub account_ids: Vec<String>,
 }
@@ -872,7 +813,6 @@ impl From<CredentialImportResult> for AccountImportData {
            .map(|account_id| account_id.to_string())
            .collect::<Vec<_>>();
        Self {
-            config_revision: result.config_revision.get(),
            imported_count: account_ids.len(),
            account_ids,
        }
@@ -900,18 +840,13 @@ impl From<AuthorizationStarted> for AccountAuthorizationData {
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct AccountMutationData {
-    pub config_revision: u64,
    pub account_id: String,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub credential_revision: Option<u64>,
 }

 impl From<CredentialMutationResult> for AccountMutationData {
    fn from(result: CredentialMutationResult) -> Self {
        Self {
-            config_revision: result.config_revision.get(),
            account_id: result.account_id.to_string(),
-            credential_revision: result.credential_revision.map(Revision::get),
        }
    }
 }
@@ -919,7 +854,6 @@ impl From<CredentialMutationResult> for AccountMutationData {
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct AccountDeletionData {
-    pub config_revision: u64,
    pub deleted_count: usize,
    pub account_ids: Vec<String>,
 }
@@ -932,7 +866,6 @@ impl From<CredentialDeletionResult> for AccountDeletionData {
            .map(|account_id| account_id.to_string())
            .collect::<Vec<_>>();
        Self {
-            config_revision: result.config_revision.get(),
            deleted_count: account_ids.len(),
            account_ids,
        }
@@ -1264,15 +1197,11 @@ async fn refresh_account<S>(
 where
    S: AdminSessionState + Send + Sync,
 {
-    let (expected_config_revision, account_id) = request.into_command().map_err(map_wire_error)?;
+    let account_id = request.into_command().map_err(map_wire_error)?;
    let result = state
        .admin_services()
        .accounts()
-        .refresh(
-            &auth.context().mutation_context(),
-            expected_config_revision,
-            account_id,
-        )
+        .refresh(&auth.context().mutation_context(), account_id)
        .await
        .map_err(map_service_error)?;
    let data = account_refresh_data(result, Utc::now());
@@ -1394,7 +1323,6 @@ fn account_page_data(
        u32::try_from(result.total.div_ceil(u64::from(page_size))).unwrap_or(u32::MAX)
    };
    AccountPageData {
-        config_revision: result.config_revision.get(),
        items: result
            .items
            .into_iter()
@@ -1412,7 +1340,6 @@ fn account_page_data(

 fn account_refresh_data(result: AccountRefreshResult, now: DateTime<Utc>) -> AccountRefreshData {
    AccountRefreshData {
-        config_revision: result.config_revision.get(),
        account: account_view(result.account, now),
    }
 }
@@ -1460,10 +1387,8 @@ fn account_view(item: AccountDirectoryItem, now: DateTime<Utc>) -> AccountView {
        status: status.clone(),
        display_status: status,
        token_refreshing: false,
-        availability: account_availability_name(account.availability).to_owned(),
+        availability: account.availability.as_str().to_owned(),
        enabled: account.enabled,
-        credential_revision: account.credential_revision.get(),
-        state_revision: None,
        access_token_expires_at: expires_at,
        access_token_expires_at_display: account
            .access_token_expires_at
@@ -1714,10 +1639,6 @@ fn empty_account_usage() -> AccountUsageView {
    }
 }

-fn revision(value: u64, field: &'static str) -> Result<Revision, WireValidationError> {
-    Revision::new(value).map_err(|_| WireValidationError::new(field))
-}
-
 fn provider_document(
    value: Value,
    field: &'static str,
@@ -1751,13 +1672,6 @@ fn require_text(
    Ok(())
 }

-fn require_positive(value: u64, field: &'static str) -> Result<(), WireValidationError> {
-    if value == 0 || i64::try_from(value).is_err() {
-        return Err(WireValidationError::new(field));
-    }
-    Ok(())
-}
-
 fn validate_oauth_material(
    access_token: &str,
    refresh_token: Option<&str>,
@@ -1805,18 +1719,6 @@ fn account_status_name(status: DomainAccountStatus) -> &'static str {
    }
 }

-fn account_availability_name(availability: AccountAvailability) -> &'static str {
-    match availability {
-        AccountAvailability::Unknown => "unknown",
-        AccountAvailability::Ready => "ready",
-        AccountAvailability::Cooldown => "cooldown",
-        AccountAvailability::QuotaExhausted => "quota_exhausted",
-        AccountAvailability::Expired => "expired",
-        AccountAvailability::Banned => "banned",
-        AccountAvailability::Invalid => "invalid",
-    }
-}
-
 fn format_number(value: u64) -> String {
    let text = value.to_string();
    let mut output = String::with_capacity(text.len() + text.len() / 3);
@@ -4,14 +4,11 @@ use std::fmt;

 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
 use chrono::{DateTime, Utc};
-use gateway_admin::model::{
-    Revision,
-    client_keys::{
-        ClientKeyCursor, ClientKeyCursorValue as DomainCursorValue, ClientKeyListQuery,
-        ClientKeyMutation, ClientKeyPage, ClientKeyPageSize, ClientKeyRecord, ClientKeySecret,
-        ClientKeySort as DomainSort, ClientKeySortField as DomainSortField, CreateClientKey,
-        CreatedClientKey, DeleteClientKey, SetClientKeyEnabled, SortDirection, UpdateClientKey,
-    },
+use gateway_admin::model::client_keys::{
+    ClientKeyCursor, ClientKeyCursorValue as DomainCursorValue, ClientKeyListQuery,
+    ClientKeyMutation, ClientKeyPage, ClientKeyPageSize, ClientKeyRecord, ClientKeySecret,
+    ClientKeySort as DomainSort, ClientKeySortField as DomainSortField, CreateClientKey,
+    CreatedClientKey, DeleteClientKey, SetClientKeyEnabled, SortDirection, UpdateClientKey,
 };
 use gateway_core::{
    policy::{ClientApiKeyId, RateLimits},
@@ -138,7 +135,6 @@ impl ClientKeySort {
 #[derive(Debug, Clone, PartialEq, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct CreateClientKeyRequest {
-    expected_config_revision: u64,
    name: String,
    label: Option<String>,
    provider_kind: String,
@@ -149,14 +145,12 @@ pub struct CreateClientKeyRequest {
 impl CreateClientKeyRequest {
    /// 校验 wire 边界并直接构造管理用例命令。
    pub fn into_command(self) -> Result<CreateClientKey, WireValidationError> {
-        validate_revision(self.expected_config_revision)?;
        validate_required_text(&self.name, "name")?;
        validate_optional_text(self.label.as_deref(), "label")?;
        validate_provider_kind(&self.provider_kind)?;
        validate_limit(self.max_concurrency, "maxConcurrency")?;
        validate_limit(self.requests_per_minute, "requestsPerMinute")?;
        Ok(CreateClientKey {
-            expected_config_revision: revision(self.expected_config_revision)?,
            name: self.name,
            label: self.label,
            provider_kind: ProviderKind::new(self.provider_kind)
@@ -174,7 +168,6 @@ impl CreateClientKeyRequest {
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct UpdateClientKeyRequest {
    id: String,
-    expected_config_revision: u64,
    name: String,
    label: Option<String>,
    provider_kind: String,
@@ -186,14 +179,12 @@ impl UpdateClientKeyRequest {
    /// 校验 wire 边界并直接构造管理用例命令。
    pub fn into_command(self) -> Result<UpdateClientKey, WireValidationError> {
        validate_required_text(&self.id, "id")?;
-        validate_revision(self.expected_config_revision)?;
        validate_required_text(&self.name, "name")?;
        validate_optional_text(self.label.as_deref(), "label")?;
        validate_provider_kind(&self.provider_kind)?;
        validate_limit(self.max_concurrency, "maxConcurrency")?;
        validate_limit(self.requests_per_minute, "requestsPerMinute")?;
        Ok(UpdateClientKey {
-            expected_config_revision: revision(self.expected_config_revision)?,
            id: client_key_id(self.id, "clientKeyMutationNotFound")?,
            name: self.name,
            label: self.label,
@@ -207,12 +198,11 @@ impl UpdateClientKeyRequest {
    }
 }

-/// 只携带 ID 与配置 revision 的 Client Key mutation 请求。
+/// 只携带 ID 的 Client Key mutation 请求。
 #[derive(Debug, Clone, PartialEq, Eq, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
-pub struct ClientKeyRevisionRequest {
+pub struct ClientKeyMutationRequest {
    id: String,
-    expected_config_revision: u64,
 }

 /// 读取一次完整 Key 的 ID query。
@@ -233,20 +223,15 @@ impl ClientKeyIdQuery {
    }
 }

-impl ClientKeyRevisionRequest {
-    /// 校验请求并取出 ID 与 revision。
-    pub fn into_parts(self) -> Result<(String, u64), WireValidationError> {
+impl ClientKeyMutationRequest {
+    /// 校验请求并取出 ID。
+    pub fn into_id(self) -> Result<String, WireValidationError> {
        validate_required_text(&self.id, "id")?;
-        validate_revision(self.expected_config_revision)?;
-        Ok((self.id, self.expected_config_revision))
+        Ok(self.id)
    }

-    fn into_command_parts(self) -> Result<(ClientApiKeyId, Revision), WireValidationError> {
-        let (id, expected_config_revision) = self.into_parts()?;
-        Ok((
-            client_key_id(id, "clientKeyMutationNotFound")?,
-            revision(expected_config_revision)?,
-        ))
+    fn into_domain_id(self) -> Result<ClientApiKeyId, WireValidationError> {
+        client_key_id(self.into_id()?, "clientKeyMutationNotFound")
    }
 }

@@ -289,7 +274,6 @@ impl From<ClientKeyRecord> for ClientKeyView {
 #[derive(Debug, Clone, PartialEq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct ClientKeyListData {
-    config_revision: u64,
    items: Vec<ClientKeyView>,
    next_cursor: Option<String>,
    total: u64,
@@ -298,14 +282,8 @@ pub struct ClientKeyListData {
 impl ClientKeyListData {
    /// 构造 Client Key 列表响应。
    #[must_use]
-    pub fn new(
-        config_revision: u64,
-        items: Vec<ClientKeyView>,
-        next_cursor: Option<String>,
-        total: u64,
-    ) -> Self {
+    pub fn new(items: Vec<ClientKeyView>, next_cursor: Option<String>, total: u64) -> Self {
        Self {
-            config_revision,
            items,
            next_cursor,
            total,
@@ -325,7 +303,6 @@ impl TryFrom<ClientKeyPage> for ClientKeyListData {
            .map(encode_client_key_cursor)
            .transpose()?;
        Ok(Self::new(
-            page.config_revision.get(),
            page.items.into_iter().map(Into::into).collect(),
            next_cursor,
            page.total,
@@ -337,7 +314,6 @@ impl TryFrom<ClientKeyPage> for ClientKeyListData {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct CreatedClientKeyData {
-    config_revision: u64,
    id: String,
    prefix: String,
    plaintext_key: String,
@@ -346,9 +322,8 @@ pub struct CreatedClientKeyData {
 impl CreatedClientKeyData {
    /// 构造一次性创建响应。
    #[must_use]
-    pub fn new(config_revision: u64, id: String, prefix: String, plaintext_key: String) -> Self {
+    pub fn new(id: String, prefix: String, plaintext_key: String) -> Self {
        Self {
-            config_revision,
            id,
            prefix,
            plaintext_key,
@@ -359,7 +334,6 @@ impl CreatedClientKeyData {
 impl From<CreatedClientKey> for CreatedClientKeyData {
    fn from(created: CreatedClientKey) -> Self {
        Self::new(
-            created.config_revision.get(),
            created.secret.record.id.to_string(),
            created.secret.record.prefix.clone(),
            created.secret.expose_for_response().to_owned(),
@@ -371,7 +345,6 @@ impl fmt::Debug for CreatedClientKeyData {
    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
        formatter
            .debug_struct("CreatedClientKeyData")
-            .field("config_revision", &self.config_revision)
            .field("id", &self.id)
            .field("prefix", &self.prefix)
            .field("plaintext_key", &"[REDACTED]")
@@ -417,24 +390,20 @@ impl fmt::Debug for RevealedClientKeyData {
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct MutatedClientKeyData {
-    config_revision: u64,
    id: String,
 }

 impl MutatedClientKeyData {
    /// 构造 mutation 响应。
    #[must_use]
-    pub fn new(config_revision: u64, id: String) -> Self {
-        Self {
-            config_revision,
-            id,
-        }
+    pub fn new(id: String) -> Self {
+        Self { id }
    }
 }

 impl From<ClientKeyMutation> for MutatedClientKeyData {
    fn from(mutation: ClientKeyMutation) -> Self {
-        Self::new(mutation.config_revision.get(), mutation.id.to_string())
+        Self::new(mutation.id.to_string())
    }
 }

@@ -582,18 +551,6 @@ fn wire_cursor(cursor: ClientKeyCursor) -> Result<ClientKeyCursorData, WireValid
    Ok(cursor)
 }

-fn validate_revision(value: u64) -> Result<(), WireValidationError> {
-    if value == 0 {
-        return Err(WireValidationError::new("expectedConfigRevision"));
-    }
-    Ok(())
-}
-
-fn revision(value: u64) -> Result<Revision, WireValidationError> {
-    validate_revision(value)?;
-    Revision::new(value).map_err(|_| WireValidationError::new("expectedConfigRevision"))
-}
-
 fn client_key_id(
    value: String,
    field: &'static str,
@@ -768,23 +725,19 @@ where
 async fn disable_client_key<S>(
    auth: AdminAuth,
    State(state): State<S>,
-    Json(payload): Json<ClientKeyRevisionRequest>,
+    Json(payload): Json<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
    S: AdminSessionState + Send + Sync,
 {
-    let (id, expected_config_revision) = payload.into_command_parts().map_err(map_wire_error)?;
+    let id = payload.into_domain_id().map_err(map_wire_error)?;
    mutation_response(
        state
            .admin_services()
            .client_keys()
            .set_enabled(
                &auth.context().mutation_context(),
-                SetClientKeyEnabled {
-                    expected_config_revision,
-                    id,
-                    enabled: false,
-                },
+                SetClientKeyEnabled { id, enabled: false },
            )
            .await,
    )
@@ -793,23 +746,19 @@ where
 async fn enable_client_key<S>(
    auth: AdminAuth,
    State(state): State<S>,
-    Json(payload): Json<ClientKeyRevisionRequest>,
+    Json(payload): Json<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
    S: AdminSessionState + Send + Sync,
 {
-    let (id, expected_config_revision) = payload.into_command_parts().map_err(map_wire_error)?;
+    let id = payload.into_domain_id().map_err(map_wire_error)?;
    mutation_response(
        state
            .admin_services()
            .client_keys()
            .set_enabled(
                &auth.context().mutation_context(),
-                SetClientKeyEnabled {
-                    expected_config_revision,
-                    id,
-                    enabled: true,
-                },
+                SetClientKeyEnabled { id, enabled: true },
            )
            .await,
    )
@@ -818,23 +767,17 @@ where
 async fn delete_client_key<S>(
    auth: AdminAuth,
    State(state): State<S>,
-    Json(payload): Json<ClientKeyRevisionRequest>,
+    Json(payload): Json<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
    S: AdminSessionState + Send + Sync,
 {
-    let (id, expected_config_revision) = payload.into_command_parts().map_err(map_wire_error)?;
+    let id = payload.into_domain_id().map_err(map_wire_error)?;
    mutation_response(
        state
            .admin_services()
            .client_keys()
-            .delete(
-                &auth.context().mutation_context(),
-                DeleteClientKey {
-                    expected_config_revision,
-                    id,
-                },
-            )
+            .delete(&auth.context().mutation_context(), DeleteClientKey { id })
            .await,
    )
 }
@@ -854,9 +797,6 @@ fn map_wire_error(error: WireValidationError) -> AdminError {
        "cursor" => AdminError::bad_request("Invalid client key cursor"),
        "clientKeyRevealNotFound" => AdminError::not_found("Client API key was not found"),
        "clientKeyMutationNotFound" => AdminError::not_found("client API key was not found"),
-        "expectedConfigRevision" => {
-            AdminError::bad_request("expectedConfigRevision must be positive")
-        }
        _ => AdminError::bad_request("Invalid client API key request"),
    }
 }
@@ -1800,7 +1800,7 @@ fn usage_record_view(record: domain::UsageRecord) -> UsageRecordView {
        model,
        requested_model: Some(record.requested_model_id),
        upstream_model: record.upstream_model_id,
-        service_tier: None,
+        service_tier: record.service_tier,
        status_code,
        transport,
        attempt_index: None,
@@ -10,12 +10,8 @@ use axum::{
    routing::{get, post},
 };
 use chrono::{DateTime, Utc};
-use gateway_admin::model::{
-    Revision,
-    settings::{
-        ModelMappings as DomainModelMappings, ReplaceRuntimeSettings, RotationStrategy,
-        RuntimeSettings,
-    },
+use gateway_admin::model::settings::{
+    ModelMappings as DomainModelMappings, ReplaceRuntimeSettings, RotationStrategy, RuntimeSettings,
 };
 use gateway_core::routing::{PublicModelId, UpstreamModelId};
 use serde::{Deserialize, Serialize};
@@ -32,7 +28,6 @@ pub type ModelMappings = BTreeMap<String, String>;
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct RuntimeSettingsView {
-    pub config_revision: u64,
    pub model_mappings: ModelMappings,
    pub refresh_margin_seconds: u64,
    pub refresh_concurrency: u64,
@@ -49,7 +44,6 @@ pub struct RuntimeSettingsView {
 #[derive(Debug, Clone, PartialEq, Eq, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct UpdateRuntimeSettingsRequest {
-    pub expected_config_revision: u64,
    pub model_mappings: ModelMappings,
    pub refresh_margin_seconds: u64,
    pub refresh_concurrency: u64,
@@ -64,9 +58,6 @@ pub struct UpdateRuntimeSettingsRequest {
 impl UpdateRuntimeSettingsRequest {
    /// 校验公共运行参数。
    pub fn validate(&self) -> Result<(), WireValidationError> {
-        if self.expected_config_revision == 0 {
-            return Err(WireValidationError::new("expectedConfigRevision"));
-        }
        validate_model_mappings(&self.model_mappings)?;
        for (value, field) in [
            (self.refresh_margin_seconds, "refreshMarginSeconds"),
@@ -93,8 +84,6 @@ impl UpdateRuntimeSettingsRequest {
    fn into_command(self) -> Result<ReplaceRuntimeSettings, WireValidationError> {
        self.validate()?;
        Ok(ReplaceRuntimeSettings {
-            expected_config_revision: Revision::new(self.expected_config_revision)
-                .map_err(|_| WireValidationError::new("settingsRevisionOverflow"))?,
            model_mappings: domain_model_mappings(self.model_mappings)?,
            refresh_margin_seconds: self.refresh_margin_seconds,
            refresh_concurrency: u32::try_from(self.refresh_concurrency)
@@ -117,7 +106,6 @@ impl UpdateRuntimeSettingsRequest {
 impl From<RuntimeSettings> for RuntimeSettingsView {
    fn from(settings: RuntimeSettings) -> Self {
        Self {
-            config_revision: settings.config_revision.get(),
            model_mappings: wire_model_mappings(settings.model_mappings),
            refresh_margin_seconds: settings.refresh_margin_seconds,
            refresh_concurrency: u64::from(settings.refresh_concurrency),
@@ -358,7 +346,6 @@ fn valid_model_name(value: &str, max_len: usize) -> bool {

 fn map_wire_error(error: WireValidationError) -> AdminError {
    let message = match error.field() {
-        "settingsRevisionOverflow" => "expectedConfigRevision must be positive".to_owned(),
        "settingsRefreshConcurrencyOverflow" => "Invalid refreshConcurrency".to_owned(),
        "settingsMaxConcurrencyOverflow" => "Invalid maxConcurrentPerAccount".to_owned(),
        "settingsUsageRetentionOverflow" => "Invalid usageRetentionDays".to_owned(),
@@ -2,7 +2,8 @@

 use axum::{
    Json,
-    http::StatusCode,
+    body::Body,
+    http::{HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
    response::{IntoResponse, Response},
 };
 use gateway_core::{
@@ -75,10 +76,14 @@ pub fn gateway_error_from_engine(error: &EngineError) -> GatewayError {
            if error.kind() == ProviderErrorKind::Unavailable
                && error.send_state() == UpstreamSendState::NotSent =>
        {
-            GatewayError::new(
+            let gateway = GatewayError::new(
                GatewayErrorKind::NoAvailableProvider,
                "no upstream provider is currently available for this request",
-            )
+            );
+            match error.client_visible_upstream_error() {
+                Some(upstream) => gateway.with_client_visible_upstream_error(upstream.clone()),
+                None => gateway,
+            }
        }
        EngineError::Provider(error) => GatewayError::from_provider(error),
        EngineError::Cancelled => {
@@ -117,6 +122,33 @@ pub fn gateway_error_response(error: &GatewayError) -> Response {
    .into_response()
 }

+/// 在下游尚未提交时优先交付 Provider 的原始 HTTP 失败响应。
+pub fn engine_error_response(error: &EngineError) -> Response {
+    if let EngineError::Provider(error) = error
+        && let Some(upstream) = error.client_visible_upstream_response()
+        && let Ok(status) = StatusCode::from_u16(upstream.status())
+    {
+        let mut response = Response::new(Body::from(upstream.body().clone()));
+        *response.status_mut() = status;
+        if let Some(content_type) = upstream.content_type()
+            && let Ok(content_type) = HeaderValue::from_bytes(content_type)
+        {
+            response.headers_mut().insert(CONTENT_TYPE, content_type);
+        }
+        for header in upstream.headers() {
+            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);
+        }
+        return response;
+    }
+    gateway_error_response(&gateway_error_from_engine(error))
+}
+
 /// Gateway 错误稳定映射，供 HTTP、SSE 和 WebSocket 共用。
 #[must_use]
 pub const fn gateway_error_contract(
@@ -189,6 +189,22 @@ fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
    } else {
        vec!["text"]
    };
+    let additional_speed_tiers = presentation
+        .service_tiers()
+        .iter()
+        .filter_map(|tier| tier.speed_tier())
+        .collect::<Vec<_>>();
+    let service_tiers = presentation
+        .service_tiers()
+        .iter()
+        .map(|tier| {
+            json!({
+                "id": tier.id(),
+                "name": tier.name(),
+                "description": tier.description(),
+            })
+        })
+        .collect::<Vec<_>>();

    json!({
        "slug": id,
@@ -200,8 +216,8 @@ fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
        "visibility": if presentation.hidden() { "hide" } else { "list" },
        "supported_in_api": true,
        "priority": index.saturating_add(1),
-        "additional_speed_tiers": [],
-        "service_tiers": [],
+        "additional_speed_tiers": additional_speed_tiers,
+        "service_tiers": service_tiers,
        "availability_nux": Value::Null,
        "upgrade": Value::Null,
        "base_instructions": CODEX_BASE_INSTRUCTIONS,
@@ -152,9 +152,6 @@ pub enum ResponseEncodeError {
    /// 协议原生流缺少可返回的终态 response object。
    #[error("responses wire stream has no terminal response")]
    MissingWireTerminal,
-    /// 协议原生事件携带了不一致的响应身份。
-    #[error("responses wire stream changed its response identity")]
-    WireIdentityChanged,
    /// 终态 response object 无法序列化为完整 HTTP JSON 响应。
    #[error("responses wire terminal serialization failed")]
    Serialization,
@@ -167,7 +164,7 @@ impl ResponseEncodeError {
        ProtocolErrorBody {
            error: ProtocolError {
                kind: "server_error",
-                code: "invalid_canonical_response",
+                code: "invalid_upstream_response",
                message: "The gateway could not forward the upstream response.".to_owned(),
                param: None,
            },
@@ -8,7 +8,7 @@ use axum::{
    body::{Body, Bytes},
    extract::{Extension, State, connect_info::ConnectInfo},
    http::{
-        HeaderMap, HeaderValue, StatusCode,
+        HeaderMap, HeaderName, HeaderValue, StatusCode,
        header::{CACHE_CONTROL, CONTENT_TYPE, USER_AGENT},
    },
    response::{IntoResponse, Response},
@@ -25,8 +25,8 @@ use crate::ApiState;
 use crate::openai::{
    auth::{authenticate_client, authentication_error_response},
    error::{
-        gateway_error_contract, gateway_error_from_engine, gateway_error_response,
-        protocol_error_response, runtime_unavailable_response,
+        engine_error_response, gateway_error_contract, gateway_error_from_engine,
+        gateway_error_response, protocol_error_response, runtime_unavailable_response,
    },
 };

@@ -180,7 +180,7 @@ 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 = gateway_error_response(&gateway_error_from_engine(&error));
+            let response = engine_error_response(&error);
            return execution.record_response_status(response).await;
        }
    };
@@ -206,7 +206,7 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
        .await
    {
        execution.cancel_and_finalize().await;
-        let response = gateway_error_response(&gateway_error_from_engine(&error));
+        let response = engine_error_response(&error);
        return execution.record_response_status(response).await;
    }
    if !session.is_finalized() {
@@ -237,9 +237,7 @@ fn encode_collected_events(
 ) -> Result<Vec<u8>, BufferedResponseEncodeError> {
    let mut encoder = OpenAiResponsesEncoder::new();
    for event in events {
-        encoder
-            .push_sse(event)
-            .map_err(BufferedResponseEncodeError::Canonical)?;
+        encoder.push_sse(event);
    }
    let response = encoder
        .finish()
@@ -253,23 +251,25 @@ fn json_body_response(encoded: Vec<u8>, response_headers: &[ProviderResponseHead
    response
        .headers_mut()
        .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
-    apply_safe_response_headers(response, response_headers)
+    apply_response_headers(response, response_headers)
 }

-fn apply_safe_response_headers(
+fn apply_response_headers(
    mut response: Response,
    response_headers: &[ProviderResponseHeader],
 ) -> Response {
+    let connection_options = super::response_connection_options(response_headers);
    for header in response_headers {
-        let Some(name) = super::safe_response_header_name(header.name()) else {
+        if !super::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_str(header.value().as_str()) else {
+        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
            continue;
        };
-        response
-            .headers_mut()
-            .insert(axum::http::header::HeaderName::from_static(name), value);
+        response.headers_mut().append(name, value);
    }
    response
 }
@@ -295,7 +295,7 @@ pub async fn stream_execution_response(
            return response;
        }
        Err(error) => {
-            let response = gateway_error_response(&gateway_error_from_engine(&error));
+            let response = engine_error_response(&error);
            return execution.record_response_status(response).await;
        }
    };
@@ -310,18 +310,7 @@ pub async fn stream_execution_response(
    let mut encoder = OpenAiResponsesEncoder::new();
    let mut frames = Vec::new();
    for event in &first_events {
-        match encoder.push_sse(event) {
-            Ok(encoded) => frames.extend(encoded),
-            Err(error) => {
-                let response = protocol_error_response(
-                    StatusCode::INTERNAL_SERVER_ERROR,
-                    error.protocol_body(),
-                );
-                let response = execution.record_response_status(response).await;
-                execution.cancel_and_finalize().await;
-                return response;
-            }
-        }
+        frames.extend(encoder.push_sse(event));
    }
    if frames.is_empty() {
        let response = internal_gateway_response("gateway commit batch encoded no output");
@@ -338,7 +327,7 @@ pub async fn stream_execution_response(
        .await
    {
        execution.cancel_and_finalize().await;
-        let response = gateway_error_response(&gateway_error_from_engine(&error));
+        let response = engine_error_response(&error);
        return execution.record_response_status(response).await;
    }
    let Some(session) = execution.into_session() else {
@@ -371,7 +360,7 @@ fn event_stream_response(body: Body, response_headers: &[ProviderResponseHeader]
    response
        .headers_mut()
        .insert(CACHE_CONTROL, HeaderValue::from_static("no-cache"));
-    apply_safe_response_headers(response, response_headers)
+    apply_response_headers(response, response_headers)
 }

 fn internal_gateway_response(message: &'static str) -> Response {
@@ -403,15 +392,10 @@ impl PendingExecution {
    }

    async fn record_response_status(&mut self, response: Response) -> Response {
-        let Some(session) = self.session.as_mut() else {
-            return internal_gateway_response("gateway response session is unavailable");
-        };
-        if session
-            .record_client_status(response.status().as_u16())
-            .await
-            .is_err()
-        {
-            return internal_gateway_response("gateway client status could not be persisted");
+        if let Some(session) = self.session.as_mut() {
+            let _ = session
+                .record_client_status(response.status().as_u16())
+                .await;
        }
        response
    }
@@ -499,10 +483,16 @@ impl ResponsesStreamState {
                    .session
                    .as_ref()
                    .is_some_and(|session| session.is_finalized());
-                self.finish_with_gateway_error(GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended without a terminal event",
-                ));
+                if self.execution_terminal {
+                    self.pending
+                        .push_back(Bytes::from_static(DONE_SSE_FRAME.as_bytes()));
+                    self.output_finished = true;
+                } else {
+                    self.finish_with_gateway_error(GatewayError::new(
+                        GatewayErrorKind::Internal,
+                        "gateway response ended without finalizing the execution",
+                    ));
+                }
            }
            Err(error) => {
                self.execution_terminal = self
@@ -521,18 +511,11 @@ impl ResponsesStreamState {
    }

    async fn push_event(&mut self, event: ProviderEvent) {
-        match self.encoder.push_sse(&event) {
-            Ok(frames) => {
-                if self.encoder.is_completed() {
-                    self.finish_completed(frames).await;
-                } else {
-                    self.pending.extend(frames);
-                }
-            }
-            Err(error) => {
-                self.cancel_execution().await;
-                self.finish_with_encode_error(error);
-            }
+        let frames = self.encoder.push_sse(&event);
+        if self.encoder.is_completed() {
+            self.finish_completed(frames).await;
+        } else {
+            self.pending.extend(frames);
        }
    }

@@ -607,20 +590,6 @@ impl ResponsesStreamState {
            .push_back(Bytes::from_static(DONE_SSE_FRAME.as_bytes()));
        self.output_finished = true;
    }
-
-    fn finish_with_encode_error(&mut self, error: ResponseEncodeError) {
-        let protocol = error.protocol_body().error;
-        self.pending
-            .push_back(Bytes::from(response_failed_sse_event_with_id(
-                self.encoder.response_id(),
-                protocol.kind,
-                protocol.code,
-                &protocol.message,
-            )));
-        self.pending
-            .push_back(Bytes::from_static(DONE_SSE_FRAME.as_bytes()));
-        self.output_finished = true;
-    }
 }

 impl Drop for ResponsesStreamState {
@@ -17,13 +17,63 @@ pub use response::OpenAiResponsesEncoder;
 pub(crate) use websocket::responses_websocket;
 pub use websocket::{ResponseCreateFrameError, decode_response_create_with_context};

-pub(super) fn safe_response_header_name(name: &str) -> Option<&'static str> {
-    match name {
-        "x-request-id" => Some("x-request-id"),
-        "openai-model" => Some("openai-model"),
-        "x-models-etag" => Some("x-models-etag"),
-        "x-reasoning-included" => Some("x-reasoning-included"),
-        "openai-processing-ms" => Some("openai-processing-ms"),
-        _ => None,
+use gateway_core::event::ProviderResponseHeader;
+
+pub(super) fn response_connection_options(headers: &[ProviderResponseHeader]) -> Vec<String> {
+    headers
+        .iter()
+        .filter(|header| header.name().trim().eq_ignore_ascii_case("connection"))
+        .filter_map(|header| std::str::from_utf8(header.value()).ok())
+        .flat_map(|value| value.split(','))
+        .map(str::trim)
+        .filter(|name| !name.is_empty())
+        .map(str::to_ascii_lowercase)
+        .collect()
+}
+
+pub(super) fn response_header_is_forwardable(name: &str, connection_options: &[String]) -> bool {
+    let name = name.trim().to_ascii_lowercase();
+    if connection_options
+        .iter()
+        .any(|option| option.eq_ignore_ascii_case(&name))
+        || name.starts_with("sec-websocket-")
+    {
+        return false;
    }
+
+    !matches!(
+        name.as_str(),
+        "connection"
+            | "keep-alive"
+            | "proxy-connection"
+            | "te"
+            | "trailer"
+            | "transfer-encoding"
+            | "upgrade"
+            | "content-length"
+            | "content-type"
+            | "content-encoding"
+            | "authorization"
+            | "x-api-key"
+            | "www-authenticate"
+            | "authentication-info"
+            | "proxy-authenticate"
+            | "proxy-authorization"
+            | "proxy-authentication-info"
+            | "cookie"
+            | "cookie2"
+            | "set-cookie"
+            | "set-cookie2"
+            | "chatgpt-account-id"
+            | "chatgpt-organization-id"
+            | "chatgpt-org-id"
+            | "chatgpt-project-id"
+            | "openai-organization"
+            | "openai-project"
+            | "x-openai-organization"
+            | "x-openai-project"
+            | "x-codex-installation-id"
+            | "x-codex-turn-state"
+            | "x-codex-turn-metadata"
+    )
 }
@@ -3,6 +3,7 @@
 use std::{fmt, net::IpAddr};

 use axum::http::HeaderMap;
+use base64::{Engine as _, engine::general_purpose::STANDARD};
 use gateway_core::operation::{GenerateRequest, Operation, ProtocolPayload, ProviderSessionState};
 use gateway_protocol::openai::{
    X_OPENAI_INTERNAL_CODEX_RESPONSES_LITE_HEADER, X_OPENAI_MEMGEN_REQUEST_HEADER,
@@ -14,6 +15,7 @@ use super::error::RequestDecodeError;
 const OPENAI_PROTOCOL: &str = "openai";
 const REVIEW_SUBAGENT: &str = "review";
 const OPENAI_SUBAGENT_KEY: &str = "x-openai-subagent";
+const PASSTHROUGH_HEADERS_CONTEXT_KEY: &str = "opaque_request_headers";

 #[derive(Clone, Default)]
 pub struct OpenAiRequestHeaders {
@@ -34,6 +36,7 @@ pub struct OpenAiRequestHeaders {
    responses_lite: Option<String>,
    memgen_request: Option<String>,
    subagent: Option<String>,
+    passthrough_headers: Vec<Value>,
 }

 impl OpenAiRequestHeaders {
@@ -57,12 +60,8 @@ impl OpenAiRequestHeaders {
            turn_id: header_string(headers, "x-codex-turn-id"),
            responses_lite: header_string(headers, X_OPENAI_INTERNAL_CODEX_RESPONSES_LITE_HEADER),
            memgen_request: header_string(headers, X_OPENAI_MEMGEN_REQUEST_HEADER),
-            subagent: header_string(headers, OPENAI_SUBAGENT_KEY).filter(|value| {
-                matches!(
-                    value.as_str(),
-                    "review" | "compact" | "memory_consolidation" | "collab_spawn"
-                )
-            }),
+            subagent: header_string(headers, OPENAI_SUBAGENT_KEY),
+            passthrough_headers: passthrough_headers(headers),
        }
    }

@@ -108,6 +107,12 @@ impl OpenAiRequestHeaders {
        insert_protocol_context(&mut context, "turn_id", self.turn_id.as_ref());
        insert_protocol_context(&mut context, "responses_lite", self.responses_lite.as_ref());
        insert_protocol_context(&mut context, "memgen_request", self.memgen_request.as_ref());
+        if !self.passthrough_headers.is_empty() {
+            context.insert(
+                PASSTHROUGH_HEADERS_CONTEXT_KEY.to_owned(),
+                Value::Array(self.passthrough_headers.clone()),
+            );
+        }
        if let Some(use_websocket) = use_websocket {
            context.insert("use_websocket".to_owned(), Value::Bool(use_websocket));
        }
@@ -322,13 +327,14 @@ pub(super) fn decode_request_object(
    review: bool,
    request_headers: &OpenAiRequestHeaders,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
-    // `use_websocket` 只影响本地 transport。无论值是否可识别，都不得进入上游 body。
-    let use_websocket = object
-        .remove("use_websocket")
-        .and_then(|value| value.as_bool());
+    // 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);
+    if use_websocket.is_some() {
+        object.remove("use_websocket");
+    }

-    let model = required_non_empty_string(&object, "model", "model")?.trim();
-    if model.is_empty() {
+    let model = required_non_empty_string(&object, "model", "model")?;
+    if model.trim().is_empty() {
        return Err(RequestDecodeError::EmptyField {
            field: "model".to_owned(),
        });
@@ -345,7 +351,6 @@ pub(super) fn decode_request_object(
    let continuation = object
        .get("previous_response_id")
        .and_then(Value::as_str)
-        .filter(|response_id| !response_id.is_empty())
        .map(|response_id| ContinuationIntent::PreviousResponseId(response_id.to_owned()))
        .unwrap_or(ContinuationIntent::None);

@@ -376,26 +381,98 @@ fn inject_subagent_metadata(body: &mut Map<String, Value>, subagent: &str) {
    let metadata = body
        .entry("client_metadata".to_owned())
        .or_insert_with(|| Value::Object(Map::new()));
-    if !metadata.is_object() {
-        *metadata = Value::Object(Map::new());
-    }
-    if let Some(metadata) = metadata.as_object_mut() {
-        metadata.insert(
-            OPENAI_SUBAGENT_KEY.to_owned(),
-            Value::String(subagent.to_owned()),
-        );
-    }
+    let Some(metadata) = metadata.as_object_mut() else {
+        return;
+    };
+    metadata.insert(
+        OPENAI_SUBAGENT_KEY.to_owned(),
+        Value::String(subagent.to_owned()),
+    );
 }

 fn header_string(headers: &HeaderMap, name: &str) -> Option<String> {
    headers
        .get(name)
        .and_then(|value| value.to_str().ok())
-        .map(str::trim)
-        .filter(|value| !value.is_empty())
        .map(ToOwned::to_owned)
 }

+fn passthrough_headers(headers: &HeaderMap) -> Vec<Value> {
+    let connection_headers = headers
+        .get_all("connection")
+        .iter()
+        .filter_map(|value| value.to_str().ok())
+        .flat_map(|value| value.split(','))
+        .map(str::trim)
+        .filter(|name| !name.is_empty())
+        .map(str::to_ascii_lowercase)
+        .collect::<Vec<_>>();
+
+    headers
+        .iter()
+        .filter(|(name, _)| passthrough_header_name(name.as_str(), &connection_headers))
+        .map(|(name, value)| {
+            Value::Array(vec![
+                Value::String(name.as_str().to_owned()),
+                Value::String(STANDARD.encode(value.as_bytes())),
+            ])
+        })
+        .collect()
+}
+
+fn passthrough_header_name(name: &str, connection_headers: &[String]) -> bool {
+    if connection_headers
+        .iter()
+        .any(|connection_header| connection_header.eq_ignore_ascii_case(name))
+        || name.starts_with("sec-websocket-")
+        || name.starts_with("x-grok-")
+        || name.starts_with("x-xai-")
+    {
+        return false;
+    }
+
+    !matches!(
+        name,
+        // 逐跳头、上游 authority 和重序列化后的实体长度由 transport 重建。
+        "connection"
+            | "keep-alive"
+            | "proxy-connection"
+            | "proxy-authenticate"
+            | "proxy-authorization"
+            | "te"
+            | "trailer"
+            | "transfer-encoding"
+            | "upgrade"
+            | "host"
+            | "content-length"
+            // 下游连接诊断事实只用于本地观测，不能伪装成 OpenAI 请求事实。
+            | "forwarded"
+            | "x-forwarded-for"
+            | "x-forwarded-host"
+            | "x-forwarded-proto"
+            | "x-forwarded-port"
+            | "x-real-ip"
+            | "true-client-ip"
+            | "cf-connecting-ip"
+            | "x-request-id"
+            // 下游鉴权和账号 cookie 绝不能成为上游账号身份。
+            | "authorization"
+            | "x-api-key"
+            | "cookie"
+            | "cookie2"
+            | "chatgpt-account-id"
+            | "chatgpt-organization-id"
+            | "chatgpt-org-id"
+            | "chatgpt-project-id"
+            | "openai-organization"
+            | "openai-project"
+            | "x-openai-organization"
+            | "x-openai-project"
+            // installation ID 始终由当前 lease 重建。
+            | "x-codex-installation-id"
+    )
+}
+
 fn required_non_empty_string<'a>(
    object: &'a Map<String, Value>,
    key: &str,
@@ -11,15 +11,14 @@ const OPENAI_PROTOCOL: &str = "openai";

 /// OpenAI Responses wire 的转发器。
 ///
-/// OpenAI Provider 与 xAI adapter 都必须交付 OpenAI wire。这里仅保留同一
-/// 响应的身份和终态校验，不再从 canonical facts 重建客户端 JSON；因此
-/// OpenAI 上游的未知字段、字段顺序和事件语义不会被 API 层二次解释。
+/// OpenAI Provider 与 xAI adapter 都必须交付 OpenAI wire。wire 是客户端交付
+/// 与终态判断的事实来源；canonical facts 只在 wire 暂未携带 ID 时提供旁路观测，
+/// 不得反过来拒绝或改写上游事件。
 #[derive(Debug, Default)]
 pub struct OpenAiResponsesEncoder {
    response_id: Option<String>,
    wire_terminal: Option<Value>,
    wire_failure: bool,
-    canonical_completed: bool,
 }

 impl OpenAiResponsesEncoder {
@@ -30,53 +29,41 @@ impl OpenAiResponsesEncoder {
            response_id: None,
            wire_terminal: None,
            wire_failure: false,
-            canonical_completed: false,
        }
    }

    /// 消费一个 Provider event，并返回 SSE frames。
-    ///
-    /// # Errors
-    ///
-    /// 同一响应身份变化时返回错误。
-    pub fn push_sse(&mut self, event: &ProviderEvent) -> Result<Vec<Bytes>, ResponseEncodeError> {
-        self.observe_identity(event)?;
+    pub fn push_sse(&mut self, event: &ProviderEvent) -> Vec<Bytes> {
+        self.observe_canonical_identity(event);
        let Some(wire) = openai_wire(event) else {
-            return Ok(Vec::new());
+            return Vec::new();
        };
-        self.observe_wire_terminal(wire);
+        self.observe_wire(wire);
        if let Some(raw_sse_frame) = wire.raw_sse_frame() {
-            return Ok(vec![raw_sse_frame.clone()]);
+            return vec![raw_sse_frame.clone()];
        }
-        Ok(vec![Bytes::from(encode_sse_event_with_metadata(
+        vec![Bytes::from(encode_sse_event_with_metadata(
            wire.event_type().unwrap_or_default(),
            &wire.data().to_string(),
            wire.sse_id(),
            wire.sse_retry(),
-        ))])
+        ))]
    }

    /// 消费一个 Provider event，并返回 WebSocket JSON messages。
-    ///
-    /// # Errors
-    ///
-    /// 同一响应身份变化时返回错误。
-    pub fn push_websocket(
-        &mut self,
-        event: &ProviderEvent,
-    ) -> Result<Vec<String>, ResponseEncodeError> {
-        self.observe_identity(event)?;
+    pub fn push_websocket(&mut self, event: &ProviderEvent) -> Vec<String> {
+        self.observe_canonical_identity(event);
        let Some(wire) = openai_wire(event).filter(|wire| wire.has_json_data()) else {
-            return Ok(Vec::new());
+            return Vec::new();
        };
-        self.observe_wire_terminal(wire);
-        Ok(vec![wire.data().to_string()])
+        self.observe_wire(wire);
+        vec![wire.data().to_string()]
    }

-    /// 返回是否已经看到同一响应的 canonical 与 wire 终态。
+    /// 返回是否已经看到客户端可见的 wire 终态。
    #[must_use]
    pub fn is_completed(&self) -> bool {
-        self.wire_terminal.is_some() && self.canonical_completed
+        self.wire_terminal.is_some()
    }

    /// 返回是否已把 Provider 原生失败 event 交付给客户端。
@@ -95,39 +82,31 @@ impl OpenAiResponsesEncoder {
    ///
    /// # Errors
    ///
-    /// 缺少 wire 或 canonical 终态时返回错误。
+    /// 缺少可转换为非流式响应的 wire 终态时返回错误。
    pub fn finish(self) -> Result<Value, ResponseEncodeError> {
-        if self.canonical_completed {
-            self.wire_terminal
-                .ok_or(ResponseEncodeError::MissingWireTerminal)
-        } else {
-            Err(ResponseEncodeError::MissingWireTerminal)
-        }
+        self.wire_terminal
+            .ok_or(ResponseEncodeError::MissingWireTerminal)
    }

-    fn observe_identity(&mut self, event: &ProviderEvent) -> Result<(), ResponseEncodeError> {
+    fn observe_canonical_identity(&mut self, event: &ProviderEvent) {
        for fact in event.canonical_facts() {
            let metadata = match fact {
-                GatewayEvent::Started(metadata) => metadata,
-                GatewayEvent::Completed(metadata) => {
-                    self.canonical_completed = true;
-                    metadata
-                }
+                GatewayEvent::Started(metadata) | GatewayEvent::Completed(metadata) => metadata,
                _ => continue,
            };
-            if self
-                .response_id
-                .as_deref()
-                .is_some_and(|current| current != metadata.response_id())
-            {
-                return Err(ResponseEncodeError::WireIdentityChanged);
-            }
            self.response_id = Some(metadata.response_id().to_owned());
        }
-        Ok(())
    }

-    fn observe_wire_terminal(&mut self, wire: &ProtocolWireEvent) {
+    fn observe_wire(&mut self, wire: &ProtocolWireEvent) {
+        if let Some(response_id) = wire
+            .data()
+            .pointer("/response/id")
+            .or_else(|| wire.data().get("response_id"))
+            .and_then(Value::as_str)
+        {
+            self.response_id = Some(response_id.to_owned());
+        }
        let effective_type = wire
            .event_type()
            .or_else(|| wire.data().get("type").and_then(Value::as_str));
@@ -9,7 +9,7 @@ use axum::{
        connect_info::ConnectInfo,
        ws::{CloseFrame, Message, WebSocket, WebSocketUpgrade, close_code},
    },
-    http::{HeaderMap, StatusCode},
+    http::{HeaderMap, HeaderName, StatusCode},
    response::{IntoResponse, Response},
 };
 use futures::StreamExt;
@@ -27,7 +27,6 @@ use crate::{
    openai::{
        auth::{authenticate_client, authentication_error_response},
        error::{gateway_error_contract, gateway_error_from_engine, runtime_unavailable_response},
-        router::MAX_CLIENT_REQUEST_BODY_BYTES,
        service::OpenAiService,
    },
 };
@@ -102,8 +101,10 @@ impl ResponsesWebSocketAdapter {
            _connection_guard: connection_guard,
        };
        websocket
-            .max_message_size(MAX_CLIENT_REQUEST_BODY_BYTES)
-            .max_frame_size(MAX_CLIENT_REQUEST_BODY_BYTES)
+            // 覆盖 axum/tungstenite 的私有 64 MiB message 与 16 MiB frame 默认值。
+            // Responses JSON 的协议可接受性由上游决定，代理不另设 wire 长度上限。
+            .max_message_size(usize::MAX)
+            .max_frame_size(usize::MAX)
            .on_upgrade(move |socket| async move {
                serve_responses_websocket(socket, session).await;
            })
@@ -303,18 +304,7 @@ async fn forward_execution(
        if let Some(update) = event.take_session_update() {
            provider_state = Some(update);
        }
-        match encoder.push_websocket(event) {
-            Ok(messages) => first_messages.extend(messages),
-            Err(error) => {
-                return send_protocol_error(
-                    socket,
-                    StatusCode::INTERNAL_SERVER_ERROR,
-                    error.protocol_body(),
-                    &request_id,
-                )
-                .await;
-            }
-        }
+        first_messages.extend(encoder.push_websocket(event));
    }
    if first_messages.is_empty() {
        let error = GatewayError::new(
@@ -336,9 +326,7 @@ async fn forward_execution(
        {
            return outcome;
        }
-        if let Err(error) = commit_connection_replay(replay, &encoder, provider_state.take()) {
-            return send_gateway_error(socket, &error, &request_id).await;
-        }
+        commit_connection_replay(replay, &encoder, provider_state.take());
        if !send_text(
            socket,
            response_metadata_event(&request_id, &response_headers),
@@ -378,18 +366,7 @@ async fn forward_execution(
                    if let Some(update) = event.take_session_update() {
                        provider_state = Some(update);
                    }
-                    match encoder.push_websocket(event) {
-                        Ok(encoded) => messages.extend(encoded),
-                        Err(error) => {
-                            return send_protocol_error(
-                                socket,
-                                StatusCode::INTERNAL_SERVER_ERROR,
-                                error.protocol_body(),
-                                &request_id,
-                            )
-                            .await;
-                        }
-                    }
+                    messages.extend(encoder.push_websocket(event));
                }
                if encoder.is_completed() {
                    if let Err(outcome) =
@@ -397,11 +374,7 @@ async fn forward_execution(
                    {
                        return outcome;
                    }
-                    if let Err(error) =
-                        commit_connection_replay(replay, &encoder, provider_state.take())
-                    {
-                        return send_gateway_error(socket, &error, &request_id).await;
-                    }
+                    commit_connection_replay(replay, &encoder, provider_state.take());
                    if !send_messages(socket, messages).await {
                        return ForwardOutcome::Disconnect;
                    }
@@ -413,9 +386,17 @@ async fn forward_execution(
                }
            }
            ActiveInput::Event(Ok(None)) => {
+                if execution
+                    .session_mut()
+                    .is_some_and(|session| session.is_finalized())
+                {
+                    commit_connection_replay(replay, &encoder, provider_state.take());
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
                let error = GatewayError::new(
                    GatewayErrorKind::Internal,
-                    "gateway response ended without a terminal event",
+                    "gateway response ended without finalizing the execution",
                );
                return send_gateway_error(socket, &error, &request_id).await;
            }
@@ -441,15 +422,10 @@ fn commit_connection_replay(
    replay: &mut ConnectionReplaySnapshot,
    encoder: &OpenAiResponsesEncoder,
    provider_state: Option<ProviderSessionState>,
-) -> Result<(), GatewayError> {
-    let response_id = encoder.response_id().ok_or_else(|| {
-        GatewayError::new(
-            GatewayErrorKind::Internal,
-            "gateway completed a response without an identity",
-        )
-    })?;
-    replay.commit(response_id.to_owned(), provider_state);
-    Ok(())
+) {
+    if let Some(response_id) = encoder.response_id() {
+        replay.commit(response_id.to_owned(), provider_state);
+    }
 }

 async fn confirm_completed_execution(
@@ -595,21 +571,24 @@ fn response_metadata_event(
    request_id: &str,
    response_headers: &[ProviderResponseHeader],
 ) -> String {
-    let mut headers = response_headers
-        .iter()
-        .filter_map(|header| {
-            super::safe_response_header_name(header.name()).map(|name| {
-                (
-                    name.to_owned(),
-                    Value::String(header.value().as_str().to_owned()),
-                )
-            })
-        })
-        .collect::<Map<String, Value>>();
-    headers.insert(
-        "x-request-id".to_owned(),
-        Value::String(request_id.to_owned()),
-    );
+    let connection_options = super::response_connection_options(response_headers);
+    let mut headers = Map::new();
+    for header in response_headers {
+        if !super::response_header_is_forwardable(header.name(), &connection_options) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+            continue;
+        };
+        let Ok(value) = std::str::from_utf8(header.value()) else {
+            continue;
+        };
+        // 官方 response.metadata 使用 string map，无法表达同名多值；后值保持既有覆盖语义。
+        headers.insert(name.as_str().to_owned(), Value::String(value.to_owned()));
+    }
+    headers
+        .entry("x-request-id".to_owned())
+        .or_insert_with(|| Value::String(request_id.to_owned()));
    json!({
        "type": "response.metadata",
        "headers": headers,
@@ -13,9 +13,6 @@ use super::{

 use crate::ApiState;

-/// OpenAI 请求正文上限。
-pub const MAX_CLIENT_REQUEST_BODY_BYTES: usize = 16 * 1024 * 1024;
-
 /// 构造 OpenAI 客户端协议路由。
 pub(crate) fn router() -> Router<ApiState> {
    Router::new()
@@ -26,5 +23,7 @@ pub(crate) fn router() -> Router<ApiState> {
        .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))
-        .layer(DefaultBodyLimit::max(MAX_CLIENT_REQUEST_BODY_BYTES))
+        // Responses 正文属于 OpenAI/Codex 协议；代理不能用私有大小上限提前拒绝
+        // 上游本可接受的未来 payload。
+        .layer(DefaultBodyLimit::disable())
 }
@@ -81,16 +81,10 @@ impl OpenAiService {
                    "requested model was not found",
                )
            })?;
-        if !self.execution.contains_public_model(&client, &public_model) {
-            return Err(GatewayError::new(
-                GatewayErrorKind::ModelNotFound,
-                "requested model was not found",
-            ));
-        }
        let previous_response_id = match metadata.continuation() {
            ContinuationIntent::None => None,
            ContinuationIntent::PreviousResponseId(value) => {
-                PreviousResponseId::new(value.clone()).ok()
+                Some(PreviousResponseId::new(value.clone()))
            }
        };
        self.execution
@@ -105,12 +105,15 @@ mod actions {
    use gateway_admin::model::{
        Revision,
        accounts::{AccountConnectionTestEvent as DomainConnectionTestEvent, AccountStatus},
-        provider_credentials::{CredentialDeletionResult, CredentialImportResult},
+        provider_credentials::{
+            CredentialDeletionResult, CredentialImportResult, CredentialMutationResult,
+        },
    };
    use gateway_api::admin::accounts::{
        AccountActionRequest, AccountConnectionTestEvent, AccountDeletionData,
        AccountDeletionRequest, AccountExportData, AccountExportQuery, AccountIdQuery,
-        AccountImportData, AccountImportRequest, AccountRefreshRequest, AccountTestQuery,
+        AccountImportData, AccountImportRequest, AccountMutationData, AccountRefreshRequest,
+        AccountTestQuery, RotateAccountRequest, StartAccountAuthorizationRequest,
    };
    use gateway_core::engine::credential::ProviderAccountId;
    use serde_json::json;
@@ -147,7 +150,7 @@ mod actions {
    }

    #[test]
-    fn account_actions_should_require_frozen_account_ids_and_revision() {
+    fn account_actions_should_require_frozen_account_ids_and_reject_unknown_revision() {
        let id: AccountIdQuery =
            serde_json::from_value(json!({ "accountId": "acct_1" })).expect("decode ID query");
        assert!(id.validate().is_ok());
@@ -155,13 +158,68 @@ mod actions {
            serde_json::from_value(json!({ "accountId": "legacy-id" })).expect("decode action");
        assert_eq!(action.validate().unwrap_err().field(), "accountId");
        let refresh: AccountRefreshRequest = serde_json::from_value(json!({
-            "accountId": "acct_1",
-            "expectedConfigRevision": 0
+            "accountId": "acct_1"
        }))
        .expect("decode refresh");
+        assert!(refresh.validate().is_ok());
+        assert!(
+            serde_json::from_value::<AccountRefreshRequest>(json!({
+                "accountId": "acct_1",
+                "expectedConfigRevision": 0
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn credential_recovery_requests_should_not_accept_client_revision_fences() {
+        let authorization: StartAccountAuthorizationRequest = serde_json::from_value(json!({
+            "provider": "openai",
+            "name": "reauthorize",
+            "accountId": "acct_1"
+        }))
+        .expect("decode reauthorization");
+        assert!(authorization.validate().is_ok());
+        assert!(
+            serde_json::from_value::<StartAccountAuthorizationRequest>(json!({
+                "provider": "openai",
+                "name": "reauthorize",
+                "accountId": "acct_1",
+                "expectedCredentialRevision": 1
+            }))
+            .is_err()
+        );
+
+        let rotation: RotateAccountRequest = serde_json::from_value(json!({
+            "provider": "openai",
+            "accountId": "acct_1",
+            "accessToken": "header.payload.signature",
+            "refreshToken": "refresh-token"
+        }))
+        .expect("decode rotation");
+        assert!(rotation.validate().is_ok());
+        assert!(
+            serde_json::from_value::<RotateAccountRequest>(json!({
+                "provider": "openai",
+                "accountId": "acct_1",
+                "expectedCredentialRevision": 1,
+                "accessToken": "header.payload.signature"
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn credential_mutation_response_should_not_expose_internal_revision() {
+        let response = AccountMutationData::from(CredentialMutationResult {
+            config_revision: Revision::new(8).expect("config revision"),
+            account_id: ProviderAccountId::new("acct_1").expect("account ID"),
+            credential_revision: Some(Revision::new(9).expect("credential revision")),
+        });
+
        assert_eq!(
-            refresh.validate().unwrap_err().field(),
-            "expectedConfigRevision"
+            serde_json::to_value(response).expect("serialize credential mutation"),
+            json!({ "accountId": "acct_1" })
        );
    }

@@ -169,7 +227,6 @@ mod actions {
    fn account_import_should_use_provider_and_opaque_data_fields() {
        let valid: AccountImportRequest = serde_json::from_value(json!({
            "provider": "openai",
-            "expectedConfigRevision": 7,
            "data": {
                "providerOwnedUnknownField": {"nested": [1, 2, 3]},
                "accounts": [{"credentials": {"access_token": "provider-validates-this"}}]
@@ -180,7 +237,6 @@ mod actions {

        let invalid: AccountImportRequest = serde_json::from_value(json!({
            "provider": "xai",
-            "expectedConfigRevision": 7,
            "data": []
        }))
        .expect("decode invalid account import");
@@ -188,27 +244,32 @@ mod actions {
        assert!(
            serde_json::from_value::<AccountImportRequest>(json!({
                "provider": "openai",
-                "expectedConfigRevision": 7,
                "document": {}
            }))
            .is_err()
        );
+        assert!(
+            serde_json::from_value::<AccountImportRequest>(json!({
+                "provider": "openai",
+                "expectedConfigRevision": 7,
+                "data": {}
+            }))
+            .is_err()
+        );
    }

    #[test]
    fn account_deletion_should_validate_one_provider_batch_and_emit_account_ids() {
        let request: AccountDeletionRequest = serde_json::from_value(json!({
            "provider": "xai",
-            "accountIds": ["acct_1", "acct_2"],
-            "expectedConfigRevision": 8
+            "accountIds": ["acct_1", "acct_2"]
        }))
        .expect("decode account deletion");
        assert!(request.validate().is_ok());

        let duplicate: AccountDeletionRequest = serde_json::from_value(json!({
            "provider": "xai",
-            "accountIds": ["acct_1", "acct_1"],
-            "expectedConfigRevision": 8
+            "accountIds": ["acct_1", "acct_1"]
        }))
        .expect("decode duplicate account deletion");
        assert_eq!(duplicate.validate().unwrap_err().field(), "accountIds");
@@ -223,7 +284,6 @@ mod actions {
        assert_eq!(
            serde_json::to_value(response).expect("serialize account deletion"),
            json!({
-                "configRevision": 9,
                "deletedCount": 2,
                "accountIds": ["acct_1", "acct_2"]
            })
@@ -239,7 +299,6 @@ mod actions {
        assert_eq!(
            serde_json::to_value(response).expect("serialize account import"),
            json!({
-                "configRevision": 8,
                "importedCount": 1,
                "accountIds": ["acct_imported"]
            })
@@ -278,6 +337,9 @@ mod actions {
                message: "upstream unavailable".to_owned(),
                provider_error_code: Some("usage_exhausted".to_owned()),
                provider_error_type: Some("invalid_request_error".to_owned()),
+                upstream_status: Some(429),
+                upstream_content_type: Some("application/json".to_owned()),
+                upstream_body: Some(r#"{"error":{"type":"usage_limit_reached"}}"#.to_owned()),
                account_status: AccountStatus::Active,
            },
        ]
@@ -309,6 +371,9 @@ mod actions {
                    "error": "upstream unavailable",
                    "providerErrorCode": "usage_exhausted",
                    "providerErrorType": "invalid_request_error",
+                    "upstreamStatus": 429,
+                    "upstreamContentType": "application/json",
+                    "upstreamBody": r#"{"error":{"type":"usage_limit_reached"}}"#,
                    "accountStatus": "active"
                }),
            ]
@@ -1,6 +1,6 @@
 use chrono::{DateTime, TimeZone as _, Utc};
 use gateway_api::admin::client_keys::{
-    self, ClientKeyCursorData, ClientKeyCursorValue, ClientKeyListData, ClientKeyRevisionRequest,
+    self, ClientKeyCursorData, ClientKeyCursorValue, ClientKeyListData, ClientKeyMutationRequest,
    ClientKeySort, ClientKeySortDirection, ClientKeySortField, ClientKeyView,
    CreateClientKeyRequest, CreatedClientKeyData, ListClientKeysQuery, MutatedClientKeyData,
    RevealedClientKeyData, UpdateClientKeyRequest, decode_client_key_cursor,
@@ -101,9 +101,8 @@ fn client_key_queries_should_reject_unknown_zero_and_oversized_fields() {
 }

 #[test]
-fn client_key_mutations_should_validate_revision_text_limits_and_unknown_fields() {
+fn client_key_mutations_should_validate_text_limits_and_unknown_fields() {
    let valid = serde_json::from_value::<CreateClientKeyRequest>(json!({
-        "expectedConfigRevision": 7,
        "name": "terminal key",
        "label": "production",
        "providerKind": "openai",
@@ -113,22 +112,11 @@ fn client_key_mutations_should_validate_revision_text_limits_and_unknown_fields(
    .expect("deserialize create")
    .into_command()
    .expect("validate create");
-    assert_eq!(valid.expected_config_revision.get(), 7);
+    assert_eq!(valid.name, "terminal key");

    for (payload, field) in [
        (
            json!({
-                "expectedConfigRevision": 0,
-                "name": "key",
-                "providerKind": "openai",
-                "maxConcurrency": 0,
-                "requestsPerMinute": 0
-            }),
-            "expectedConfigRevision",
-        ),
-        (
-            json!({
-                "expectedConfigRevision": 1,
                "name": " ",
                "providerKind": "openai",
                "maxConcurrency": 0,
@@ -138,7 +126,6 @@ fn client_key_mutations_should_validate_revision_text_limits_and_unknown_fields(
        ),
        (
            json!({
-                "expectedConfigRevision": 1,
                "name": "key",
                "providerKind": "openai",
                "maxConcurrency": u64::MAX,
@@ -170,14 +157,23 @@ fn client_key_mutations_should_validate_revision_text_limits_and_unknown_fields(
        }))
        .is_err()
    );
-    let revision = serde_json::from_value::<ClientKeyRevisionRequest>(json!({
-        "id": "key_1",
-        "expectedConfigRevision": 3
+    assert!(
+        serde_json::from_value::<CreateClientKeyRequest>(json!({
+            "expectedConfigRevision": 7,
+            "name": "terminal key",
+            "providerKind": "openai",
+            "maxConcurrency": 2,
+            "requestsPerMinute": 60
+        }))
+        .is_err()
+    );
+    let mutation_id = serde_json::from_value::<ClientKeyMutationRequest>(json!({
+        "id": "key_1"
    }))
-    .expect("deserialize revision mutation")
-    .into_parts()
-    .expect("validate revision mutation");
-    assert_eq!(revision, ("key_1".to_owned(), 3));
+    .expect("deserialize mutation")
+    .into_id()
+    .expect("validate mutation");
+    assert_eq!(mutation_id, "key_1");
 }

 #[test]
@@ -225,9 +221,9 @@ fn client_key_responses_should_keep_shape_and_redact_creation_debug() {
        updated_at: created_at,
        last_used_at: Some(created_at),
    });
-    let list = serde_json::to_value(ClientKeyListData::new(9, vec![view], None, 1))
-        .expect("serialize list");
-    assert_eq!(list["configRevision"], 9);
+    let list =
+        serde_json::to_value(ClientKeyListData::new(vec![view], None, 1)).expect("serialize list");
+    assert!(list.get("configRevision").is_none());
    assert_eq!(list["total"], 1);
    assert_eq!(list["items"][0]["id"], "key_visible");
    assert_eq!(list["items"][0]["providerKind"], "openai");
@@ -248,7 +244,6 @@ fn client_key_responses_should_keep_shape_and_redact_creation_debug() {

    let plaintext = format!("sk_{}", "a".repeat(43));
    let created = CreatedClientKeyData::new(
-        10,
        "key_created".to_owned(),
        "sk_aaaaaaaaa".to_owned(),
        plaintext.clone(),
@@ -263,9 +258,9 @@ fn client_key_responses_should_keep_shape_and_redact_creation_debug() {
        json!({ "id": "key_created", "plaintextKey": plaintext })
    );
    assert_eq!(
-        serde_json::to_value(MutatedClientKeyData::new(11, "key_created".to_owned()))
+        serde_json::to_value(MutatedClientKeyData::new("key_created".to_owned()))
            .expect("serialize mutation"),
-        json!({ "configRevision": 11, "id": "key_created" })
+        json!({ "id": "key_created" })
    );
 }

@@ -58,9 +58,8 @@ use gateway_api::admin::AdminSessionState;
 use gateway_core::{
    engine::{
        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeRequest, AccountProbeResult},
+        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
    },
-    error::GatewayError,
    policy::{ClientApiKeyId, RateLimits},
    routing::{
        ConfigRevision, ProviderKind, PublicModelId, UpstreamModelId, snapshot::SnapshotControl,
@@ -279,8 +278,9 @@ impl SettingsStore for MemorySettingsStore {
        command: ReplaceRuntimeSettings,
        _: &MutationContext,
    ) -> AdminStoreResult<RuntimeSettings> {
+        let mut settings = self.settings.lock().expect("settings");
        let updated = RuntimeSettings {
-            config_revision: next_revision(command.expected_config_revision),
+            config_revision: next_revision(settings.config_revision),
            model_mappings: command.model_mappings,
            refresh_margin_seconds: command.refresh_margin_seconds,
            refresh_concurrency: command.refresh_concurrency,
@@ -292,31 +292,31 @@ impl SettingsStore for MemorySettingsStore {
            audit_retention_days: command.audit_retention_days,
            updated_at: Utc::now(),
        };
-        *self.settings.lock().expect("settings") = updated.clone();
+        *settings = updated.clone();
        Ok(updated)
    }

    async fn replace_admin_api_key(
        &self,
-        expected_config_revision: Revision,
        key: AdminApiKey,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
        *self.api_key.lock().expect("API key") = Some(key);
+        let revision = self.settings.lock().expect("settings").config_revision;
        Ok(AdminApiKeyMutation {
-            config_revision: next_revision(expected_config_revision),
+            config_revision: next_revision(revision),
            exists: true,
        })
    }

    async fn delete_admin_api_key(
        &self,
-        expected_config_revision: Revision,
        _: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
        *self.api_key.lock().expect("API key") = None;
+        let revision = self.settings.lock().expect("settings").config_revision;
        Ok(AdminApiKeyMutation {
-            config_revision: next_revision(expected_config_revision),
+            config_revision: next_revision(revision),
            exists: false,
        })
    }
@@ -674,7 +674,7 @@ impl AccountProbe for NoopProbe {
    fn probe(
        &self,
        _: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>> {
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
        Box::pin(async { panic!("unused account probe") })
    }
 }
@@ -326,6 +326,7 @@ async fn usage_route_should_expose_image_and_websocket_facts() {
            upstream_transport: Some("http_sse".to_owned()),
            http_version: Some("h2".to_owned()),
            websocket_pool: Some("reuse".to_owned()),
+            service_tier: Some("priority".to_owned()),
            provider_metadata_json: Some(
                serde_json::json!({
                    "effectiveModel": "grok-4.5",
@@ -402,6 +403,7 @@ async fn usage_route_should_expose_image_and_websocket_facts() {
    assert_eq!(
        serde_json::json!({
            "route": value["data"]["items"][0]["route"],
+            "serviceTier": value["data"]["items"][0]["serviceTier"],
            "authenticationKind": value["data"]["items"][0]["authenticationKind"],
            "imageInputTokens": value["data"]["items"][0]["tokenDetails"]["imageInputTokens"],
            "imageOutputTokens": value["data"]["items"][0]["tokenDetails"]["imageOutputTokens"],
@@ -428,6 +430,7 @@ async fn usage_route_should_expose_image_and_websocket_facts() {
        }),
        serde_json::json!({
            "route": "/v1/responses",
+            "serviceTier": "priority",
            "authenticationKind": "oauth",
            "imageInputTokens": 31,
            "imageOutputTokens": 9,
@@ -37,7 +37,6 @@ async fn response_json(response: axum::response::Response) -> Value {

 fn update_body() -> Value {
    json!({
-        "expectedConfigRevision": 7,
        "modelMappings": {
            "gpt-5.4": "gpt-5.5",
            "grok-latest": "grok-4.5"
@@ -64,22 +63,11 @@ fn settings_request_should_reject_unknown_rotation_strategy() {
 }

 #[test]
-fn settings_request_should_require_positive_revision() {
+fn settings_request_should_reject_unknown_revision_field() {
    let mut body = update_body();
-    body["expectedConfigRevision"] = json!(0);
-    let request: UpdateRuntimeSettingsRequest =
-        serde_json::from_value(body).expect("decode settings");
-    assert_eq!(
-        request.validate().unwrap_err().field(),
-        "expectedConfigRevision"
-    );
+    body["expectedConfigRevision"] = json!(7);

-    let mut missing = update_body();
-    missing
-        .as_object_mut()
-        .expect("settings object")
-        .remove("expectedConfigRevision");
-    assert!(serde_json::from_value::<UpdateRuntimeSettingsRequest>(missing).is_err());
+    assert!(serde_json::from_value::<UpdateRuntimeSettingsRequest>(body).is_err());
 }

 #[test]
@@ -124,7 +112,7 @@ async fn settings_post_should_replace_global_model_mappings() {
        .expect("settings update response");
    let data = response_json(response).await["data"].clone();

-    assert_eq!(data["configRevision"], 8);
+    assert!(data.get("configRevision").is_none());
    assert_eq!(data["modelMappings"]["gpt-5.4"], "gpt-5.5");
    assert_eq!(data["modelMappings"]["grok-latest"], "grok-4.5");
 }
@@ -135,6 +135,35 @@ fn local_provider_capacity_exhaustion_should_map_to_service_unavailable() {
    );
 }

+#[test]
+fn local_provider_capacity_exhaustion_should_preserve_safe_provider_detail() {
+    let detail = ClientVisibleUpstreamError::new(
+        "no account is eligible for the requested model",
+        Some("no_eligible_account".to_owned()),
+        Some("account_unavailable_error".to_owned()),
+    );
+    let error = EngineError::Provider(
+        ProviderError::new(ProviderErrorKind::Unavailable, UpstreamSendState::NotSent)
+            .with_client_visible_upstream_error(detail),
+    );
+    let gateway = gateway_error_from_engine(&error);
+
+    assert_eq!(gateway.kind(), GatewayErrorKind::NoAvailableProvider);
+    assert_eq!(
+        gateway.client_message(),
+        "no account is eligible for the requested model"
+    );
+    assert_eq!(gateway.client_error_code(), Some("no_eligible_account"));
+    assert_eq!(
+        gateway.client_error_type(),
+        Some("account_unavailable_error")
+    );
+    assert_eq!(
+        gateway.safe_message(),
+        "no upstream provider is currently available for this request"
+    );
+}
+
 #[test]
 fn no_eligible_provider_account_should_map_to_service_unavailable() {
    let error = EngineError::Provider(ProviderError::new(
@@ -297,14 +326,11 @@ fn openai_error_response_should_preserve_only_safe_contract_fields() {
 async fn gateway_error_response_should_expose_only_structured_client_visible_upstream_fields() {
    let error = GatewayError::from_provider(
        &ProviderError::new(ProviderErrorKind::QuotaExhausted, UpstreamSendState::Sent)
-            .with_client_visible_upstream_error(
-                ClientVisibleUpstreamError::new(
-                    "Your Codex quota is exhausted",
-                    Some("quota_exhausted".to_owned()),
-                    Some("rate_limit_error".to_owned()),
-                )
-                .expect("safe structured upstream error"),
-            ),
+            .with_client_visible_upstream_error(ClientVisibleUpstreamError::new(
+                "Your Codex quota is exhausted",
+                Some("quota_exhausted".to_owned()),
+                Some("rate_limit_error".to_owned()),
+            )),
    );

    let response = gateway_error_response(&error);
@@ -10,7 +10,9 @@ use gateway_core::engine::execution::{
    StartedExecution,
 };
 use gateway_core::error::{GatewayError, GatewayErrorKind};
-use gateway_core::routing::{ModelPresentation, PublicModelId, PublicModelProfile};
+use gateway_core::routing::{
+    ModelPresentation, ModelServiceTier, PublicModelId, PublicModelProfile,
+};
 use tower::ServiceExt;

 use super::{api_router, authenticated_client};
@@ -73,7 +75,15 @@ impl ExecutionService for ModelsExecution {
            )
            .with_context_window_tokens(Some(500_000))
            .with_image_input(true)
-            .with_agent_tools(true, true),
+            .with_agent_tools(true, true)
+            .with_service_tiers(vec![
+                ModelServiceTier::new(
+                    "priority",
+                    "Fast",
+                    "Route the request through Codex fast mode.",
+                )
+                .with_speed_tier("fast"),
+            ]),
        )]
    }

@@ -145,7 +155,15 @@ async fn models_should_encode_provider_profiles_for_current_codex_clients() {
    assert_eq!(model["default_reasoning_level"], "medium");
    assert_eq!(model["context_window"], 500_000);
    assert_eq!(model["apply_patch_tool_type"], "freeform");
-    assert_eq!(model["service_tiers"], serde_json::json!([]));
+    assert_eq!(model["additional_speed_tiers"], serde_json::json!(["fast"]));
+    assert_eq!(
+        model["service_tiers"],
+        serde_json::json!([{
+            "id": "priority",
+            "name": "Fast",
+            "description": "Route the request through Codex fast mode."
+        }])
+    );
    assert_eq!(
        model["supported_reasoning_levels"],
        serde_json::json!([
@@ -8,7 +8,10 @@ use std::sync::{
 use axum::{
    body::{Body, to_bytes},
    extract::connect_info::ConnectInfo,
-    http::{HeaderMap, Request, StatusCode, header::AUTHORIZATION},
+    http::{
+        HeaderMap, HeaderValue, Request, StatusCode,
+        header::{AUTHORIZATION, CONTENT_TYPE},
+    },
 };
 use bytes::Bytes;
 use futures::future::{BoxFuture, pending};
@@ -18,8 +21,8 @@ use gateway_core::engine::execution::{
 };
 use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError, UpstreamSendState};
 use gateway_core::error::{
-    ClientVisibleUpstreamError, GatewayError, GatewayErrorKind, ProviderError, ProviderErrorKind,
-    SafeUpstreamValue,
+    ClientVisibleUpstreamError, ClientVisibleUpstreamResponse, GatewayError, GatewayErrorKind,
+    ProviderError, ProviderErrorKind,
 };
 use gateway_core::event::{
    ContentItem, ContentKind, GatewayEvent, ProtocolWireEvent, ProviderEvent,
@@ -101,6 +104,8 @@ struct ContextCaptureExecution {

 #[derive(Debug, Clone, PartialEq)]
 struct CapturedClientContext {
+    public_model: String,
+    wire_model: Option<String>,
    client_ip: Option<IpAddr>,
    user_agent: Option<String>,
    endpoint: String,
@@ -109,6 +114,7 @@ struct CapturedClientContext {
    client_metadata: Option<Value>,
    protocol_context: Option<Value>,
    prompt_cache_key: Option<String>,
+    previous_response_id: Option<String>,
 }

 impl ExecutionService for ContextCaptureExecution {
@@ -124,11 +130,14 @@ impl ExecutionService for ContextCaptureExecution {
    }

    fn public_models(&self, _: &AuthenticatedClient) -> Vec<PublicModelId> {
-        Vec::new()
+        ["model-a", "model-b"]
+            .into_iter()
+            .map(|model| PublicModelId::new(model).expect("catalog model"))
+            .collect()
    }

-    fn contains_public_model(&self, _: &AuthenticatedClient, _: &PublicModelId) -> bool {
-        true
+    fn contains_public_model(&self, _: &AuthenticatedClient, model: &PublicModelId) -> bool {
+        matches!(model.as_str(), "model-a" | "model-b")
    }

    fn start(
@@ -136,11 +145,16 @@ impl ExecutionService for ContextCaptureExecution {
        request: StartExecution,
    ) -> BoxFuture<'_, Result<StartedExecution, GatewayError>> {
        Box::pin(async move {
+            let public_model = request.public_model.as_str().to_owned();
            let operation_kind = request.operation.kind();
            let generation = match &request.operation {
                Operation::Generate(generation) => Some(generation),
                _ => None,
            };
+            let wire_model = generation
+                .and_then(|generation| generation.protocol_payload().body().get("model"))
+                .and_then(Value::as_str)
+                .map(ToOwned::to_owned);
            let (client_metadata, protocol_context, prompt_cache_key, input) =
                generation.map_or((None, None, None, None), |generation| {
                    let payload = generation.protocol_payload();
@@ -152,7 +166,14 @@ impl ExecutionService for ContextCaptureExecution {
                        payload.body().get("input").cloned(),
                    )
                });
+            let previous_response_id = request
+                .metadata
+                .previous_response_id
+                .as_ref()
+                .map(|value| value.as_str().to_owned());
            *self.observed.lock().expect("context capture lock") = Some(CapturedClientContext {
+                public_model,
+                wire_model,
                client_ip: request.metadata.client_ip,
                user_agent: request.metadata.user_agent,
                endpoint: request.metadata.endpoint,
@@ -161,6 +182,7 @@ impl ExecutionService for ContextCaptureExecution {
                client_metadata,
                protocol_context,
                prompt_cache_key,
+                previous_response_id,
            });
            Err(GatewayError::new(
                GatewayErrorKind::Internal,
@@ -503,14 +525,19 @@ async fn request_context_should_resolve_forwarded_precedence_and_peer_fallback()
    assert_eq!(
        captured_client_context(headers, peer).await,
        CapturedClientContext {
+            public_model: "smart-code".to_owned(),
+            wire_model: Some("smart-code".to_owned()),
            client_ip: Some("198.51.100.1".parse().expect("expected IP")),
            user_agent: Some("Codex-CLI/1.0".to_owned()),
            endpoint: "/v1/responses".to_owned(),
            operation_kind: OperationKind::Generate,
            input: Some(json!("hello")),
            client_metadata: None,
-            protocol_context: None,
+            protocol_context: Some(json!({
+                "opaque_request_headers": [["user-agent", "IENvZGV4LUNMSS8xLjAg"]]
+            })),
            prompt_cache_key: None,
+            previous_response_id: None,
        }
    );

@@ -533,14 +560,58 @@ async fn request_context_should_resolve_forwarded_precedence_and_peer_fallback()
 }

 #[tokio::test]
-async fn http_request_should_forward_safe_codex_headers_without_projecting_xai_headers() {
+async fn stale_model_catalog_should_not_block_a_new_model_request() {
+    let model = "  gpt-future-codex  ";
+    let captured = captured_http_request(
+        "openai",
+        json!({"model": model, "input": "hello"}),
+        HeaderMap::new(),
+        None,
+    )
+    .await;
+
+    assert_eq!(captured.public_model, model);
+    assert_eq!(captured.wire_model.as_deref(), Some(model));
+}
+
+#[tokio::test]
+async fn http_request_should_pass_opaque_previous_response_id_to_core() {
+    for response_id in [
+        format!("resp_{}", "x".repeat(257)),
+        "resp_control\0opaque".to_owned(),
+        String::new(),
+    ] {
+        let captured = captured_http_request(
+            "openai",
+            json!({
+                "model": "smart-code",
+                "input": "continue",
+                "previous_response_id": response_id.clone()
+            }),
+            HeaderMap::new(),
+            None,
+        )
+        .await;
+
+        assert_eq!(
+            captured.previous_response_id.as_deref(),
+            Some(response_id.as_str())
+        );
+    }
+}
+
+#[tokio::test]
+async fn http_request_should_forward_codex_headers_without_projecting_xai_headers() {
    let peer = "192.0.2.10:443".parse().expect("peer address");
    let mut headers = HeaderMap::new();
    headers.insert("x-codex-turn-state", "turn-state".parse().expect("header"));
    headers.insert("conversation-id", "conversation-1".parse().expect("header"));
    headers.insert("session-id", "session-1".parse().expect("header"));
    headers.insert("x-grok-turn-idx", "7".parse().expect("header"));
-    headers.insert("x-openai-subagent", "compact".parse().expect("header"));
+    headers.insert(
+        "x-openai-subagent",
+        "future_codex_mode".parse().expect("header"),
+    );
    headers.insert(
        "x-openai-internal-codex-responses-lite",
        "true".parse().expect("header"),
@@ -566,10 +637,33 @@ async fn http_request_should_forward_safe_codex_headers_without_projecting_xai_h
            .client_metadata
            .as_ref()
            .and_then(|metadata| metadata.get("x-openai-subagent")),
-        Some(&json!("compact"))
+        Some(&json!("future_codex_mode"))
    );
 }

+#[tokio::test]
+async fn subagent_header_should_not_replace_non_object_client_metadata() {
+    let mut headers = HeaderMap::new();
+    headers.insert(
+        "x-openai-subagent",
+        "future_codex_mode".parse().expect("header"),
+    );
+
+    let captured = captured_http_request(
+        "openai",
+        json!({
+            "model": "smart-code",
+            "input": "preserve metadata",
+            "client_metadata": "opaque-client-value"
+        }),
+        headers,
+        None,
+    )
+    .await;
+
+    assert_eq!(captured.client_metadata, Some(json!("opaque-client-value")));
+}
+
 #[tokio::test]
 async fn xai_private_headers_should_not_enter_openai_request_facts() {
    let peer = "192.0.2.10:443".parse().expect("peer address");
@@ -632,6 +726,43 @@ async fn review_route_should_inject_review_subagent_and_record_its_endpoint() {
    );
 }

+#[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());
@@ -653,19 +784,22 @@ async fn streaming_encodes_first_frame_before_commit_and_http_delivery() {
 }

 #[tokio::test]
-async fn streaming_response_forwards_only_allowlisted_provider_headers() {
+async fn streaming_response_should_append_ordinary_headers_and_skip_unrepresentable_or_sensitive_ones()
+ {
    let trace = Arc::new(Trace::default());
    let headers = vec![
-        ProviderResponseHeader::new(
-            "x-models-etag",
-            SafeUpstreamValue::new("models-v2").expect("etag"),
-        )
-        .expect("safe header"),
+        ProviderResponseHeader::new("x-models-etag", Bytes::from_static(b"models-v2")),
+        ProviderResponseHeader::new("x-future-multi", Bytes::from_static(b"first")),
+        ProviderResponseHeader::new("x-future-multi", Bytes::from_static(b"second")),
+        ProviderResponseHeader::new("x-future-bytes", Bytes::from_static(b"\xffopaque")),
        ProviderResponseHeader::new(
            "authorization",
-            SafeUpstreamValue::new("should-not-cross-boundary").expect("header value"),
-        )
-        .expect("syntactically safe header"),
+            Bytes::from_static(b"should-not-cross-boundary"),
+        ),
+        ProviderResponseHeader::new("connection", Bytes::from_static(b"x-hop-secret")),
+        ProviderResponseHeader::new("x-hop-secret", Bytes::from_static(b"hop-secret")),
+        ProviderResponseHeader::new("content-type", Bytes::from_static(b"application/private")),
+        ProviderResponseHeader::new("bad\0name", Bytes::from_static(b"unrepresentable")),
    ];
    let session = FakeSession::streaming(
        Arc::clone(&trace),
@@ -685,7 +819,29 @@ async fn streaming_response_forwards_only_allowlisted_provider_headers() {
            .and_then(|value| value.to_str().ok()),
        Some("models-v2")
    );
+    assert_eq!(
+        response
+            .headers()
+            .get_all("x-future-multi")
+            .iter()
+            .map(HeaderValue::as_bytes)
+            .collect::<Vec<_>>(),
+        vec![b"first".as_slice(), b"second".as_slice()]
+    );
+    assert_eq!(
+        response
+            .headers()
+            .get("x-future-bytes")
+            .map(HeaderValue::as_bytes),
+        Some(b"\xffopaque".as_slice())
+    );
    assert!(response.headers().get("authorization").is_none());
+    assert!(response.headers().get("connection").is_none());
+    assert!(response.headers().get("x-hop-secret").is_none());
+    assert_eq!(
+        response.headers().get(CONTENT_TYPE),
+        Some(&HeaderValue::from_static("text/event-stream"))
+    );
    std::mem::forget(response);
 }

@@ -801,7 +957,107 @@ async fn streaming_rate_limit_before_first_frame_should_persist_the_returned_429
 }

 #[tokio::test]
-async fn streaming_postcommit_encode_failure_cancels_without_second_commit() {
+async fn streaming_upstream_http_failure_before_first_frame_should_preserve_raw_response() {
+    let trace = Arc::new(Trace::default());
+    let raw_body = Bytes::from_static(
+        b"{\"error\":{\"message\":\"rate limited\",\"future_field\":{\"kept\":true}},\"top_level\":17}\x00",
+    );
+    let error = ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
+        .with_client_visible_upstream_response(
+            ClientVisibleUpstreamResponse::new(
+                429,
+                Some(b"application/problem+json; charset=utf-8".to_vec()),
+                raw_body.clone(),
+            )
+            .with_headers(vec![
+                ProviderResponseHeader::new("retry-after", Bytes::from_static(b"17")),
+                ProviderResponseHeader::new("x-request-id", Bytes::from_static(b"req-failure")),
+                ProviderResponseHeader::new("x-future-error", Bytes::from_static(b"first")),
+                ProviderResponseHeader::new("x-future-error", Bytes::from_static(b"second")),
+                ProviderResponseHeader::new("x-future-bytes", Bytes::from_static(b"\xffopaque")),
+            ]),
+        );
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![NextStep::Error(EngineError::Provider(error))],
+    );
+
+    let response = stream_execution_response(Box::new(session), None).await;
+
+    assert_eq!(response.status(), StatusCode::TOO_MANY_REQUESTS);
+    assert_eq!(
+        response
+            .headers()
+            .get(CONTENT_TYPE)
+            .map(|value| value.as_bytes()),
+        Some(b"application/problem+json; charset=utf-8".as_slice())
+    );
+    assert_eq!(
+        response
+            .headers()
+            .get("retry-after")
+            .map(|value| value.as_bytes()),
+        Some(b"17".as_slice())
+    );
+    assert_eq!(
+        response
+            .headers()
+            .get("x-request-id")
+            .map(|value| value.as_bytes()),
+        Some(b"req-failure".as_slice())
+    );
+    assert_eq!(
+        response
+            .headers()
+            .get_all("x-future-error")
+            .iter()
+            .map(|value| value.as_bytes())
+            .collect::<Vec<_>>(),
+        vec![b"first".as_slice(), b"second".as_slice()]
+    );
+    assert_eq!(
+        response
+            .headers()
+            .get("x-future-bytes")
+            .map(|value| value.as_bytes()),
+        Some(b"\xffopaque".as_slice())
+    );
+    assert_eq!(
+        to_bytes(response.into_body(), usize::MAX)
+            .await
+            .expect("read raw error body"),
+        raw_body
+    );
+    assert_eq!(trace.client_statuses(), vec![429]);
+}
+
+#[tokio::test]
+async fn buffered_upstream_http_failure_should_preserve_raw_response() {
+    let trace = Arc::new(Trace::default());
+    let raw_body = Bytes::from_static(b"not-json\xffstill-upstream");
+    let error = ProviderError::new(ProviderErrorKind::Unavailable, UpstreamSendState::Sent)
+        .with_client_visible_upstream_response(ClientVisibleUpstreamResponse::new(
+            503,
+            Some(b"application/octet-stream".to_vec()),
+            raw_body.clone(),
+        ));
+    let session = FakeSession::buffered(Arc::clone(&trace), vec![started(), completed()])
+        .with_collect_error(EngineError::Provider(error));
+
+    let response = collect_execution_response(Box::new(session)).await;
+
+    assert_eq!(response.status(), StatusCode::SERVICE_UNAVAILABLE);
+    assert_eq!(
+        to_bytes(response.into_body(), usize::MAX)
+            .await
+            .expect("read raw error body"),
+        raw_body
+    );
+    assert_eq!(trace.client_statuses(), vec![503]);
+}
+
+#[tokio::test]
+async fn streaming_canonical_identity_change_does_not_interrupt_wire_delivery() {
    let trace = Arc::new(Trace::default());
    let session = FakeSession::streaming(
        Arc::clone(&trace),
@@ -811,7 +1067,7 @@ async fn streaming_postcommit_encode_failure_cancels_without_second_commit() {
                mismatched_terminal_event(),
                CommitRequirement::AlreadyCommitted,
            )),
-            NextStep::FinalizeCancelled,
+            NextStep::FinalizeSuccess,
        ],
    );

@@ -820,12 +1076,16 @@ async fn streaming_postcommit_encode_failure_cancels_without_second_commit() {
        .await
        .expect("read SSE body");

-    assert!(String::from_utf8_lossy(&body).contains("response.failed"));
+    let body = String::from_utf8_lossy(&body);
+    assert!(body.contains("response.completed"));
+    assert!(body.contains("resp_other"));
+    assert!(!body.contains("response.failed"));
+    assert!(body.ends_with("data: [DONE]\n\n"));
    assert_eq!(trace.client_statuses(), vec![200]);
-    assert!(trace.is_cancelled());
+    assert!(!trace.is_cancelled());
    assert_eq!(
        trace.snapshot(),
-        vec!["next_event", "commit", "next_event", "cancel_finalize"]
+        vec!["next_event", "commit", "next_event", "next_end"]
    );
 }

@@ -874,6 +1134,38 @@ async fn streaming_success_should_emit_terminal_event_and_done_marker() {
    );
 }

+#[tokio::test]
+async fn streaming_finalized_unknown_wire_should_end_cleanly_without_synthetic_failure() {
+    let trace = Arc::new(Trace::default());
+    let raw = Bytes::from_static(
+        b"event: response.future_terminal\ndata: {\"type\":\"response.future_terminal\",\"opaque\":true}\n\n",
+    );
+    let event = ProviderEvent::wire(
+        ProtocolWireEvent::raw_sse("openai", raw.clone()).expect("raw future event"),
+    );
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::Event(delivery_provider(
+                event,
+                CommitRequirement::CommitBeforeDelivery,
+            )),
+            NextStep::FinalizeSuccess,
+        ],
+    );
+
+    let response = stream_execution_response(Box::new(session), None).await;
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read transparent SSE body");
+
+    assert!(body.as_ref().starts_with(raw.as_ref()));
+    assert!(body.as_ref().ends_with(b"data: [DONE]\n\n"));
+    assert!(!String::from_utf8_lossy(&body).contains("response.failed"));
+    assert!(!trace.is_cancelled());
+    assert_eq!(trace.snapshot(), vec!["next_event", "commit", "next_end"]);
+}
+
 #[tokio::test]
 async fn streaming_completed_event_without_finalized_execution_should_fail_closed() {
    let trace = Arc::new(Trace::default());
@@ -942,14 +1234,11 @@ async fn streaming_empty_terminal_should_emit_failure_done_and_cancel_execution(
 async fn streaming_error_should_emit_client_visible_upstream_details() {
    let trace = Arc::new(Trace::default());
    let error = ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
-        .with_client_visible_upstream_error(
-            ClientVisibleUpstreamError::new(
-                "Your Codex quota is exhausted",
-                Some("quota_exhausted".to_owned()),
-                Some("rate_limit_error".to_owned()),
-            )
-            .expect("safe structured upstream error"),
-        );
+        .with_client_visible_upstream_error(ClientVisibleUpstreamError::new(
+            "Your Codex quota is exhausted",
+            Some("quota_exhausted".to_owned()),
+            Some("rate_limit_error".to_owned()),
+        ));
    let session = FakeSession::streaming(
        Arc::clone(&trace),
        vec![
@@ -1055,6 +1344,86 @@ async fn streaming_upstream_wire_failure_should_not_be_rewritten_as_a_gateway_er
    );
 }

+#[tokio::test]
+async fn atomic_uncommitted_upstream_failure_batch_should_be_forwarded_once() {
+    let trace = Arc::new(Trace::default());
+    let raw_created = Bytes::from_static(
+        b"event: response.created\r\ndata: {\"type\":\"response.created\",\"response\":{\"id\":\"resp_atomic_api\",\"model\":\"public-model\",\"status\":\"in_progress\"}}\r\n\r\n",
+    );
+    let raw_failure = Bytes::from_static(
+        b"event: response.failed\r\ndata: {\"type\":\"response.failed\",\"response\":{\"id\":\"resp_atomic_api\",\"status\":\"failed\",\"error\":{\"code\":\"rate_limit_exceeded\",\"message\":\"atomic upstream marker\"}}}\r\n\r\n",
+    );
+    let started_wire = ProviderEvent::canonical_with_wire(
+        vec![started()],
+        ProtocolWireEvent::json_with_raw_sse_metadata(
+            "openai",
+            Some("response.created".to_owned()),
+            json!({
+                "type": "response.created",
+                "response": {
+                    "id": "resp_atomic_api",
+                    "model": "public-model",
+                    "status": "in_progress"
+                }
+            }),
+            raw_created.clone(),
+            None,
+            None,
+        )
+        .expect("valid upstream started wire"),
+    );
+    let failed_wire = ProviderEvent::wire(
+        ProtocolWireEvent::json_with_raw_sse_metadata(
+            "openai",
+            Some("response.failed".to_owned()),
+            json!({
+                "type": "response.failed",
+                "response": {
+                    "id": "resp_atomic_api",
+                    "status": "failed",
+                    "error": {
+                        "code": "rate_limit_exceeded",
+                        "message": "atomic upstream marker"
+                    }
+                }
+            }),
+            raw_failure.clone(),
+            None,
+            None,
+        )
+        .expect("valid upstream failure wire"),
+    );
+    let batch = CoordinatedEvent::try_batch(
+        vec![started_wire, failed_wire],
+        CommitRequirement::CommitBeforeDelivery,
+    )
+    .expect("atomic failure delivery");
+    let session = FakeSession::streaming(
+        Arc::clone(&trace),
+        vec![
+            NextStep::Event(batch),
+            NextStep::Error(EngineError::Provider(ProviderError::new(
+                ProviderErrorKind::RateLimited,
+                UpstreamSendState::Sent,
+            ))),
+        ],
+    );
+
+    let response = stream_execution_response(Box::new(session), None).await;
+    let body = to_bytes(response.into_body(), usize::MAX)
+        .await
+        .expect("read SSE body");
+    let body = String::from_utf8(body.to_vec()).expect("SSE is UTF-8");
+
+    assert_eq!(body.matches("atomic upstream marker").count(), 1);
+    assert_eq!(body.matches("event: response.failed").count(), 1);
+    assert!(body.contains(std::str::from_utf8(&raw_created).expect("created frame")));
+    assert!(body.contains(std::str::from_utf8(&raw_failure).expect("failure frame")));
+    assert!(!body.contains("upstream capacity is temporarily unavailable"));
+    assert!(body.ends_with("data: [DONE]\n\n"));
+    assert_eq!(trace.snapshot(), vec!["next_event", "commit", "next_error"]);
+}
+
 #[tokio::test]
 async fn streaming_second_commit_request_should_fail_and_finalize_once() {
    let trace = Arc::new(Trace::default());
@@ -1132,13 +1501,10 @@ async fn buffered_response_commits_only_after_complete_json_is_encoded() {
 }

 #[tokio::test]
-async fn buffered_response_forwards_allowlisted_provider_headers() {
+async fn buffered_response_forwards_long_ordinary_provider_header_values() {
    let trace = Arc::new(Trace::default());
-    let header = ProviderResponseHeader::new(
-        "openai-model",
-        SafeUpstreamValue::new("gpt-5.5-effective").expect("model header"),
-    )
-    .expect("safe header");
+    let model = format!("gpt-{}", "x".repeat(512));
+    let header = ProviderResponseHeader::new("openai-model", Bytes::from(model.clone()));
    let session = FakeSession::buffered(Arc::clone(&trace), vec![started(), completed()])
        .with_response_headers(vec![header]);

@@ -1149,7 +1515,7 @@ async fn buffered_response_forwards_allowlisted_provider_headers() {
            .headers()
            .get("openai-model")
            .and_then(|value| value.to_str().ok()),
-        Some("gpt-5.5-effective")
+        Some(model.as_str())
    );
 }

@@ -2,6 +2,7 @@ mod http;
 mod websocket;

 use axum::http::{HeaderMap, HeaderValue};
+use base64::{Engine as _, engine::general_purpose::STANDARD};
 use bytes::Bytes;
 use gateway_api::openai::responses::{
    ContinuationIntent, DecodedResponsesRequest, OpenAiRequestHeaders, OpenAiResponsesEncoder,
@@ -117,6 +118,28 @@ fn decoder_should_preserve_the_openai_body_and_only_derive_stable_routing_facts(
    assert!(decoded.metadata().store());
 }

+#[test]
+fn decoder_should_preserve_opaque_client_model_values() {
+    for model in [
+        format!("future-{}", "x".repeat(512)),
+        "future\0model".to_owned(),
+        "  future-model  ".to_owned(),
+    ] {
+        let decoded = generate_request(json!({
+            "model": model.clone(),
+            "input": "hello"
+        }));
+
+        assert_eq!(decoded.metadata().public_model(), model);
+        assert_eq!(
+            openai_wire_body(&decoded)
+                .get("model")
+                .and_then(Value::as_str),
+            Some(model.as_str())
+        );
+    }
+}
+
 #[test]
 fn decoder_should_preserve_compaction_trigger_for_the_openai_provider() {
    let decoded = generate_request(json!({
@@ -149,6 +172,21 @@ fn decoder_should_keep_transport_override_out_of_the_openai_wire_body() {
    );
 }

+#[test]
+fn decoder_should_preserve_unrecognized_use_websocket_values() {
+    let decoded = generate_request(json!({
+        "model": "smart-code",
+        "input": "hello",
+        "use_websocket": {"future": "transport-mode"}
+    }));
+
+    assert_eq!(
+        openai_wire_body(&decoded).get("use_websocket"),
+        Some(&json!({"future": "transport-mode"}))
+    );
+    assert!(!openai_protocol_context(&decoded).contains_key("use_websocket"));
+}
+
 #[test]
 fn decoder_should_preserve_connection_metadata_outside_the_openai_wire_body() {
    let mut headers = HeaderMap::new();
@@ -170,10 +208,142 @@ fn decoder_should_preserve_connection_metadata_outside_the_openai_wire_body() {
            ("turn_state".to_owned(), json!("turn-state")),
            ("turn_metadata".to_owned(), json!("{\"kind\":\"review\"}")),
            ("conversation_id".to_owned(), json!("conversation")),
+            (
+                "opaque_request_headers".to_owned(),
+                json!([
+                    ["x-codex-turn-state", STANDARD.encode(b"turn-state")],
+                    [
+                        "x-codex-turn-metadata",
+                        STANDARD.encode(br#"{"kind":"review"}"#)
+                    ],
+                    ["conversation-id", STANDARD.encode(b"conversation")]
+                ]),
+            ),
        ])
    );
 }

+#[test]
+fn decoder_should_preserve_ordinary_request_headers_as_opaque_multivalues() {
+    let mut headers = HeaderMap::new();
+    headers.append(
+        "x-openai-future-mode",
+        HeaderValue::from_static("future-ascii"),
+    );
+    headers.append(
+        "x-openai-future-mode",
+        HeaderValue::from_bytes(b"\x80\xff").expect("opaque header bytes"),
+    );
+    headers.append("version", HeaderValue::from_static("future-v1"));
+    headers.append(
+        "version",
+        HeaderValue::from_bytes(b"future-\x80").expect("opaque known header bytes"),
+    );
+    headers.insert(
+        "accept",
+        HeaderValue::from_static("application/vnd.openai.responses+json"),
+    );
+    headers.insert(
+        "content-type",
+        HeaderValue::from_static("application/vnd.openai.responses.request+json"),
+    );
+    headers.insert(
+        "user-agent",
+        HeaderValue::from_static("Codex future-client"),
+    );
+    headers.insert("originator", HeaderValue::from_static("future-codex"));
+    headers.append(
+        "openai-beta",
+        HeaderValue::from_static("future_responses=v2"),
+    );
+    headers.append("openai-beta", HeaderValue::from_static("future_tools=v3"));
+    headers.insert(
+        "x-openai-internal-codex-residency",
+        HeaderValue::from_static("future-region"),
+    );
+    headers.insert(
+        "x-codex-turn-state",
+        HeaderValue::from_static("same-account-turn"),
+    );
+
+    headers.insert(
+        "connection",
+        HeaderValue::from_static("keep-alive, x-private-hop"),
+    );
+    headers.insert("x-private-hop", HeaderValue::from_static("drop-me"));
+    headers.insert("host", HeaderValue::from_static("downstream.invalid"));
+    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("cookie", HeaderValue::from_static("client=cookie"));
+    headers.insert(
+        "chatgpt-account-id",
+        HeaderValue::from_static("client-account"),
+    );
+    headers.insert(
+        "chatgpt-project-id",
+        HeaderValue::from_static("client-project"),
+    );
+    headers.insert(
+        "x-codex-installation-id",
+        HeaderValue::from_static("client-installation"),
+    );
+
+    let decoded =
+        decode_request_with_headers(br#"{"model":"smart-code","input":"hello"}"#, &headers)
+            .expect("opaque request headers should not affect body decoding");
+    let entries = openai_protocol_context(&decoded)
+        .get("opaque_request_headers")
+        .and_then(Value::as_array)
+        .expect("opaque request header context");
+    let values = |target: &str| {
+        entries
+            .iter()
+            .filter_map(Value::as_array)
+            .filter(|entry| entry.first().and_then(Value::as_str) == Some(target))
+            .filter_map(|entry| entry.get(1).and_then(Value::as_str))
+            .map(|encoded| STANDARD.decode(encoded).expect("valid base64 header value"))
+            .collect::<Vec<_>>()
+    };
+
+    assert_eq!(
+        values("x-openai-future-mode"),
+        vec![b"future-ascii".to_vec(), b"\x80\xff".to_vec()]
+    );
+    assert_eq!(
+        values("version"),
+        vec![b"future-v1".to_vec(), b"future-\x80".to_vec()]
+    );
+    assert_eq!(
+        values("openai-beta"),
+        vec![b"future_responses=v2".to_vec(), b"future_tools=v3".to_vec()]
+    );
+    for preserved in [
+        "accept",
+        "content-type",
+        "user-agent",
+        "originator",
+        "x-openai-internal-codex-residency",
+        "x-codex-turn-state",
+    ] {
+        assert_eq!(values(preserved).len(), 1, "missing {preserved}");
+    }
+    for excluded in [
+        "connection",
+        "x-private-hop",
+        "host",
+        "content-length",
+        "authorization",
+        "x-api-key",
+        "cookie",
+        "chatgpt-account-id",
+        "chatgpt-project-id",
+        "x-codex-installation-id",
+    ] {
+        assert!(values(excluded).is_empty(), "unexpected {excluded}");
+    }
+}
+
 #[test]
 fn decoder_should_preserve_unknown_nested_values_without_debug_disclosure() {
    let secret = "nested-private-value";
@@ -191,25 +361,51 @@ fn decoder_should_preserve_unknown_nested_values_without_debug_disclosure() {
 }

 #[test]
-fn decoder_should_preserve_continuation_and_mark_the_routing_requirement() {
-    let decoded = generate_request(json!({
-        "model": "smart-code",
-        "input": "continue",
-        "previous_response_id": "resp_private_continuation"
-    }));
+fn decoder_should_preserve_unknown_arbitrary_precision_numbers() {
+    let number = "12345678901234567890123456789012345678901234567890";
+    let body = format!(r#"{{"model":"smart-code","input":"hello","future_number":{number}}}"#);

-    assert!(matches!(
-        decoded.metadata().continuation(),
-        ContinuationIntent::PreviousResponseId(value) if value == "resp_private_continuation"
-    ));
-    assert!(
-        decoded
-            .operation()
-            .capability_requirements()
-            .features()
-            .contains(&Feature::NativeContinuation)
-    );
-    assert!(!format!("{decoded:?}").contains("resp_private_continuation"));
+    let decoded = decode_request_with_headers(body.as_bytes(), &HeaderMap::new())
+        .expect("opaque numeric field should decode");
+    let encoded = serde_json::to_string(openai_wire_body(&decoded)).expect("encode request body");
+
+    assert!(encoded.contains(&format!(r#""future_number":{number}"#)));
+}
+
+#[test]
+fn decoder_should_preserve_opaque_continuation_and_mark_the_routing_requirement() {
+    for response_id in [
+        "resp_private_continuation".to_owned(),
+        format!("resp_{}\0opaque", "x".repeat(257)),
+        String::new(),
+    ] {
+        let decoded = generate_request(json!({
+            "model": "smart-code",
+            "input": "continue",
+            "previous_response_id": response_id.clone()
+        }));
+
+        assert!(matches!(
+            decoded.metadata().continuation(),
+            ContinuationIntent::PreviousResponseId(value) if value == &response_id
+        ));
+        assert_eq!(
+            openai_wire_body(&decoded)
+                .get("previous_response_id")
+                .and_then(Value::as_str),
+            Some(response_id.as_str())
+        );
+        assert!(
+            decoded
+                .operation()
+                .capability_requirements()
+                .features()
+                .contains(&Feature::NativeContinuation)
+        );
+        if !response_id.is_empty() {
+            assert!(!format!("{decoded:?}").contains(&response_id));
+        }
+    }
 }

 #[test]
@@ -316,7 +512,7 @@ fn transparent_encoder_should_forward_raw_sse_frames_unknown_events_and_terminal
    let mut encoder = OpenAiResponsesEncoder::new();
    let frames = events
        .iter()
-        .flat_map(|event| encoder.push_sse(event).expect("wire event should encode"))
+        .flat_map(|event| encoder.push_sse(event))
        .collect::<Vec<_>>();
    let response = encoder.finish().expect("wire response should finish");
    let body = frames
@@ -370,15 +566,11 @@ fn transparent_encoder_should_use_identical_json_for_sse_and_websocket() {

    let sse = events
        .iter()
-        .flat_map(|event| sse_encoder.push_sse(event).expect("SSE wire event"))
+        .flat_map(|event| sse_encoder.push_sse(event))
        .collect::<Vec<_>>();
    let websocket = events
        .iter()
-        .flat_map(|event| {
-            websocket_encoder
-                .push_websocket(event)
-                .expect("WebSocket wire event")
-        })
+        .flat_map(|event| websocket_encoder.push_websocket(event))
        .collect::<Vec<_>>();
    let sse_text = String::from_utf8(
        sse.iter()
@@ -400,8 +592,40 @@ fn transparent_encoder_should_use_identical_json_for_sse_and_websocket() {
 }

 #[test]
-fn transparent_encoder_should_require_matching_canonical_and_wire_terminals() {
+fn transparent_encoder_should_follow_wire_when_canonical_identity_changes() {
    let mut encoder = OpenAiResponsesEncoder::new();
+    let started = openai_wire_event(
+        vec![GatewayEvent::Started(ResponseMeta::new(
+            "resp_1", "gpt-test",
+        ))],
+        "response.created",
+        json!({"type": "response.created", "response": {"id": "wire_resp_1"}}),
+    );
+    encoder.push_sse(&started);
+    let changed_identity = openai_wire_event(
+        vec![GatewayEvent::Completed(ResponseMeta::new(
+            "resp_2", "gpt-test",
+        ))],
+        "response.completed",
+        json!({"type": "response.completed", "response": {"id": "wire_resp_2"}}),
+    );
+
+    let completed = encoder.push_sse(&changed_identity);
+
+    assert_eq!(completed.len(), 1);
+    assert!(encoder.is_completed());
+    assert_eq!(encoder.response_id(), Some("wire_resp_2"));
+    assert_eq!(
+        encoder
+            .finish()
+            .expect("wire terminal remains authoritative"),
+        json!({"id": "wire_resp_2"})
+    );
+}
+
+#[test]
+fn transparent_encoder_should_only_require_wire_terminal_for_buffered_conversion() {
+    let mut missing_terminal = OpenAiResponsesEncoder::new();
    let started = openai_wire_event(
        vec![GatewayEvent::Started(ResponseMeta::new(
            "resp_1", "gpt-test",
@@ -409,24 +633,8 @@ fn transparent_encoder_should_require_matching_canonical_and_wire_terminals() {
        "response.created",
        json!({"type": "response.created", "response": {"id": "resp_1"}}),
    );
-    encoder.push_sse(&started).expect("started event");
-    let changed_identity = openai_wire_event(
-        vec![GatewayEvent::Completed(ResponseMeta::new(
-            "resp_2", "gpt-test",
-        ))],
-        "response.completed",
-        json!({"type": "response.completed", "response": {"id": "resp_2"}}),
-    );

-    assert_eq!(
-        encoder
-            .push_sse(&changed_identity)
-            .expect_err("identity changes must fail"),
-        ResponseEncodeError::WireIdentityChanged
-    );
-
-    let mut missing_terminal = OpenAiResponsesEncoder::new();
-    missing_terminal.push_sse(&started).expect("started event");
+    missing_terminal.push_sse(&started);
    assert_eq!(
        missing_terminal
            .finish()
@@ -1,14 +1,35 @@
+use std::sync::{
+    Arc,
+    atomic::{AtomicBool, AtomicUsize, Ordering},
+};
+use std::time::{Duration, SystemTime};
+
 use axum::{
    body::Body,
    http::{Request, StatusCode, header::AUTHORIZATION},
 };
+use bytes::Bytes;
+use futures::{SinkExt, StreamExt, future::BoxFuture};
 use gateway_api::openai::responses::ResponseCreateFrameError;
+use gateway_core::engine::execution::{
+    AuthenticatedClient, ClientAuthenticationError, ExecutionService, ExecutionSession,
+    StartExecution, StartedExecution,
+};
+use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError, UpstreamSendState};
+use gateway_core::error::{GatewayError, ProviderError, ProviderErrorKind};
+use gateway_core::event::{
+    GatewayEvent, ProtocolWireEvent, ProviderEvent, ProviderResponseHeader, ResponseMeta,
+};
 use gateway_core::operation::Operation;
-use serde_json::json;
+use gateway_core::routing::PublicModelId;
+use serde_json::{Value, json};
+use tokio_tungstenite::connect_async;
+use tokio_tungstenite::tungstenite::Message as ClientMessage;
+use tokio_tungstenite::tungstenite::client::IntoClientRequest;
 use tower::ServiceExt;

 use super::decode_response_create;
-use crate::openai::{api_router, models::ModelsExecution};
+use crate::openai::{api_router, authenticated_client, models::ModelsExecution};

 #[test]
 fn response_create_should_default_to_the_websocket_streaming_contract() {
@@ -148,11 +169,403 @@ fn response_create_should_reject_non_boolean_stream_without_disclosing_body_valu
    assert!(!rendered.contains(opaque_stream_value));
 }

-// `serve_responses_websocket`/`forward_execution` 只有拿到 `hyper::upgrade::OnUpgrade`
-// 的真实 HTTP/1.1 升级连接才会运行;本 crate 的依赖图按 axum `ws` feature 编译
-// hyper(无 `http1`),测试进程内不存在能完成升级的服务端,`hyper::upgrade` 也不
-// 提供公开构造器。集成测试因此止步于 upgrade 边界:会话循环内的事件转发、错误帧
-// 与断连取消仍未被覆盖,需要 dev 依赖开启 `http1` 或 socket 泛化后才能落地。
+#[derive(Default)]
+struct AtomicFailureTrace {
+    next_calls: AtomicUsize,
+    committed: AtomicBool,
+    finalized: AtomicBool,
+}
+
+struct AtomicFailureSession {
+    trace: Arc<AtomicFailureTrace>,
+    response_headers: Vec<ProviderResponseHeader>,
+}
+
+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) {
+                0 => Ok(Some(atomic_failure_batch())),
+                1 => {
+                    self.trace.finalized.store(true, Ordering::Release);
+                    Err(EngineError::Provider(ProviderError::new(
+                        ProviderErrorKind::RateLimited,
+                        UpstreamSendState::Sent,
+                    )))
+                }
+                _ => Ok(None),
+            }
+        })
+    }
+
+    fn collect_uncommitted(&mut self) -> BoxFuture<'_, Result<Vec<ProviderEvent>, EngineError>> {
+        Box::pin(async { Err(EngineError::InvalidDeliveryState) })
+    }
+
+    fn response_headers(&self) -> &[ProviderResponseHeader] {
+        &self.response_headers
+    }
+
+    fn commit_downstream(&mut self, _: Option<u16>) -> BoxFuture<'_, Result<(), EngineError>> {
+        Box::pin(async move {
+            self.trace.committed.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.trace.finalized.load(Ordering::Acquire)
+    }
+
+    fn cancel(&self) {}
+
+    fn detach_finalize(self: Box<Self>) -> BoxFuture<'static, ()> {
+        Box::pin(async move {
+            self.trace.finalized.store(true, Ordering::Release);
+        })
+    }
+}
+
+struct AtomicFailureExecution {
+    client: AuthenticatedClient,
+    trace: Arc<AtomicFailureTrace>,
+    response_headers: Vec<ProviderResponseHeader>,
+}
+
+impl ExecutionService for AtomicFailureExecution {
+    fn authenticate(
+        &self,
+        plaintext: &str,
+    ) -> Result<AuthenticatedClient, ClientAuthenticationError> {
+        (plaintext == "sk_ws_atomic")
+            .then(|| self.client.clone())
+            .ok_or(ClientAuthenticationError::InvalidKey)
+    }
+
+    fn public_models(&self, _: &AuthenticatedClient) -> Vec<PublicModelId> {
+        vec![PublicModelId::new("model-a").expect("public model")]
+    }
+
+    fn contains_public_model(&self, _: &AuthenticatedClient, model: &PublicModelId) -> bool {
+        model.as_str() == "model-a"
+    }
+
+    fn start(
+        &self,
+        request: StartExecution,
+    ) -> BoxFuture<'_, Result<StartedExecution, GatewayError>> {
+        Box::pin(async move {
+            Ok(StartedExecution {
+                request_id: gateway_core::engine::ModelRequestId::new("req_ws_atomic")
+                    .expect("request id"),
+                created_at: SystemTime::now(),
+                stream: request.metadata.stream,
+                session: Box::new(AtomicFailureSession {
+                    trace: Arc::clone(&self.trace),
+                    response_headers: self.response_headers.clone(),
+                }),
+            })
+        })
+    }
+}
+
+fn atomic_failure_batch() -> CoordinatedEvent {
+    let started = ProviderEvent::canonical_with_wire(
+        vec![GatewayEvent::Started(ResponseMeta::new(
+            "resp_ws_atomic",
+            "model-a",
+        ))],
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.created".to_owned()),
+            json!({
+                "type": "response.created",
+                "response": {
+                    "id": "resp_ws_atomic",
+                    "model": "model-a",
+                    "status": "in_progress"
+                }
+            }),
+        )
+        .expect("created wire"),
+    );
+    let failed = ProviderEvent::wire(
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.failed".to_owned()),
+            json!({
+                "type": "response.failed",
+                "response": {
+                    "id": "resp_ws_atomic",
+                    "status": "failed",
+                    "error": {
+                        "code": "rate_limit_exceeded",
+                        "message": "websocket atomic upstream marker"
+                    }
+                }
+            }),
+        )
+        .expect("failed wire"),
+    );
+    CoordinatedEvent::try_batch(
+        vec![started, failed],
+        CommitRequirement::CommitBeforeDelivery,
+    )
+    .expect("atomic WebSocket batch")
+}
+
+#[tokio::test]
+async fn websocket_atomic_upstream_failure_batch_should_be_forwarded_once() {
+    let trace = Arc::new(AtomicFailureTrace::default());
+    let execution = Arc::new(AtomicFailureExecution {
+        client: authenticated_client("sk_ws_atomic"),
+        trace: Arc::clone(&trace),
+        response_headers: Vec::new(),
+    });
+    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();
+    loop {
+        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;
+        };
+        let value: Value = serde_json::from_str(&text).expect("JSON WebSocket event");
+        let failed = value.get("type").and_then(Value::as_str) == Some("response.failed");
+        messages.push(value);
+        if failed {
+            break;
+        }
+    }
+
+    assert_eq!(
+        messages
+            .iter()
+            .filter(|message| message.get("type").and_then(Value::as_str) == Some("response.failed"))
+            .count(),
+        1
+    );
+    let failed = messages
+        .iter()
+        .find(|message| message.get("type").and_then(Value::as_str) == Some("response.failed"))
+        .expect("upstream failed event");
+    assert_eq!(
+        failed
+            .pointer("/response/error/message")
+            .and_then(Value::as_str),
+        Some("websocket atomic upstream marker")
+    );
+    assert!(trace.committed.load(Ordering::Acquire));
+    assert_eq!(trace.next_calls.load(Ordering::Acquire), 2);
+    assert!(trace.finalized.load(Ordering::Acquire));
+
+    socket.close(None).await.expect("close WebSocket");
+    server.abort();
+}
+
+#[tokio::test]
+async fn websocket_response_metadata_should_preserve_ordinary_headers_without_blocking_events() {
+    let trace = Arc::new(AtomicFailureTrace::default());
+    let execution = Arc::new(AtomicFailureExecution {
+        client: authenticated_client("sk_ws_atomic"),
+        trace,
+        response_headers: vec![
+            ProviderResponseHeader::new("x-future-header", Bytes::from_static(b"future-value")),
+            ProviderResponseHeader::new("x-future-multi", Bytes::from_static(b"first")),
+            ProviderResponseHeader::new("x-future-multi", Bytes::from_static(b"second")),
+            ProviderResponseHeader::new("x-future-bytes", Bytes::from_static(b"\xffopaque")),
+            ProviderResponseHeader::new("bad\0name", Bytes::from_static(b"unrepresentable")),
+            ProviderResponseHeader::new(
+                "authorization",
+                Bytes::from_static(b"should-not-cross-boundary"),
+            ),
+            ProviderResponseHeader::new("connection", Bytes::from_static(b"x-private-hop")),
+            ProviderResponseHeader::new("x-private-hop", Bytes::from_static(b"private-hop")),
+            ProviderResponseHeader::new("content-type", Bytes::from_static(b"application/private")),
+            ProviderResponseHeader::new("x-request-id", Bytes::from_static(b"req_upstream")),
+        ],
+    });
+    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 metadata = None;
+    let mut saw_failed = false;
+    while metadata.is_none() || !saw_failed {
+        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;
+        };
+        let value: Value = serde_json::from_str(&text).expect("JSON WebSocket event");
+        match value.get("type").and_then(Value::as_str) {
+            Some("response.metadata") => metadata = Some(value),
+            Some("response.failed") => saw_failed = true,
+            _ => {}
+        }
+    }
+
+    let headers = metadata
+        .as_ref()
+        .and_then(|value| value.get("headers"))
+        .and_then(Value::as_object)
+        .expect("response metadata headers");
+    assert_eq!(headers.get("x-future-header"), Some(&json!("future-value")));
+    // 官方 metadata 是 string map，同名多值只能保持既有的后值覆盖语义。
+    assert_eq!(headers.get("x-future-multi"), Some(&json!("second")));
+    assert_eq!(headers.get("x-request-id"), Some(&json!("req_upstream")));
+    for omitted in [
+        "x-future-bytes",
+        "bad\0name",
+        "authorization",
+        "connection",
+        "x-private-hop",
+        "content-type",
+    ] {
+        assert!(
+            !headers.contains_key(omitted),
+            "unexpected metadata header: {omitted:?}"
+        );
+    }
+    assert!(saw_failed);
+
+    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());
+    let execution = Arc::new(AtomicFailureExecution {
+        client: authenticated_client("sk_ws_atomic"),
+        trace,
+        response_headers: Vec::new(),
+    });
+    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);
+    let payload = json!({
+        "type": "response.create",
+        "model": "model-a",
+        "input": "x".repeat(16 * 1024 * 1024 + 1),
+    })
+    .to_string();
+    assert!(payload.len() > 16 * 1024 * 1024);
+
+    socket
+        .send(ClientMessage::Text(payload.into()))
+        .await
+        .expect("send response.create above the former frame limit");
+
+    let mut saw_upstream_event = false;
+    for _ in 0..3 {
+        let message = tokio::time::timeout(Duration::from_secs(10), socket.next())
+            .await
+            .expect("WebSocket response timeout")
+            .expect("WebSocket remains open")
+            .expect("valid WebSocket frame");
+        let ClientMessage::Text(text) = message else {
+            continue;
+        };
+        let value: Value = serde_json::from_str(&text).expect("JSON WebSocket event");
+        if matches!(
+            value.get("type").and_then(Value::as_str),
+            Some("response.created" | "response.failed")
+        ) {
+            saw_upstream_event = true;
+            break;
+        }
+    }
+    assert!(saw_upstream_event);
+
+    socket.close(None).await.expect("close WebSocket");
+    server.abort();
+}

 const TEST_WEBSOCKET_KEY: &str = "AAAAAAAAAAAAAAAAAAAAAA==";

@@ -1,57 +1,29 @@
 use axum::{
-    Router,
-    body::{Body, Bytes},
-    extract::DefaultBodyLimit,
+    body::Body,
    http::{Method, Request, StatusCode},
-    routing::post,
 };
-use gateway_api::openai::router::MAX_CLIENT_REQUEST_BODY_BYTES;
 use tower::ServiceExt;

 use super::api_router_with_origins;
 use super::models::ModelsExecution;

-fn body_limit_app() -> Router {
-    Router::new()
-        .route(
-            "/v1/responses",
-            post(|body: Bytes| async move {
-                if body.len() == MAX_CLIENT_REQUEST_BODY_BYTES {
-                    StatusCode::NO_CONTENT
-                } else {
-                    StatusCode::INTERNAL_SERVER_ERROR
-                }
-            }),
-        )
-        .layer(DefaultBodyLimit::max(MAX_CLIENT_REQUEST_BODY_BYTES))
-}
+const REMOVED_BODY_LIMIT_BYTES: usize = 16 * 1024 * 1024;

 #[tokio::test]
-async fn responses_body_limit_should_accept_exactly_sixteen_mibibytes() {
-    let response = body_limit_app()
+async fn responses_body_should_accept_payload_above_the_removed_private_limit() {
+    let router = api_router_with_origins(ModelsExecution::new(), Vec::new()).await;
+    let response = router
        .oneshot(
            Request::post("/v1/responses")
-                .body(Body::from(vec![b'a'; MAX_CLIENT_REQUEST_BODY_BYTES]))
-                .expect("build exact-limit request"),
+                .body(Body::from(vec![b'a'; REMOVED_BODY_LIMIT_BYTES + 1]))
+                .expect("build request above the removed limit"),
        )
        .await
-        .expect("route exact-limit request");
+        .expect("route request above the removed limit");

-    assert_eq!(response.status(), StatusCode::NO_CONTENT);
-}
-
-#[tokio::test]
-async fn responses_body_limit_should_reject_one_byte_over_sixteen_mibibytes() {
-    let response = body_limit_app()
-        .oneshot(
-            Request::post("/v1/responses")
-                .body(Body::from(vec![b'a'; MAX_CLIENT_REQUEST_BODY_BYTES + 1]))
-                .expect("build over-limit request"),
-        )
-        .await
-        .expect("route over-limit request");
-
-    assert_eq!(response.status(), StatusCode::PAYLOAD_TOO_LARGE);
+    // The handler sees the body and rejects the missing credentials. A restored body limit
+    // would return 413 before authentication runs.
+    assert_eq!(response.status(), StatusCode::UNAUTHORIZED);
 }

 #[tokio::test]
@@ -17,8 +17,9 @@ 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 = ["preserve_order"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 thiserror = "2.0.18"
+tracing = "0.1.44"
 uuid = { version = "1.23.3", features = ["v7"] }

 [lints]
@@ -8,24 +8,21 @@ use std::fmt;
 use futures::future::BoxFuture;

 use crate::engine::credential::ProviderAccountId;
-use crate::error::{IdentifierError, SafeUpstreamValue, validate_text};
 use crate::operation::ProviderSessionState;
 use crate::routing::ProviderKind;

-/// 客户端传入的 previous response ID。
-#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
+/// 客户端或 Provider 传递的 opaque response handle。
+///
+/// Codex 定义这个值的语义和格式。网关只将其作为亲和查找键或同账号上游
+/// continuation 的载体，不得按私有长度、字符集或前缀规则拒绝、归一化或改写。
+#[derive(Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
 pub struct PreviousResponseId(String);

 impl PreviousResponseId {
-    /// 校验并创建 previous response ID。
-    ///
-    /// # Errors
-    ///
-    /// ID 为空、过长或包含控制字符时返回错误。
-    pub fn new(value: impl Into<String>) -> Result<Self, IdentifierError> {
-        let value = value.into();
-        validate_text(&value, 256, false, None)?;
-        Ok(Self(value))
+    /// 按原样创建 opaque response handle。
+    #[must_use]
+    pub fn new(value: impl Into<String>) -> Self {
+        Self(value.into())
    }

    #[must_use]
@@ -34,6 +31,12 @@ impl PreviousResponseId {
    }
 }

+impl fmt::Debug for PreviousResponseId {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter.write_str("PreviousResponseId(<redacted>)")
+    }
+}
+
 /// Provider 原生 response handle 的续接范围。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub enum NativeContinuationScope {
@@ -52,7 +55,7 @@ pub struct NativeContinuationPin {
    /// 客户端提交、用于查找可丢失会话亲和记录的 response ID。
    previous_response_id: PreviousResponseId,
    /// Provider 原生 response handle。
-    upstream_response_id: SafeUpstreamValue,
+    upstream_response_id: PreviousResponseId,
    provider: ProviderKind,
    account: ProviderAccountId,
    scope: NativeContinuationScope,
@@ -63,7 +66,7 @@ impl NativeContinuationPin {
    #[must_use]
    pub const fn new(
        previous_response_id: PreviousResponseId,
-        upstream_response_id: SafeUpstreamValue,
+        upstream_response_id: PreviousResponseId,
        provider: ProviderKind,
        account: ProviderAccountId,
    ) -> Self {
@@ -98,7 +101,7 @@ impl NativeContinuationPin {

    /// 返回只允许发送给已冻结 Provider 目标的原生上游 handle。
    #[must_use]
-    pub const fn upstream_response_id(&self) -> &SafeUpstreamValue {
+    pub const fn upstream_response_id(&self) -> &PreviousResponseId {
        &self.upstream_response_id
    }

@@ -1,6 +1,7 @@
 //! 唯一的账号重试、发送与下游 commit barrier owner。

 use std::collections::BTreeSet;
+use std::future::Future;
 use std::num::NonZeroU32;
 use std::sync::Arc;
 use std::time::{Duration, Instant, SystemTime};
@@ -17,7 +18,7 @@ use crate::engine::{
    ModelRequestTimings, NewModelRequest, ProviderAccountStateOwner, ProviderAttemptOutcome,
    RequestAttemptContext, UpstreamSendState,
 };
-use crate::error::{GatewayError, GatewayErrorKind, ProviderError, ProviderErrorKind};
+use crate::error::{GatewayError, GatewayErrorKind, ProviderError, ProviderErrorKind, StoreError};
 use crate::event::{
    GatewayEvent, ProviderEvent, ProviderResponseHeader, ProviderResponseObservation,
 };
@@ -32,6 +33,21 @@ pub struct AttemptCoordinator<S: ?Sized> {
    engine: Arc<GatewayEngine<S>>,
 }

+#[derive(Debug, Clone)]
+enum AccountSelection {
+    Scheduled(Option<crate::engine::credential::ProviderAccountId>),
+    Diagnostic(crate::engine::credential::ProviderAccountId),
+}
+
+impl AccountSelection {
+    fn required_account(&self) -> Option<&crate::engine::credential::ProviderAccountId> {
+        match self {
+            Self::Scheduled(account) => account.as_ref(),
+            Self::Diagnostic(account) => Some(account),
+        }
+    }
+}
+
 impl<S: ?Sized> AttemptCoordinator<S>
 where
    S: ExecutionStore,
@@ -56,6 +72,49 @@ where
        required_account: Option<crate::engine::credential::ProviderAccountId>,
        continuation: Option<ContinuationBinding>,
        cancellation: CancellationToken,
+    ) -> Result<ResponseExecutionSession<S>, EngineError> {
+        self.start_with_account_selection(
+            request,
+            operation,
+            plan,
+            AccountSelection::Scheduled(required_account),
+            continuation,
+            cancellation,
+        )
+        .await
+    }
+
+    /// 对固定账号执行诊断请求。
+    ///
+    /// 仅跳过该账号的本地可用性投影；账号租约、并发和请求间隔仍必须满足。
+    pub async fn start_diagnostic(
+        &self,
+        request: NewModelRequest,
+        operation: Operation,
+        plan: RoutingPlan,
+        required_account: crate::engine::credential::ProviderAccountId,
+        continuation: Option<ContinuationBinding>,
+        cancellation: CancellationToken,
+    ) -> Result<ResponseExecutionSession<S>, EngineError> {
+        self.start_with_account_selection(
+            request,
+            operation,
+            plan,
+            AccountSelection::Diagnostic(required_account),
+            continuation,
+            cancellation,
+        )
+        .await
+    }
+
+    async fn start_with_account_selection(
+        &self,
+        request: NewModelRequest,
+        operation: Operation,
+        plan: RoutingPlan,
+        account_selection: AccountSelection,
+        continuation: Option<ContinuationBinding>,
+        cancellation: CancellationToken,
    ) -> Result<ResponseExecutionSession<S>, EngineError> {
        let request_id = request.id.clone();
        let client_api_key_ref = request.client_api_key_ref.clone();
@@ -84,7 +143,7 @@ where
            request_persisted: false,
            operation,
            plan,
-            required_account,
+            account_selection,
            continuation,
            continuation_attempt,
            account_state_owner,
@@ -107,7 +166,9 @@ where
            client_response_id: None,
            upstream_response_id: None,
            last_account_exhaustion: None,
+            last_account_exhaustion_events: Vec::new(),
            provider_attempt_outcomes: Vec::new(),
+            pending_terminal_failure: None,
        };

        if session.cancellation.is_cancelled() {
@@ -158,7 +219,7 @@ pub struct ResponseExecutionSession<S: ?Sized> {
    request_persisted: bool,
    operation: Operation,
    plan: RoutingPlan,
-    required_account: Option<crate::engine::credential::ProviderAccountId>,
+    account_selection: AccountSelection,
    continuation: Option<ContinuationBinding>,
    continuation_attempt: ContinuationAttempt,
    account_state_owner: Option<ProviderAccountStateOwner>,
@@ -185,7 +246,16 @@ pub struct ResponseExecutionSession<S: ?Sized> {
    client_response_id: Option<String>,
    upstream_response_id: Option<String>,
    last_account_exhaustion: Option<ProviderError>,
+    /// 最近一次账号耗尽在重试时被丢弃的原始失败批次；只用于后续空选路终态。
+    last_account_exhaustion_events: Vec<ProviderEvent>,
    provider_attempt_outcomes: Vec<ProviderAttemptOutcome>,
+    /// 原子失败批次已交给协议层、但尚待下游提交后收敛的原 Provider 错误。
+    pending_terminal_failure: Option<PendingTerminalFailure>,
+}
+
+struct PendingTerminalFailure {
+    error: ProviderError,
+    send_state: UpstreamSendState,
 }

 impl<S: ?Sized> ResponseExecutionSession<S>
@@ -201,6 +271,11 @@ where
        if self.delivery_pending {
            return Err(EngineError::DownstreamCommitRequired);
        }
+        if let Some(pending) = self.pending_terminal_failure.take() {
+            self.finish_provider_error_with_send_state(&pending.error, pending.send_state)
+                .await?;
+            return Err(provider_engine_error(pending.error));
+        }
        if self.finalized {
            return Ok(None);
        }
@@ -220,6 +295,21 @@ where
                    )));
                }
                PullOutcome::AttemptDiscarded => {}
+                PullOutcome::TerminalFailure {
+                    events,
+                    error,
+                    send_state,
+                } => {
+                    let requirement = if self.downstream_committed_at.is_some() {
+                        CommitRequirement::AlreadyCommitted
+                    } else {
+                        self.delivery_pending = true;
+                        CommitRequirement::CommitBeforeDelivery
+                    };
+                    self.pending_terminal_failure =
+                        Some(PendingTerminalFailure { error, send_state });
+                    return CoordinatedEvent::try_batch(events, requirement).map(Some);
+                }
                PullOutcome::End => {
                    if self.downstream_committed_at.is_some() {
                        self.finish_success().await?;
@@ -248,6 +338,13 @@ where
            match self.pull().await? {
                PullOutcome::Event(event) => events.push(event),
                PullOutcome::AttemptDiscarded => events.clear(),
+                PullOutcome::TerminalFailure {
+                    error, send_state, ..
+                } => {
+                    self.finish_provider_error_with_send_state(&error, send_state)
+                        .await?;
+                    return Err(provider_engine_error(error));
+                }
                PullOutcome::End => {
                    if events.is_empty() {
                        return Err(EngineError::InvalidDeliveryState);
@@ -259,11 +356,11 @@ where
        }
    }

-    /// 在协议 adapter 真正写出首字节前持久化下游不可撤回边界。
+    /// 在协议 adapter 真正写出首字节前记录下游不可撤回边界。
    ///
    /// # Errors
    ///
-    /// 没有待提交结果、重复提交或 Store 失败时返回错误。
+    /// 没有待提交结果或重复提交时返回错误；观测 Store 失败只记服务端告警。
    pub async fn commit_downstream(
        &mut self,
        client_status_code: Option<u16>,
@@ -272,10 +369,18 @@ where
            return Err(EngineError::InvalidDeliveryState);
        }
        let committed_at = SystemTime::now();
-        self.engine
-            .store()
-            .mark_downstream_committed(&self.request_id, committed_at, client_status_code)
-            .await?;
+        if self.request_persisted {
+            best_effort_store_write(
+                "mark_downstream_committed",
+                &self.request_id,
+                self.engine.store().mark_downstream_committed(
+                    &self.request_id,
+                    committed_at,
+                    client_status_code,
+                ),
+            )
+            .await;
+        }
        self.downstream_committed_at = Some(committed_at);
        self.client_status_code = client_status_code;
        self.delivery_pending = false;
@@ -289,7 +394,7 @@ where
    ///
    /// # Errors
    ///
-    /// 状态已经写入或 Store 无法写回时返回错误。
+    /// 状态已经写入时返回错误；观测 Store 失败只记服务端告警。
    pub async fn record_client_status(
        &mut self,
        client_status_code: u16,
@@ -298,10 +403,14 @@ where
            return Err(EngineError::InvalidDeliveryState);
        }
        if self.request_persisted {
-            self.engine
-                .store()
-                .record_client_status(&self.request_id, client_status_code)
-                .await?;
+            best_effort_store_write(
+                "record_client_status",
+                &self.request_id,
+                self.engine
+                    .store()
+                    .record_client_status(&self.request_id, client_status_code),
+            )
+            .await;
        }
        self.client_status_code = Some(client_status_code);
        Ok(())
@@ -345,9 +454,8 @@ where
        }
        let account = current.metadata.provider_account_id()?.clone();
        let response_id = self.upstream_response_id.as_deref()?;
-        let previous_response_id = PreviousResponseId::new(response_id.to_owned()).ok()?;
-        let upstream_response_id =
-            crate::error::SafeUpstreamValue::new(response_id.to_owned()).ok()?;
+        let previous_response_id = PreviousResponseId::new(response_id.to_owned());
+        let upstream_response_id = PreviousResponseId::new(response_id.to_owned());
        Some(
            NativeContinuationPin::new(
                previous_response_id,
@@ -376,13 +484,20 @@ where
            return Ok(());
        }
        self.delivery_pending = false;
+        if let Some(pending) = self.pending_terminal_failure.take() {
+            return self
+                .finish_provider_error_with_send_state(&pending.error, pending.send_state)
+                .await;
+        }
        self.finish_interruption(EngineError::Cancelled).await
    }

    async fn pull(&mut self) -> Result<PullOutcome, EngineError> {
        loop {
-            if self.current.is_none() {
-                self.prepare_attempt().await?;
+            if self.current.is_none()
+                && let Some(outcome) = self.prepare_attempt().await?
+            {
+                return Ok(outcome);
            }

            let boundary = {
@@ -409,32 +524,17 @@ where
                    return Err(EngineError::Deadline);
                }
                PollBoundary::Item(Some(Ok(mut event))) => {
-                    if let Some(observation) = event.take_observation()
-                        && let Err(error) = self.observe_response(observation)
-                    {
-                        if self.handle_stream_error(error).await? {
-                            return Ok(PullOutcome::AttemptDiscarded);
-                        }
-                        continue;
-                    }
-                    let mut identity_error = None;
-                    for fact in event.canonical_facts() {
-                        if let Err(error) = self.observe_response_identity(fact) {
-                            identity_error = Some(error);
-                            break;
-                        }
-                    }
-                    if let Some(error) = identity_error {
-                        if self.handle_stream_error(error).await? {
-                            return Ok(PullOutcome::AttemptDiscarded);
-                        }
-                        continue;
+                    if let Some(observation) = event.take_observation() {
+                        self.observe_response(observation);
                    }
                    for fact in event.canonical_facts() {
-                        self.observe_event(fact).await?;
+                        self.observe_response_identity(fact);
+                    }
+                    for fact in event.canonical_facts() {
+                        self.observe_event(fact).await;
                    }
                    if event.wire_event().is_some() && !event.has_canonical_facts() {
-                        self.observe_wire_event().await?;
+                        self.observe_wire_event().await;
                    }
                    if !event.has_client_event() {
                        continue;
@@ -442,8 +542,13 @@ where
                    return Ok(PullOutcome::Event(event));
                }
                PollBoundary::Item(Some(Err(error))) => {
-                    if self.handle_stream_error(error).await? {
-                        return Ok(PullOutcome::AttemptDiscarded);
+                    match self.handle_stream_error(error).await? {
+                        StreamErrorOutcome::AttemptDiscarded => {
+                            return Ok(PullOutcome::AttemptDiscarded);
+                        }
+                        terminal @ StreamErrorOutcome::TerminalFailure { .. } => {
+                            return Ok(terminal.into_pull_outcome());
+                        }
                    }
                }
                PollBoundary::Item(None) => {
@@ -455,7 +560,7 @@ where
        }
    }

-    async fn prepare_attempt(&mut self) -> Result<(), EngineError> {
+    async fn prepare_attempt(&mut self) -> Result<Option<PullOutcome>, EngineError> {
        if self.attempts >= self.plan.max_attempts().get() {
            return Err(EngineError::EmptyRoutingPlan);
        }
@@ -483,27 +588,36 @@ where
            .ok_or(EngineError::EmptyRoutingPlan)?;
        // recovery 钉选在此被一次性消费，只绑定本次 replay attempt；
        // 外部 required_account 每次 attempt 都重新生效。
-        let pinned_account = self
-            .recovery_account
-            .take()
-            .or_else(|| self.required_account.clone());
+        let pinned_account = match &self.account_selection {
+            AccountSelection::Diagnostic(account) => Some(account.clone()),
+            AccountSelection::Scheduled(_) => self
+                .recovery_account
+                .take()
+                .or_else(|| self.account_selection.required_account().cloned()),
+        };
+        let account_context = match &self.account_selection {
+            AccountSelection::Diagnostic(account) => AccountAttemptContext::diagnostic(
+                self.excluded_accounts.clone(),
+                account.clone(),
+                self.account_state_owner.clone(),
+            ),
+            AccountSelection::Scheduled(_) => AccountAttemptContext::new(
+                self.excluded_accounts.clone(),
+                pinned_account.clone(),
+                self.account_state_owner.clone(),
+            ),
+        }
+        .with_credential_recovery_attempted(pinned_account.as_ref().is_some_and(|account| {
+            self.credential_recovery_attempted_accounts
+                .contains(account)
+        }));
        let context = AttemptContext::new(
            RequestAttemptContext::new(self.request_id.clone(), self.client_api_key_ref.clone())
                .with_timing_started_at(self.timing_started_at),
            next_attempt,
            self.deadline,
            self.plan.account_selection_policy(),
-            AccountAttemptContext::new(
-                self.excluded_accounts.clone(),
-                pinned_account.clone(),
-                self.account_state_owner.clone(),
-            )
-            .with_credential_recovery_attempted(pinned_account.as_ref().is_some_and(
-                |account| {
-                    self.credential_recovery_attempted_accounts
-                        .contains(account)
-                },
-            )),
+            account_context,
            self.continuation.clone(),
            self.cancellation.clone(),
        )
@@ -546,11 +660,20 @@ where
                Ok(stream) => stream,
                Err(error) => {
                    if error.kind() == ProviderErrorKind::NoEligibleAccount
-                        && let Some(exhaustion) = self.last_account_exhaustion.clone()
+                        && let Some(exhaustion) = self.last_account_exhaustion.take()
                    {
-                        let engine_error = provider_engine_error(&exhaustion);
+                        let send_state = self.current_send_state();
+                        let mut events = std::mem::take(&mut self.last_account_exhaustion_events);
+                        if !events.is_empty() {
+                            self.observe_atomic_terminal_events(&mut events);
+                            return Ok(Some(PullOutcome::TerminalFailure {
+                                events,
+                                error: exhaustion,
+                                send_state,
+                            }));
+                        }
                        self.finish_provider_error(&exhaustion).await?;
-                        return Err(engine_error);
+                        return Err(provider_engine_error(exhaustion));
                    }
                    if !(matches!(
                        error.kind(),
@@ -559,9 +682,8 @@ where
                    {
                        self.record_provider_failure(candidate.provider().clone(), error.kind());
                    }
-                    let engine_error = provider_engine_error(&error);
                    self.finish_provider_error(&error).await?;
-                    return Err(engine_error);
+                    return Err(provider_engine_error(error));
                }
            },
        };
@@ -650,17 +772,30 @@ where
            http_version: None,
        };
        if self.request_persisted {
-            self.engine.store().record_attempt(attempt_record).await?;
+            best_effort_store_write(
+                "record_attempt",
+                &self.request_id,
+                self.engine.store().record_attempt(attempt_record),
+            )
+            .await;
        } else {
            let request = self
                .pending_request
-                .take()
+                .as_ref()
                .ok_or(EngineError::InvalidDeliveryState)?;
-            self.engine
-                .store()
-                .create_model_request_with_attempt(request, attempt_record)
-                .await?;
-            self.request_persisted = true;
+            if best_effort_store_write(
+                "create_model_request_with_attempt",
+                &self.request_id,
+                self.engine
+                    .store()
+                    .create_model_request_with_attempt(request.clone(), attempt_record),
+            )
+            .await
+            .is_some()
+            {
+                self.pending_request = None;
+                self.request_persisted = true;
+            }
        }
        self.attempts = next_attempt.get();
        self.current = Some(CurrentAttempt {
@@ -672,10 +807,15 @@ where
            send_observed: false,
            response_observation: None,
        });
-        Ok(())
+        Ok(None)
    }

-    async fn observe_event(&mut self, event: &GatewayEvent) -> Result<(), EngineError> {
+    async fn observe_event(&mut self, event: &GatewayEvent) {
+        self.observe_event_facts(event);
+        self.mark_send_observed().await;
+    }
+
+    fn observe_event_facts(&mut self, event: &GatewayEvent) {
        let elapsed = elapsed_ms(self.timing_started_at);
        observe_event_timing(&mut self.timings, event, elapsed);
        if let GatewayEvent::Usage(observed) = event {
@@ -689,46 +829,42 @@ where
        if let GatewayEvent::ProviderCost(observed) = event {
            self.cost = observed.into_estimate();
        }
-        let current = self.current.as_mut().ok_or(EngineError::NoActiveAttempt)?;
+    }
+
+    async fn observe_wire_event(&mut self) {
+        self.mark_send_observed().await;
+    }
+
+    async fn mark_send_observed(&mut self) {
+        let Some(current) = self.current.as_mut() else {
+            return;
+        };
        if !current.send_observed {
-            self.engine
-                .store()
-                .mark_send_state(&self.request_id, UpstreamSendState::Sent)
-                .await?;
+            if self.request_persisted {
+                best_effort_store_write(
+                    "mark_send_state",
+                    &self.request_id,
+                    self.engine
+                        .store()
+                        .mark_send_state(&self.request_id, UpstreamSendState::Sent),
+                )
+                .await;
+            }
            current.send_observed = true;
            self.send_state_watermark = UpstreamSendState::Sent;
        }
-        Ok(())
    }

-    async fn observe_wire_event(&mut self) -> Result<(), EngineError> {
-        let current = self.current.as_mut().ok_or(EngineError::NoActiveAttempt)?;
-        if !current.send_observed {
-            self.engine
-                .store()
-                .mark_send_state(&self.request_id, UpstreamSendState::Sent)
-                .await?;
-            current.send_observed = true;
-            self.send_state_watermark = UpstreamSendState::Sent;
-        }
-        Ok(())
-    }
-
-    fn observe_response(
-        &mut self,
-        observation: ProviderResponseObservation,
-    ) -> Result<(), ProviderError> {
-        let send_state = self.current_send_state();
-        let current = self
-            .current
-            .as_mut()
-            .ok_or_else(|| ProviderError::new(ProviderErrorKind::Protocol, send_state))?;
+    fn observe_response(&mut self, observation: ProviderResponseObservation) {
+        let Some(current) = self.current.as_mut() else {
+            return;
+        };
        if current
            .response_observation
            .as_ref()
            .is_some_and(|existing| existing.transport() != observation.transport())
        {
-            return Err(ProviderError::new(ProviderErrorKind::Protocol, send_state));
+            return;
        }
        let observed = observation.timings();
        if let Some(value) = observed.transport_decision_wait_ms {
@@ -756,47 +892,31 @@ where
            self.timings.provider_processing_ms = Some(value);
        }
        current.response_observation = Some(observation);
-        Ok(())
    }

-    fn observe_response_identity(&mut self, event: &GatewayEvent) -> Result<(), ProviderError> {
+    fn observe_response_identity(&mut self, event: &GatewayEvent) {
        let metadata = match event {
            GatewayEvent::Started(metadata) | GatewayEvent::Completed(metadata) => metadata,
-            _ => return Ok(()),
+            _ => return,
        };
-        let response_id = crate::error::SafeUpstreamValue::new(metadata.response_id().to_owned())
-            .map_err(|_| {
-            ProviderError::new(ProviderErrorKind::Protocol, UpstreamSendState::Sent)
-        })?;
-        let response_id = response_id.as_str();
-        if response_id.is_empty() {
-            return Ok(());
-        }
-        if self
-            .upstream_response_id
-            .as_deref()
-            .is_some_and(|expected| expected != response_id)
-        {
-            return Err(ProviderError::new(
-                ProviderErrorKind::Protocol,
-                UpstreamSendState::Sent,
-            ));
-        }
-        let response_id = response_id.to_owned();
+        let response_id = metadata.response_id().to_owned();
        self.client_response_id = Some(response_id.clone());
        self.upstream_response_id = Some(response_id);
-        Ok(())
    }

-    /// 返回 `true` 表示调用方必须丢弃本 attempt 已收集的未提交事件。
-    async fn handle_stream_error(&mut self, error: ProviderError) -> Result<bool, EngineError> {
+    /// 失败可重试时要求丢弃本 attempt；预算耗尽时可返回最后一批原始失败事件。
+    async fn handle_stream_error(
+        &mut self,
+        mut error: ProviderError,
+    ) -> Result<StreamErrorOutcome, EngineError> {
+        // 原始 wire 只能活在本次决策栈内；后续 clone、attempt 记录与终态对象均只
+        // 接触已剥离的稳定错误字段。
+        let mut atomic_client_events = error.take_atomic_client_events();
        let current = self.current.take().ok_or(EngineError::NoActiveAttempt)?;
-        if matches!(
+        let account_exhausted = matches!(
            error.kind(),
            ProviderErrorKind::RateLimited | ProviderErrorKind::QuotaExhausted
-        ) {
-            self.last_account_exhaustion = Some(error.clone());
-        }
+        );
        self.record_provider_failure(current.metadata.provider().clone(), error.kind());
        // attempt_send_state 是本 attempt 自身的发送事实，驱动重试门；
        // 持久化与终态用请求级水位，二者不可混用（水位会把早先 attempt 的
@@ -807,10 +927,16 @@ where
            error.send_state()
        };
        let send_state = self.raise_send_watermark(attempt_send_state);
-        self.engine
-            .store()
-            .mark_send_state(&self.request_id, send_state)
-            .await?;
+        if self.request_persisted {
+            best_effort_store_write(
+                "mark_send_state",
+                &self.request_id,
+                self.engine
+                    .store()
+                    .mark_send_state(&self.request_id, send_state),
+            )
+            .await;
+        }
        let provider_proved_replay_safe = provider_proved_replay_safe(&error);
        let continuation_retry = self.prepare_continuation_retry(
            &current,
@@ -818,7 +944,13 @@ where
            attempt_send_state,
            provider_proved_replay_safe,
        );
-        let ordinary_retry = self.required_account.is_none()
+        let pre_delivery_retry = self.account_selection.required_account().is_none()
+            && self.continuation_attempt == ContinuationAttempt::None
+            && self.downstream_committed_at.is_none()
+            && !self.delivery_pending
+            && error.allows_pre_delivery_retry()
+            && self.attempts < self.plan.max_attempts().get();
+        let ordinary_retry = self.account_selection.required_account().is_none()
            && self.continuation_attempt == ContinuationAttempt::None
            && self.downstream_committed_at.is_none()
            && !self.delivery_pending
@@ -840,9 +972,13 @@ where
                        .credential_recovery_attempted_accounts
                        .contains(account)
                });
-        let retryable = continuation_retry || same_account_retry || ordinary_retry;
+        let retryable =
+            continuation_retry || same_account_retry || ordinary_retry || pre_delivery_retry;

        if retryable {
+            // 普通 clone 只保留稳定事实；原始失败响应只能随最后一次客户端可见
+            // 的账号耗尽错误继续，不能进入中间失败记录。
+            let persistence_error = self.request_persisted.then(|| error.clone());
            if same_account_retry {
                if let Some(account) = current.metadata.provider_account_id() {
                    self.credential_recovery_attempted_accounts
@@ -856,37 +992,66 @@ where
            {
                self.excluded_accounts.insert(account.clone());
            }
-            self.engine
-                .store()
-                .record_intermediate_failure(IntermediateFailure {
-                    request_id: self.request_id.clone(),
-                    attempt_index: current.index,
-                    trigger: current.trigger,
-                    provider_kind: current.metadata.provider().clone(),
-                    account_id: current.metadata.provider_account_id().cloned(),
-                    upstream_model_id: current.metadata.upstream_model().clone(),
-                    upstream_status_code: current
-                        .response_observation
-                        .as_ref()
-                        .and_then(ProviderResponseObservation::status_code),
-                    upstream_request_id: current
-                        .response_observation
-                        .as_ref()
-                        .and_then(ProviderResponseObservation::request_id)
-                        .map(|value| value.as_str().to_owned()),
-                    latency: current.started_at.elapsed().unwrap_or_default(),
-                    error,
-                })
-                .await?;
+            if account_exhausted {
+                self.last_account_exhaustion_events = atomic_client_events;
+                self.last_account_exhaustion = Some(error);
+            }
+            if let Some(error) = persistence_error {
+                best_effort_store_write(
+                    "record_intermediate_failure",
+                    &self.request_id,
+                    self.engine
+                        .store()
+                        .record_intermediate_failure(IntermediateFailure {
+                            request_id: self.request_id.clone(),
+                            attempt_index: current.index,
+                            trigger: current.trigger,
+                            provider_kind: current.metadata.provider().clone(),
+                            account_id: current.metadata.provider_account_id().cloned(),
+                            upstream_model_id: current.metadata.upstream_model().clone(),
+                            upstream_status_code: current
+                                .response_observation
+                                .as_ref()
+                                .and_then(ProviderResponseObservation::status_code),
+                            upstream_request_id: current
+                                .response_observation
+                                .as_ref()
+                                .and_then(ProviderResponseObservation::request_id)
+                                .map(|value| value.as_str().to_owned()),
+                            latency: current.started_at.elapsed().unwrap_or_default(),
+                            error,
+                        }),
+                )
+                .await;
+            }
            self.reset_uncommitted_observations();
-            return Ok(true);
+            return Ok(StreamErrorOutcome::AttemptDiscarded);
        }

-        let engine_error = provider_engine_error(&error);
        self.current = Some(current);
+        if !atomic_client_events.is_empty() {
+            self.observe_atomic_terminal_events(&mut atomic_client_events);
+            return Ok(StreamErrorOutcome::TerminalFailure {
+                events: atomic_client_events,
+                error,
+                send_state,
+            });
+        }
        self.finish_provider_error_with_send_state(&error, send_state)
            .await?;
-        Err(engine_error)
+        Err(provider_engine_error(error))
+    }
+
+    fn observe_atomic_terminal_events(&mut self, events: &mut [ProviderEvent]) {
+        for event in events {
+            if let Some(observation) = event.take_observation() {
+                self.observe_response(observation);
+            }
+            for fact in event.canonical_facts() {
+                self.observe_response_identity(fact);
+                self.observe_event_facts(fact);
+            }
+        }
    }

    fn prepare_continuation_retry(
@@ -896,7 +1061,7 @@ where
        send_state: UpstreamSendState,
        provider_proved_replay_safe: bool,
    ) -> bool {
-        if self.required_account.is_some()
+        if self.account_selection.required_account().is_some()
            || self.continuation_attempt == ContinuationAttempt::None
            || self.downstream_committed_at.is_some()
            || self.delivery_pending
@@ -976,34 +1141,42 @@ where
            .and_then(ProviderResponseObservation::status_code);
        let (upstream_transport, http_version, websocket_pool) =
            self.current_transport_observation();
+        let service_tier = self.current_service_tier();
        let provider_metadata_json = self.current_provider_metadata_json();
-        self.engine
-            .store()
-            .finalize_model_request(ModelRequestFinalization {
-                request_id: self.request_id.clone(),
-                outcome: ExecutionOutcome::Succeeded,
-                send_state: UpstreamSendState::Sent,
-                attempt_count: self.attempts,
-                downstream_committed_at: self.downstream_committed_at,
-                client_status_code: self.client_status_code,
-                upstream_status_code,
-                client_response_id: self.client_response_id.clone(),
-                upstream_request_id,
-                upstream_response_id: self.upstream_response_id.clone(),
-                upstream_transport,
-                http_version,
-                websocket_pool,
-                provider_metadata_json,
-                error: None,
-                provider_error_code: None,
-                retry_after_ms: None,
-                usage: self.usage.clone(),
-                image_generation_succeeded: self.image_generation_succeeded(),
-                cost: self.cost.clone(),
-                timings: self.timings.clone(),
-                completed_at,
-            })
-            .await?;
+        if self.request_persisted {
+            best_effort_store_write(
+                "finalize_model_request",
+                &self.request_id,
+                self.engine
+                    .store()
+                    .finalize_model_request(ModelRequestFinalization {
+                        request_id: self.request_id.clone(),
+                        outcome: ExecutionOutcome::Succeeded,
+                        send_state: UpstreamSendState::Sent,
+                        attempt_count: self.attempts,
+                        downstream_committed_at: self.downstream_committed_at,
+                        client_status_code: self.client_status_code,
+                        upstream_status_code,
+                        client_response_id: self.client_response_id.clone(),
+                        upstream_request_id,
+                        upstream_response_id: self.upstream_response_id.clone(),
+                        upstream_transport,
+                        http_version,
+                        websocket_pool,
+                        service_tier,
+                        provider_metadata_json,
+                        error: None,
+                        provider_error_code: None,
+                        retry_after_ms: None,
+                        usage: self.usage.clone(),
+                        image_generation_succeeded: self.image_generation_succeeded(),
+                        cost: self.cost.clone(),
+                        timings: self.timings.clone(),
+                        completed_at,
+                    }),
+            )
+            .await;
+        }
        self.finalized = true;
        Ok(())
    }
@@ -1072,11 +1245,15 @@ where
            UpstreamSendState::Ambiguous
        };
        let send_state = self.raise_send_watermark(send_state);
-        if self.attempts > 0 {
-            self.engine
-                .store()
-                .mark_send_state(&self.request_id, send_state)
-                .await?;
+        if self.attempts > 0 && self.request_persisted {
+            best_effort_store_write(
+                "mark_send_state",
+                &self.request_id,
+                self.engine
+                    .store()
+                    .mark_send_state(&self.request_id, send_state),
+            )
+            .await;
        }
        self.finish_failure(FailureFinalization {
            outcome,
@@ -1126,36 +1303,44 @@ where
            .and_then(ProviderResponseObservation::status_code);
        let (upstream_transport, http_version, websocket_pool) =
            self.current_transport_observation();
+        let service_tier = self.current_service_tier();
        let provider_metadata_json = self.current_provider_metadata_json();
-        self.engine
-            .store()
-            .finalize_model_request(ModelRequestFinalization {
-                request_id: self.request_id.clone(),
-                outcome: finalization.outcome,
-                send_state: finalization.send_state,
-                attempt_count: self.attempts,
-                downstream_committed_at: self.downstream_committed_at,
-                client_status_code: self.client_status_code,
-                upstream_status_code: finalization.upstream_status_code.or(observed_status_code),
-                client_response_id: self.client_response_id.clone(),
-                upstream_request_id,
-                upstream_response_id: finalization
-                    .provider_response_id
-                    .or_else(|| self.upstream_response_id.clone()),
-                upstream_transport,
-                http_version,
-                websocket_pool,
-                provider_metadata_json,
-                error: Some(finalization.error),
-                provider_error_code: finalization.provider_error_code,
-                retry_after_ms: finalization.retry_after_ms,
-                usage: self.usage.clone(),
-                image_generation_succeeded: self.image_generation_succeeded(),
-                cost: self.cost.clone(),
-                timings: self.timings.clone(),
-                completed_at,
-            })
-            .await?;
+        best_effort_store_write(
+            "finalize_model_request",
+            &self.request_id,
+            self.engine
+                .store()
+                .finalize_model_request(ModelRequestFinalization {
+                    request_id: self.request_id.clone(),
+                    outcome: finalization.outcome,
+                    send_state: finalization.send_state,
+                    attempt_count: self.attempts,
+                    downstream_committed_at: self.downstream_committed_at,
+                    client_status_code: self.client_status_code,
+                    upstream_status_code: finalization
+                        .upstream_status_code
+                        .or(observed_status_code),
+                    client_response_id: self.client_response_id.clone(),
+                    upstream_request_id,
+                    upstream_response_id: finalization
+                        .provider_response_id
+                        .or_else(|| self.upstream_response_id.clone()),
+                    upstream_transport,
+                    http_version,
+                    websocket_pool,
+                    service_tier,
+                    provider_metadata_json,
+                    error: Some(finalization.error),
+                    provider_error_code: finalization.provider_error_code,
+                    retry_after_ms: finalization.retry_after_ms,
+                    usage: self.usage.clone(),
+                    image_generation_succeeded: self.image_generation_succeeded(),
+                    cost: self.cost.clone(),
+                    timings: self.timings.clone(),
+                    completed_at,
+                }),
+        )
+        .await;
        self.finalized = true;
        Ok(())
    }
@@ -1186,6 +1371,14 @@ where
            .map(|metadata| metadata.as_json().to_owned())
    }

+    fn current_service_tier(&self) -> Option<String> {
+        self.current
+            .as_ref()
+            .and_then(|current| current.response_observation.as_ref())
+            .and_then(ProviderResponseObservation::service_tier)
+            .map(str::to_owned)
+    }
+
    fn image_generation_succeeded(&self) -> Option<bool> {
        self.image_generation_requested
            .then(|| self.usage.image_output_tokens.unwrap_or_default() > 0)
@@ -1235,12 +1428,62 @@ where
    }
 }

+async fn best_effort_store_write<T>(
+    operation: &'static str,
+    request_id: &ModelRequestId,
+    write: impl Future<Output = Result<T, StoreError>>,
+) -> Option<T> {
+    match write.await {
+        Ok(value) => Some(value),
+        Err(error) => {
+            tracing::warn!(
+                operation,
+                request_id = request_id.as_str(),
+                error_kind = ?error.kind(),
+                "执行观测写入失败，数据面不受影响"
+            );
+            None
+        }
+    }
+}
+
 enum PullOutcome {
    Event(ProviderEvent),
    AttemptDiscarded,
+    TerminalFailure {
+        events: Vec<ProviderEvent>,
+        error: ProviderError,
+        send_state: UpstreamSendState,
+    },
    End,
 }

+enum StreamErrorOutcome {
+    AttemptDiscarded,
+    TerminalFailure {
+        events: Vec<ProviderEvent>,
+        error: ProviderError,
+        send_state: UpstreamSendState,
+    },
+}
+
+impl StreamErrorOutcome {
+    fn into_pull_outcome(self) -> PullOutcome {
+        match self {
+            Self::AttemptDiscarded => PullOutcome::AttemptDiscarded,
+            Self::TerminalFailure {
+                events,
+                error,
+                send_state,
+            } => PullOutcome::TerminalFailure {
+                events,
+                error,
+                send_state,
+            },
+        }
+    }
+}
+
 enum PollBoundary {
    Item(Option<Result<ProviderEvent, ProviderError>>),
    Cancelled,
@@ -1313,11 +1556,11 @@ fn initial_continuation_attempt(
    }
 }

-fn provider_engine_error(error: &ProviderError) -> EngineError {
+fn provider_engine_error(error: ProviderError) -> EngineError {
    if error.kind() == ProviderErrorKind::Cancelled {
        EngineError::Cancelled
    } else {
-        EngineError::Provider(error.clone())
+        EngineError::Provider(error)
    }
 }

@@ -44,6 +44,46 @@ impl fmt::Display for ProviderAccountId {
    }
 }

+/// credential 轮换时可选替换的上游账号身份。
+#[derive(Clone, PartialEq, Eq)]
+pub struct ProviderAccountIdentity {
+    upstream_user_id: String,
+    upstream_account_id: Option<String>,
+}
+
+impl fmt::Debug for ProviderAccountIdentity {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("ProviderAccountIdentity")
+            .field("upstream_user_id", &"<redacted>")
+            .field(
+                "upstream_account_id",
+                &self.upstream_account_id.as_ref().map(|_| "<redacted>"),
+            )
+            .finish()
+    }
+}
+
+impl ProviderAccountIdentity {
+    #[must_use]
+    pub const fn new(upstream_user_id: String, upstream_account_id: Option<String>) -> Self {
+        Self {
+            upstream_user_id,
+            upstream_account_id,
+        }
+    }
+
+    #[must_use]
+    pub fn upstream_user_id(&self) -> &str {
+        &self.upstream_user_id
+    }
+
+    #[must_use]
+    pub fn upstream_account_id(&self) -> Option<&str> {
+        self.upstream_account_id.as_deref()
+    }
+}
+
 /// `provider_accounts.credential_revision` 的正数 CAS revision。
 #[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
 pub struct CredentialRevision(NonZeroU64);
@@ -602,6 +642,15 @@ pub trait ProviderAccountStore: Send + Sync {
        expected_revision: CredentialRevision,
    ) -> Result<LoadedCredential, StoreError>;

+    /// 读取账号当前 credential 及其 revision，不做任何版本比对。
+    ///
+    /// 管理写入必须在临近 CAS 时用它取 fence，而不是携带调用方持有的旧 revision：
+    /// 后台刷新随时会推进 revision，用陈旧快照会把正常的恢复操作误判为冲突。
+    async fn load_current_credential(
+        &self,
+        account: &ProviderAccountId,
+    ) -> Result<LoadedCredential, StoreError>;
+
    async fn compare_and_swap_credential(
        &self,
        update: CredentialCasUpdate,
@@ -901,6 +950,63 @@ pub struct AccountSelectionContext {
    pub excluded_accounts: BTreeSet<ProviderAccountId>,
    pub preferred_account: Option<ProviderAccountId>,
    pub round_robin_cursor: u64,
+    pub availability: AccountAvailabilityPolicy,
+}
+
+/// 选择账号时是否信任本地可用性投影。
+///
+/// 管理端对指定账号执行诊断时，会直接向上游确认实际状态；该模式跳过
+/// `enabled`、可用性、冷却和 token 到期等本地投影，仍保留租约、并发和
+/// 请求间隔约束，且只能与固定账号约束组合使用。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
+pub enum AccountAvailabilityPolicy {
+    #[default]
+    Enforce,
+    BypassForDiagnostic,
+}
+
+impl AccountAvailabilityPolicy {
+    #[must_use]
+    pub const fn bypasses_local_availability(self) -> bool {
+        matches!(self, Self::BypassForDiagnostic)
+    }
+}
+
+/// 候选账号未进入调度池的约束。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum AccountSchedulingBlocker {
+    LocalAvailability,
+    Excluded,
+    ConcurrencyLimit,
+    RequestInterval,
+}
+
+/// 优先账号在本次选择中的处理结果。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum PreferredAccountSelection {
+    NotRequested,
+    Hit,
+    Missing,
+    Blocked(AccountSchedulingBlocker),
+}
+
+/// 一次完整账号选择；同时保留优先账号决策，供 Provider 记录调度遥测。
+#[derive(Debug, Clone, Copy)]
+pub struct AccountSelection<'a> {
+    candidate: &'a AccountCandidate,
+    preferred: PreferredAccountSelection,
+}
+
+impl<'a> AccountSelection<'a> {
+    #[must_use]
+    pub const fn candidate(self) -> &'a AccountCandidate {
+        self.candidate
+    }
+
+    #[must_use]
+    pub const fn preferred(self) -> PreferredAccountSelection {
+        self.preferred
+    }
 }

 /// 同一 target 内唯一的账号排序器。
@@ -914,43 +1020,55 @@ impl AccountSelector {
        &self,
        candidates: &'a [AccountCandidate],
        context: &AccountSelectionContext,
-    ) -> Option<&'a AccountCandidate> {
+    ) -> Option<AccountSelection<'a>> {
+        let preferred = if let Some(preferred) = context.preferred_account.as_ref() {
+            match candidates
+                .iter()
+                .find(|candidate| candidate.account.id() == preferred)
+            {
+                Some(candidate) => match self.scheduling_blocker(candidate, context) {
+                    None => {
+                        return Some(AccountSelection {
+                            candidate,
+                            preferred: PreferredAccountSelection::Hit,
+                        });
+                    }
+                    Some(blocker) => PreferredAccountSelection::Blocked(blocker),
+                },
+                None => PreferredAccountSelection::Missing,
+            }
+        } else {
+            PreferredAccountSelection::NotRequested
+        };
+
        let mut eligible = candidates
            .iter()
-            .filter(|candidate| eligible(candidate, context))
+            .filter(|candidate| self.scheduling_blocker(candidate, context).is_none())
            .collect::<Vec<_>>();
        if eligible.is_empty() {
            return None;
        }

-        if let Some(preferred) = context.preferred_account.as_ref()
-            && let Some(candidate) = eligible
-                .iter()
-                .find(|candidate| candidate.account.id() == preferred)
-            && (context.policy.strategy() == RotationStrategy::Sticky
-                || (context.policy.strategy() == RotationStrategy::Smart
-                    && !smart_preference_should_escape(&candidate.signals)))
-        {
-            return Some(candidate);
-        }
-
-        match context.policy.strategy() {
-            RotationStrategy::QuotaResetPriority => eligible.sort_by_key(|candidate| {
-                (
-                    candidate.signals.quota_reset_at.is_none(),
-                    candidate.signals.quota_reset_at,
-                    candidate.signals.in_flight,
-                    candidate.signals.last_started_at,
-                    candidate.account.id().clone(),
-                )
-            }),
+        let candidate = match context.policy.strategy() {
+            RotationStrategy::QuotaResetPriority => {
+                eligible.sort_by_key(|candidate| {
+                    (
+                        candidate.signals.quota_reset_at.is_none(),
+                        candidate.signals.quota_reset_at,
+                        candidate.signals.in_flight,
+                        candidate.signals.last_started_at,
+                        candidate.account.id().clone(),
+                    )
+                });
+                eligible.first().copied()?
+            }
            RotationStrategy::RoundRobin => {
                eligible.sort_by_key(|candidate| candidate.account.id().clone());
                let index = context.round_robin_cursor as usize % eligible.len();
-                return Some(eligible[index]);
+                eligible.get(index).copied()?
            }
            RotationStrategy::Smart => {
-                return select_smart_candidate(&eligible, context.round_robin_cursor);
+                select_smart_candidate(&eligible, context.round_robin_cursor)?
            }
            RotationStrategy::Sticky => {
                eligible.sort_by_key(|candidate| {
@@ -959,9 +1077,44 @@ impl AccountSelector {
                        candidate.account.id().clone(),
                    )
                });
+                eligible.first().copied()?
            }
+        };
+        Some(AccountSelection {
+            candidate,
+            preferred,
+        })
+    }
+
+    fn scheduling_blocker(
+        &self,
+        candidate: &AccountCandidate,
+        context: &AccountSelectionContext,
+    ) -> Option<AccountSchedulingBlocker> {
+        if !context.availability.bypasses_local_availability()
+            && !candidate.account.is_schedulable(context.now)
+        {
+            return Some(AccountSchedulingBlocker::LocalAvailability);
        }
-        eligible.into_iter().next()
+        if context.excluded_accounts.contains(candidate.account.id()) {
+            return Some(AccountSchedulingBlocker::Excluded);
+        }
+        if candidate.signals.in_flight >= context.policy.max_concurrent_per_account().get() {
+            return Some(AccountSchedulingBlocker::ConcurrencyLimit);
+        }
+        if candidate
+            .signals
+            .last_started_at
+            .is_some_and(|last_started| {
+                !context
+                    .now
+                    .duration_since(last_started)
+                    .is_ok_and(|elapsed| elapsed >= context.policy.request_interval())
+            })
+        {
+            return Some(AccountSchedulingBlocker::RequestInterval);
+        }
+        None
    }
 }

@@ -969,8 +1122,6 @@ const SMART_LOAD_WEIGHT: f64 = 1.0;
 const SMART_QUOTA_WEIGHT: f64 = 0.8;
 const SMART_FAILURE_WEIGHT: f64 = 1.0;
 const SMART_LATENCY_WEIGHT: f64 = 0.5;
-const SMART_PREFERENCE_FAILURE_ESCAPE_BASIS_POINTS: u16 = 5_000;
-const SMART_PREFERENCE_LATENCY_ESCAPE_MS: u64 = 15_000;

 struct SmartNormalization {
    max_in_flight: u32,
@@ -1091,34 +1242,6 @@ fn higher_is_better(value: u64, minimum: u64, maximum: u64) -> f64 {
    (value.saturating_sub(minimum) as f64 / (maximum - minimum) as f64).clamp(0.0, 1.0)
 }

-fn smart_preference_should_escape(signals: &AccountRuntimeSignals) -> bool {
-    signals
-        .failure_rate_basis_points
-        .is_some_and(|rate| rate > SMART_PREFERENCE_FAILURE_ESCAPE_BASIS_POINTS)
-        || signals
-            .first_output_latency_ms
-            .is_some_and(|latency| latency > SMART_PREFERENCE_LATENCY_ESCAPE_MS)
-}
-
-fn eligible(candidate: &AccountCandidate, context: &AccountSelectionContext) -> bool {
-    if !candidate.account.is_schedulable(context.now)
-        || context.excluded_accounts.contains(candidate.account.id())
-        || candidate.signals.in_flight >= context.policy.max_concurrent_per_account().get()
-    {
-        return false;
-    }
-
-    candidate
-        .signals
-        .last_started_at
-        .is_none_or(|last_started| {
-            context
-                .now
-                .duration_since(last_started)
-                .is_ok_and(|elapsed| elapsed >= context.policy.request_interval())
-        })
-}
-
 /// Credential 值对象构造错误。
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Error)]
 pub enum CredentialError {
@@ -17,7 +17,10 @@ use crate::engine::continuation::{
    ContinuationBinding, NativeContinuationPin, NativeContinuationPort, PreviousResponseId,
 };
 use crate::engine::coordinator::ResponseExecutionSession;
-use crate::engine::probe::{AccountProbe, AccountProbeRequest, AccountProbeResult};
+use crate::engine::probe::{
+    AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult,
+    AccountProbeUpstreamResponse,
+};
 use crate::engine::provider::ProviderRegistry;
 use crate::engine::{
    AttemptCoordinator, AttemptRecord, CancellationToken, CoordinatedEvent, EngineError,
@@ -36,7 +39,7 @@ use crate::routing::{
 };

 const MODEL_REQUEST_DEADLINE: Duration = Duration::from_secs(10 * 60);
-const CONTINUATION_AFFINITY_TIMEOUT: Duration = Duration::from_millis(100);
+const REDIS_COORDINATION_TIMEOUT: Duration = Duration::from_millis(100);

 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub enum ClientTransport {
@@ -233,15 +236,6 @@ impl DefaultExecutionService {
        request.client.policy.authorize().map_err(|_| {
            GatewayError::new(GatewayErrorKind::PolicyDenied, "client API key is disabled")
        })?;
-        if !request.client.snapshot.contains_public_model_for_provider(
-            &request.public_model,
-            request.client.policy.provider_kind(),
-        ) {
-            return Err(GatewayError::new(
-                GatewayErrorKind::ModelNotFound,
-                "requested model was not found",
-            ));
-        }
        let started_at = SystemTime::now();
        let deadline_at = started_at
            .checked_add(MODEL_REQUEST_DEADLINE)
@@ -260,7 +254,7 @@ impl DefaultExecutionService {
        let continuation = match request.metadata.previous_response_id.as_ref() {
            Some(previous) => {
                let resolve = self.continuation.resolve(previous).fuse();
-                let timeout = Delay::new(CONTINUATION_AFFINITY_TIMEOUT).fuse();
+                let timeout = Delay::new(REDIS_COORDINATION_TIMEOUT).fuse();
                pin_mut!(resolve, timeout);
                let pin = select_biased! {
                    result = resolve => result.ok().flatten(),
@@ -398,14 +392,33 @@ impl DefaultExecutionService {
        &self,
        provider_kind: &ProviderKind,
    ) -> Result<RoutingContext, GatewayError> {
-        let blocked_providers = match self.circuits.decision(provider_kind).await.map_err(|_| {
-            GatewayError::new(
-                GatewayErrorKind::NoAvailableProvider,
-                "provider health state is temporarily unavailable",
-            )
-        })? {
-            ProviderCircuitDecision::Allow => BTreeSet::new(),
-            ProviderCircuitDecision::BlockedUntil(_) => BTreeSet::from([provider_kind.clone()]),
+        let decision = self.circuits.decision(provider_kind).fuse();
+        let timeout = Delay::new(REDIS_COORDINATION_TIMEOUT).fuse();
+        pin_mut!(decision, timeout);
+        let decision = select_biased! {
+            result = decision => Some(result),
+            _ = timeout => None,
+        };
+        let blocked_providers = match decision {
+            Some(Ok(ProviderCircuitDecision::Allow)) => BTreeSet::new(),
+            Some(Ok(ProviderCircuitDecision::BlockedUntil(_))) => {
+                BTreeSet::from([provider_kind.clone()])
+            }
+            Some(Err(error)) => {
+                tracing::warn!(
+                    provider = provider_kind.as_str(),
+                    %error,
+                    "Provider circuit 读取失败，按可重建协调状态 fail-open"
+                );
+                BTreeSet::new()
+            }
+            None => {
+                tracing::warn!(
+                    provider = provider_kind.as_str(),
+                    "Provider circuit 读取超时，按可重建协调状态 fail-open"
+                );
+                BTreeSet::new()
+            }
        };
        Ok(RoutingContext {
            provider_kind: Some(provider_kind.clone()),
@@ -416,7 +429,7 @@ impl DefaultExecutionService {
    async fn probe_inner(
        &self,
        request: AccountProbeRequest,
-    ) -> Result<AccountProbeResult, GatewayError> {
+    ) -> Result<AccountProbeResult, AccountProbeError> {
        let AccountProbeRequest {
            account_id,
            provider_kind,
@@ -477,11 +490,11 @@ impl DefaultExecutionService {
        };
        let mut session = match self
            .probe_coordinator
-            .start(
+            .start_diagnostic(
                new_request,
                operation,
                plan,
-                Some(account_id),
+                account_id,
                None,
                CancellationToken::new(),
            )
@@ -525,26 +538,55 @@ impl DefaultExecutionService {
        })
    }

-    /// 探测失败先落库再转成客户端错误；转换会丢掉上游状态码与 provider code。
+    /// 探测失败先记录脱敏分类事实，再把请求局部的原始上游响应交给认证管理端。
    async fn observe_probe_failure(
        &self,
        observed: &ProbeObservation,
        started_at: SystemTime,
        error: &EngineError,
-    ) -> GatewayError {
+    ) -> AccountProbeError {
+        let upstream_response = match error {
+            EngineError::Provider(provider_error) => provider_error
+                .client_visible_upstream_response()
+                .map(AccountProbeUpstreamResponse::from_client_response),
+            _ => None,
+        };
        if let EngineError::Provider(provider_error) = error {
-            let _ = self
+            let latency = started_at.elapsed().unwrap_or_default();
+            let latency_ms = u64::try_from(latency.as_millis()).unwrap_or(u64::MAX);
+            tracing::warn!(
+                target: "gateway_probe",
+                provider_kind = observed.provider_kind.as_str(),
+                account_id = observed.account_id.as_str(),
+                upstream_model = observed.upstream_model.as_str(),
+                failure_kind = provider_error.kind().as_str(),
+                send_state = ?provider_error.send_state(),
+                upstream_status = ?provider_error.upstream_status(),
+                provider_error_code = ?provider_error.upstream_code().map(|code| code.as_str()),
+                latency_ms,
+                "账号连接测试失败"
+            );
+            if let Err(store_error) = self
                .observations
                .record_probe_failure(ProbeFailure {
                    provider_kind: observed.provider_kind.clone(),
                    account_id: observed.account_id.clone(),
                    upstream_model_id: observed.upstream_model.clone(),
                    error: provider_error.clone(),
-                    latency: started_at.elapsed().unwrap_or_default(),
+                    latency,
                })
-                .await;
+                .await
+            {
+                tracing::warn!(
+                    operation = "record_probe_failure",
+                    provider_kind = observed.provider_kind.as_str(),
+                    account_id = observed.account_id.as_str(),
+                    error_kind = ?store_error.kind(),
+                    "账号连接测试观测写入失败，测试结果不受影响"
+                );
+            }
        }
-        gateway_error_from_engine(error)
+        AccountProbeError::new(gateway_error_from_engine(error), upstream_response)
    }
 }

@@ -651,7 +693,7 @@ impl AccountProbe for DefaultExecutionService {
    fn probe(
        &self,
        request: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>> {
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
        Box::pin(async move { self.probe_inner(request).await })
    }
 }
@@ -664,10 +706,13 @@ struct AdmissionLease {

 impl AdmissionLease {
    async fn release(self) {
-        let _ = self
+        if let Err(error) = self
            .port
            .release(&self.client_api_key_id, &self.model_request_id)
-            .await;
+            .await
+        {
+            tracing::warn!(%error, "Client admission 释放失败，依赖租约 TTL 收敛");
+        }
    }
 }

@@ -742,13 +787,7 @@ impl DefaultExecutionSession {
            return;
        };
        self.continuation_recorded = true;
-        let record = self.continuation.record(pin).fuse();
-        let timeout = Delay::new(CONTINUATION_AFFINITY_TIMEOUT).fuse();
-        pin_mut!(record, timeout);
-        select_biased! {
-            _ = record => {},
-            _ = timeout => {},
-        }
+        record_native_continuation(self.continuation.as_ref(), pin).await;
    }

    async fn finalize_detached(&mut self) {
@@ -756,8 +795,10 @@ impl DefaultExecutionSession {
            return;
        };
        core.cancel();
-        if !core.is_finalized() {
-            let _ = core.cancel_and_finalize().await;
+        if !core.is_finalized()
+            && let Err(error) = core.cancel_and_finalize().await
+        {
+            tracing::warn!(%error, "Detached execution 终态收敛失败");
        }
        let pending = core
            .provider_attempt_outcomes()
@@ -878,7 +919,32 @@ async fn publish_provider_attempt_outcomes(
            }
            Some(_) => continue,
        };
-        let _ = result;
+        if let Err(error) = result {
+            tracing::warn!(
+                provider = outcome.provider_kind().as_str(),
+                %error,
+                "Provider circuit feedback 写入失败，数据面不受影响"
+            );
+        }
+    }
+}
+
+async fn record_native_continuation(
+    continuation: &dyn NativeContinuationPort,
+    pin: NativeContinuationPin,
+) {
+    let record = continuation.record(pin).fuse();
+    let timeout = Delay::new(REDIS_COORDINATION_TIMEOUT).fuse();
+    pin_mut!(record, timeout);
+    select_biased! {
+        result = record => {
+            if let Err(error) = result {
+                tracing::warn!(%error, "Continuation affinity 写入失败，后续请求将退化为外部续接");
+            }
+        },
+        _ = timeout => {
+            tracing::warn!("Continuation affinity 后台写入超时，已丢弃本次亲和记录");
+        },
    }
 }

@@ -232,6 +232,7 @@ pub struct AccountAttemptContext {
    required_account: Option<ProviderAccountId>,
    state_owner: Option<ProviderAccountStateOwner>,
    credential_recovery_attempted: bool,
+    diagnostic_required_account: bool,
 }

 impl AccountAttemptContext {
@@ -246,6 +247,25 @@ impl AccountAttemptContext {
            required_account,
            state_owner,
            credential_recovery_attempted: false,
+            diagnostic_required_account: false,
+        }
+    }
+
+    /// 为管理端对固定账号的上游诊断创建上下文。
+    ///
+    /// 诊断只绕过本地的被动可用性投影，不能换号，并继续受账号租约保护。
+    #[must_use]
+    pub const fn diagnostic(
+        excluded_accounts: BTreeSet<ProviderAccountId>,
+        required_account: ProviderAccountId,
+        state_owner: Option<ProviderAccountStateOwner>,
+    ) -> Self {
+        Self {
+            excluded_accounts,
+            required_account: Some(required_account),
+            state_owner,
+            credential_recovery_attempted: false,
+            diagnostic_required_account: true,
        }
    }

@@ -275,6 +295,12 @@ impl AccountAttemptContext {
    pub const fn credential_recovery_attempted(&self) -> bool {
        self.credential_recovery_attempted
    }
+
+    /// 此尝试是否要由真实上游而非本地投影确认固定账号的可用性。
+    #[must_use]
+    pub const fn is_diagnostic_required_account(&self) -> bool {
+        self.diagnostic_required_account
+    }
 }

 /// 请求中 Provider 账号绑定状态的唯一归属。
@@ -474,6 +500,12 @@ impl AttemptContext {
        self.account.credential_recovery_attempted()
    }

+    /// 管理端固定账号诊断会跳过本地可用性投影，保留全部租约约束。
+    #[must_use]
+    pub const fn is_diagnostic_required_account(&self) -> bool {
+        self.account.is_diagnostic_required_account()
+    }
+
    #[must_use]
    pub const fn continuation(&self) -> Option<&ContinuationBinding> {
        self.continuation.as_ref()
@@ -583,6 +615,7 @@ pub struct ModelRequestFinalization {
    pub upstream_transport: Option<String>,
    pub http_version: Option<String>,
    pub websocket_pool: Option<String>,
+    pub service_tier: Option<String>,
    /// Provider 已筛选的专有观测 JSON；Core 不解释字段。
    pub provider_metadata_json: Option<String>,
    pub error: Option<GatewayError>,
@@ -1,8 +1,11 @@
 //! 管理端账号连通性测试的真实执行链端口。

+use std::fmt;
+
+use bytes::Bytes;
 use futures::future::BoxFuture;

-use crate::error::GatewayError;
+use crate::error::{ClientVisibleUpstreamResponse, GatewayError, GatewayErrorKind};
 use crate::routing::{ProviderKind, UpstreamModelId};
 use crate::{engine::credential::ProviderAccountId, operation::Operation};

@@ -19,9 +22,111 @@ pub struct AccountProbeResult {
    pub text: Vec<String>,
 }

+/// 仅供当前管理端连接测试展示的原始上游失败响应。
+///
+/// 正文不进入 `Debug`、日志或持久化；Core 只在探测终态从原始 Provider 错误显式复制。
+#[derive(PartialEq, Eq)]
+pub struct AccountProbeUpstreamResponse {
+    status: u16,
+    content_type: Option<Vec<u8>>,
+    body: Bytes,
+}
+
+impl AccountProbeUpstreamResponse {
+    pub(crate) fn from_client_response(response: &ClientVisibleUpstreamResponse) -> Self {
+        Self {
+            status: response.status(),
+            content_type: response.content_type().map(<[u8]>::to_vec),
+            body: response.body().clone(),
+        }
+    }
+
+    #[must_use]
+    pub const fn status(&self) -> u16 {
+        self.status
+    }
+
+    #[must_use]
+    pub fn content_type(&self) -> Option<&[u8]> {
+        self.content_type.as_deref()
+    }
+
+    #[must_use]
+    pub const fn body(&self) -> &Bytes {
+        &self.body
+    }
+}
+
+impl fmt::Debug for AccountProbeUpstreamResponse {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("AccountProbeUpstreamResponse")
+            .field("status", &self.status)
+            .field(
+                "content_type",
+                &self.content_type.as_ref().map(|_| "<present>"),
+            )
+            .field("body", &"<redacted>")
+            .finish()
+    }
+}
+
+/// 管理端连接测试的终态错误。
+///
+/// `gateway` 保留稳定分类，`upstream_response` 只面向本次认证管理请求展示源响应。
+#[derive(Debug)]
+pub struct AccountProbeError {
+    gateway: GatewayError,
+    upstream_response: Option<AccountProbeUpstreamResponse>,
+}
+
+impl AccountProbeError {
+    #[must_use]
+    pub const fn new(
+        gateway: GatewayError,
+        upstream_response: Option<AccountProbeUpstreamResponse>,
+    ) -> Self {
+        Self {
+            gateway,
+            upstream_response,
+        }
+    }
+
+    #[must_use]
+    pub const fn kind(&self) -> GatewayErrorKind {
+        self.gateway.kind()
+    }
+
+    #[must_use]
+    pub fn client_message(&self) -> &str {
+        self.gateway.client_message()
+    }
+
+    #[must_use]
+    pub fn client_error_type(&self) -> Option<&str> {
+        self.gateway.client_error_type()
+    }
+
+    #[must_use]
+    pub fn client_error_code(&self) -> Option<&str> {
+        self.gateway.client_error_code()
+    }
+
+    #[must_use]
+    pub const fn upstream_response(&self) -> Option<&AccountProbeUpstreamResponse> {
+        self.upstream_response.as_ref()
+    }
+}
+
+impl From<GatewayError> for AccountProbeError {
+    fn from(gateway: GatewayError) -> Self {
+        Self::new(gateway, None)
+    }
+}
+
 pub trait AccountProbe: Send + Sync {
    fn probe(
        &self,
        request: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>>;
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>>;
 }
@@ -16,7 +16,7 @@ use crate::engine::credential::{
 };
 use crate::engine::{AttemptContext, UpstreamSendState};
 use crate::error::{
-    IdentifierError, ProviderError, ProviderErrorKind, SafeUpstreamValue, validate_text,
+    IdentifierError, OpaqueUpstreamValue, ProviderError, ProviderErrorKind, validate_text,
 };
 use crate::event::{EventSequenceValidator, ProviderEvent};
 use crate::operation::Operation;
@@ -125,7 +125,7 @@ pub struct ProviderCallMetadata {
    provider: ProviderKind,
    upstream_model: UpstreamModelId,
    resource: ProviderResource,
-    upstream_request_id: Option<SafeUpstreamValue>,
+    upstream_request_id: Option<OpaqueUpstreamValue>,
    transport: UpstreamTransport,
 }

@@ -149,7 +149,7 @@ impl ProviderCallMetadata {

    /// 设置 adapter 已分类为非 bearer 的 request ID。
    #[must_use]
-    pub fn with_upstream_request_id(mut self, request_id: SafeUpstreamValue) -> Self {
+    pub fn with_upstream_request_id(mut self, request_id: OpaqueUpstreamValue) -> Self {
        self.upstream_request_id = Some(request_id);
        self
    }
@@ -186,7 +186,7 @@ impl ProviderCallMetadata {

    /// 返回安全上游 request ID。
    #[must_use]
-    pub const fn upstream_request_id(&self) -> Option<&SafeUpstreamValue> {
+    pub const fn upstream_request_id(&self) -> Option<&OpaqueUpstreamValue> {
        self.upstream_request_id.as_ref()
    }

@@ -3,9 +3,11 @@
 use std::fmt;
 use std::time::Duration;

+use bytes::Bytes;
 use thiserror::Error;

 use crate::engine::UpstreamSendState;
+use crate::event::{ProviderEvent, ProviderResponseHeader};

 /// 应用层标识不满足约束。
 #[derive(Debug, Clone, PartialEq, Eq, Error)]
@@ -174,22 +176,18 @@ pub enum ContinuationFailure {
    HistoryUnavailable,
 }

-/// Adapter 已明确分类为非 bearer、可用于诊断的上游值。
+/// Adapter 已明确分类为非 bearer 的不透明上游值。
+///
+/// Core 不解释或校验内容，只通过自定义 [`Debug`] 避免它意外进入日志。协议 adapter
+/// 可在原客户端响应中读取原值。
 #[derive(Clone, PartialEq, Eq, Hash)]
-pub struct SafeUpstreamValue(String);
+pub struct OpaqueUpstreamValue(String);

-impl SafeUpstreamValue {
-    const MAX_BYTES: usize = 256;
-
-    /// 校验并创建诊断值。
-    ///
-    /// # Errors
-    ///
-    /// 空值、超长值或控制字符会返回 [`IdentifierError`]。
-    pub fn new(value: impl Into<String>) -> Result<Self, IdentifierError> {
-        let value = value.into();
-        validate_text(&value, Self::MAX_BYTES, false, None)?;
-        Ok(Self(value))
+impl OpaqueUpstreamValue {
+    /// 原样保存上游值。
+    #[must_use]
+    pub fn new(value: impl Into<String>) -> Self {
+        Self(value.into())
    }

    /// 返回已经由 adapter 安全分类的原值。
@@ -199,9 +197,9 @@ impl SafeUpstreamValue {
    }
 }

-impl fmt::Debug for SafeUpstreamValue {
+impl fmt::Debug for OpaqueUpstreamValue {
    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
-        formatter.write_str("SafeUpstreamValue(<redacted-from-Debug>)")
+        formatter.write_str("OpaqueUpstreamValue(<redacted-from-Debug>)")
    }
 }

@@ -212,31 +210,23 @@ impl fmt::Debug for SafeUpstreamValue {
 #[derive(Clone, PartialEq, Eq)]
 pub struct ClientVisibleUpstreamError {
    message: String,
-    code: Option<SafeUpstreamValue>,
-    error_type: Option<SafeUpstreamValue>,
+    code: Option<OpaqueUpstreamValue>,
+    error_type: Option<OpaqueUpstreamValue>,
 }

 impl ClientVisibleUpstreamError {
-    const MAX_MESSAGE_BYTES: usize = 8_192;
-
-    /// 从结构化上游 `message`、`code` 和 `type` 创建客户端可见错误。
-    ///
-    /// # Errors
-    ///
-    /// message 为空、过长或含控制字符时返回错误；可选 code/type 不满足安全
-    /// 约束时会被省略，不会把整段上游 body 重新暴露。
+    /// 原样保存结构化上游 `message`、`code` 和 `type`。
+    #[must_use]
    pub fn new(
        message: impl Into<String>,
        code: Option<String>,
        error_type: Option<String>,
-    ) -> Result<Self, IdentifierError> {
-        let message = message.into();
-        validate_text(&message, Self::MAX_MESSAGE_BYTES, false, None)?;
-        Ok(Self {
-            message,
-            code: code.and_then(|value| SafeUpstreamValue::new(value).ok()),
-            error_type: error_type.and_then(|value| SafeUpstreamValue::new(value).ok()),
-        })
+    ) -> Self {
+        Self {
+            message: message.into(),
+            code: code.map(OpaqueUpstreamValue::new),
+            error_type: error_type.map(OpaqueUpstreamValue::new),
+        }
    }

    /// 返回原上游的结构化 message。
@@ -248,13 +238,13 @@ impl ClientVisibleUpstreamError {
    /// 返回原上游的结构化 code。
    #[must_use]
    pub fn code(&self) -> Option<&str> {
-        self.code.as_ref().map(SafeUpstreamValue::as_str)
+        self.code.as_ref().map(OpaqueUpstreamValue::as_str)
    }

    /// 返回原上游的结构化 type。
    #[must_use]
    pub fn error_type(&self) -> Option<&str> {
-        self.error_type.as_ref().map(SafeUpstreamValue::as_str)
+        self.error_type.as_ref().map(OpaqueUpstreamValue::as_str)
    }
 }

@@ -264,28 +254,110 @@ impl fmt::Debug for ClientVisibleUpstreamError {
    }
 }

+/// 只供当前客户端请求使用的原始上游 HTTP 失败响应。
+///
+/// 该值不属于稳定诊断事实，不能进入日志或持久化。它刻意不实现 [`Clone`]；
+/// [`ProviderError`] 的普通 clone 会丢弃它，只有最终失败的原对象才能把响应交给
+/// 原客户端协议，或由认证管理端的账号连接测试显式复制到请求局部结果。
+#[derive(PartialEq, Eq)]
+pub struct ClientVisibleUpstreamResponse {
+    status: u16,
+    content_type: Option<Vec<u8>>,
+    headers: Vec<ProviderResponseHeader>,
+    body: Bytes,
+}
+
+impl ClientVisibleUpstreamResponse {
+    /// 保存 transport 实际收到的状态码、Content-Type 原值和正文。
+    #[must_use]
+    pub fn new(status: u16, content_type: Option<Vec<u8>>, body: Bytes) -> Self {
+        Self {
+            status,
+            content_type,
+            headers: Vec::new(),
+            body,
+        }
+    }
+
+    /// 附加 Provider 已剔除账号绑定与 framing 信息的普通响应头。
+    #[must_use]
+    pub fn with_headers(mut self, headers: Vec<ProviderResponseHeader>) -> Self {
+        self.headers = headers;
+        self
+    }
+
+    #[must_use]
+    pub const fn status(&self) -> u16 {
+        self.status
+    }
+
+    #[must_use]
+    pub fn content_type(&self) -> Option<&[u8]> {
+        self.content_type.as_deref()
+    }
+
+    #[must_use]
+    pub fn headers(&self) -> &[ProviderResponseHeader] {
+        &self.headers
+    }
+
+    #[must_use]
+    pub const fn body(&self) -> &Bytes {
+        &self.body
+    }
+}
+
+impl fmt::Debug for ClientVisibleUpstreamResponse {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("ClientVisibleUpstreamResponse")
+            .field("status", &self.status)
+            .field(
+                "content_type",
+                &self.content_type.as_ref().map(|_| "<present>"),
+            )
+            .field("header_count", &self.headers.len())
+            .field("body", &"<redacted>")
+            .finish()
+    }
+}
+
 /// 单次 Provider 调用的稳定错误。
 ///
-/// 该类型不接收原始响应正文，也不会在 `Debug` 或 `Display` 中打印上游
+/// 稳定诊断字段不接收原始响应正文，也不会在 `Debug` 或 `Display` 中打印上游
 /// code/request ID/response ID。Adapter 若捕获到可能含 secret 的上下文，只能调用
 /// [`ProviderError::redact_sensitive_context`] 丢弃正文并留下脱敏标记。
-#[derive(Clone)]
+///
+/// 唯一例外是 [`ProviderError::with_atomic_client_events`]：它只承载尚未交付客户端、
+/// 必须与本错误一起完成重试判断的协议事件。Core 会在任何持久化或日志记录前取走
+/// 这些事件，不能把它们当作诊断上下文使用。
 pub struct ProviderError {
    kind: ProviderErrorKind,
    send_state: UpstreamSendState,
    upstream_status: Option<u16>,
-    upstream_code: Option<SafeUpstreamValue>,
-    upstream_request_id: Option<SafeUpstreamValue>,
-    upstream_response_id: Option<SafeUpstreamValue>,
+    upstream_values: Option<Box<ProviderErrorUpstreamValues>>,
    retry_after: Option<Duration>,
    continuation_failure: Option<ContinuationFailure>,
    replay_safe: bool,
+    pre_delivery_retry: bool,
    credential_recovery_required: bool,
    retry_same_account: bool,
    sensitive_context_redacted: bool,
    client_visible_upstream_error: Option<Box<ClientVisibleUpstreamError>>,
+    client_visible_upstream_response: Option<Box<ClientVisibleUpstreamResponse>>,
+    atomic_client_events: Option<Box<AtomicClientEvents>>,
 }

+#[derive(Clone, Default)]
+struct ProviderErrorUpstreamValues {
+    code: Option<OpaqueUpstreamValue>,
+    request_id: Option<OpaqueUpstreamValue>,
+    response_id: Option<OpaqueUpstreamValue>,
+}
+
+#[derive(Clone)]
+struct AtomicClientEvents(Vec<ProviderEvent>);
+
 impl ProviderError {
    /// 创建 Provider 错误。
    #[must_use]
@@ -294,16 +366,17 @@ impl ProviderError {
            kind,
            send_state,
            upstream_status: None,
-            upstream_code: None,
-            upstream_request_id: None,
-            upstream_response_id: None,
+            upstream_values: None,
            retry_after: None,
            continuation_failure: None,
            replay_safe: false,
+            pre_delivery_retry: false,
            credential_recovery_required: false,
            retry_same_account: false,
            sensitive_context_redacted: false,
            client_visible_upstream_error: None,
+            client_visible_upstream_response: None,
+            atomic_client_events: None,
        }
    }

@@ -318,25 +391,30 @@ impl ProviderError {

    /// 附加 adapter 已分类为安全的上游错误 code。
    #[must_use]
-    pub fn with_upstream_code(mut self, code: SafeUpstreamValue) -> Self {
-        self.upstream_code = Some(code);
+    pub fn with_upstream_code(mut self, code: OpaqueUpstreamValue) -> Self {
+        self.upstream_values_mut().code = Some(code);
        self
    }

    /// 附加 adapter 已分类为非 bearer 的上游 request ID。
    #[must_use]
-    pub fn with_upstream_request_id(mut self, request_id: SafeUpstreamValue) -> Self {
-        self.upstream_request_id = Some(request_id);
+    pub fn with_upstream_request_id(mut self, request_id: OpaqueUpstreamValue) -> Self {
+        self.upstream_values_mut().request_id = Some(request_id);
        self
    }

    /// 附加 adapter 已分类为非 bearer 的上游 response ID。
    #[must_use]
-    pub fn with_upstream_response_id(mut self, response_id: SafeUpstreamValue) -> Self {
-        self.upstream_response_id = Some(response_id);
+    pub fn with_upstream_response_id(mut self, response_id: OpaqueUpstreamValue) -> Self {
+        self.upstream_values_mut().response_id = Some(response_id);
        self
    }

+    fn upstream_values_mut(&mut self) -> &mut ProviderErrorUpstreamValues {
+        self.upstream_values
+            .get_or_insert_with(|| Box::new(ProviderErrorUpstreamValues::default()))
+    }
+
    /// 附加 Provider 建议的冷却时间。
    #[must_use]
    pub const fn with_retry_after(mut self, retry_after: Duration) -> Self {
@@ -358,6 +436,17 @@ impl ProviderError {
        self
    }

+    /// 允许 Core 仅在客户端尚未收到任何事件时执行一次受预算约束的换号恢复。
+    ///
+    /// 该标记不证明上游未执行，也不等价于 [`Self::with_replay_safe`]；它只表达
+    /// Provider 选择了“客户端无感恢复优先”的传输策略。Core 在 continuation、
+    /// 指定账号或下游已经进入提交状态时必须忽略它。
+    #[must_use]
+    pub const fn with_pre_delivery_retry(mut self) -> Self {
+        self.pre_delivery_retry = true;
+        self
+    }
+
    /// 要求 Core 在账号凭据已恢复后仅对原账号重放一次。
    #[must_use]
    pub const fn with_same_account_retry(mut self) -> Self {
@@ -379,6 +468,27 @@ impl ProviderError {
        self
    }

+    /// 附加仅可返回给当前请求方的原始上游 HTTP 失败响应。
+    #[must_use]
+    pub fn with_client_visible_upstream_response(
+        mut self,
+        response: ClientVisibleUpstreamResponse,
+    ) -> Self {
+        self.client_visible_upstream_response = Some(Box::new(response));
+        self
+    }
+
+    /// 附加必须先由 Core 判断重试、再决定丢弃或交付的客户端协议事件。
+    ///
+    /// Provider 只能放入当前 attempt 尚未交付的事件；调用方应设置明确的有界缓冲，
+    /// 并保证失败事件本身位于这批事件的末尾。
+    #[must_use]
+    pub fn with_atomic_client_events(mut self, events: Vec<ProviderEvent>) -> Self {
+        self.atomic_client_events =
+            (!events.is_empty()).then(|| Box::new(AtomicClientEvents(events)));
+        self
+    }
+
    /// 丢弃敏感正文，只记录“发生过脱敏”这一事实。
    #[must_use]
    pub fn redact_sensitive_context(mut self, _sensitive_context: impl AsRef<str>) -> Self {
@@ -406,20 +516,26 @@ impl ProviderError {

    /// 返回安全分类的上游错误 code。
    #[must_use]
-    pub fn upstream_code(&self) -> Option<&SafeUpstreamValue> {
-        self.upstream_code.as_ref()
+    pub fn upstream_code(&self) -> Option<&OpaqueUpstreamValue> {
+        self.upstream_values
+            .as_deref()
+            .and_then(|values| values.code.as_ref())
    }

    /// 返回安全分类的上游 request ID。
    #[must_use]
-    pub fn upstream_request_id(&self) -> Option<&SafeUpstreamValue> {
-        self.upstream_request_id.as_ref()
+    pub fn upstream_request_id(&self) -> Option<&OpaqueUpstreamValue> {
+        self.upstream_values
+            .as_deref()
+            .and_then(|values| values.request_id.as_ref())
    }

    /// 返回安全分类的上游 response ID。
    #[must_use]
-    pub fn upstream_response_id(&self) -> Option<&SafeUpstreamValue> {
-        self.upstream_response_id.as_ref()
+    pub fn upstream_response_id(&self) -> Option<&OpaqueUpstreamValue> {
+        self.upstream_values
+            .as_deref()
+            .and_then(|values| values.response_id.as_ref())
    }

    /// 返回 Provider 建议的冷却时间。
@@ -440,6 +556,12 @@ impl ProviderError {
        self.replay_safe
    }

+    /// 返回 Provider 是否允许在首个客户端事件前换号恢复传输失败。
+    #[must_use]
+    pub const fn allows_pre_delivery_retry(&self) -> bool {
+        self.pre_delivery_retry
+    }
+
    /// 返回 Provider 是否已完成凭据恢复并要求原账号重放。
    #[must_use]
    pub const fn retries_same_account(&self) -> bool {
@@ -462,6 +584,50 @@ impl ProviderError {
    pub fn client_visible_upstream_error(&self) -> Option<&ClientVisibleUpstreamError> {
        self.client_visible_upstream_error.as_deref()
    }
+
+    /// 返回只供当前协议响应使用的原始上游 HTTP 失败响应。
+    #[must_use]
+    pub fn client_visible_upstream_response(&self) -> Option<&ClientVisibleUpstreamResponse> {
+        self.client_visible_upstream_response.as_deref()
+    }
+
+    /// 取走只供本次重试/提交决策使用的原子客户端事件。
+    ///
+    /// Core 必须在克隆错误、记录中间失败或构造终态前调用本方法，避免原始 wire
+    /// 进入诊断或持久化对象。
+    #[must_use]
+    pub fn take_atomic_client_events(&mut self) -> Vec<ProviderEvent> {
+        self.atomic_client_events
+            .take()
+            .map_or_else(Vec::new, |events| events.0)
+    }
+
+    /// 返回是否携带尚未提交的原子客户端事件；不暴露事件内容。
+    #[must_use]
+    pub fn has_atomic_client_events(&self) -> bool {
+        self.atomic_client_events.is_some()
+    }
+}
+
+impl Clone for ProviderError {
+    fn clone(&self) -> Self {
+        Self {
+            kind: self.kind,
+            send_state: self.send_state,
+            upstream_status: self.upstream_status,
+            upstream_values: self.upstream_values.clone(),
+            retry_after: self.retry_after,
+            continuation_failure: self.continuation_failure,
+            replay_safe: self.replay_safe,
+            pre_delivery_retry: self.pre_delivery_retry,
+            credential_recovery_required: self.credential_recovery_required,
+            retry_same_account: self.retry_same_account,
+            sensitive_context_redacted: self.sensitive_context_redacted,
+            client_visible_upstream_error: self.client_visible_upstream_error.clone(),
+            client_visible_upstream_response: None,
+            atomic_client_events: None,
+        }
+    }
 }

 impl fmt::Debug for ProviderError {
@@ -473,25 +639,20 @@ impl fmt::Debug for ProviderError {
            .field("upstream_status", &self.upstream_status)
            .field(
                "upstream_code",
-                &self.upstream_code.as_ref().map(|_| "<classified-safe>"),
+                &self.upstream_code().map(|_| "<classified-safe>"),
            )
            .field(
                "upstream_request_id",
-                &self
-                    .upstream_request_id
-                    .as_ref()
-                    .map(|_| "<classified-safe>"),
+                &self.upstream_request_id().map(|_| "<classified-safe>"),
            )
            .field(
                "upstream_response_id",
-                &self
-                    .upstream_response_id
-                    .as_ref()
-                    .map(|_| "<classified-safe>"),
+                &self.upstream_response_id().map(|_| "<classified-safe>"),
            )
            .field("retry_after", &self.retry_after)
            .field("continuation_failure", &self.continuation_failure)
            .field("replay_safe", &self.replay_safe)
+            .field("pre_delivery_retry", &self.pre_delivery_retry)
            .field(
                "credential_recovery_required",
                &self.credential_recovery_required,
@@ -508,6 +669,20 @@ impl fmt::Debug for ProviderError {
                    .as_ref()
                    .map(|_| "<present>"),
            )
+            .field(
+                "client_visible_upstream_response",
+                &self
+                    .client_visible_upstream_response
+                    .as_ref()
+                    .map(|_| "<present>"),
+            )
+            .field(
+                "atomic_client_events",
+                &self
+                    .atomic_client_events
+                    .as_ref()
+                    .map_or(0, |events| events.0.len()),
+            )
            .finish()
    }
 }
@@ -9,7 +9,7 @@ use thiserror::Error;

 use crate::accounting::{CalculatedCost, ProviderReportedCost, Usage};
 use crate::engine::provider::UpstreamTransport;
-use crate::error::{IdentifierError, SafeUpstreamValue, validate_text};
+use crate::error::{IdentifierError, OpaqueUpstreamValue, validate_text};
 use crate::operation::ProviderSessionState;

 /// 一次响应的稳定元数据。
@@ -199,7 +199,7 @@ impl ProtocolWireEvent {
    ///
    /// # Errors
    ///
-    /// 协议名或显式事件名为空、过长或含控制字符时返回错误。
+    /// 协议名不满足内部路由标识约束时返回错误。上游事件名保持不透明。
    pub fn json(
        protocol: impl Into<String>,
        event_type: Option<String>,
@@ -212,7 +212,7 @@ impl ProtocolWireEvent {
    ///
    /// # Errors
    ///
-    /// 协议名、显式事件名或 SSE ID 不满足 wire 安全约束时返回错误。
+    /// 协议名不满足内部路由标识约束时返回错误。SSE 元数据保持不透明。
    pub fn json_with_sse_metadata(
        protocol: impl Into<String>,
        event_type: Option<String>,
@@ -222,15 +222,6 @@ impl ProtocolWireEvent {
    ) -> Result<Self, IdentifierError> {
        let protocol = protocol.into();
        validate_text(&protocol, 64, true, None)?;
-        if let Some(event_type) = event_type.as_deref() {
-            validate_text(event_type, 256, true, None)?;
-        }
-        if sse_id
-            .as_deref()
-            .is_some_and(|id| id.contains(['\0', '\r', '\n']))
-        {
-            return Err(IdentifierError::ControlCharacter);
-        }
        Ok(Self {
            protocol,
            event_type,
@@ -440,24 +431,21 @@ impl fmt::Debug for ProviderResponseMetadata {
    }
 }

-/// Provider 已筛选、可由协议 adapter 再次按白名单表达的响应头。
+/// Provider 已筛选、可由协议 adapter 尝试表达的不透明响应头。
 #[derive(Clone, PartialEq, Eq)]
 pub struct ProviderResponseHeader {
    name: String,
-    value: SafeUpstreamValue,
+    value: Bytes,
 }

 impl ProviderResponseHeader {
-    /// 创建规范化的小写响应头；非 ASCII token 名称直接拒绝。
+    /// 保存 Provider 交付的原始名称和值；HTTP 可表达性由最终 adapter 判断。
    #[must_use]
-    pub fn new(name: impl Into<String>, value: SafeUpstreamValue) -> Option<Self> {
-        let name = name.into().trim().to_ascii_lowercase();
-        let valid = !name.is_empty()
-            && name.len() <= 64
-            && name
-                .bytes()
-                .all(|byte| byte.is_ascii_lowercase() || byte.is_ascii_digit() || byte == b'-');
-        valid.then_some(Self { name, value })
+    pub fn new(name: impl Into<String>, value: Bytes) -> Self {
+        Self {
+            name: name.into(),
+            value,
+        }
    }

    #[must_use]
@@ -466,7 +454,7 @@ impl ProviderResponseHeader {
    }

    #[must_use]
-    pub const fn value(&self) -> &SafeUpstreamValue {
+    pub const fn value(&self) -> &Bytes {
        &self.value
    }
 }
@@ -475,7 +463,7 @@ impl fmt::Debug for ProviderResponseHeader {
    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
        formatter
            .debug_struct("ProviderResponseHeader")
-            .field("name", &self.name)
+            .field("name", &"<redacted>")
            .field("value", &"<redacted>")
            .finish()
    }
@@ -488,7 +476,8 @@ pub struct ProviderResponseObservation {
    http_version: Option<UpstreamHttpVersion>,
    websocket_pool: Option<WebSocketPoolKind>,
    status_code: Option<u16>,
-    request_id: Option<SafeUpstreamValue>,
+    request_id: Option<OpaqueUpstreamValue>,
+    service_tier: Option<String>,
    timings: ProviderResponseTimings,
    client_headers: Vec<ProviderResponseHeader>,
    provider_metadata: Option<ProviderResponseMetadata>,
@@ -503,6 +492,7 @@ impl ProviderResponseObservation {
            websocket_pool: None,
            status_code: None,
            request_id: None,
+            service_tier: None,
            timings: ProviderResponseTimings::default(),
            client_headers: Vec::new(),
            provider_metadata: None,
@@ -528,11 +518,36 @@ impl ProviderResponseObservation {
    }

    #[must_use]
-    pub fn with_request_id(mut self, request_id: SafeUpstreamValue) -> Self {
+    pub fn with_request_id(mut self, request_id: OpaqueUpstreamValue) -> Self {
        self.request_id = Some(request_id);
        self
    }

+    /// 附加 Provider 在响应中确认的服务档位。
+    ///
+    /// # Errors
+    ///
+    /// 档位为空、超过 64 字节或包含控制字符时返回错误。
+    pub fn try_with_service_tier(
+        mut self,
+        service_tier: impl Into<String>,
+    ) -> Result<Self, IdentifierError> {
+        let service_tier = service_tier.into();
+        validate_text(&service_tier, 64, false, None)?;
+        self.service_tier = Some(service_tier);
+        Ok(self)
+    }
+
+    /// 附加合法服务档位；不适合持久化的上游观测值会被忽略。
+    #[must_use]
+    pub fn with_service_tier_if_valid(mut self, service_tier: impl Into<String>) -> Self {
+        let service_tier = service_tier.into();
+        if validate_text(&service_tier, 64, false, None).is_ok() {
+            self.service_tier = Some(service_tier);
+        }
+        self
+    }
+
    #[must_use]
    pub const fn with_timings(mut self, timings: ProviderResponseTimings) -> Self {
        self.timings = timings;
@@ -573,10 +588,15 @@ impl ProviderResponseObservation {
    }

    #[must_use]
-    pub const fn request_id(&self) -> Option<&SafeUpstreamValue> {
+    pub const fn request_id(&self) -> Option<&OpaqueUpstreamValue> {
        self.request_id.as_ref()
    }

+    #[must_use]
+    pub fn service_tier(&self) -> Option<&str> {
+        self.service_tier.as_deref()
+    }
+
    #[must_use]
    pub const fn timings(&self) -> ProviderResponseTimings {
        self.timings
@@ -302,7 +302,7 @@ impl GenerateRequest {
        self.body()
            .get("previous_response_id")
            .and_then(Value::as_str)
-            .is_some_and(|response_id| !response_id.is_empty())
+            .is_some()
    }

    /// 返回客户端是否请求了图片生成工具。
@@ -13,7 +13,7 @@ use crate::engine::credential::{
    OpaqueProviderData, ProviderAccountId, ProviderAccountStore,
 };
 use crate::error::{IdentifierError, validate_text};
-use crate::routing::ProviderKind;
+use crate::routing::{ProviderKind, UpstreamModelId};

 const MAX_PENDING_FLOW_TTL: Duration = Duration::from_secs(30 * 60);

@@ -527,6 +527,80 @@ impl ProviderCooldown {
    }
 }

+/// 可丢失 cooldown 的细粒度作用域。
+#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
+pub enum ProviderCooldownScope {
+    /// 只阻止同一账号调用指定上游模型。
+    UpstreamModel(UpstreamModelId),
+}
+
+impl ProviderCooldownScope {
+    #[must_use]
+    pub const fn upstream_model(model: UpstreamModelId) -> Self {
+        Self::UpstreamModel(model)
+    }
+
+    #[must_use]
+    pub const fn kind(&self) -> &'static str {
+        match self {
+            Self::UpstreamModel(_) => "model",
+        }
+    }
+
+    #[must_use]
+    pub fn value(&self) -> &str {
+        match self {
+            Self::UpstreamModel(model) => model.as_str(),
+        }
+    }
+}
+
+/// 不进入账号持久状态的账号+作用域 cooldown。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderScopedCooldown {
+    account_id: ProviderAccountId,
+    credential_revision: CredentialRevision,
+    scope: ProviderCooldownScope,
+    until: SystemTime,
+}
+
+impl ProviderScopedCooldown {
+    #[must_use]
+    pub const fn new(
+        account_id: ProviderAccountId,
+        credential_revision: CredentialRevision,
+        scope: ProviderCooldownScope,
+        until: SystemTime,
+    ) -> Self {
+        Self {
+            account_id,
+            credential_revision,
+            scope,
+            until,
+        }
+    }
+
+    #[must_use]
+    pub const fn account_id(&self) -> &ProviderAccountId {
+        &self.account_id
+    }
+
+    #[must_use]
+    pub const fn credential_revision(&self) -> CredentialRevision {
+        self.credential_revision
+    }
+
+    #[must_use]
+    pub const fn scope(&self) -> &ProviderCooldownScope {
+        &self.scope
+    }
+
+    #[must_use]
+    pub const fn until(&self) -> SystemTime {
+        self.until
+    }
+}
+
 pub trait ProviderCooldownPort: Send + Sync {
    fn put_if_later(
        &self,
@@ -543,6 +617,24 @@ pub trait ProviderCooldownPort: Send + Sync {
        account_id: &'a ProviderAccountId,
        through_revision: CredentialRevision,
    ) -> BoxFuture<'a, Result<bool, ProviderStoreError>>;
+
+    fn put_scoped_if_later(
+        &self,
+        cooldown: ProviderScopedCooldown,
+    ) -> BoxFuture<'_, Result<bool, ProviderStoreError>>;
+
+    fn read_scoped<'a>(
+        &'a self,
+        account_id: &'a ProviderAccountId,
+        scope: &'a ProviderCooldownScope,
+    ) -> BoxFuture<'a, Result<Option<ProviderScopedCooldown>, ProviderStoreError>>;
+
+    fn clear_scoped<'a>(
+        &'a self,
+        account_id: &'a ProviderAccountId,
+        scope: &'a ProviderCooldownScope,
+        through_revision: CredentialRevision,
+    ) -> BoxFuture<'a, Result<bool, ProviderStoreError>>;
 }

 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -575,32 +667,21 @@ impl ProviderRefreshPolicy {
        self.concurrency
    }

-    /// 按账号稳定扰动刷新提前量；相同账号与过期时间跨进程得到同一执行时刻。
+    /// 按配置的精确提前量计算刷新时刻。
    pub fn next_attempt_at(
        self,
-        account_id: &ProviderAccountId,
+        _account_id: &ProviderAccountId,
        access_token_expires_at: SystemTime,
        observed_at: SystemTime,
    ) -> Result<SystemTime, ProviderStoreError> {
        let remaining = access_token_expires_at
            .duration_since(observed_at)
            .map_err(|_| invalid_refresh_policy("schedule expired access token"))?;
-        let base_margin_seconds = self.margin.as_secs();
-        if base_margin_seconds == 0 {
+        if self.margin >= remaining {
            return Ok(observed_at);
        }
-
-        let factor = stable_factor(account_id.as_str(), "normal", 850, 1_150);
-        let jittered_seconds = base_margin_seconds
-            .saturating_mul(u64::from(factor))
-            .saturating_add(500)
-            / 1_000;
-        if jittered_seconds >= remaining.as_secs() {
-            return Ok(observed_at);
-        }
-        let lead = jittered_seconds.max(1);
        access_token_expires_at
-            .checked_sub(Duration::from_secs(lead))
+            .checked_sub(self.margin)
            .ok_or_else(|| invalid_refresh_policy("schedule access token refresh"))
    }
 }
@@ -778,35 +859,75 @@ pub enum OAuthPendingPutOutcome {
    AlreadyExists,
 }

+/// OAuth 回调处理取得临时 flow 的独占权结果。
+///
+/// 与一次性消费不同，Provider 在上游换取令牌失败时可以释放 claim，让同一 flow
+/// 使用新的回调地址重试；只有完整校验成功后才会消费 flow。
 #[derive(Clone, PartialEq)]
-pub enum OAuthPendingTakeOutcome {
-    Taken(OpaqueProviderData),
+pub enum OAuthPendingClaimOutcome {
+    Claimed(OpaqueProviderData),
    NotFound,
    OwnerMismatch,
+    InProgress,
 }

-impl fmt::Debug for OAuthPendingTakeOutcome {
+impl fmt::Debug for OAuthPendingClaimOutcome {
    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
        match self {
-            Self::Taken(_) => formatter.write_str("Taken([PROVIDER-OWNED])"),
+            Self::Claimed(_) => formatter.write_str("Claimed([PROVIDER-OWNED])"),
            Self::NotFound => formatter.write_str("NotFound"),
            Self::OwnerMismatch => formatter.write_str("OwnerMismatch"),
+            Self::InProgress => formatter.write_str("InProgress"),
        }
    }
 }

+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum OAuthPendingReleaseOutcome {
+    Released,
+    NotFound,
+    OwnerMismatch,
+    ClaimMismatch,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum OAuthPendingConsumeOutcome {
+    Consumed,
+    NotFound,
+    OwnerMismatch,
+    ClaimMismatch,
+}
+
 pub trait OAuthPendingFlowPort: Send + Sync {
    fn put_if_absent(
        &self,
        flow: NewOAuthPendingFlow,
    ) -> BoxFuture<'_, Result<OAuthPendingPutOutcome, ProviderStoreError>>;

-    fn take_if_owner<'a>(
+    fn claim_if_owner<'a>(
        &'a self,
        provider_kind: &'a ProviderKind,
        flow: &'a OAuthPendingBinding,
        owner: &'a OAuthPendingBinding,
-    ) -> BoxFuture<'a, Result<OAuthPendingTakeOutcome, ProviderStoreError>>;
+        claim: &'a OAuthPendingBinding,
+        claim_ttl: Duration,
+    ) -> BoxFuture<'a, Result<OAuthPendingClaimOutcome, ProviderStoreError>>;
+
+    fn release_claim<'a>(
+        &'a self,
+        provider_kind: &'a ProviderKind,
+        flow: &'a OAuthPendingBinding,
+        owner: &'a OAuthPendingBinding,
+        claim: &'a OAuthPendingBinding,
+    ) -> BoxFuture<'a, Result<OAuthPendingReleaseOutcome, ProviderStoreError>>;
+
+    fn consume_claim<'a>(
+        &'a self,
+        provider_kind: &'a ProviderKind,
+        flow: &'a OAuthPendingBinding,
+        owner: &'a OAuthPendingBinding,
+        claim: &'a OAuthPendingBinding,
+    ) -> BoxFuture<'a, Result<OAuthPendingConsumeOutcome, ProviderStoreError>>;
 }

 /// Provider 只能按能力取用端口，无法取得 Redis client 或 repository 集合。
@@ -89,6 +89,18 @@ impl UpstreamModelId {
        Ok(Self(value))
    }

+    /// 从未命中显式映射的客户端模型名构造同名上游模型。
+    ///
+    /// 目录和配置仍使用 [`Self::new`] 的内部标识约束；客户端 wire 只要求非空，
+    /// 具体模型字符串是否可用由绑定 Provider 决定。
+    pub fn from_client_wire(value: impl Into<String>) -> Result<Self, IdentifierError> {
+        let value = value.into();
+        if value.is_empty() {
+            return Err(IdentifierError::Empty);
+        }
+        Ok(Self(value))
+    }
+
    #[must_use]
    pub fn as_str(&self) -> &str {
        &self.0
@@ -152,9 +164,61 @@ pub struct ModelPresentation {
    search_tool: bool,
    image_detail_original: bool,
    verbosity: bool,
+    service_tiers: Vec<ModelServiceTier>,
    hidden: bool,
 }

+/// Provider 声明给 Codex 客户端的服务档位。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ModelServiceTier {
+    id: String,
+    name: String,
+    description: String,
+    speed_tier: Option<String>,
+}
+
+impl ModelServiceTier {
+    #[must_use]
+    pub fn new(
+        id: impl Into<String>,
+        name: impl Into<String>,
+        description: impl Into<String>,
+    ) -> Self {
+        Self {
+            id: id.into(),
+            name: name.into(),
+            description: description.into(),
+            speed_tier: None,
+        }
+    }
+
+    #[must_use]
+    pub fn with_speed_tier(mut self, speed_tier: impl Into<String>) -> Self {
+        self.speed_tier = Some(speed_tier.into());
+        self
+    }
+
+    #[must_use]
+    pub fn id(&self) -> &str {
+        &self.id
+    }
+
+    #[must_use]
+    pub fn name(&self) -> &str {
+        &self.name
+    }
+
+    #[must_use]
+    pub fn description(&self) -> &str {
+        &self.description
+    }
+
+    #[must_use]
+    pub fn speed_tier(&self) -> Option<&str> {
+        self.speed_tier.as_deref()
+    }
+}
+
 impl ModelPresentation {
    #[must_use]
    pub fn new(display_name: Option<String>, description: Option<String>) -> Self {
@@ -213,6 +277,12 @@ impl ModelPresentation {
        self
    }

+    #[must_use]
+    pub fn with_service_tiers(mut self, service_tiers: Vec<ModelServiceTier>) -> Self {
+        self.service_tiers = service_tiers;
+        self
+    }
+
    #[must_use]
    pub const fn with_hidden(mut self, hidden: bool) -> Self {
        self.hidden = hidden;
@@ -274,6 +344,11 @@ impl ModelPresentation {
        self.verbosity
    }

+    #[must_use]
+    pub fn service_tiers(&self) -> &[ModelServiceTier] {
+        &self.service_tiers
+    }
+
    #[must_use]
    pub const fn hidden(&self) -> bool {
        self.hidden
@@ -488,15 +488,11 @@ impl RuntimeSnapshot {

    #[must_use]
    pub fn mapped_model(&self, requested: &str) -> String {
-        let original = requested.trim();
+        let original = requested;
        let mut current = original.to_owned();
        let mut seen = BTreeSet::new();
        for _ in 0..20 {
-            let Some(target) = self
-                .model_mappings
-                .get(&current)
-                .map(|target| target.trim())
-            else {
+            let Some(target) = self.model_mappings.get(&current).map(String::as_str) else {
                return current;
            };
            if !seen.insert(current.clone()) || seen.contains(target) {
@@ -529,8 +525,14 @@ impl RuntimeSnapshot {
            {
                continue;
            }
-            let upstream_model = UpstreamModelId::new(self.mapped_model(public_model.as_str()))
-                .map_err(|_| RoutingError::InvalidIdentifier)?;
+            let requested_model = public_model.as_str();
+            let mapped_model = self.mapped_model(requested_model);
+            let upstream_model = if self.model_mappings.contains_key(requested_model) {
+                UpstreamModelId::new(mapped_model)
+            } else {
+                UpstreamModelId::from_client_wire(mapped_model)
+            }
+            .map_err(|_| RoutingError::InvalidIdentifier)?;
            let emulated_features = match self
                .provider_models
                .get(provider)
@@ -2,13 +2,12 @@ use gateway_core::engine::continuation::{
    ContinuationBinding, NativeContinuationPin, PreviousResponseId,
 };
 use gateway_core::engine::credential::ProviderAccountId;
-use gateway_core::error::SafeUpstreamValue;
 use gateway_core::routing::ProviderKind;

 fn pin() -> NativeContinuationPin {
    NativeContinuationPin::new(
-        PreviousResponseId::new("response-private").expect("valid response"),
-        SafeUpstreamValue::new("upstream-private").expect("valid upstream response"),
+        PreviousResponseId::new("response-private"),
+        PreviousResponseId::new("upstream-private"),
        ProviderKind::new("openai").expect("valid provider"),
        ProviderAccountId::new("acct_codex").expect("valid account"),
    )
@@ -23,13 +22,20 @@ fn native_pin_debug_should_redact_previous_response_id() {

 #[test]
 fn external_binding_debug_should_redact_previous_response_id() {
-    let binding = ContinuationBinding::External(
-        PreviousResponseId::new("external-private").expect("valid response"),
-    );
+    let binding = ContinuationBinding::External(PreviousResponseId::new("external-private"));

    assert!(!format!("{binding:?}").contains("external-private"));
 }

+#[test]
+fn opaque_response_id_preserves_any_codex_string_without_debug_disclosure() {
+    let value = format!("resp_{}\0opaque", "x".repeat(257));
+    let response_id = PreviousResponseId::new(value.clone());
+
+    assert_eq!(response_id.as_str(), value);
+    assert!(!format!("{response_id:?}").contains(&value));
+}
+
 #[test]
 fn native_pin_should_reject_different_account() {
    assert!(!pin().matches(
@@ -6,6 +6,7 @@ use std::sync::{Arc, Mutex};
 use std::time::{Duration, SystemTime};

 use async_trait::async_trait;
+use bytes::Bytes;
 use futures::StreamExt;
 use futures::executor::block_on;

@@ -28,8 +29,8 @@ use gateway_core::engine::{
    ProviderAttemptOutcome, RecoveryReport, UpstreamSendState,
 };
 use gateway_core::error::{
-    ContinuationFailure, GatewayErrorKind, ProviderError, ProviderErrorKind, SafeUpstreamValue,
-    StoreError,
+    ClientVisibleUpstreamResponse, ContinuationFailure, GatewayErrorKind, OpaqueUpstreamValue,
+    ProviderError, ProviderErrorKind, StoreError, StoreErrorKind,
 };
 use gateway_core::event::{
    ContentItem, ContentKind, GatewayEvent, ProtocolWireEvent, ProviderEvent,
@@ -65,6 +66,7 @@ struct FinalState {
    upstream_transport: Option<String>,
    http_version: Option<String>,
    websocket_pool: Option<String>,
+    service_tier: Option<String>,
    upstream_request_id: Option<String>,
    upstream_status_code: Option<u16>,
    transport_decision_wait_ms: Option<u64>,
@@ -97,11 +99,37 @@ struct StoreState {
 #[derive(Default)]
 struct FakeStore {
    state: Mutex<StoreState>,
+    failures: BTreeSet<StoreWriteFailure>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
+enum StoreWriteFailure {
+    Create,
+    Commit,
+    Finalize,
+}
+
+impl FakeStore {
+    fn failing(failure: StoreWriteFailure) -> Self {
+        Self {
+            state: Mutex::new(StoreState::default()),
+            failures: BTreeSet::from([failure]),
+        }
+    }
+
+    fn fails(&self, failure: StoreWriteFailure) -> Result<(), StoreError> {
+        if self.failures.contains(&failure) {
+            Err(StoreError::new(StoreErrorKind::Unavailable))
+        } else {
+            Ok(())
+        }
+    }
 }

 #[async_trait]
 impl ExecutionStore for FakeStore {
    async fn create_model_request(&self, _request: NewModelRequest) -> Result<(), StoreError> {
+        self.fails(StoreWriteFailure::Create)?;
        self.state.lock().expect("store lock").created += 1;
        Ok(())
    }
@@ -134,6 +162,7 @@ impl ExecutionStore for FakeStore {
        _committed_at: SystemTime,
        client_status_code: Option<u16>,
    ) -> Result<(), StoreError> {
+        self.fails(StoreWriteFailure::Commit)?;
        let mut state = self.state.lock().expect("store lock");
        state.commits += 1;
        state.committed_statuses.push(client_status_code);
@@ -172,6 +201,7 @@ impl ExecutionStore for FakeStore {
        &self,
        finalization: ModelRequestFinalization,
    ) -> Result<(), StoreError> {
+        self.fails(StoreWriteFailure::Finalize)?;
        self.state
            .lock()
            .expect("store lock")
@@ -194,6 +224,7 @@ impl ExecutionStore for FakeStore {
                upstream_transport: finalization.upstream_transport,
                http_version: finalization.http_version,
                websocket_pool: finalization.websocket_pool,
+                service_tier: finalization.service_tier,
                upstream_request_id: finalization.upstream_request_id,
                upstream_status_code: finalization.upstream_status_code,
                transport_decision_wait_ms: finalization.timings.transport_decision_wait_ms,
@@ -291,15 +322,11 @@ impl Provider for ScriptedProvider {
                    },
                    UpstreamTransport::new("http_sse").expect("transport"),
                )
-                .with_upstream_request_id(
-                    SafeUpstreamValue::new("upstream-request").expect("safe request id"),
-                );
+                .with_upstream_request_id(OpaqueUpstreamValue::new("upstream-request"));
                Ok(ProviderStream::new(
                    metadata,
                    Box::pin(futures::stream::iter(
-                        items
-                            .into_iter()
-                            .map(|event| event.map(ProviderEvent::from)),
+                        items.into_iter().map(canonical_provider_event),
                    )),
                    (),
                ))
@@ -318,12 +345,8 @@ impl Provider for ScriptedProvider {
                Ok(ProviderStream::new(
                    metadata,
                    Box::pin(
-                        futures::stream::iter(
-                            items
-                                .into_iter()
-                                .map(|event| event.map(ProviderEvent::from)),
-                        )
-                        .chain(futures::stream::pending()),
+                        futures::stream::iter(items.into_iter().map(canonical_provider_event))
+                            .chain(futures::stream::pending()),
                    ),
                    (),
                ))
@@ -399,6 +422,75 @@ fn complete_stream(total_tokens: Option<u64>) -> Vec<Result<GatewayEvent, Provid
    events
 }

+fn canonical_provider_event(
+    event: Result<GatewayEvent, ProviderError>,
+) -> Result<ProviderEvent, ProviderError> {
+    event.map(ProviderEvent::canonical)
+}
+
+fn atomic_response_failed(response_id: &str, marker: &str) -> ProviderError {
+    let started = ProviderEvent::canonical_with_wire(
+        vec![GatewayEvent::Started(ResponseMeta::new(
+            response_id,
+            "gpt-5",
+        ))],
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.created".to_owned()),
+            json!({
+                "type": "response.created",
+                "response": {"id": response_id, "model": "gpt-5", "status": "in_progress"}
+            }),
+        )
+        .expect("started wire"),
+    );
+    let failed = ProviderEvent::wire(
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.failed".to_owned()),
+            json!({
+                "type": "response.failed",
+                "response": {
+                    "id": response_id,
+                    "status": "failed",
+                    "error": {"code": "rate_limit_exceeded", "message": marker}
+                }
+            }),
+        )
+        .expect("failed wire"),
+    );
+    ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
+        .with_status(429)
+        .with_replay_safe()
+        .with_atomic_client_events(vec![started, failed])
+}
+
+fn bare_atomic_response_failed(response_id: &str) -> ProviderError {
+    let failed = ProviderEvent::canonical_with_wire(
+        vec![GatewayEvent::Started(ResponseMeta::new(
+            response_id,
+            "fallback-model",
+        ))],
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.failed".to_owned()),
+            json!({
+                "type": "response.failed",
+                "response": {
+                    "id": response_id,
+                    "status": "failed",
+                    "error": {"code": "rate_limit_exceeded", "message": "bare failure"}
+                }
+            }),
+        )
+        .expect("bare failed wire"),
+    );
+    ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
+        .with_status(429)
+        .with_replay_safe()
+        .with_atomic_client_events(vec![failed])
+}
+
 fn image_stream(image_output_tokens: Option<u64>) -> Vec<Result<GatewayEvent, ProviderError>> {
    let mut usage = Usage::new();
    usage.input_tokens = Some(12);
@@ -484,6 +576,17 @@ fn coordinator(
    Arc<ScriptedProvider>,
 ) {
    let store = Arc::new(FakeStore::default());
+    coordinator_with_store(scripts, store)
+}
+
+fn coordinator_with_store(
+    scripts: Vec<Script>,
+    store: Arc<FakeStore>,
+) -> (
+    AttemptCoordinator<FakeStore>,
+    Arc<FakeStore>,
+    Arc<ScriptedProvider>,
+) {
    let provider = Arc::new(ScriptedProvider::new(scripts));
    let mut registry = ProviderRegistry::builder();
    registry
@@ -587,6 +690,170 @@ fn success_updates_one_model_request_and_persists_usage() {
    );
 }

+#[test]
+fn observation_store_failures_never_block_successful_delivery() {
+    for failure in [
+        StoreWriteFailure::Create,
+        StoreWriteFailure::Commit,
+        StoreWriteFailure::Finalize,
+    ] {
+        let operation = operation(RetrySafety::NonIdempotent);
+        let route_plan = plan(&operation);
+        let store = Arc::new(FakeStore::failing(failure));
+        let (coordinator, _, provider) = coordinator_with_store(
+            vec![Script::Stream {
+                account_id: "acct_one",
+                items: complete_stream(None),
+            }],
+            store,
+        );
+        let mut session = block_on(coordinator.start(
+            model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+            operation,
+            route_plan,
+            None,
+            None,
+            CancellationToken::new(),
+        ))
+        .expect("start execution");
+
+        let events = block_on(session.collect_uncommitted())
+            .unwrap_or_else(|error| panic!("{failure:?} blocked collection: {error}"));
+        assert_eq!(events.len(), 2);
+        block_on(session.commit_downstream(Some(200)))
+            .unwrap_or_else(|error| panic!("{failure:?} blocked commit: {error}"));
+        assert!(session.is_finalized());
+        assert_eq!(provider.contexts.lock().expect("contexts lock").len(), 1);
+    }
+}
+
+#[test]
+fn terminal_provider_error_preserves_request_local_upstream_response() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let raw_body = Bytes::from_static(b"{\"upstream\":\"unchanged\"}\x00");
+    let provider_error =
+        ProviderError::new(ProviderErrorKind::InvalidRequest, UpstreamSendState::Sent)
+            .with_client_visible_upstream_response(ClientVisibleUpstreamResponse::new(
+                422,
+                Some(b"application/problem+json".to_vec()),
+                raw_body.clone(),
+            ));
+    let (coordinator, _, _) = coordinator(vec![Script::Error(provider_error)]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let error = block_on(session.collect_uncommitted()).expect_err("provider rejection");
+    let EngineError::Provider(error) = error else {
+        panic!("expected provider error");
+    };
+    let response = error
+        .client_visible_upstream_response()
+        .expect("request-local upstream response");
+
+    assert_eq!(response.status(), 422);
+    assert_eq!(response.body(), &raw_body);
+}
+
+#[test]
+fn success_preserves_opaque_upstream_response_id_and_builds_native_pin() {
+    let response_id = format!("resp_{}\0opaque", "x".repeat(4_096));
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let (coordinator, store, _) = coordinator(vec![Script::Stream {
+        account_id: "acct_one",
+        items: vec![
+            Ok(GatewayEvent::Started(ResponseMeta::new(
+                response_id.clone(),
+                "gpt-5",
+            ))),
+            Ok(GatewayEvent::Completed(ResponseMeta::new(
+                response_id.clone(),
+                "gpt-5",
+            ))),
+        ],
+    }]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    block_on(session.collect_uncommitted()).expect("collect opaque response");
+    let provider_state = ProviderSessionState::new("openai", Map::new()).expect("provider state");
+    let pin = session
+        .native_continuation_pin(&provider_state)
+        .expect("native continuation pin");
+    assert_eq!(pin.previous_response_id().as_str(), response_id);
+    assert_eq!(pin.upstream_response_id().as_str(), response_id);
+
+    block_on(session.commit_downstream(Some(200))).expect("commit response");
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(
+        state.finalizations[0].client_response_id,
+        Some(response_id.clone())
+    );
+    assert_eq!(
+        state.finalizations[0].upstream_response_id,
+        Some(response_id)
+    );
+}
+
+#[test]
+fn canonical_identity_change_and_empty_terminal_id_are_observational() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let (coordinator, store, _) = coordinator(vec![Script::Stream {
+        account_id: "acct_one",
+        items: vec![
+            Ok(GatewayEvent::Started(ResponseMeta::new(
+                "response-created",
+                "gpt-5",
+            ))),
+            Ok(GatewayEvent::Completed(ResponseMeta::new("", "gpt-5"))),
+        ],
+    }]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    block_on(session.collect_uncommitted()).expect("identity observation cannot fail delivery");
+    let provider_state = ProviderSessionState::new("openai", Map::new()).expect("provider state");
+    let pin = session
+        .native_continuation_pin(&provider_state)
+        .expect("empty opaque response ID remains recordable");
+    assert_eq!(pin.previous_response_id().as_str(), "");
+    assert_eq!(pin.upstream_response_id().as_str(), "");
+
+    block_on(session.commit_downstream(Some(200))).expect("commit response");
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(
+        state.finalizations[0].client_response_id.as_deref(),
+        Some("")
+    );
+    assert_eq!(
+        state.finalizations[0].upstream_response_id.as_deref(),
+        Some("")
+    );
+}
+
 fn finalized_image_request(image_output_tokens: Option<u64>) -> FinalState {
    let operation = image_generate_operation();
    let route_plan = plan(&operation);
@@ -669,7 +936,9 @@ fn response_observation_is_persisted_but_never_delivered() {
    .with_http_version(UpstreamHttpVersion::Http2)
    .with_websocket_pool(WebSocketPoolKind::New)
    .with_status_code(200)
-    .with_request_id(SafeUpstreamValue::new("upstream-observed").expect("request id"))
+    .with_request_id(OpaqueUpstreamValue::new("upstream-observed"))
+    .try_with_service_tier("priority")
+    .expect("service tier")
    .with_timings(ProviderResponseTimings {
        transport_decision_wait_ms: Some(7),
        connect_ms: Some(11),
@@ -681,7 +950,7 @@ fn response_observation_is_persisted_but_never_delivered() {
    items.extend(
        complete_stream(Some(21))
            .into_iter()
-            .map(|event| event.map(ProviderEvent::canonical)),
+            .map(canonical_provider_event),
    );
    let (coordinator, store, _) = coordinator(vec![Script::ObservedStream {
        account_id: "acct_observed",
@@ -706,6 +975,7 @@ fn response_observation_is_persisted_but_never_delivered() {
    assert_eq!(finalization.upstream_transport.as_deref(), Some("http_sse"));
    assert_eq!(finalization.http_version.as_deref(), Some("HTTP/2"));
    assert_eq!(finalization.websocket_pool.as_deref(), Some("new"));
+    assert_eq!(finalization.service_tier.as_deref(), Some("priority"));
    assert_eq!(
        finalization.upstream_request_id.as_deref(),
        Some("upstream-observed")
@@ -717,6 +987,48 @@ fn response_observation_is_persisted_but_never_delivered() {
    assert_eq!(finalization.first_event_ms, Some(17));
 }

+#[test]
+fn mismatched_response_observation_should_not_interrupt_client_events() {
+    let operation = operation(RetrySafety::Idempotent);
+    let route_plan = plan(&operation);
+    let first = ProviderEvent::observation(ProviderResponseObservation::new(
+        UpstreamTransport::new("websocket").expect("first transport"),
+    ));
+    let mismatched = ProviderEvent::observation(ProviderResponseObservation::new(
+        UpstreamTransport::new("http_sse").expect("mismatched transport"),
+    ));
+    let mut items = vec![Ok(first), Ok(mismatched)];
+    items.extend(
+        complete_stream(None)
+            .into_iter()
+            .map(canonical_provider_event),
+    );
+    let (coordinator, store, _) = coordinator(vec![Script::ObservedStream {
+        account_id: "acct_observation_mismatch",
+        items,
+    }]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let events = block_on(session.collect_uncommitted()).expect("client events survive");
+    block_on(session.commit_downstream(Some(200))).expect("commit response");
+
+    assert_eq!(events.len(), 2);
+    assert_eq!(
+        store.state.lock().expect("store lock").finalizations[0]
+            .upstream_transport
+            .as_deref(),
+        Some("websocket")
+    );
+}
+
 #[test]
 fn response_observation_should_persist_provider_metadata_and_output_timings() {
    let operation = operation(RetrySafety::Idempotent);
@@ -741,7 +1053,7 @@ fn response_observation_should_persist_provider_metadata_and_output_timings() {
    items.extend(
        complete_stream(Some(21))
            .into_iter()
-            .map(|event| event.map(ProviderEvent::canonical)),
+            .map(canonical_provider_event),
    );
    let (coordinator, store, _) = coordinator(vec![Script::ObservedStream {
        account_id: "acct_observed",
@@ -881,7 +1193,7 @@ fn discarded_attempt_observation_does_not_leak_into_retry_result() {
    )
    .with_http_version(UpstreamHttpVersion::Http11)
    .with_status_code(503)
-    .with_request_id(SafeUpstreamValue::new("discarded-request").expect("request id"))
+    .with_request_id(OpaqueUpstreamValue::new("discarded-request"))
    .with_timings(ProviderResponseTimings {
        transport_decision_wait_ms: Some(7),
        connect_ms: Some(11),
@@ -895,12 +1207,12 @@ fn discarded_attempt_observation_does_not_leak_into_retry_result() {
    )
    .with_http_version(UpstreamHttpVersion::Http2)
    .with_status_code(200)
-    .with_request_id(SafeUpstreamValue::new("winning-request").expect("request id"));
+    .with_request_id(OpaqueUpstreamValue::new("winning-request"));
    let mut second_items = vec![Ok(ProviderEvent::observation(second_observation))];
    second_items.extend(
        complete_stream(None)
            .into_iter()
-            .map(|event| event.map(ProviderEvent::canonical)),
+            .map(canonical_provider_event),
    );
    let (coordinator, store, _) = coordinator(vec![
        Script::ObservedStream {
@@ -1029,8 +1341,8 @@ fn authenticated_native_continuation_reaches_every_attempt_context() {
        items: complete_stream(None),
    }]);
    let continuation = NativeContinuationPin::new(
-        PreviousResponseId::new("previous-secret-id").expect("previous response"),
-        SafeUpstreamValue::new("provider-native-id").expect("upstream response"),
+        PreviousResponseId::new("previous-secret-id"),
+        PreviousResponseId::new("provider-native-id"),
        ProviderKind::new("openai").expect("provider"),
        ProviderAccountId::new("acct_one").expect("account"),
    );
@@ -1086,8 +1398,8 @@ fn streaming_native_continuation_delivers_started_event_before_later_output() {
        items: complete_stream(None),
    }]);
    let continuation = NativeContinuationPin::new(
-        PreviousResponseId::new("previous-response").expect("previous response"),
-        SafeUpstreamValue::new("upstream-response").expect("upstream response"),
+        PreviousResponseId::new("previous-response"),
+        PreviousResponseId::new("upstream-response"),
        ProviderKind::new("openai").expect("provider"),
        ProviderAccountId::new("acct_one").expect("account"),
    );
@@ -1162,8 +1474,8 @@ fn native_continuation_replays_owner_before_safely_switching_account() {
        },
    ]);
    let continuation = NativeContinuationPin::new(
-        PreviousResponseId::new("previous-secret-id").expect("previous response"),
-        SafeUpstreamValue::new("provider-native-id").expect("upstream response"),
+        PreviousResponseId::new("previous-secret-id"),
+        PreviousResponseId::new("provider-native-id"),
        ProviderKind::new("openai").expect("provider"),
        ProviderAccountId::new("acct_one").expect("account"),
    );
@@ -1202,7 +1514,7 @@ fn native_continuation_replays_owner_before_safely_switching_account() {
 }

 #[test]
-fn required_account_reaches_provider_and_matching_metadata_succeeds() {
+fn diagnostic_account_reaches_provider_and_matching_metadata_succeeds() {
    let operation = operation(RetrySafety::Idempotent);
    let route_plan = plan(&operation);
    let (coordinator, _, provider) = coordinator(vec![Script::Stream {
@@ -1210,11 +1522,11 @@ fn required_account_reaches_provider_and_matching_metadata_succeeds() {
        items: complete_stream(None),
    }]);
    let required = ProviderAccountId::new("acct_required").expect("account id");
-    let mut session = block_on(coordinator.start(
+    let mut session = block_on(coordinator.start_diagnostic(
        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
        operation,
        route_plan,
-        Some(required.clone()),
+        required.clone(),
        None,
        CancellationToken::new(),
    ))
@@ -1225,6 +1537,7 @@ fn required_account_reaches_provider_and_matching_metadata_succeeds() {
    let contexts = provider.contexts.lock().expect("contexts lock");
    assert_eq!(contexts.len(), 1);
    assert_eq!(contexts[0].required_account(), Some(&required));
+    assert!(contexts[0].is_diagnostic_required_account());
 }

 #[test]
@@ -1709,9 +2022,7 @@ fn rate_limited_account_exhaustion_survives_a_later_empty_selection() {
                UpstreamSendState::Sent,
            )
            .with_status(429)
-            .with_upstream_code(
-                SafeUpstreamValue::new("rate_limit_exceeded").expect("provider code"),
-            )
+            .with_upstream_code(OpaqueUpstreamValue::new("rate_limit_exceeded"))
            .with_retry_after(Duration::from_secs(30))
            .with_replay_safe())],
        },
@@ -1739,7 +2050,7 @@ fn rate_limited_account_exhaustion_survives_a_later_empty_selection() {
    assert_eq!(error.kind(), ProviderErrorKind::RateLimited);
    assert_eq!(error.upstream_status(), Some(429));
    assert_eq!(
-        error.upstream_code().map(SafeUpstreamValue::as_str),
+        error.upstream_code().map(OpaqueUpstreamValue::as_str),
        Some("rate_limit_exceeded")
    );
    assert_eq!(error.retry_after(), Some(Duration::from_secs(30)));
@@ -1836,11 +2147,282 @@ fn explicit_429_after_structural_event_should_retry_before_commit() {
    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Succeeded);
 }

+#[test]
+fn atomic_response_failed_should_rotate_account_before_stream_commit() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let (coordinator, store, provider) = coordinator(vec![
+        Script::ObservedStream {
+            account_id: "acct_first",
+            items: vec![Err(atomic_response_failed(
+                "response-first-failed",
+                "first account failure",
+            ))],
+        },
+        Script::Stream {
+            account_id: "acct_second",
+            items: complete_stream(None),
+        },
+    ]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let first = block_on(session.next_event())
+        .expect("second account should produce the first delivery")
+        .expect("started event");
+    let delivered = first.into_provider_events();
+    assert!(delivered.iter().flat_map(ProviderEvent::canonical_facts).any(
+        |event| matches!(event, GatewayEvent::Started(meta) if meta.response_id() == "response-1")
+    ));
+    assert!(
+        !delivered
+            .iter()
+            .filter_map(ProviderEvent::wire_event)
+            .any(|wire| {
+                wire.data().pointer("/response/id").and_then(Value::as_str)
+                    == Some("response-first-failed")
+            })
+    );
+    block_on(session.commit_downstream(Some(200))).expect("commit second account");
+    while block_on(session.next_event())
+        .expect("successful stream")
+        .is_some()
+    {}
+
+    assert_eq!(provider.contexts.lock().expect("contexts lock").len(), 2);
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(state.commits, 1);
+    assert_eq!(state.intermediate_failures, 1);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Succeeded);
+}
+
+#[test]
+fn bare_atomic_response_failed_should_rotate_before_the_first_delivery() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let (coordinator, store, provider) = coordinator(vec![
+        Script::ObservedStream {
+            account_id: "acct_first",
+            items: vec![Err(bare_atomic_response_failed("response-bare-failed"))],
+        },
+        Script::Stream {
+            account_id: "acct_second",
+            items: complete_stream(None),
+        },
+    ]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let first = block_on(session.next_event())
+        .expect("second account should replace the bare failure")
+        .expect("second account started event");
+    assert!(first
+        .into_provider_events()
+        .iter()
+        .flat_map(ProviderEvent::canonical_facts)
+        .any(|event| matches!(event, GatewayEvent::Started(meta) if meta.response_id() == "response-1")));
+    block_on(session.commit_downstream(Some(200))).expect("commit second account");
+    while block_on(session.next_event())
+        .expect("successful stream")
+        .is_some()
+    {}
+
+    assert_eq!(provider.contexts.lock().expect("contexts lock").len(), 2);
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(state.intermediate_failures, 1);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Succeeded);
+}
+
+#[test]
+fn exhausted_atomic_response_failed_should_deliver_only_the_last_failure_once() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let scripts = (1..=route_plan.max_attempts().get())
+        .map(|attempt| {
+            let response_id = format!("response-attempt-{attempt}-failed");
+            let marker = if attempt == route_plan.max_attempts().get() {
+                "last upstream failure".to_owned()
+            } else {
+                format!("discarded failure {attempt}")
+            };
+            Script::ObservedStream {
+                account_id: "acct_failed",
+                items: vec![Err(atomic_response_failed(&response_id, &marker))],
+            }
+        })
+        .collect::<Vec<_>>();
+    let expected_attempts = route_plan.max_attempts().get();
+    let expected_last_response = format!("response-attempt-{expected_attempts}-failed");
+    let (coordinator, store, provider) = coordinator(scripts);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let terminal = block_on(session.next_event())
+        .expect("last failure remains deliverable")
+        .expect("terminal failure batch");
+    assert_eq!(
+        terminal.commit_requirement(),
+        CommitRequirement::CommitBeforeDelivery
+    );
+    let events = terminal.into_provider_events();
+    let failures = events
+        .iter()
+        .filter_map(ProviderEvent::wire_event)
+        .filter(|wire| wire.event_type() == Some("response.failed"))
+        .collect::<Vec<_>>();
+    assert_eq!(failures.len(), 1);
+    assert_eq!(
+        failures[0]
+            .data()
+            .pointer("/response/id")
+            .and_then(Value::as_str),
+        Some(expected_last_response.as_str())
+    );
+    assert!(
+        failures[0]
+            .data()
+            .to_string()
+            .contains("last upstream failure")
+    );
+    block_on(session.commit_downstream(Some(200))).expect("commit original terminal failure");
+    let error = block_on(session.next_event()).expect_err("typed failure finalizes the request");
+    assert!(matches!(error, EngineError::Provider(_)));
+    assert!(session.is_finalized());
+
+    assert_eq!(
+        provider.contexts.lock().expect("contexts lock").len(),
+        usize::try_from(expected_attempts).expect("attempt count fits usize")
+    );
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(
+        state.intermediate_failures,
+        usize::try_from(expected_attempts - 1).expect("attempt count fits usize")
+    );
+    assert_eq!(state.commits, 1);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Incomplete);
+    assert!(state.finalizations[0].committed);
+}
+
+#[test]
+fn empty_selection_after_atomic_failure_should_deliver_the_last_upstream_wire() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let (coordinator, store, provider) = coordinator(vec![
+        Script::ObservedStream {
+            account_id: "acct_only",
+            items: vec![Err(bare_atomic_response_failed("response-only-failed"))],
+        },
+        Script::Error(ProviderError::new(
+            ProviderErrorKind::NoEligibleAccount,
+            UpstreamSendState::NotSent,
+        )),
+    ]);
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let terminal = block_on(session.next_event())
+        .expect("last account failure remains deliverable")
+        .expect("terminal failure batch");
+    let events = terminal.into_provider_events();
+    let failure = events
+        .iter()
+        .filter_map(ProviderEvent::wire_event)
+        .find(|wire| wire.event_type() == Some("response.failed"))
+        .expect("last upstream response.failed");
+    assert_eq!(
+        failure
+            .data()
+            .pointer("/response/id")
+            .and_then(Value::as_str),
+        Some("response-only-failed")
+    );
+    block_on(session.commit_downstream(Some(200))).expect("commit terminal failure");
+    assert!(matches!(
+        block_on(session.next_event()),
+        Err(EngineError::Provider(_))
+    ));
+
+    assert_eq!(provider.contexts.lock().expect("contexts lock").len(), 2);
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(state.attempts.len(), 1);
+    assert_eq!(state.intermediate_failures, 1);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Incomplete);
+    assert_eq!(
+        state.finalizations[0].client_response_id.as_deref(),
+        Some("response-only-failed")
+    );
+    assert_eq!(
+        state.finalizations[0].upstream_response_id.as_deref(),
+        Some("response-only-failed")
+    );
+}
+
+#[test]
+fn atomic_response_failed_keeps_collect_uncommitted_error_semantics() {
+    let operation = generate_operation();
+    let route_plan = plan(&operation);
+    let (coordinator, store, provider) = coordinator(vec![Script::ObservedStream {
+        account_id: "acct_required",
+        items: vec![Err(atomic_response_failed(
+            "response-required-failed",
+            "required account failure",
+        ))],
+    }]);
+    let required = ProviderAccountId::new("acct_required").expect("required account");
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        Some(required),
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+
+    let error = block_on(session.collect_uncommitted())
+        .expect_err("non-streaming collection must keep returning the typed failure");
+    assert!(matches!(error, EngineError::Provider(_)));
+    assert!(session.is_finalized());
+    assert_eq!(provider.contexts.lock().expect("contexts lock").len(), 1);
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(state.commits, 0);
+    assert_eq!(state.intermediate_failures, 0);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Failed);
+}
+
 #[test]
 fn native_continuation_explicit_429_is_not_retried() {
    let continuation = NativeContinuationPin::new(
-        PreviousResponseId::new("previous-secret-id").expect("previous response"),
-        SafeUpstreamValue::new("provider-native-id").expect("upstream response"),
+        PreviousResponseId::new("previous-secret-id"),
+        PreviousResponseId::new("provider-native-id"),
        ProviderKind::new("openai").expect("provider"),
        ProviderAccountId::new("acct_first").expect("account"),
    );
@@ -1861,9 +2443,8 @@ fn native_continuation_explicit_429_is_not_retried() {

 #[test]
 fn external_continuation_explicit_429_is_not_retried() {
-    let continuation = ContinuationBinding::External(
-        PreviousResponseId::new("external-provider-response").expect("previous response"),
-    );
+    let opaque_response_id = format!("resp_{}\0opaque", "x".repeat(257));
+    let continuation = ContinuationBinding::External(PreviousResponseId::new(opaque_response_id));
    let (store, provider) = terminal_non_idempotent_failure(
        vec![Err(ProviderError::new(
            ProviderErrorKind::RateLimited,
@@ -1930,6 +2511,100 @@ fn ambiguous_send_state_stops_retry() {
    assert!(finalization.latency_ms.is_some());
 }

+#[test]
+fn pre_delivery_transport_failure_rotates_account_for_non_idempotent_generation() {
+    let operation = operation(RetrySafety::NonIdempotent);
+    let route_plan = plan(&operation);
+    let (coordinator, store, provider) = coordinator(vec![
+        Script::Stream {
+            account_id: "acct_first",
+            items: vec![Err(ProviderError::new(
+                ProviderErrorKind::Transport,
+                UpstreamSendState::Ambiguous,
+            )
+            .with_pre_delivery_retry())],
+        },
+        Script::Stream {
+            account_id: "acct_second",
+            items: complete_stream(None),
+        },
+    ]);
+
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+    block_on(session.collect_uncommitted()).expect("second account succeeds before delivery");
+    block_on(session.commit_downstream(Some(200))).expect("commit winning response");
+
+    let contexts = provider.contexts.lock().expect("contexts lock");
+    assert_eq!(contexts.len(), 2);
+    assert!(
+        contexts[1]
+            .excluded_accounts()
+            .contains(&ProviderAccountId::new("acct_first").expect("account id"))
+    );
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(state.intermediate_failures, 1);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Succeeded);
+}
+
+#[test]
+fn pre_delivery_retry_marker_is_ignored_after_downstream_commit() {
+    let operation = operation(RetrySafety::NonIdempotent);
+    let route_plan = plan(&operation);
+    let (coordinator, store, provider) = coordinator(vec![
+        Script::Stream {
+            account_id: "acct_first",
+            items: vec![
+                Ok(GatewayEvent::Started(ResponseMeta::new(
+                    "response-visible",
+                    "gpt-5",
+                ))),
+                Err(
+                    ProviderError::new(ProviderErrorKind::Transport, UpstreamSendState::Ambiguous)
+                        .with_pre_delivery_retry(),
+                ),
+            ],
+        },
+        Script::Stream {
+            account_id: "acct_second",
+            items: complete_stream(None),
+        },
+    ]);
+
+    let mut session = block_on(coordinator.start(
+        model_request(&operation, SystemTime::now() + Duration::from_secs(30)),
+        operation,
+        route_plan,
+        None,
+        None,
+        CancellationToken::new(),
+    ))
+    .expect("start execution");
+    let first = block_on(session.next_event())
+        .expect("first event")
+        .expect("visible event");
+    assert_eq!(
+        first.commit_requirement(),
+        CommitRequirement::CommitBeforeDelivery
+    );
+    block_on(session.commit_downstream(Some(200))).expect("commit first event");
+    let error = block_on(session.next_event()).expect_err("committed output cannot be replayed");
+
+    assert!(matches!(error, EngineError::Provider(_)));
+    assert_eq!(provider.contexts.lock().expect("contexts lock").len(), 1);
+    let state = store.state.lock().expect("store lock");
+    assert_eq!(state.intermediate_failures, 0);
+    assert_eq!(state.finalizations[0].outcome, ExecutionOutcome::Incomplete);
+    assert!(state.finalizations[0].committed);
+}
+
 #[test]
 fn structural_event_before_replay_safe_failure_should_switch_account_before_commit() {
    let operation = operation(RetrySafety::Idempotent);
@@ -5,10 +5,11 @@ use std::time::{Duration, SystemTime};
 use serde_json::{Map, Value};

 use gateway_core::engine::credential::{
-    AccountAttemptFeedback, AccountAvailability, AccountCandidate, AccountFeedbackStats,
-    AccountQuotaSignals, AccountRuntimeSignals, AccountSelectionContext, AccountSelectionPolicy,
-    AccountSelector, CredentialCasUpdate, CredentialRevision, OpaqueProviderData,
-    PlaintextCredential, ProviderAccount, ProviderAccountId, ProviderAccountUpdate,
+    AccountAttemptFeedback, AccountAvailability, AccountAvailabilityPolicy, AccountCandidate,
+    AccountFeedbackStats, AccountQuotaSignals, AccountRuntimeSignals, AccountSchedulingBlocker,
+    AccountSelectionContext, AccountSelectionPolicy, AccountSelector, CredentialCasUpdate,
+    CredentialRevision, OpaqueProviderData, PlaintextCredential, PreferredAccountSelection,
+    ProviderAccount, ProviderAccountId, ProviderAccountIdentity, ProviderAccountUpdate,
    RotationStrategy,
 };
 use gateway_core::routing::ProviderKind;
@@ -51,6 +52,7 @@ fn context(strategy: RotationStrategy) -> AccountSelectionContext {
        excluded_accounts: BTreeSet::new(),
        preferred_account: None,
        round_robin_cursor: 0,
+        availability: AccountAvailabilityPolicy::Enforce,
    }
 }

@@ -72,6 +74,18 @@ fn opaque_provider_data_should_not_expose_quota_values_in_debug() {
    assert!(!format!("{quota:?}").contains("private-window"));
 }

+#[test]
+fn provider_account_identity_debug_should_redact_upstream_ids() {
+    let identity = ProviderAccountIdentity::new(
+        "private-user-id".to_owned(),
+        Some("private-account-id".to_owned()),
+    );
+    let debug = format!("{identity:?}");
+
+    assert!(!debug.contains("private-user-id"));
+    assert!(!debug.contains("private-account-id"));
+}
+
 #[test]
 fn availability_should_round_trip_all_database_values() {
    assert_eq!(
@@ -80,6 +94,55 @@ fn availability_should_round_trip_all_database_values() {
    );
 }

+#[test]
+fn diagnostic_selection_bypasses_all_local_account_availability() {
+    let exhausted = AccountCandidate {
+        account: account("acct_exhausted").with_runtime_state(
+            true,
+            AccountAvailability::QuotaExhausted,
+            None,
+        ),
+        signals: AccountRuntimeSignals {
+            in_flight: 0,
+            last_started_at: None,
+            quota_reset_at: None,
+            quota_remaining_rank: None,
+            failure_rate_basis_points: None,
+            first_output_latency_ms: None,
+        },
+    };
+    let disabled = AccountCandidate {
+        account: account("acct_disabled").with_runtime_state(
+            false,
+            AccountAvailability::QuotaExhausted,
+            None,
+        ),
+        signals: AccountRuntimeSignals {
+            in_flight: 0,
+            last_started_at: None,
+            quota_reset_at: None,
+            quota_remaining_rank: None,
+            failure_rate_basis_points: None,
+            first_output_latency_ms: None,
+        },
+    };
+    let mut context = context(RotationStrategy::Sticky);
+    context.availability = AccountAvailabilityPolicy::BypassForDiagnostic;
+
+    assert_eq!(
+        AccountSelector
+            .select(std::slice::from_ref(&exhausted), &context)
+            .map(|selection| selection.candidate().account.id()),
+        Some(exhausted.account.id())
+    );
+    assert_eq!(
+        AccountSelector
+            .select(std::slice::from_ref(&disabled), &context)
+            .map(|selection| selection.candidate().account.id()),
+        Some(disabled.account.id())
+    );
+}
+
 #[test]
 fn disabled_account_should_not_be_schedulable() {
    let account =
@@ -119,7 +182,7 @@ fn smart_selector_should_prefer_lower_inflight_count() {
        .select(&candidates, &context(RotationStrategy::Smart))
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_idle");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_idle");
 }

 #[test]
@@ -136,15 +199,13 @@ fn smart_selector_should_balance_signals_instead_of_using_lexicographic_load() {
        .select(&candidates, &context(RotationStrategy::Smart))
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_healthy");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_healthy");
 }

 #[test]
-fn smart_selector_should_keep_healthy_preferred_account_at_escape_boundary() {
+fn smart_selector_should_report_a_schedulable_preferred_account_hit() {
    let fallback = candidate("acct_fallback", 0, Some(100));
-    let mut preferred = candidate("acct_preferred", 0, Some(1));
-    preferred.signals.failure_rate_basis_points = Some(5_000);
-    preferred.signals.first_output_latency_ms = Some(15_000);
+    let preferred = candidate("acct_preferred", 0, Some(1));
    let preferred_id = preferred.account.id().clone();
    let mut selection = context(RotationStrategy::Smart);
    selection.preferred_account = Some(preferred_id);
@@ -154,16 +215,22 @@ fn smart_selector_should_keep_healthy_preferred_account_at_escape_boundary() {
        .select(&candidates, &selection)
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_preferred");
+    assert_eq!(
+        (
+            selected.candidate().account.id().as_str(),
+            selected.preferred(),
+        ),
+        ("acct_preferred", PreferredAccountSelection::Hit)
+    );
 }

 #[test]
-fn smart_selector_should_escape_preferred_account_after_failure_threshold() {
+fn smart_selector_should_keep_preferred_account_despite_failure_signals() {
    let mut fallback = candidate("acct_fallback", 0, Some(100));
    fallback.signals.failure_rate_basis_points = Some(0);
    fallback.signals.first_output_latency_ms = Some(100);
    let mut preferred = candidate("acct_preferred", 0, Some(100));
-    preferred.signals.failure_rate_basis_points = Some(5_001);
+    preferred.signals.failure_rate_basis_points = Some(10_000);
    preferred.signals.first_output_latency_ms = Some(100);
    let preferred_id = preferred.account.id().clone();
    let mut selection = context(RotationStrategy::Smart);
@@ -172,19 +239,19 @@ fn smart_selector_should_escape_preferred_account_after_failure_threshold() {

    let selected = AccountSelector
        .select(&candidates, &selection)
-        .expect("fallback candidate available");
+        .expect("preferred candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_fallback");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_preferred");
 }

 #[test]
-fn smart_selector_should_escape_preferred_account_after_latency_threshold() {
+fn smart_selector_should_keep_preferred_account_despite_latency_signals() {
    let mut fallback = candidate("acct_fallback", 0, Some(100));
    fallback.signals.failure_rate_basis_points = Some(0);
    fallback.signals.first_output_latency_ms = Some(100);
    let mut preferred = candidate("acct_preferred", 0, Some(100));
    preferred.signals.failure_rate_basis_points = Some(0);
-    preferred.signals.first_output_latency_ms = Some(15_001);
+    preferred.signals.first_output_latency_ms = Some(120_000);
    let preferred_id = preferred.account.id().clone();
    let mut selection = context(RotationStrategy::Smart);
    selection.preferred_account = Some(preferred_id);
@@ -192,9 +259,9 @@ fn smart_selector_should_escape_preferred_account_after_latency_threshold() {

    let selected = AccountSelector
        .select(&candidates, &selection)
-        .expect("fallback candidate available");
+        .expect("preferred candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_fallback");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_preferred");
 }

 #[test]
@@ -210,7 +277,16 @@ fn smart_selector_should_escape_preferred_account_at_concurrency_limit() {
        .select(&candidates, &selection)
        .expect("fallback candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_fallback");
+    assert_eq!(
+        (
+            selected.candidate().account.id().as_str(),
+            selected.preferred(),
+        ),
+        (
+            "acct_fallback",
+            PreferredAccountSelection::Blocked(AccountSchedulingBlocker::ConcurrencyLimit),
+        )
+    );
 }

 #[test]
@@ -296,7 +372,10 @@ fn smart_selector_should_use_provider_quota_rank_after_load_is_equal() {
        .select(&candidates, &context(RotationStrategy::Smart))
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_high_quota");
+    assert_eq!(
+        selected.candidate().account.id().as_str(),
+        "acct_high_quota"
+    );
 }

 #[test]
@@ -312,7 +391,7 @@ fn quota_reset_selector_should_prefer_known_earliest_window() {
        .select(&candidates, &context(RotationStrategy::QuotaResetPriority))
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_earlier");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_earlier");
 }

 #[test]
@@ -325,7 +404,7 @@ fn smart_selector_should_prefer_known_quota_over_unknown_after_load_is_equal() {
        .select(&candidates, &context(RotationStrategy::Smart))
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_known");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_known");
 }

 #[test]
@@ -338,7 +417,7 @@ fn selector_should_reject_account_at_concurrency_limit() {
        .select(&candidates, &context(RotationStrategy::Smart))
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_available");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_available");
 }

 #[test]
@@ -360,7 +439,7 @@ fn selector_should_enforce_request_interval_until_boundary() {
        .select(&candidates, &context)
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_ready");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_ready");
 }

 #[test]
@@ -377,7 +456,7 @@ fn sticky_selector_should_fall_back_when_requested_account_is_excluded() {
        .select(&candidates, &context)
        .expect("fallback candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_fallback");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_fallback");
 }

 #[test]
@@ -397,11 +476,38 @@ fn round_robin_selector_should_be_stable_for_unsorted_candidates() {
        .expect("second candidate available");

    assert_eq!(
-        (first.account.id().as_str(), second.account.id().as_str()),
+        (
+            first.candidate().account.id().as_str(),
+            second.candidate().account.id().as_str(),
+        ),
        ("acct_first", "acct_second")
    );
 }

+#[test]
+fn round_robin_selector_should_honor_a_schedulable_preferred_account_before_the_cursor() {
+    let candidates = vec![
+        candidate("acct_first", 0, None),
+        candidate("acct_second", 0, None),
+    ];
+    let mut context = context(RotationStrategy::RoundRobin);
+    context.round_robin_cursor = 0;
+    context.preferred_account =
+        Some(ProviderAccountId::new("acct_second").expect("preferred account"));
+
+    let selected = AccountSelector
+        .select(&candidates, &context)
+        .expect("preferred account available");
+
+    assert_eq!(
+        (
+            selected.candidate().account.id().as_str(),
+            selected.preferred(),
+        ),
+        ("acct_second", PreferredAccountSelection::Hit)
+    );
+}
+
 #[test]
 fn selector_should_honor_request_local_exclusion() {
    let candidates = vec![
@@ -416,7 +522,7 @@ fn selector_should_honor_request_local_exclusion() {
        .select(&candidates, &context)
        .expect("second account available");

-    assert_eq!(selected.account.id().as_str(), "acct_second");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_second");
 }

 #[test]
@@ -432,7 +538,7 @@ fn sticky_selector_should_prefer_requested_account() {
        .select(&candidates, &context)
        .expect("sticky account available");

-    assert_eq!(selected.account.id().as_str(), "acct_second");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_second");
 }

 #[test]
@@ -447,7 +553,7 @@ fn sticky_selector_without_request_binding_should_reuse_latest_account() {
        .select(&candidates, &context(RotationStrategy::Sticky))
        .expect("sticky candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_latest");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_latest");
 }

 #[test]
@@ -462,7 +568,7 @@ fn round_robin_selector_should_use_frozen_cursor() {
        .select(&candidates, &context)
        .expect("candidate available");

-    assert_eq!(selected.account.id().as_str(), "acct_second");
+    assert_eq!(selected.candidate().account.id().as_str(), "acct_second");
 }

 #[test]
@@ -4,10 +4,11 @@ use std::{
        Arc, Mutex,
        atomic::{AtomicBool, Ordering},
    },
-    time::{Duration, SystemTime},
+    time::{Duration, Instant, SystemTime},
 };

 use async_trait::async_trait;
+use bytes::Bytes;
 use futures::{executor::block_on, future::BoxFuture};
 use gateway_core::engine::admission::{
    ClientAdmissionDecision, ClientAdmissionError, ClientAdmissionPort, ClientAdmissionRecovery,
@@ -20,8 +21,9 @@ use gateway_core::engine::credential::{
    AccountSelectionPolicy, ProviderAccountId, RotationStrategy,
 };
 use gateway_core::engine::execution::{
-    ClientApiKeyUsageSink, DefaultExecutionService, ExecutionService, ProviderCircuitDecision,
-    ProviderCircuitError, ProviderCircuitPort, provider_failure_affects_circuit,
+    ClientApiKeyUsageSink, ClientTransport, DefaultExecutionService, ExecutionRequestMetadata,
+    ExecutionService, ProviderCircuitDecision, ProviderCircuitError, ProviderCircuitPort,
+    StartExecution, provider_failure_affects_circuit,
 };
 use gateway_core::engine::probe::{AccountProbe, AccountProbeRequest};
 use gateway_core::engine::provider::{
@@ -32,12 +34,15 @@ use gateway_core::engine::{
    AttemptContext, AttemptRecord, ExecutionStore, IntermediateFailure, ModelRequestFinalization,
    ModelRequestId, NewModelRequest, ProbeFailure, RecoveryReport, UpstreamSendState,
 };
-use gateway_core::error::{GatewayErrorKind, ProviderError, ProviderErrorKind, StoreError};
+use gateway_core::error::{
+    ClientVisibleUpstreamResponse, GatewayErrorKind, ProviderError, ProviderErrorKind, StoreError,
+    StoreErrorKind,
+};
 use gateway_core::operation::{GenerateRequest, Operation, OperationKind, ProtocolPayload};
 use gateway_core::policy::{ClientApiKeyId, ClientPolicy, PlaintextClientApiKey, RateLimits};
 use gateway_core::routing::snapshot::RuntimeSnapshotHandle;
 use gateway_core::routing::{
-    ConfigRevision, ModelCapabilities, ProviderKind, ProviderModel, RuntimeSnapshot,
+    ConfigRevision, ModelCapabilities, ProviderKind, ProviderModel, PublicModelId, RuntimeSnapshot,
    UpstreamModelId,
 };
 use serde_json::json;
@@ -105,10 +110,54 @@ fn probe_failures_should_be_observable_without_a_model_request_row() {
    .expect_err("the provider rejects every probe");

    assert_eq!(error.kind(), GatewayErrorKind::UpstreamUnavailable);
+    let upstream = error
+        .upstream_response()
+        .expect("probe must preserve its request-local upstream response");
+    assert_eq!(upstream.status(), 502);
+    assert_eq!(
+        upstream.content_type(),
+        Some(b"application/json".as_slice())
+    );
+    assert_eq!(
+        upstream.body(),
+        &Bytes::from_static(br#"{"error":{"message":"source upstream failure"}}"#),
+    );
+    assert!(!format!("{error:?}").contains("source upstream failure"));
    assert!(!store.touched.load(Ordering::SeqCst));
    assert_eq!(store.probe_failures(), vec!["transport".to_owned()]);
 }

+#[test]
+fn probe_observation_store_failure_preserves_the_provider_error() {
+    let store = Arc::new(TrackingExecutionStore {
+        fail_probe_observation: AtomicBool::new(true),
+        ..TrackingExecutionStore::default()
+    });
+    let providers = ProviderRegistry::new([Arc::new(FailingProvider) as Arc<dyn Provider>])
+        .expect("provider registry");
+    let service = DefaultExecutionService::new(
+        RuntimeSnapshotHandle::new(probe_snapshot()),
+        store.clone(),
+        providers,
+        Arc::new(UnusedAdmissions),
+        Arc::new(UnusedCircuits),
+        Arc::new(UnusedContinuation),
+        Arc::new(RecordingClientApiKeyUsage::default()),
+    );
+
+    let error = block_on(service.probe(AccountProbeRequest {
+        account_id: ProviderAccountId::new("acct_probe").expect("account ID"),
+        provider_kind: ProviderKind::new("openai").expect("provider kind"),
+        upstream_model: UpstreamModelId::new("gpt-probe").expect("model ID"),
+        operation: probe_operation(),
+    }))
+    .expect_err("the provider error must survive observation failure");
+
+    assert_eq!(error.kind(), GatewayErrorKind::UpstreamUnavailable);
+    assert!(!store.touched.load(Ordering::SeqCst));
+    assert!(store.probe_failures().is_empty());
+}
+
 struct FailingProvider;

 #[async_trait]
@@ -132,10 +181,14 @@ impl Provider for FailingProvider {
        _request: ProviderRequest,
        _context: AttemptContext,
    ) -> Result<ProviderStream, ProviderError> {
-        Err(ProviderError::new(
-            ProviderErrorKind::Transport,
-            UpstreamSendState::NotSent,
-        ))
+        Err(
+            ProviderError::new(ProviderErrorKind::Transport, UpstreamSendState::NotSent)
+                .with_client_visible_upstream_response(ClientVisibleUpstreamResponse::new(
+                    502,
+                    Some(b"application/json".to_vec()),
+                    Bytes::from_static(br#"{"error":{"message":"source upstream failure"}}"#),
+                )),
+        )
    }
 }

@@ -159,6 +212,111 @@ fn successful_authentication_should_record_client_key_usage() {
    assert_eq!(usage.recorded(), vec!["key_usage_test".to_owned()]);
 }

+#[test]
+fn circuit_store_failure_should_fail_open_during_request_start() {
+    let service = DefaultExecutionService::new(
+        RuntimeSnapshotHandle::new(start_snapshot()),
+        Arc::new(TrackingExecutionStore::default()),
+        ProviderRegistry::default(),
+        Arc::new(UnusedAdmissions),
+        Arc::new(FailingDecisionCircuits),
+        Arc::new(UnusedContinuation),
+        Arc::new(RecordingClientApiKeyUsage::default()),
+    );
+    let client = service
+        .authenticate("sk_start_test")
+        .expect("authenticated client");
+
+    let started = block_on(service.start(StartExecution {
+        client,
+        public_model: PublicModelId::new("gpt-start").expect("public model"),
+        operation: start_operation(),
+        metadata: ExecutionRequestMetadata {
+            protocol: "openai".to_owned(),
+            endpoint: "/v1/responses".to_owned(),
+            transport: ClientTransport::HttpJson,
+            stream: false,
+            client_ip: None,
+            user_agent: None,
+            previous_response_id: None,
+        },
+    }))
+    .expect("recoverable circuit state must not reject the request");
+
+    assert!(!started.session.is_finalized());
+}
+
+#[test]
+fn slow_circuit_store_should_time_out_and_fail_open_during_request_start() {
+    let service = DefaultExecutionService::new(
+        RuntimeSnapshotHandle::new(start_snapshot()),
+        Arc::new(TrackingExecutionStore::default()),
+        ProviderRegistry::default(),
+        Arc::new(UnusedAdmissions),
+        Arc::new(PendingDecisionCircuits),
+        Arc::new(UnusedContinuation),
+        Arc::new(RecordingClientApiKeyUsage::default()),
+    );
+    let client = service
+        .authenticate("sk_start_test")
+        .expect("authenticated client");
+    let started_at = Instant::now();
+
+    let started = block_on(service.start(StartExecution {
+        client,
+        public_model: PublicModelId::new("gpt-start").expect("public model"),
+        operation: start_operation(),
+        metadata: ExecutionRequestMetadata {
+            protocol: "openai".to_owned(),
+            endpoint: "/v1/responses".to_owned(),
+            transport: ClientTransport::HttpJson,
+            stream: false,
+            client_ip: None,
+            user_agent: None,
+            previous_response_id: None,
+        },
+    }))
+    .expect("slow recoverable circuit state must not reject the request");
+
+    assert!(started_at.elapsed() < Duration::from_secs(2));
+    assert!(!started.session.is_finalized());
+}
+
+#[test]
+fn stale_nonempty_catalog_should_not_block_a_new_model_during_request_start() {
+    let service = DefaultExecutionService::new(
+        RuntimeSnapshotHandle::new(start_snapshot()),
+        Arc::new(TrackingExecutionStore::default()),
+        ProviderRegistry::default(),
+        Arc::new(UnusedAdmissions),
+        Arc::new(UnusedCircuits),
+        Arc::new(UnusedContinuation),
+        Arc::new(RecordingClientApiKeyUsage::default()),
+    );
+    let client = service
+        .authenticate("sk_start_test")
+        .expect("authenticated client");
+    let model = "gpt-future-not-in-catalog";
+
+    let started = block_on(service.start(StartExecution {
+        client,
+        public_model: PublicModelId::from_client_wire(model).expect("client model"),
+        operation: start_operation_for_model(model),
+        metadata: ExecutionRequestMetadata {
+            protocol: "openai".to_owned(),
+            endpoint: "/v1/responses".to_owned(),
+            transport: ClientTransport::HttpJson,
+            stream: false,
+            client_ip: None,
+            user_agent: None,
+            previous_response_id: None,
+        },
+    }))
+    .expect("stale model catalog must not reject the request");
+
+    assert!(!started.session.is_finalized());
+}
+
 #[derive(Default)]
 struct RecordingClientApiKeyUsage {
    ids: Mutex<Vec<String>>,
@@ -183,6 +341,7 @@ impl ClientApiKeyUsageSink for RecordingClientApiKeyUsage {
 struct TrackingExecutionStore {
    touched: AtomicBool,
    probe_failures: Mutex<Vec<String>>,
+    fail_probe_observation: AtomicBool,
 }

 impl TrackingExecutionStore {
@@ -240,6 +399,9 @@ impl ExecutionStore for TrackingExecutionStore {
    }

    async fn record_probe_failure(&self, failure: ProbeFailure) -> Result<(), StoreError> {
+        if self.fail_probe_observation.load(Ordering::SeqCst) {
+            return Err(StoreError::new(StoreErrorKind::Unavailable));
+        }
        self.probe_failures
            .lock()
            .expect("probe failures lock")
@@ -309,6 +471,56 @@ impl ProviderCircuitPort for UnusedCircuits {
    }
 }

+struct FailingDecisionCircuits;
+
+impl ProviderCircuitPort for FailingDecisionCircuits {
+    fn decision<'a>(
+        &'a self,
+        _: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<ProviderCircuitDecision, ProviderCircuitError>> {
+        Box::pin(async { Err(ProviderCircuitError) })
+    }
+
+    fn observe_failure<'a>(
+        &'a self,
+        _: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<(), ProviderCircuitError>> {
+        Box::pin(async { Ok(()) })
+    }
+
+    fn observe_success<'a>(
+        &'a self,
+        _: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<(), ProviderCircuitError>> {
+        Box::pin(async { Ok(()) })
+    }
+}
+
+struct PendingDecisionCircuits;
+
+impl ProviderCircuitPort for PendingDecisionCircuits {
+    fn decision<'a>(
+        &'a self,
+        _: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<ProviderCircuitDecision, ProviderCircuitError>> {
+        Box::pin(futures::future::pending())
+    }
+
+    fn observe_failure<'a>(
+        &'a self,
+        _: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<(), ProviderCircuitError>> {
+        Box::pin(async { Ok(()) })
+    }
+
+    fn observe_success<'a>(
+        &'a self,
+        _: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<(), ProviderCircuitError>> {
+        Box::pin(async { Ok(()) })
+    }
+}
+
 struct UnusedContinuation;

 impl NativeContinuationPort for UnusedContinuation {
@@ -371,6 +583,34 @@ fn client_snapshot() -> RuntimeSnapshot {
    .expect("client snapshot")
 }

+fn start_snapshot() -> RuntimeSnapshot {
+    let provider = ProviderKind::new("openai").expect("provider kind");
+    let capabilities =
+        ModelCapabilities::new(BTreeSet::from([OperationKind::Generate]), Some(16_000));
+    RuntimeSnapshot::new(
+        ConfigRevision::new(1).expect("config revision"),
+        AccountSelectionPolicy::new(
+            RotationStrategy::Smart,
+            std::num::NonZeroU32::new(1).expect("concurrency"),
+            Duration::from_millis(1),
+        ),
+        vec![provider.clone()],
+        vec![ProviderModel::new(
+            provider.clone(),
+            UpstreamModelId::new("gpt-start").expect("model ID"),
+            capabilities,
+        )],
+        vec![ClientPolicy::new(
+            ClientApiKeyId::new("key_start_test").expect("client API key ID"),
+            PlaintextClientApiKey::new("sk_start_test").expect("plaintext client API key"),
+            provider,
+            true,
+            RateLimits::unlimited(),
+        )],
+    )
+    .expect("start snapshot")
+}
+
 fn probe_operation() -> Operation {
    let body = json!({
        "model": "gpt-probe",
@@ -381,3 +621,18 @@ fn probe_operation() -> Operation {
            .expect("OpenAI payload"),
    ))
 }
+
+fn start_operation() -> Operation {
+    start_operation_for_model("gpt-start")
+}
+
+fn start_operation_for_model(model: &str) -> Operation {
+    let body = json!({
+        "model": model,
+        "input": [{"type": "message", "role": "user", "content": "ping"}],
+    });
+    Operation::Generate(GenerateRequest::from_protocol_payload(
+        ProtocolPayload::json_object("openai", body.as_object().expect("request object").clone())
+            .expect("OpenAI payload"),
+    ))
+}
@@ -1,7 +1,11 @@
+use bytes::Bytes;
 use gateway_core::engine::UpstreamSendState;
 use gateway_core::error::{
-    ClientVisibleUpstreamError, GatewayError, ProviderError, ProviderErrorKind, SafeUpstreamValue,
+    ClientVisibleUpstreamError, ClientVisibleUpstreamResponse, GatewayError, OpaqueUpstreamValue,
+    ProviderError, ProviderErrorKind,
 };
+use gateway_core::event::{ProtocolWireEvent, ProviderEvent, ProviderResponseHeader};
+use serde_json::json;

 #[test]
 fn provider_error_debug_should_not_expose_sensitive_context() {
@@ -15,13 +19,22 @@ fn provider_error_debug_should_not_expose_sensitive_context() {
 #[test]
 fn provider_error_debug_should_not_print_classified_upstream_values() {
    let diagnostic = "request-visible-only-through-explicit-accessor";
-    let value = SafeUpstreamValue::new(diagnostic).expect("test diagnostic is valid");
+    let value = OpaqueUpstreamValue::new(diagnostic);
    let error = ProviderError::new(ProviderErrorKind::Unavailable, UpstreamSendState::Sent)
        .with_upstream_request_id(value);

    assert!(!format!("{error:?}").contains(diagnostic));
 }

+#[test]
+fn opaque_upstream_value_should_preserve_arbitrary_text_without_logging_it() {
+    let original = format!("\0{}\n", "x".repeat(9_000));
+    let value = OpaqueUpstreamValue::new(original.clone());
+
+    assert_eq!(value.as_str(), original);
+    assert!(!format!("{value:?}").contains(&original));
+}
+
 #[test]
 fn provider_error_replay_proof_should_default_to_false() {
    let error = ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent);
@@ -37,18 +50,82 @@ fn provider_error_replay_proof_should_be_explicit() {
    assert!(error.replay_is_safe());
 }

+#[test]
+fn provider_error_atomic_client_events_should_be_take_only_and_debug_redacted() {
+    let marker = "atomic-wire-must-not-enter-debug";
+    let event = ProviderEvent::wire(
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.failed".to_owned()),
+            json!({"type": "response.failed", "message": marker}),
+        )
+        .expect("atomic wire"),
+    );
+    let mut error = ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
+        .with_atomic_client_events(vec![event]);
+
+    assert!(error.has_atomic_client_events());
+    assert!(!format!("{error:?}").contains(marker));
+    assert_eq!(error.take_atomic_client_events().len(), 1);
+    assert!(!error.has_atomic_client_events());
+}
+
+#[test]
+fn provider_error_clone_should_drop_request_local_upstream_response() {
+    let marker = Bytes::from_static(b"raw-client-response-only");
+    let error = ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
+        .with_client_visible_upstream_response(
+            ClientVisibleUpstreamResponse::new(
+                429,
+                Some(b"application/problem+json".to_vec()),
+                marker.clone(),
+            )
+            .with_headers(vec![ProviderResponseHeader::new(
+                "x-future-error",
+                Bytes::from_static(b"opaque-header-value"),
+            )]),
+        );
+
+    let cloned = error.clone();
+
+    assert_eq!(
+        error
+            .client_visible_upstream_response()
+            .map(ClientVisibleUpstreamResponse::body),
+        Some(&marker)
+    );
+    assert!(cloned.client_visible_upstream_response().is_none());
+    assert!(!format!("{error:?}").contains("raw-client-response-only"));
+    assert!(!format!("{error:?}").contains("opaque-header-value"));
+}
+
+#[test]
+fn provider_error_clone_should_drop_atomic_client_events() {
+    let event = ProviderEvent::wire(
+        ProtocolWireEvent::json(
+            "openai",
+            Some("response.failed".to_owned()),
+            json!({"type": "response.failed"}),
+        )
+        .expect("atomic wire"),
+    );
+    let error = ProviderError::new(ProviderErrorKind::RateLimited, UpstreamSendState::Sent)
+        .with_atomic_client_events(vec![event]);
+    let cloned = error.clone();
+
+    assert!(error.has_atomic_client_events());
+    assert!(!cloned.has_atomic_client_events());
+}
+
 #[test]
 fn gateway_error_should_keep_client_visible_upstream_fields_out_of_safe_diagnostics() {
    let message = "Your Codex quota is exhausted";
    let error = ProviderError::new(ProviderErrorKind::QuotaExhausted, UpstreamSendState::Sent)
-        .with_client_visible_upstream_error(
-            ClientVisibleUpstreamError::new(
-                message,
-                Some("quota_exhausted".to_owned()),
-                Some("rate_limit_error".to_owned()),
-            )
-            .expect("safe structured upstream error"),
-        );
+        .with_client_visible_upstream_error(ClientVisibleUpstreamError::new(
+            message,
+            Some("quota_exhausted".to_owned()),
+            Some("rate_limit_error".to_owned()),
+        ));
    let gateway = GatewayError::from_provider(&error);

    assert_eq!(
@@ -60,3 +137,20 @@ fn gateway_error_should_keep_client_visible_upstream_fields_out_of_safe_diagnost
    assert_eq!(gateway.client_error_type(), Some("rate_limit_error"));
    assert!(!format!("{gateway:?}").contains(message));
 }
+
+#[test]
+fn client_visible_upstream_error_should_preserve_opaque_structured_fields() {
+    let message = format!("\0{}\n", "m".repeat(9_000));
+    let code = format!("\0{}", "c".repeat(300));
+    let error_type = String::new();
+    let detail = ClientVisibleUpstreamError::new(
+        message.clone(),
+        Some(code.clone()),
+        Some(error_type.clone()),
+    );
+
+    assert_eq!(detail.message(), message);
+    assert_eq!(detail.code(), Some(code.as_str()));
+    assert_eq!(detail.error_type(), Some(error_type.as_str()));
+    assert!(!format!("{detail:?}").contains(&message));
+}
@@ -1,8 +1,9 @@
+use bytes::Bytes;
 use gateway_core::engine::provider::UpstreamTransport;
 use gateway_core::event::{
    ContentItem, ContentKind, EventSequenceError, EventSequenceValidator, GatewayEvent,
-    ProtocolWireEvent, ProviderEvent, ProviderResponseObservation, ReasoningDelta, ResponseMeta,
-    TextDelta, ToolCallDelta,
+    ProtocolWireEvent, ProviderEvent, ProviderResponseHeader, ProviderResponseObservation,
+    ReasoningDelta, ResponseMeta, TextDelta, ToolCallDelta,
 };
 use serde_json::json;

@@ -21,6 +22,28 @@ fn provider_event_keeps_large_wire_and_observation_payloads_behind_one_indirecti
    assert!(!observation.has_client_event());
 }

+#[test]
+fn provider_response_header_should_preserve_opaque_name_and_bytes_without_debug_disclosure() {
+    let name = format!("x-future-{}\0", "n".repeat(512));
+    let value = Bytes::from_static(b"\xffopaque-response-header-secret");
+    let header = ProviderResponseHeader::new(name.clone(), value.clone());
+
+    assert_eq!(header.name(), name);
+    assert_eq!(header.value(), &value);
+    let rendered = format!("{header:?}");
+    assert!(!rendered.contains(&name));
+    assert!(!rendered.contains("opaque-response-header-secret"));
+}
+
+#[test]
+fn invalid_observed_service_tier_should_be_ignored() {
+    let observation =
+        ProviderResponseObservation::new(UpstreamTransport::new("http_sse").expect("transport"))
+            .with_service_tier_if_valid(format!("priority\0{}", "x".repeat(128)));
+
+    assert_eq!(observation.service_tier(), None);
+}
+
 #[test]
 fn protocol_wire_event_should_preserve_sse_metadata_without_exposing_id_in_debug() {
    let wire = ProtocolWireEvent::json_with_sse_metadata(
@@ -37,6 +60,23 @@ fn protocol_wire_event_should_preserve_sse_metadata_without_exposing_id_in_debug
    assert!(!format!("{wire:?}").contains("upstream-event-id"));
 }

+#[test]
+fn protocol_wire_event_should_preserve_opaque_sse_metadata() {
+    let event_type = format!("\0{}", "event".repeat(80));
+    let sse_id = "id\0with\r\ncontrols".to_owned();
+    let wire = ProtocolWireEvent::json_with_sse_metadata(
+        "openai",
+        Some(event_type.clone()),
+        json!({"type": "future.event"}),
+        Some(sse_id.clone()),
+        None,
+    )
+    .expect("internal protocol name is valid");
+
+    assert_eq!(wire.event_type(), Some(event_type.as_str()));
+    assert_eq!(wire.sse_id(), Some(sse_id.as_str()));
+}
+
 #[test]
 fn validator_should_accept_started_content_delta_completed_sequence() {
    let mut validator = EventSequenceValidator::new();
@@ -57,7 +57,7 @@ fn refresh_policy_requires_a_positive_margin() {
 }

 #[test]
-fn refresh_schedule_is_stable_and_never_uses_query_time_margin() {
+fn refresh_schedule_should_use_the_exact_configured_margin() {
    let account = ProviderAccountId::new("acct_stable").expect("valid account");
    let policy = ProviderRefreshPolicy::try_new(
        Duration::from_secs(3_600),
@@ -70,13 +70,7 @@ fn refresh_schedule_is_stable_and_never_uses_query_time_margin() {
    let first = policy
        .next_attempt_at(&account, expires_at, observed_at)
        .expect("schedule refresh");
-    let second = policy
-        .next_attempt_at(&account, expires_at, observed_at)
-        .expect("schedule refresh again");
-
-    assert_eq!(first, second);
-    assert!(first > observed_at);
-    assert!(first < expires_at);
+    assert_eq!(first, expires_at - Duration::from_secs(3_600));
 }

 #[test]
@@ -190,21 +190,36 @@ fn global_mapping_should_apply_to_every_provider() {
 #[test]
 fn unmapped_model_should_pass_through_unchanged() {
    let snapshot = snapshot();
-    let plan = snapshot
-        .plan(
-            &PublicModelId::new("future-openai-model").expect("model"),
-            &operation(),
-            &RoutingContext {
-                provider_kind: Some(ProviderKind::new("openai").expect("provider")),
-                ..RoutingContext::default()
-            },
-        )
-        .expect("unknown model remains transparent");
+    for requested in [
+        "future-openai-model".to_owned(),
+        format!("future-{}", "x".repeat(512)),
+        "future\0model".to_owned(),
+        "  future-openai-model  ".to_owned(),
+    ] {
+        let plan = snapshot
+            .plan(
+                &PublicModelId::from_client_wire(requested.clone()).expect("client model"),
+                &operation(),
+                &RoutingContext {
+                    provider_kind: Some(ProviderKind::new("openai").expect("provider")),
+                    ..RoutingContext::default()
+                },
+            )
+            .expect("unknown model remains transparent");

-    assert_eq!(
-        plan.candidates()[0].upstream_model().as_str(),
-        "future-openai-model"
-    );
+        assert_eq!(plan.candidates()[0].upstream_model().as_str(), requested);
+    }
+}
+
+#[test]
+fn model_mapping_should_use_exact_client_keys() {
+    let snapshot = snapshot().with_model_mappings(BTreeMap::from([(
+        "  exact-alias  ".to_owned(),
+        "gpt-5.5".to_owned(),
+    )]));
+
+    assert_eq!(snapshot.mapped_model("  exact-alias  "), "gpt-5.5");
+    assert_eq!(snapshot.mapped_model("exact-alias"), "exact-alias");
 }

 #[test]
@@ -13,7 +13,7 @@ path = "tests/main.rs"

 [dependencies]
 serde = { version = "1.0.228", features = ["derive"] }
-serde_json = { version = "1.0.150", features = ["preserve_order"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 thiserror = "2.0.18"
 uuid = { version = "1.23.3", features = ["v4"] }

@@ -0,0 +1,126 @@
+use serde_json::{Map, Value};
+
+const MULTI_AGENT_MODE_OPEN_TAG: &str = "<multi_agent_mode>";
+const MULTI_AGENT_MODE_CLOSE_TAG: &str = "</multi_agent_mode>";
+const PROACTIVE_MULTI_AGENT_MODE_PREFIX: &str = "Proactive multi-agent delegation is active.";
+
+/// 从 OpenAI Responses 请求中提取的稳定 Codex 请求语义。
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct CodexResponsesRequestSemantics {
+    /// 客户端原始选择的推理强度。
+    pub reasoning_effort: Option<String>,
+    /// Codex turn metadata 中的请求类型。
+    pub request_kind: Option<String>,
+    /// Codex turn metadata 中的子代理类型。
+    pub subagent_kind: Option<String>,
+    /// 网关侧派生出的推理预设。
+    pub reasoning_preset: Option<&'static str>,
+    /// 请求是否为 Codex 压缩请求。
+    pub compact: bool,
+}
+
+/// 从 Responses body 与非 wire 协议上下文中提取 Codex 语义。
+#[must_use]
+pub fn codex_responses_request_semantics(
+    body: &Map<String, Value>,
+    context: &Map<String, Value>,
+) -> CodexResponsesRequestSemantics {
+    codex_responses_request_semantics_with_turn_metadata(
+        body,
+        non_empty_string(context.get("turn_metadata")),
+    )
+}
+
+/// 调用方已解析权威 turn metadata 时，从 Responses body 中提取 Codex 语义。
+#[must_use]
+pub fn codex_responses_request_semantics_with_turn_metadata(
+    body: &Map<String, Value>,
+    turn_metadata: Option<&str>,
+) -> CodexResponsesRequestSemantics {
+    let reasoning_effort = body
+        .get("reasoning")
+        .and_then(Value::as_object)
+        .and_then(|reasoning| non_empty_string(reasoning.get("effort")))
+        .map(ToOwned::to_owned);
+    let parsed_turn_metadata = turn_metadata
+        .or_else(|| request_turn_metadata(body))
+        .and_then(|value| serde_json::from_str::<Value>(value).ok());
+    let request_kind = parsed_turn_metadata
+        .as_ref()
+        .and_then(|metadata| non_empty_string(metadata.get("request_kind")))
+        .map(ToOwned::to_owned);
+    let subagent_kind = parsed_turn_metadata
+        .as_ref()
+        .and_then(|metadata| non_empty_string(metadata.get("subagent_kind")))
+        .map(ToOwned::to_owned);
+    let proactive_multi_agent = latest_multi_agent_mode(input_items(body).iter())
+        .is_some_and(|mode| mode.starts_with(PROACTIVE_MULTI_AGENT_MODE_PREFIX));
+    let compact_trigger = input_items(body)
+        .iter()
+        .any(|item| non_empty_string(item.get("type")) == Some("compaction_trigger"));
+    let reasoning_preset = (subagent_kind.is_none()
+        && reasoning_effort.as_deref() == Some("max")
+        && proactive_multi_agent)
+        .then_some("ultra");
+    let compact = request_kind.as_deref() == Some("compaction") || compact_trigger;
+
+    CodexResponsesRequestSemantics {
+        reasoning_effort,
+        request_kind,
+        subagent_kind,
+        reasoning_preset,
+        compact,
+    }
+}
+
+fn request_turn_metadata(body: &Map<String, Value>) -> Option<&str> {
+    non_empty_string(body.get("turnMetadata"))
+        .or_else(|| non_empty_string(body.get("turn_metadata")))
+        .or_else(|| non_empty_string(body.get("x-codex-turn-metadata")))
+        .or_else(|| client_metadata_string(body, "x-codex-turn-metadata"))
+        .or_else(|| client_metadata_string(body, "turnMetadata"))
+        .or_else(|| client_metadata_string(body, "turn_metadata"))
+}
+
+fn client_metadata_string<'a>(body: &'a Map<String, Value>, key: &str) -> Option<&'a str> {
+    body.get("client_metadata")
+        .and_then(Value::as_object)
+        .and_then(|metadata| non_empty_string(metadata.get(key)))
+}
+
+fn input_items(body: &Map<String, Value>) -> &[Value] {
+    body.get("input")
+        .and_then(Value::as_array)
+        .map_or(&[], Vec::as_slice)
+}
+
+fn latest_multi_agent_mode<'a>(
+    input: impl DoubleEndedIterator<Item = &'a Value>,
+) -> Option<&'a str> {
+    input.rev().find_map(|item| {
+        if non_empty_string(item.get("role")) != Some("developer") {
+            return None;
+        }
+        item.get("content")?
+            .as_array()?
+            .iter()
+            .rev()
+            .filter_map(|content| non_empty_string(content.get("text")))
+            .find_map(multi_agent_mode_from_text)
+    })
+}
+
+fn multi_agent_mode_from_text(text: &str) -> Option<&str> {
+    let close = text.rfind(MULTI_AGENT_MODE_CLOSE_TAG)?;
+    let before_close = &text[..close];
+    let open = before_close.rfind(MULTI_AGENT_MODE_OPEN_TAG)?;
+    let body = &before_close[open + MULTI_AGENT_MODE_OPEN_TAG.len()..];
+    Some(body.trim())
+}
+
+fn non_empty_string(value: Option<&Value>) -> Option<&str> {
+    value
+        .and_then(Value::as_str)
+        .map(str::trim)
+        .filter(|value| !value.is_empty())
+}
@@ -151,7 +151,7 @@ pub fn retry_after_seconds_from_value(value: &Value) -> Option<u64> {
        .or_else(|| {
            error
                .get("resets_in_seconds")
-                .and_then(Value::as_u64)
+                .and_then(positive_u64)
                .filter(|seconds| *seconds > 0)
        })
        .or_else(|| retry_after_seconds_from_resets_at(error))
@@ -317,11 +317,7 @@ pub fn is_rate_limit_header_name(name: &str) -> bool {

 /// 从内部 `codex.rate_limits` 事件中解析限流信息。
 pub fn parse_rate_limits_event(value: &Value) -> Option<ParsedRateLimits> {
-    if value
-        .get("type")
-        .and_then(Value::as_str)
-        .is_some_and(|event_type| event_type != "codex.rate_limits")
-    {
+    if value.get("type").and_then(Value::as_str) != Some("codex.rate_limits") {
        return None;
    }

@@ -396,6 +392,12 @@ pub fn rate_limits_to_header_pairs(rate_limits: &ParsedRateLimits) -> Vec<(Strin
            &format!("{prefix}-secondary"),
            details.secondary,
        );
+        if let Some(allowed) = details.allowed {
+            headers.push((format!("{prefix}-allowed"), allowed.to_string()));
+        }
+        if let Some(limit_reached) = details.limit_reached {
+            headers.push((format!("{prefix}-limit-reached"), limit_reached.to_string()));
+        }
        if let Some(limit_name) = &details.limit_name {
            headers.push((format!("{prefix}-limit-name"), limit_name.clone()));
        }
@@ -441,7 +443,7 @@ fn nested_number_field(value: &Value, path: &[&str]) -> Option<u64> {
 }

 fn retry_after_seconds_from_resets_at(error: &Value) -> Option<u64> {
-    let resets_at = error.get("resets_at").and_then(Value::as_u64)?;
+    let resets_at = error.get("resets_at").and_then(positive_u64)?;
    let now = std::time::SystemTime::now()
        .duration_since(std::time::UNIX_EPOCH)
        .ok()?
@@ -449,6 +451,13 @@ fn retry_after_seconds_from_resets_at(error: &Value) -> Option<u64> {
    (resets_at > now).then_some(resets_at - now)
 }

+fn positive_u64(value: &Value) -> Option<u64> {
+    value
+        .as_u64()
+        .or_else(|| value.as_str().and_then(|value| value.parse::<u64>().ok()))
+        .filter(|value| *value > 0)
+}
+
 fn retry_after_seconds_from_rate_limit_message(error: &Value) -> Option<u64> {
    let code = error
        .get("code")
@@ -9,7 +9,14 @@ pub const WS_REQUEST_HEADER_RESPONSES_LITE_CLIENT_METADATA_KEY: &str =
 /// Codex memory consolidation 请求标记。
 pub const X_OPENAI_MEMGEN_REQUEST_HEADER: &str = "x-openai-memgen-request";

+/// OpenAI Responses 请求中携带的 Codex 专属语义。
+pub mod codex;
 /// OpenAI/Codex 事件语义、用量与限流字段编解码。
 pub mod events;
 /// Server-Sent Events 帧的解析与编码。
 pub mod sse;
+
+pub use codex::{
+    CodexResponsesRequestSemantics, codex_responses_request_semantics,
+    codex_responses_request_semantics_with_turn_metadata,
+};
@@ -18,10 +18,11 @@ pub struct SseEvent {
    pub retry: Option<u64>,
 }

-/// 保留完整原始字节与旁路解析结果的单个 SSE 帧。
+/// 保留原始字节与旁路解析结果的 SSE wire 片段。
 ///
-/// 这用于需要原样转发的 transport；`events` 只供旁路观测，不能反过来重建
-/// `raw`。
+/// 通常一个片段就是完整 SSE 帧。单帧超过旁路观测预算时会拆成多个原始片段，
+/// 此时 `events` 为空；透明 transport 必须按顺序交付 `raw`，不能从 `events`
+/// 反向重建或否决原始数据。
 #[derive(Clone, PartialEq, Eq)]
 pub struct SseFrame {
    raw: Vec<u8>,
@@ -62,7 +63,7 @@ impl fmt::Debug for SseFrame {
    }
 }

-/// 单事件缓冲上限。
+/// 单事件旁路解析缓冲上限。
 pub const MAX_SSE_EVENT_BUFFER_BYTES: usize = 64 * 1024 * 1024;

 /// SSE 流结束标记帧。
@@ -75,6 +76,9 @@ pub struct SseEventDecoder {
    /// `pending` 中已确认不含帧分隔符的前缀长度。新数据到达时从该边界
    /// 回退分隔符最大跨界宽度继续扫描，大帧跨多个 chunk 不会被反复重扫。
    scanned: usize,
+    /// 超大未完成帧已开始直接交付；在遇到帧分隔符前只保留跨 chunk 扫描尾部，
+    /// 不再尝试解析该帧。
+    opaque_frame: bool,
 }

 impl SseEventDecoder {
@@ -129,28 +133,35 @@ impl SseEventDecoder {
    /// 与 [`Self::push`] 相比，此方法仅应由需要原样转发的 transport 使用；普通
    /// 解析路径无需为原始帧额外分配内存。旁路解析失败时仍保留原始帧，并以空
    /// event 列表表示不可观测，避免观测失败截断客户端字节流。
-    pub fn push_frames(&mut self, chunk: &[u8]) -> Result<Vec<SseFrame>, SseError> {
+    pub fn push_frames(&mut self, chunk: &[u8]) -> Vec<SseFrame> {
        self.pending.extend_from_slice(chunk);
        let mut frames = Vec::new();
+        if self.opaque_frame && !self.finish_opaque_frame(&mut frames) {
+            self.flush_opaque_prefix(&mut frames);
+            return frames;
+        }
        let mut consumed = 0usize;

        while let Some(end) = self.next_frame_end(consumed) {
            let raw = self.pending[consumed..end].to_vec();
-            let events = std::str::from_utf8(&raw)
-                .ok()
-                .and_then(|frame| parse_sse_events(frame).ok())
-                .unwrap_or_default();
+            let events = if raw.len() > MAX_SSE_EVENT_BUFFER_BYTES {
+                Vec::new()
+            } else {
+                std::str::from_utf8(&raw)
+                    .ok()
+                    .and_then(|frame| parse_sse_events(frame).ok())
+                    .unwrap_or_default()
+            };
            frames.push(SseFrame::new(raw, events));
            consumed = end;
        }

        self.commit_consumed(consumed);
        if self.pending.len() > MAX_SSE_EVENT_BUFFER_BYTES {
-            return Err(SseError::BufferExceeded {
-                max_bytes: MAX_SSE_EVENT_BUFFER_BYTES,
-            });
+            self.opaque_frame = true;
+            self.flush_opaque_prefix(&mut frames);
        }
-        Ok(frames)
+        frames
    }

    /// 流结束时解析尚未带空行分隔符的最后一帧。
@@ -168,17 +179,53 @@ impl SseEventDecoder {
    /// 在流结束时返回未带空行分隔符的最后一帧及其旁路解析结果。
    ///
    /// 与 [`Self::push_frames`] 一致，旁路解析失败不会丢弃原始帧。
-    pub fn finish_frames(&mut self) -> Result<Vec<SseFrame>, SseError> {
+    pub fn finish_frames(&mut self) -> Vec<SseFrame> {
        self.scanned = 0;
        if self.pending.is_empty() {
-            return Ok(Vec::new());
+            self.opaque_frame = false;
+            return Vec::new();
        }
        let raw = std::mem::take(&mut self.pending);
-        let events = std::str::from_utf8(&raw)
-            .ok()
-            .and_then(|frame| parse_sse_events(frame).ok())
-            .unwrap_or_default();
-        Ok(vec![SseFrame::new(raw, events)])
+        let events = if self.opaque_frame || raw.len() > MAX_SSE_EVENT_BUFFER_BYTES {
+            Vec::new()
+        } else {
+            std::str::from_utf8(&raw)
+                .ok()
+                .and_then(|frame| parse_sse_events(frame).ok())
+                .unwrap_or_default()
+        };
+        self.opaque_frame = false;
+        vec![SseFrame::new(raw, events)]
+    }
+
+    /// 继续透明交付一个已超出观测预算的帧，并在分隔符后恢复普通解析。
+    fn finish_opaque_frame(&mut self, frames: &mut Vec<SseFrame>) -> bool {
+        let Some((position, separator_len)) = sse_frame_separator_bytes(&self.pending) else {
+            return false;
+        };
+        let end = position + separator_len;
+        let remaining = self.pending.split_off(end);
+        let raw = std::mem::replace(&mut self.pending, remaining);
+        frames.push(SseFrame::new(raw, Vec::new()));
+        self.opaque_frame = false;
+        self.scanned = 0;
+        true
+    }
+
+    /// 仅保留分隔符可能跨 chunk 的最大前缀宽度，其余原始字节立即释放给下游。
+    fn flush_opaque_prefix(&mut self, frames: &mut Vec<SseFrame>) {
+        const SEPARATOR_CROSS_CHUNK_BYTES: usize = 3;
+        let emit_len = self
+            .pending
+            .len()
+            .saturating_sub(SEPARATOR_CROSS_CHUNK_BYTES);
+        if emit_len == 0 {
+            return;
+        }
+        let tail = self.pending.split_off(emit_len);
+        let raw = std::mem::replace(&mut self.pending, tail);
+        self.scanned = 0;
+        frames.push(SseFrame::new(raw, Vec::new()));
    }
 }

@@ -366,12 +413,12 @@ pub fn encode_sse_event_with_metadata(
    retry: Option<u64>,
 ) -> String {
    let mut frame = String::new();
-    if let Some(id) = id {
+    if let Some(id) = id.filter(|id| sse_id_is_representable(id)) {
        frame.push_str("id: ");
        frame.push_str(id);
        frame.push('\n');
    }
-    if !event.is_empty() {
+    if !event.is_empty() && sse_field_value_is_single_line(event) {
        frame.push_str("event: ");
        frame.push_str(event);
        frame.push('\n');
@@ -390,6 +437,14 @@ pub fn encode_sse_event_with_metadata(
    frame
 }

+fn sse_field_value_is_single_line(value: &str) -> bool {
+    !value.contains(['\r', '\n'])
+}
+
+fn sse_id_is_representable(value: &str) -> bool {
+    sse_field_value_is_single_line(value) && !value.contains('\0')
+}
+
 fn track_event_buffer_bytes(current_bytes: &mut usize, line: &str) -> Result<(), SseError> {
    let line_separator_bytes = usize::from(*current_bytes != 0);
    *current_bytes = current_bytes
@@ -0,0 +1,61 @@
+use gateway_protocol::openai::codex_responses_request_semantics;
+use serde_json::{Map, Value, json};
+
+#[test]
+fn codex_semantics_should_use_protocol_context_before_body_metadata() {
+    let body = json!({
+        "model": "grok-4.5",
+        "reasoning": {"effort": " xhigh "},
+        "client_metadata": {
+            "x-codex-turn-metadata": "{\"request_kind\":\"review\"}"
+        },
+        "input": [
+            {"type": "message", "role": "user", "content": "history"},
+            {"type": "compaction_trigger"}
+        ]
+    });
+    let body = object(body);
+    let context = Map::from_iter([(
+        "turn_metadata".to_owned(),
+        json!("{\"request_kind\":\"compaction\",\"subagent_kind\":\"compact\"}"),
+    )]);
+
+    let semantics = codex_responses_request_semantics(&body, &context);
+
+    assert_eq!(semantics.reasoning_effort.as_deref(), Some("xhigh"));
+    assert_eq!(semantics.request_kind.as_deref(), Some("compaction"));
+    assert_eq!(semantics.subagent_kind.as_deref(), Some("compact"));
+    assert_eq!(semantics.reasoning_preset, None);
+    assert!(semantics.compact);
+}
+
+#[test]
+fn codex_semantics_should_detect_ultra_preset_from_proactive_multi_agent() {
+    let body = object(json!({
+        "model": "gpt-test",
+        "reasoning": {"effort": "max"},
+        "input": [
+            {
+                "type": "message",
+                "role": "developer",
+                "content": [{
+                    "type": "input_text",
+                    "text": "<multi_agent_mode>Proactive multi-agent delegation is active.</multi_agent_mode>"
+                }]
+            }
+        ]
+    }));
+
+    let semantics = codex_responses_request_semantics(&body, &Map::new());
+
+    assert_eq!(semantics.reasoning_effort.as_deref(), Some("max"));
+    assert_eq!(semantics.reasoning_preset, Some("ultra"));
+    assert!(!semantics.compact);
+}
+
+fn object(value: Value) -> Map<String, Value> {
+    let Value::Object(object) = value else {
+        panic!("test value must be an object");
+    };
+    object
+}
@@ -226,6 +226,32 @@ fn retry_after_should_read_structured_response_delay() {
    assert_eq!(retry_after_seconds_from_body(&body), Some(45));
 }

+#[test]
+fn retry_after_should_read_string_reset_delay() {
+    let body = json!({
+        "error": {"type": "usage_limit_reached", "resets_in_seconds": "46"}
+    })
+    .to_string();
+
+    assert_eq!(retry_after_seconds_from_body(&body), Some(46));
+}
+
+#[test]
+fn retry_after_should_read_string_reset_timestamp() {
+    let reset_at = std::time::SystemTime::now()
+        .duration_since(std::time::UNIX_EPOCH)
+        .expect("system clock")
+        .as_secs()
+        + 60;
+    let body = json!({
+        "error": {"type": "usage_limit_reached", "resets_at": reset_at.to_string()}
+    })
+    .to_string();
+
+    let retry_after = retry_after_seconds_from_body(&body).expect("retry-after");
+    assert!((59..=60).contains(&retry_after));
+}
+
 #[test]
 fn retry_after_should_read_nested_error_delay() {
    let body = json!({
@@ -414,6 +440,8 @@ fn parse_rate_limits_event_should_extract_websocket_metered_limit() {
        "metered_limit_name": "codex-other",
        "limit_name": "Other requests",
        "rate_limits": {
+            "allowed": false,
+            "limit_reached": true,
            "primary": {
                "used_percent": 33,
                "window_minutes": 60,
@@ -424,7 +452,8 @@ fn parse_rate_limits_event_should_extract_websocket_metered_limit() {
            "has_credits": true,
            "unlimited": false,
            "balance": "9.25"
-        }
+        },
+        "rate_limit_reached_type": "usage_limit_reached"
    });

    let parsed = parse_rate_limits_event(&event).expect("rate-limit event");
@@ -434,29 +463,39 @@ fn parse_rate_limits_event_should_extract_websocket_metered_limit() {
        (
            parsed.active_limit.as_deref(),
            details.limit_name.as_deref(),
+            details.allowed,
+            details.limit_reached,
            details.primary.expect("primary window").window_minutes,
            parsed.plan_type.as_deref(),
            parsed.credits.expect("credits").balance,
+            parsed.rate_limit_reached_type.as_deref(),
        ),
        (
            Some("codex_other"),
            Some("Other requests"),
+            Some(false),
+            Some(true),
            Some(60),
            Some("team"),
            Some("9.25".to_owned()),
+            Some("usage_limit_reached"),
        )
    );
 }

 #[test]
 fn parse_rate_limits_event_should_reject_unrelated_event_type() {
-    assert_eq!(
-        parse_rate_limits_event(&json!({
+    for event in [
+        json!({
            "type": "response.completed",
            "rate_limits": {"primary": {"used_percent": 100}}
-        })),
-        None
-    );
+        }),
+        json!({
+            "rate_limits": {"primary": {"used_percent": 100}}
+        }),
+    ] {
+        assert_eq!(parse_rate_limits_event(&event), None);
+    }
 }

 #[test]
@@ -468,9 +507,15 @@ fn rate_limit_header_round_trip_should_preserve_wire_facts() {
            "300".to_owned(),
        ),
        ("x-codex-active-limit".to_owned(), "codex".to_owned()),
+        ("x-codex-allowed".to_owned(), "false".to_owned()),
+        ("x-codex-limit-reached".to_owned(), "true".to_owned()),
        ("x-codex-credits-has-credits".to_owned(), "true".to_owned()),
        ("x-codex-credits-unlimited".to_owned(), "false".to_owned()),
        ("x-codex-plan-type".to_owned(), "plus".to_owned()),
+        (
+            "x-codex-rate-limit-reached-type".to_owned(),
+            "usage_limit_reached".to_owned(),
+        ),
    ];
    let parsed = parse_rate_limit_headers(&source).expect("initial parse");
    let encoded = rate_limits_to_header_pairs(&parsed);
@@ -1,2 +1,3 @@
+mod codex;
 mod events;
 mod sse;
@@ -135,13 +135,8 @@ fn raw_frame_decoder_should_preserve_exact_frame_across_chunk_boundaries() {
    let raw = b": keep-alive\r\nid: evt_1\r\nevent: response.future\r\nretry: 250\r\ndata: { \"type\": \"response.future\", \"opaque\": true }\r\n\r\n";
    let mut decoder = SseEventDecoder::default();

-    assert!(
-        decoder
-            .push_frames(&raw[..37])
-            .expect("partial raw frame")
-            .is_empty()
-    );
-    let frames = decoder.push_frames(&raw[37..]).expect("complete raw frame");
+    assert!(decoder.push_frames(&raw[..37]).is_empty());
+    let frames = decoder.push_frames(&raw[37..]);

    assert_eq!(frames.len(), 1);
    assert_eq!(frames[0].raw(), raw);
@@ -161,15 +156,11 @@ fn raw_frame_decoder_should_preserve_unparseable_frames_for_transparent_transpor
    let non_utf8 = b"data: \xff\n\n";
    let mut decoder = SseEventDecoder::default();

-    let frames = decoder
-        .push_frames(invalid_retry)
-        .expect("raw frame remains deliverable");
+    let frames = decoder.push_frames(invalid_retry);
    assert_eq!(frames[0].raw(), invalid_retry);
    assert!(frames[0].events().is_empty());

-    let frames = decoder
-        .push_frames(non_utf8)
-        .expect("non-UTF-8 raw frame remains deliverable");
+    let frames = decoder.push_frames(non_utf8);
    assert_eq!(frames[0].raw(), non_utf8);
    assert!(frames[0].events().is_empty());
 }
@@ -179,15 +170,8 @@ fn raw_frame_decoder_finish_should_preserve_unparseable_trailing_frame() {
    let raw = b"retry: later\ndata: opaque";
    let mut decoder = SseEventDecoder::default();

-    assert!(
-        decoder
-            .push_frames(raw)
-            .expect("unfinished raw frame remains buffered")
-            .is_empty()
-    );
-    let frames = decoder
-        .finish_frames()
-        .expect("trailing raw frame remains deliverable");
+    assert!(decoder.push_frames(raw).is_empty());
+    let frames = decoder.finish_frames();

    assert_eq!(frames[0].raw(), raw);
    assert!(frames[0].events().is_empty());
@@ -232,6 +216,32 @@ fn incremental_decoder_should_accept_exact_limit_and_reject_one_byte_over() {
    );
 }

+#[test]
+fn raw_frame_decoder_should_stream_oversized_unfinished_frame_and_resume_observation() {
+    let oversized = vec![b'x'; MAX_SSE_EVENT_BUFFER_BYTES + 1];
+    let mut decoder = SseEventDecoder::default();
+    let mut raw = decoder
+        .push_frames(&oversized)
+        .into_iter()
+        .flat_map(|frame| frame.into_parts().0)
+        .collect::<Vec<_>>();
+
+    assert!(!raw.is_empty());
+    let tail = decoder.push_frames(b"\n\n");
+    assert!(tail.iter().all(|frame| frame.events().is_empty()));
+    raw.extend(tail.into_iter().flat_map(|frame| frame.into_parts().0));
+    assert_eq!(raw.len(), oversized.len() + 2);
+    assert_eq!(&raw[..oversized.len()], oversized.as_slice());
+    assert_eq!(&raw[oversized.len()..], b"\n\n");
+
+    let observed = decoder.push_frames(b"event: response.future\ndata: {\"ok\":true}\n\n");
+    assert_eq!(observed.len(), 1);
+    assert_eq!(
+        observed[0].events()[0].event.as_deref(),
+        Some("response.future")
+    );
+}
+
 #[test]
 fn encoder_should_round_trip_multiline_data() {
    let frame = encode_sse_event("response.output_text.delta", "first\nsecond");
@@ -267,6 +277,20 @@ fn encoder_should_round_trip_sse_id_and_retry() {
    );
 }

+#[test]
+fn encoder_should_omit_metadata_that_sse_cannot_represent_as_one_field() {
+    let frame = encode_sse_event_with_metadata(
+        "future\nevent",
+        r#"{"type":"future\nevent"}"#,
+        Some("id\0with\nline"),
+        None,
+    );
+
+    assert!(!frame.contains("event:"));
+    assert!(!frame.contains("id:"));
+    assert!(frame.contains(r#"data: {"type":"future\nevent"}"#));
+}
+
 #[test]
 fn response_failed_event_should_match_openai_failure_shape() {
    let frame = response_failed_sse_event("server_error", "stream_disconnected", "closed early");
@@ -20,7 +20,7 @@ gateway-core = { path = "../gateway-core" }
 hex = "0.4.3"
 redis = { version = "1.3.0", default-features = false, features = ["tokio-comp", "connection-manager", "script"] }
 serde = { version = "1.0.228", features = ["derive"] }
-serde_json = { version = "1.0.150", features = ["preserve_order"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 sha2 = "0.11.0"
 sqlx = { version = "0.9.0", default-features = false, features = ["runtime-tokio", "tls-rustls", "postgres", "chrono", "json", "macros", "migrate"] }
 thiserror = "2.0.18"
@@ -21,7 +21,7 @@ use gateway_core::CoreStorePorts;
 use gateway_core::health::{HealthProbe, HealthState};
 use gateway_core::provider_ports::ProviderStorePorts;
 use gateway_core::task::{
-    ScheduledTask, WorkerContribution, WorkerCycleContext, WorkerDisabledReason, WorkerId,
+    DaemonRestartPolicy, ScheduledTask, WorkerContribution, WorkerCycleContext, WorkerId,
    WorkerKind, WorkerLeaderLeasePort, WorkerLeaseRequest, WorkerRegistration, WorkerRunnable,
    WorkerSchedule, WorkerTaskError,
 };
@@ -318,28 +318,39 @@ pub async fn initialize(mut config: StoreConfig) -> StoreResult<StoreBundle> {
        }),
    );

-    let execution = Arc::new(postgres::PgExecutionStore::new(pool.clone()));
+    let execution_repository = Arc::new(postgres::PgExecutionStore::new(pool.clone()));
+    let (execution, execution_writer) =
+        postgres::BufferedExecutionStore::new(Arc::clone(&execution_repository));
+    let execution = Arc::new(execution);
    let retention = Arc::new(postgres::PgRetentionRepository::new(pool.clone()));
-    let core_ports = CoreStorePorts::new(
-        execution.clone(),
-        (
-            Arc::new(redis::RedisClientAdmissionRepository::new(
-                redis_connection.clone(),
-                REDIS_NAMESPACE,
-            )?),
-            Arc::new(postgres::PgClientAdmissionRecoveryRepository::new(
-                pool.clone(),
-            )),
-        ),
+    let admissions: Arc<dyn gateway_core::engine::admission::ClientAdmissionPort> = Arc::new(
+        redis::RedisClientAdmissionRepository::new(redis_connection.clone(), REDIS_NAMESPACE)?,
+    );
+    let circuits: Arc<dyn gateway_core::engine::execution::ProviderCircuitPort> =
        Arc::new(redis::RedisProviderCircuitRepository::new(
            redis_connection.clone(),
            REDIS_NAMESPACE,
            redis::ProviderCircuitPolicy::default(),
-        )?),
+        )?);
+    // Continuation affinity 是下一轮请求的路由事实，Core 必须直接等待 Redis 确认。
+    let continuation: Arc<dyn gateway_core::engine::continuation::NativeContinuationPort> =
        Arc::new(redis::RedisNativeContinuationRepository::new(
            redis_connection.clone(),
            REDIS_NAMESPACE,
-        )?),
+        )?);
+    let (admissions, admission_release_writer) =
+        redis::BufferedClientAdmissionPort::new(admissions);
+    let (circuits, circuit_feedback_writer) = redis::BufferedProviderCircuitPort::new(circuits);
+    let core_ports = CoreStorePorts::new(
+        execution,
+        (
+            Arc::new(admissions),
+            Arc::new(postgres::PgClientAdmissionRecoveryRepository::new(
+                pool.clone(),
+            )),
+        ),
+        Arc::new(circuits),
+        continuation,
        (
            Arc::new(postgres::PgRuntimeSnapshotRepository::new(pool.clone())),
            Arc::new(redis::RedisRuntimeChangeRepository::new(
@@ -373,7 +384,13 @@ pub async fn initialize(mut config: StoreConfig) -> StoreResult<StoreBundle> {
            connection: redis_connection,
        }),
    ];
-    let worker_contributions = store_worker_contributions(execution, retention)?;
+    let worker_contributions = store_worker_contributions(
+        execution_repository,
+        execution_writer,
+        admission_release_writer,
+        circuit_feedback_writer,
+        retention,
+    )?;
    Ok(StoreBundle {
        admin_ports,
        core_ports,
@@ -386,12 +403,24 @@ pub async fn initialize(mut config: StoreConfig) -> StoreResult<StoreBundle> {

 fn store_worker_contributions(
    execution: Arc<postgres::PgExecutionStore>,
+    execution_writer: postgres::ExecutionObservationWriter<postgres::PgExecutionStore>,
+    admission_release_writer: redis::ClientAdmissionReleaseWriter,
+    circuit_feedback_writer: redis::ProviderCircuitFeedbackWriter,
    retention: Arc<postgres::PgRetentionRepository>,
 ) -> StoreResult<Vec<WorkerContribution>> {
    let stale_id = WorkerId::try_new(WorkerKind::StaleModelRequestRecovery, "postgres")
        .map_err(worker_definition_error)?;
    let retention_id =
        WorkerId::try_new(WorkerKind::Retention, "postgres").map_err(worker_definition_error)?;
+    let ops_flush_id =
+        WorkerId::try_new(WorkerKind::OpsFlush, "postgres").map_err(worker_definition_error)?;
+    let admission_flush_id = WorkerId::try_new(WorkerKind::OpsFlush, "redis_admission")
+        .map_err(worker_definition_error)?;
+    let circuit_flush_id = WorkerId::try_new(WorkerKind::OpsFlush, "redis_circuit")
+        .map_err(worker_definition_error)?;
+    let ops_flush_restart =
+        DaemonRestartPolicy::try_new(Duration::from_secs(1), Duration::from_secs(60))
+            .map_err(worker_definition_error)?;
    Ok(vec![
        WorkerContribution::Registration(scheduled_worker(
            stale_id,
@@ -403,10 +432,36 @@ fn store_worker_contributions(
            Duration::from_secs(60 * 60),
            Box::new(RetentionTask { retention }),
        )?),
-        WorkerContribution::Disabled {
-            kind: WorkerKind::OpsFlush,
-            reason: WorkerDisabledReason::NoBufferedOpsEvents,
-        },
+        WorkerContribution::Registration(
+            WorkerRegistration::try_new(
+                ops_flush_id,
+                WorkerRunnable::Daemon {
+                    restart: ops_flush_restart,
+                    task: Box::new(execution_writer),
+                },
+            )
+            .map_err(worker_definition_error)?,
+        ),
+        WorkerContribution::Registration(
+            WorkerRegistration::try_new(
+                admission_flush_id,
+                WorkerRunnable::Daemon {
+                    restart: ops_flush_restart,
+                    task: Box::new(admission_release_writer),
+                },
+            )
+            .map_err(worker_definition_error)?,
+        ),
+        WorkerContribution::Registration(
+            WorkerRegistration::try_new(
+                circuit_flush_id,
+                WorkerRunnable::Daemon {
+                    restart: ops_flush_restart,
+                    task: Box::new(circuit_feedback_writer),
+                },
+            )
+            .map_err(worker_definition_error)?,
+        ),
    ])
 }

@@ -582,7 +637,6 @@ impl SettingsStore for AdminSettingsStoreAdapter {
        };
        let snapshot = postgres::ControlPlaneRepository::replace_control_plane(
            &self.control_plane,
-            store_revision(command.expected_config_revision)?,
            replacement,
        )
        .await
@@ -592,32 +646,24 @@ impl SettingsStore for AdminSettingsStoreAdapter {

    async fn replace_admin_api_key(
        &self,
-        expected_config_revision: AdminRevision,
        key: AdminApiKey,
        context: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
-        self.replace_admin_api_key_value(
-            expected_config_revision,
-            Some(key.expose_for_auth().to_owned()),
-            context,
-        )
-        .await
+        self.replace_admin_api_key_value(Some(key.expose_for_auth().to_owned()), context)
+            .await
    }

    async fn delete_admin_api_key(
        &self,
-        expected_config_revision: AdminRevision,
        context: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
-        self.replace_admin_api_key_value(expected_config_revision, None, context)
-            .await
+        self.replace_admin_api_key_value(None, context).await
    }
 }

 impl AdminSettingsStoreAdapter {
    async fn replace_admin_api_key_value(
        &self,
-        expected_config_revision: AdminRevision,
        admin_api_key: Option<String>,
        context: &MutationContext,
    ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -639,7 +685,6 @@ impl AdminSettingsStoreAdapter {
        };
        let snapshot = postgres::ControlPlaneRepository::replace_control_plane(
            &self.control_plane,
-            store_revision(expected_config_revision)?,
            postgres::ControlPlaneReplacement {
                settings: update,
                audit: mutation_audit(
@@ -36,7 +36,7 @@ use sqlx::{PgPool, Postgres, QueryBuilder, Transaction};

 use crate::{
    StoreError, StoreResult, admin_revision, admin_store_error, mutation_audit,
-    postgres_unavailable, require_nonempty, store_revision,
+    postgres_unavailable, require_nonempty,
 };

 use super::{ControlPlaneRepository, PgControlPlaneRepository};
@@ -633,7 +633,6 @@ impl ClientKeyStore for PgAdminClientKeyStore {
        let revision = self
            .control_plane
            .create_client_api_key(
-                store_revision(command.expected_config_revision)?,
                NewClientApiKey {
                    id: id.as_str().to_owned(),
                    name: command.name,
@@ -676,7 +675,6 @@ impl ClientKeyStore for PgAdminClientKeyStore {
        let revision = self
            .control_plane
            .update_client_api_key(
-                store_revision(command.expected_config_revision)?,
                UpdateClientApiKeyDetails {
                    id: id.as_str().to_owned(),
                    name: command.name,
@@ -716,7 +714,6 @@ impl ClientKeyStore for PgAdminClientKeyStore {
        let revision = self
            .control_plane
            .set_client_api_key_enabled(
-                store_revision(command.expected_config_revision)?,
                id.as_str(),
                command.enabled,
                mutation_audit(
@@ -739,7 +736,6 @@ impl ClientKeyStore for PgAdminClientKeyStore {
    ) -> AdminStoreResult<gateway_admin::model::Revision> {
        self.control_plane
            .delete_client_api_key(
-                store_revision(command.expected_config_revision)?,
                command.id.as_str(),
                mutation_audit(
                    context,
@@ -224,6 +224,7 @@ pub struct ModelRequestFinalization {
    pub upstream_transport: Option<String>,
    pub http_version: Option<String>,
    pub websocket_pool: Option<String>,
+    pub service_tier: Option<String>,
    pub provider_metadata_json: Option<Value>,
    pub error_kind: Option<String>,
    pub provider_error_code: Option<String>,
@@ -276,6 +277,12 @@ impl ModelRequestFinalization {
        {
            return Err(invalid("websocket pool must be new or reuse"));
        }
+        if let Some(service_tier) = self.service_tier.as_deref() {
+            require_nonempty(ENTITY, "service_tier", service_tier)?;
+            if service_tier.len() > 64 || service_tier.chars().any(char::is_control) {
+                return Err(invalid("service tier is invalid"));
+            }
+        }
        if self
            .provider_metadata_json
            .as_ref()
@@ -573,7 +580,7 @@ impl ModelRequestRepository for PgExecutionStore {
                 latency_ms = $35, completed_at = $36,
                 upstream_transport = coalesce($37, upstream_transport),
                 http_version = coalesce($38, http_version), websocket_pool = $39,
-                 provider_observation_json = $40
+                 service_tier = $40, provider_observation_json = $41
             where id = $1 and outcome = 'running'",
        )
        .bind(&finalization.model_request_id)
@@ -586,9 +593,9 @@ impl ModelRequestRepository for PgExecutionStore {
        .bind(finalization.downstream_committed_at)
        .bind(finalization.client_status_code.map(i32::from))
        .bind(finalization.upstream_status_code.map(i32::from))
-        .bind(finalization.client_response_id)
+        .bind(finalization.client_response_id.map(String::into_bytes))
        .bind(finalization.upstream_request_id)
-        .bind(finalization.upstream_response_id)
+        .bind(finalization.upstream_response_id.map(String::into_bytes))
        .bind(finalization.error_kind)
        .bind(finalization.provider_error_code)
        .bind(finalization.error_message)
@@ -660,6 +667,7 @@ impl ModelRequestRepository for PgExecutionStore {
        .bind(finalization.upstream_transport)
        .bind(finalization.http_version)
        .bind(finalization.websocket_pool)
+        .bind(finalization.service_tier)
        .bind(finalization.provider_metadata_json.map(sqlx::types::Json))
        .execute(&self.pool)
        .await
@@ -831,18 +839,6 @@ impl ExecutionStore for PgExecutionStore {
        let latency_ms = u64::try_from(failure.latency.as_millis())
            .map_err(|_| CoreStoreError::new(CoreStoreErrorKind::InvalidData))?;
        let provider_error_code = error.upstream_code().map(|code| code.as_str().to_owned());
-        tracing::warn!(
-            target: "gateway_probe",
-            provider_kind = failure.provider_kind.as_str(),
-            account_id = failure.account_id.as_str(),
-            upstream_model = failure.upstream_model_id.as_str(),
-            failure_kind = error.kind().as_str(),
-            send_state = ?error.send_state(),
-            upstream_status = ?error.upstream_status(),
-            provider_error_code = ?provider_error_code,
-            latency_ms,
-            "账号连接测试失败"
-        );
        super::OpsEventRepository::append_ops_event(
            &super::PgOpsEventRepository::new(self.pool.clone()),
            super::OpsEvent {
@@ -927,6 +923,7 @@ impl ExecutionStore for PgExecutionStore {
                upstream_transport: finalization.upstream_transport,
                http_version: finalization.http_version,
                websocket_pool: finalization.websocket_pool,
+                service_tier: finalization.service_tier,
                provider_metadata_json,
                error_kind,
                provider_error_code: finalization.provider_error_code,
@@ -0,0 +1,699 @@
+//! 数据面执行观测的非阻塞 PostgreSQL 写入队列。
+
+use std::mem::size_of;
+use std::num::NonZeroUsize;
+use std::sync::Arc;
+use std::sync::atomic::{AtomicU64, AtomicUsize, Ordering};
+use std::time::{Duration, Instant, SystemTime};
+
+use async_trait::async_trait;
+use gateway_core::engine::{
+    AttemptRecord, CancellationToken, ExecutionStore, IntermediateFailure,
+    ModelRequestFinalization, ModelRequestId, NewModelRequest, ProbeFailure, RecoveryReport,
+    UpstreamSendState,
+};
+use gateway_core::error::{ProviderError, StoreError};
+use gateway_core::task::{DaemonTask, WorkerTaskError};
+use tokio::sync::{Mutex, mpsc};
+
+const DEFAULT_QUEUE_CAPACITY: usize = 4_096;
+const DEFAULT_QUEUE_BYTE_CAPACITY: usize = 64 * 1024 * 1024;
+const SHUTDOWN_DRAIN_TIMEOUT: Duration = Duration::from_secs(2);
+
+/// 执行观测缓冲区的进程内累计状态。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct ExecutionBufferStats {
+    /// 尚未完成落库的队列项和当前写入项数量。
+    pub queued_items: usize,
+    /// 尚未完成落库的观测对象估算字节数。
+    pub queued_bytes: usize,
+    /// 进程启动后成功入队的累计数量。
+    pub enqueued_total: u64,
+    /// 因队列、字节预算或关闭排空超时丢弃的累计数量。
+    pub dropped_total: u64,
+    /// 已成功写入底层 Store 的累计数量。
+    pub persisted_total: u64,
+    /// 底层 Store 返回失败的累计数量。
+    pub write_failure_total: u64,
+}
+
+struct ExecutionBufferState {
+    maximum_queued_bytes: usize,
+    queued_items: AtomicUsize,
+    queued_bytes: AtomicUsize,
+    enqueued_total: AtomicU64,
+    dropped_total: AtomicU64,
+    persisted_total: AtomicU64,
+    write_failure_total: AtomicU64,
+}
+
+impl ExecutionBufferState {
+    fn new(maximum_queued_bytes: NonZeroUsize) -> Self {
+        Self {
+            maximum_queued_bytes: maximum_queued_bytes.get(),
+            queued_items: AtomicUsize::new(0),
+            queued_bytes: AtomicUsize::new(0),
+            enqueued_total: AtomicU64::new(0),
+            dropped_total: AtomicU64::new(0),
+            persisted_total: AtomicU64::new(0),
+            write_failure_total: AtomicU64::new(0),
+        }
+    }
+
+    fn reserve(&self, bytes: usize) -> bool {
+        let reserved = self
+            .queued_bytes
+            .fetch_update(Ordering::AcqRel, Ordering::Acquire, |current| {
+                current
+                    .checked_add(bytes)
+                    .filter(|next| *next <= self.maximum_queued_bytes)
+            })
+            .is_ok();
+        if reserved {
+            self.queued_items.fetch_add(1, Ordering::Relaxed);
+        }
+        reserved
+    }
+
+    fn release(&self, bytes: usize) {
+        self.queued_bytes.fetch_sub(bytes, Ordering::AcqRel);
+        self.queued_items.fetch_sub(1, Ordering::AcqRel);
+    }
+
+    fn record_enqueued(&self) {
+        saturating_increment(&self.enqueued_total, 1);
+    }
+
+    fn record_dropped(&self, count: usize) {
+        saturating_increment(
+            &self.dropped_total,
+            u64::try_from(count).unwrap_or(u64::MAX),
+        );
+    }
+
+    fn record_persisted(&self) {
+        saturating_increment(&self.persisted_total, 1);
+    }
+
+    fn record_write_failure(&self) {
+        saturating_increment(&self.write_failure_total, 1);
+    }
+
+    fn snapshot(&self) -> ExecutionBufferStats {
+        ExecutionBufferStats {
+            queued_items: self.queued_items.load(Ordering::Acquire),
+            queued_bytes: self.queued_bytes.load(Ordering::Acquire),
+            enqueued_total: self.enqueued_total.load(Ordering::Acquire),
+            dropped_total: self.dropped_total.load(Ordering::Acquire),
+            persisted_total: self.persisted_total.load(Ordering::Acquire),
+            write_failure_total: self.write_failure_total.load(Ordering::Acquire),
+        }
+    }
+}
+
+fn saturating_increment(counter: &AtomicU64, increment: u64) {
+    let _ = counter.fetch_update(Ordering::Relaxed, Ordering::Relaxed, |current| {
+        Some(current.saturating_add(increment))
+    });
+}
+
+/// 将数据面观测写入转换为有界、非阻塞的进程内命令。
+///
+/// 队列满、worker 尚未启动或已经退出时只丢弃观测并记录告警；协议数据面不会
+/// 等待 PostgreSQL，也不会看到 Store 错误。启动恢复仍直接访问底层 Store。
+pub struct BufferedExecutionStore<S: ?Sized> {
+    inner: Arc<S>,
+    sender: mpsc::Sender<QueuedExecutionObservation>,
+    state: Arc<ExecutionBufferState>,
+}
+
+impl<S: ?Sized> BufferedExecutionStore<S> {
+    #[must_use]
+    pub fn new(inner: Arc<S>) -> (Self, ExecutionObservationWriter<S>) {
+        Self::with_capacity(
+            inner,
+            NonZeroUsize::new(DEFAULT_QUEUE_CAPACITY).expect("queue capacity is non-zero"),
+        )
+    }
+
+    #[must_use]
+    pub fn with_capacity(
+        inner: Arc<S>,
+        capacity: NonZeroUsize,
+    ) -> (Self, ExecutionObservationWriter<S>) {
+        Self::with_limits(
+            inner,
+            capacity,
+            NonZeroUsize::new(DEFAULT_QUEUE_BYTE_CAPACITY)
+                .expect("queue byte capacity is non-zero"),
+        )
+    }
+
+    #[must_use]
+    pub fn with_limits(
+        inner: Arc<S>,
+        capacity: NonZeroUsize,
+        maximum_queued_bytes: NonZeroUsize,
+    ) -> (Self, ExecutionObservationWriter<S>) {
+        let (sender, receiver) = mpsc::channel(capacity.get());
+        let state = Arc::new(ExecutionBufferState::new(maximum_queued_bytes));
+        (
+            Self {
+                inner: Arc::clone(&inner),
+                sender,
+                state: Arc::clone(&state),
+            },
+            ExecutionObservationWriter {
+                inner,
+                receiver: Mutex::new(receiver),
+                state,
+            },
+        )
+    }
+
+    #[must_use]
+    pub fn stats(&self) -> ExecutionBufferStats {
+        self.state.snapshot()
+    }
+
+    fn enqueue(&self, write: ExecutionObservationWrite) {
+        let estimated_bytes = write
+            .estimated_bytes()
+            .saturating_add(write.request_id().map_or(0, str::len))
+            .max(1);
+        if !self.state.reserve(estimated_bytes) {
+            self.state.record_dropped(1);
+            let stats = self.state.snapshot();
+            tracing::warn!(
+                operation = write.operation(),
+                request_id = ?write.request_id(),
+                reason = "byte_capacity",
+                estimated_bytes,
+                maximum_queued_bytes = self.state.maximum_queued_bytes,
+                dropped_total = stats.dropped_total,
+                "执行观测队列字节预算不足，已丢弃本次写入"
+            );
+            return;
+        }
+        let queued =
+            QueuedExecutionObservation::new(write, estimated_bytes, Arc::clone(&self.state));
+        match self.sender.try_send(queued) {
+            Ok(()) => self.state.record_enqueued(),
+            Err(error) => {
+                let (reason, queued) = match error {
+                    mpsc::error::TrySendError::Full(queued) => ("full", queued),
+                    mpsc::error::TrySendError::Closed(queued) => ("closed", queued),
+                };
+                let operation = queued.operation();
+                let request_id = queued.request_id().map(ToOwned::to_owned);
+                drop(queued);
+                self.state.record_dropped(1);
+                let stats = self.state.snapshot();
+                tracing::warn!(
+                    operation,
+                    request_id = ?request_id,
+                    reason,
+                    queued_items = stats.queued_items,
+                    queued_bytes = stats.queued_bytes,
+                    dropped_total = stats.dropped_total,
+                    "执行观测队列不可用，已丢弃本次写入"
+                );
+            }
+        }
+    }
+}
+
+#[async_trait]
+impl<S> ExecutionStore for BufferedExecutionStore<S>
+where
+    S: ExecutionStore + ?Sized,
+{
+    async fn create_model_request(&self, request: NewModelRequest) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::Create(Box::new(request)));
+        Ok(())
+    }
+
+    async fn record_attempt(&self, attempt: AttemptRecord) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::Attempt(Box::new(attempt)));
+        Ok(())
+    }
+
+    async fn create_model_request_with_attempt(
+        &self,
+        request: NewModelRequest,
+        attempt: AttemptRecord,
+    ) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::CreateWithAttempt(Box::new((
+            request, attempt,
+        ))));
+        Ok(())
+    }
+
+    async fn mark_send_state(
+        &self,
+        request_id: &ModelRequestId,
+        state: UpstreamSendState,
+    ) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::MarkSendState {
+            request_id: request_id.clone(),
+            state,
+        });
+        Ok(())
+    }
+
+    async fn mark_downstream_committed(
+        &self,
+        request_id: &ModelRequestId,
+        committed_at: SystemTime,
+        client_status_code: Option<u16>,
+    ) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::MarkDownstreamCommitted {
+            request_id: request_id.clone(),
+            committed_at,
+            client_status_code,
+        });
+        Ok(())
+    }
+
+    async fn record_client_status(
+        &self,
+        request_id: &ModelRequestId,
+        client_status_code: u16,
+    ) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::RecordClientStatus {
+            request_id: request_id.clone(),
+            client_status_code,
+        });
+        Ok(())
+    }
+
+    async fn record_intermediate_failure(
+        &self,
+        failure: IntermediateFailure,
+    ) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::IntermediateFailure(Box::new(
+            failure,
+        )));
+        Ok(())
+    }
+
+    async fn record_probe_failure(&self, failure: ProbeFailure) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::ProbeFailure(Box::new(failure)));
+        Ok(())
+    }
+
+    async fn finalize_model_request(
+        &self,
+        finalization: ModelRequestFinalization,
+    ) -> Result<(), StoreError> {
+        self.enqueue(ExecutionObservationWrite::Finalize(Box::new(finalization)));
+        Ok(())
+    }
+
+    async fn recover_expired(&self, now: SystemTime) -> Result<RecoveryReport, StoreError> {
+        self.inner.recover_expired(now).await
+    }
+}
+
+/// 由 Host 监督的单消费者，保证同一请求的观测命令按入队顺序落库。
+pub struct ExecutionObservationWriter<S: ?Sized> {
+    inner: Arc<S>,
+    receiver: Mutex<mpsc::Receiver<QueuedExecutionObservation>>,
+    state: Arc<ExecutionBufferState>,
+}
+
+impl<S: ?Sized> ExecutionObservationWriter<S> {
+    #[must_use]
+    pub fn stats(&self) -> ExecutionBufferStats {
+        self.state.snapshot()
+    }
+}
+
+impl<S> DaemonTask for ExecutionObservationWriter<S>
+where
+    S: ExecutionStore + ?Sized,
+{
+    fn run(
+        &self,
+        cancellation: CancellationToken,
+    ) -> futures::future::BoxFuture<'_, Result<(), WorkerTaskError>> {
+        Box::pin(async move {
+            let mut receiver = self.receiver.lock().await;
+            loop {
+                let queued = tokio::select! {
+                    () = cancellation.cancelled() => {
+                        drain_on_shutdown(
+                            &mut receiver,
+                            self.inner.as_ref(),
+                            self.state.as_ref(),
+                        ).await;
+                        return Ok(());
+                    },
+                    queued = receiver.recv() => queued,
+                };
+                let Some(queued) = queued else {
+                    return Err(WorkerTaskError::safe("execution observation queue closed"));
+                };
+                persist_queued(queued, self.inner.as_ref()).await;
+            }
+        })
+    }
+}
+
+async fn persist_queued<S>(mut queued: QueuedExecutionObservation, store: &S)
+where
+    S: ExecutionStore + ?Sized,
+{
+    let operation = queued.operation();
+    let request_id = queued.request_id().map(ToOwned::to_owned);
+    let state = Arc::clone(&queued.state);
+    let Some(write) = queued.take_write() else {
+        state.record_write_failure();
+        tracing::error!(
+            operation,
+            request_id = ?request_id,
+            "执行观测队列内部状态无效，已丢弃本次写入"
+        );
+        return;
+    };
+    // Store 写入没有统一幂等键；超时可能表示已提交，不能在这里盲目重试并
+    // 制造重复 ops_events。失败会被计数并丢弃，数据面始终不等待补偿。
+    match write.persist(store).await {
+        Ok(()) => state.record_persisted(),
+        Err(error) => {
+            state.record_write_failure();
+            let stats = state.snapshot();
+            tracing::warn!(
+                operation,
+                request_id = ?request_id,
+                error_kind = ?error.kind(),
+                write_failure_total = stats.write_failure_total,
+                "执行观测写入失败，数据面不受影响"
+            );
+        }
+    }
+}
+
+async fn drain_on_shutdown<S>(
+    receiver: &mut mpsc::Receiver<QueuedExecutionObservation>,
+    store: &S,
+    state: &ExecutionBufferState,
+) where
+    S: ExecutionStore + ?Sized,
+{
+    receiver.close();
+    let queued_at_shutdown = receiver.len();
+    let started_at = Instant::now();
+    let mut dropped = 0_usize;
+
+    while let Some(queued) = receiver.recv().await {
+        let remaining = SHUTDOWN_DRAIN_TIMEOUT.saturating_sub(started_at.elapsed());
+        if remaining.is_zero() {
+            drop(queued);
+            dropped = dropped.saturating_add(1);
+            break;
+        }
+        if tokio::time::timeout(remaining, persist_queued(queued, store))
+            .await
+            .is_err()
+        {
+            dropped = dropped.saturating_add(1);
+            break;
+        }
+    }
+    while let Ok(queued) = receiver.try_recv() {
+        drop(queued);
+        dropped = dropped.saturating_add(1);
+    }
+
+    if dropped > 0 {
+        state.record_dropped(dropped);
+        let stats = state.snapshot();
+        tracing::warn!(
+            queued_at_shutdown,
+            dropped,
+            dropped_total = stats.dropped_total,
+            drain_timeout_ms =
+                u64::try_from(SHUTDOWN_DRAIN_TIMEOUT.as_millis()).unwrap_or(u64::MAX),
+            "执行观测队列关闭排空超时，剩余写入已丢弃"
+        );
+    } else if queued_at_shutdown > 0 {
+        tracing::info!(queued_at_shutdown, "执行观测队列已在关闭前排空");
+    }
+}
+
+struct QueuedExecutionObservation {
+    write: Option<ExecutionObservationWrite>,
+    operation: &'static str,
+    request_id: Option<String>,
+    estimated_bytes: usize,
+    state: Arc<ExecutionBufferState>,
+}
+
+impl QueuedExecutionObservation {
+    fn new(
+        write: ExecutionObservationWrite,
+        estimated_bytes: usize,
+        state: Arc<ExecutionBufferState>,
+    ) -> Self {
+        let operation = write.operation();
+        let request_id = write.request_id().map(ToOwned::to_owned);
+        Self {
+            write: Some(write),
+            operation,
+            request_id,
+            estimated_bytes,
+            state,
+        }
+    }
+
+    fn operation(&self) -> &'static str {
+        self.operation
+    }
+
+    fn request_id(&self) -> Option<&str> {
+        self.request_id.as_deref()
+    }
+
+    fn take_write(&mut self) -> Option<ExecutionObservationWrite> {
+        self.write.take()
+    }
+}
+
+impl Drop for QueuedExecutionObservation {
+    fn drop(&mut self) {
+        self.state.release(self.estimated_bytes);
+    }
+}
+
+enum ExecutionObservationWrite {
+    Create(Box<NewModelRequest>),
+    Attempt(Box<AttemptRecord>),
+    CreateWithAttempt(Box<(NewModelRequest, AttemptRecord)>),
+    MarkSendState {
+        request_id: ModelRequestId,
+        state: UpstreamSendState,
+    },
+    MarkDownstreamCommitted {
+        request_id: ModelRequestId,
+        committed_at: SystemTime,
+        client_status_code: Option<u16>,
+    },
+    RecordClientStatus {
+        request_id: ModelRequestId,
+        client_status_code: u16,
+    },
+    IntermediateFailure(Box<IntermediateFailure>),
+    ProbeFailure(Box<ProbeFailure>),
+    Finalize(Box<ModelRequestFinalization>),
+}
+
+impl ExecutionObservationWrite {
+    const fn operation(&self) -> &'static str {
+        match self {
+            Self::Create(_) => "create_model_request",
+            Self::Attempt(_) => "record_attempt",
+            Self::CreateWithAttempt(_) => "create_model_request_with_attempt",
+            Self::MarkSendState { .. } => "mark_send_state",
+            Self::MarkDownstreamCommitted { .. } => "mark_downstream_committed",
+            Self::RecordClientStatus { .. } => "record_client_status",
+            Self::IntermediateFailure(_) => "record_intermediate_failure",
+            Self::ProbeFailure(_) => "record_probe_failure",
+            Self::Finalize(_) => "finalize_model_request",
+        }
+    }
+
+    fn request_id(&self) -> Option<&str> {
+        match self {
+            Self::Create(request) => Some(request.id.as_str()),
+            Self::Attempt(attempt) => Some(attempt.request_id.as_str()),
+            Self::CreateWithAttempt(write) => Some(write.0.id.as_str()),
+            Self::MarkSendState { request_id, .. }
+            | Self::MarkDownstreamCommitted { request_id, .. }
+            | Self::RecordClientStatus { request_id, .. } => Some(request_id.as_str()),
+            Self::IntermediateFailure(failure) => Some(failure.request_id.as_str()),
+            Self::ProbeFailure(_) => None,
+            Self::Finalize(finalization) => Some(finalization.request_id.as_str()),
+        }
+    }
+
+    fn estimated_bytes(&self) -> usize {
+        size_of::<Self>().saturating_add(match self {
+            Self::Create(request) => new_request_bytes(request),
+            Self::Attempt(attempt) => attempt_bytes(attempt),
+            Self::CreateWithAttempt(write) => {
+                new_request_bytes(&write.0).saturating_add(attempt_bytes(&write.1))
+            }
+            Self::MarkSendState { request_id, .. }
+            | Self::MarkDownstreamCommitted { request_id, .. }
+            | Self::RecordClientStatus { request_id, .. } => request_id.as_str().len(),
+            Self::IntermediateFailure(failure) => text_bytes([
+                Some(failure.request_id.as_str()),
+                Some(failure.provider_kind.as_str()),
+                failure.account_id.as_ref().map(|value| value.as_str()),
+                Some(failure.upstream_model_id.as_str()),
+                failure.upstream_request_id.as_deref(),
+            ])
+            .saturating_add(provider_error_bytes(&failure.error)),
+            Self::ProbeFailure(failure) => text_bytes([
+                Some(failure.provider_kind.as_str()),
+                Some(failure.account_id.as_str()),
+                Some(failure.upstream_model_id.as_str()),
+            ])
+            .saturating_add(provider_error_bytes(&failure.error)),
+            Self::Finalize(finalization) => {
+                let error_bytes = finalization.error.as_ref().map_or(0, |error| {
+                    text_bytes([
+                        Some(error.client_message()),
+                        error.client_error_code(),
+                        error.client_error_type(),
+                    ])
+                });
+                text_bytes([
+                    Some(finalization.request_id.as_str()),
+                    finalization.client_response_id.as_deref(),
+                    finalization.upstream_request_id.as_deref(),
+                    finalization.upstream_response_id.as_deref(),
+                    finalization.upstream_transport.as_deref(),
+                    finalization.http_version.as_deref(),
+                    finalization.websocket_pool.as_deref(),
+                    finalization.service_tier.as_deref(),
+                    finalization.provider_metadata_json.as_deref(),
+                    finalization.provider_error_code.as_deref(),
+                ])
+                .saturating_add(error_bytes)
+                .saturating_add(size_of::<ModelRequestFinalization>())
+            }
+        })
+    }
+
+    async fn persist<S>(self, store: &S) -> Result<(), StoreError>
+    where
+        S: ExecutionStore + ?Sized,
+    {
+        match self {
+            Self::Create(request) => store.create_model_request(*request).await,
+            Self::Attempt(attempt) => store.record_attempt(*attempt).await,
+            Self::CreateWithAttempt(write) => {
+                let (request, attempt) = *write;
+                store
+                    .create_model_request_with_attempt(request, attempt)
+                    .await
+            }
+            Self::MarkSendState { request_id, state } => {
+                store.mark_send_state(&request_id, state).await
+            }
+            Self::MarkDownstreamCommitted {
+                request_id,
+                committed_at,
+                client_status_code,
+            } => {
+                store
+                    .mark_downstream_committed(&request_id, committed_at, client_status_code)
+                    .await
+            }
+            Self::RecordClientStatus {
+                request_id,
+                client_status_code,
+            } => {
+                store
+                    .record_client_status(&request_id, client_status_code)
+                    .await
+            }
+            Self::IntermediateFailure(failure) => store.record_intermediate_failure(*failure).await,
+            Self::ProbeFailure(failure) => store.record_probe_failure(*failure).await,
+            Self::Finalize(finalization) => store.finalize_model_request(*finalization).await,
+        }
+    }
+}
+
+fn new_request_bytes(request: &NewModelRequest) -> usize {
+    size_of::<NewModelRequest>().saturating_add(text_bytes([
+        Some(request.id.as_str()),
+        request
+            .client_api_key_id
+            .as_ref()
+            .map(|value| value.as_str()),
+        Some(request.client_api_key_ref.as_str()),
+        Some(request.protocol.as_str()),
+        Some(request.endpoint.as_str()),
+        Some(request.client_transport.as_str()),
+        Some(request.requested_model.as_str()),
+        request.user_agent.as_deref(),
+        request.reasoning_effort.as_deref(),
+        request.reasoning_preset.as_deref(),
+        request.request_kind.as_deref(),
+        request.subagent_kind.as_deref(),
+    ]))
+}
+
+fn attempt_bytes(attempt: &AttemptRecord) -> usize {
+    size_of::<AttemptRecord>().saturating_add(text_bytes([
+        Some(attempt.request_id.as_str()),
+        Some(attempt.provider_kind.as_str()),
+        attempt
+            .provider_account_id
+            .as_ref()
+            .map(|value| value.as_str()),
+        attempt
+            .provider_account_ref
+            .as_ref()
+            .map(|value| value.as_str()),
+        Some(attempt.upstream_model_id.as_str()),
+        Some(attempt.upstream_transport.as_str()),
+        attempt.http_version.as_deref(),
+    ]))
+}
+
+fn provider_error_bytes(error: &ProviderError) -> usize {
+    let mut bytes = text_bytes([
+        error.upstream_code().map(|value| value.as_str()),
+        error.upstream_request_id().map(|value| value.as_str()),
+        error.upstream_response_id().map(|value| value.as_str()),
+    ]);
+    if let Some(client_error) = error.client_visible_upstream_error() {
+        bytes = bytes.saturating_add(text_bytes([
+            Some(client_error.message()),
+            client_error.code(),
+            client_error.error_type(),
+        ]));
+    }
+    if let Some(response) = error.client_visible_upstream_response() {
+        bytes = bytes
+            .saturating_add(response.body().len())
+            .saturating_add(response.content_type().map_or(0, <[u8]>::len));
+        for header in response.headers() {
+            bytes = bytes
+                .saturating_add(header.name().len())
+                .saturating_add(header.value().len());
+        }
+    }
+    bytes
+}
+
+fn text_bytes<const N: usize>(values: [Option<&str>; N]) -> usize {
+    values
+        .into_iter()
+        .flatten()
+        .fold(0, |total, value| total.saturating_add(value.len()))
+}
@@ -11,6 +11,7 @@ mod admin_security_audit;
 mod admission_recovery;
 mod client_keys;
 mod execution;
+mod execution_buffer;
 mod observability;
 mod ops_events;
 mod provider_accounts;
@@ -22,6 +23,7 @@ pub use admin_security_audit::*;
 pub use admission_recovery::*;
 pub use client_keys::*;
 pub use execution::*;
+pub use execution_buffer::*;
 pub use observability::*;
 pub use ops_events::*;
 pub use provider_accounts::*;
@@ -74,27 +76,23 @@ pub trait ControlPlaneRepository: Send + Sync {

    async fn replace_control_plane(
        &self,
-        expected_revision: Revision,
        replacement: ControlPlaneReplacement,
    ) -> StoreResult<ControlPlaneSnapshot>;

    async fn create_client_api_key(
        &self,
-        expected_revision: Revision,
        key: NewClientApiKey,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision>;

    async fn update_client_api_key(
        &self,
-        expected_revision: Revision,
        key: UpdateClientApiKeyDetails,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision>;

    async fn set_client_api_key_enabled(
        &self,
-        expected_revision: Revision,
        id: &str,
        enabled: bool,
        audit: AdminAuditEvent,
@@ -102,7 +100,6 @@ pub trait ControlPlaneRepository: Send + Sync {

    async fn delete_client_api_key(
        &self,
-        expected_revision: Revision,
        id: &str,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision>;
@@ -142,7 +139,6 @@ impl ControlPlaneRepository for PgControlPlaneRepository {

    async fn replace_control_plane(
        &self,
-        expected_revision: Revision,
        replacement: ControlPlaneReplacement,
    ) -> StoreResult<ControlPlaneSnapshot> {
        replacement.settings.validate()?;
@@ -152,12 +148,9 @@ impl ControlPlaneRepository for PgControlPlaneRepository {
            .await
            .map_err(|_| postgres_unavailable("begin control plane replacement"))?;
        let result = async {
-            let revision = update_runtime_settings_in_transaction(
-                &mut transaction,
-                expected_revision,
-                &replacement.settings,
-            )
-            .await?;
+            let revision =
+                update_runtime_settings_in_transaction(&mut transaction, &replacement.settings)
+                    .await?;
            append_admin_audit_event_in_transaction(&mut transaction, replacement.audit, revision)
                .await?;
            load_control_plane_in_transaction(&mut transaction).await
@@ -183,41 +176,29 @@ impl ControlPlaneRepository for PgControlPlaneRepository {

    async fn create_client_api_key(
        &self,
-        expected_revision: Revision,
        key: NewClientApiKey,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision> {
-        self.apply_targeted_mutation(
-            expected_revision,
-            ControlPlaneMutation::CreateClientApiKey(key),
-            audit,
-        )
-        .await
+        self.apply_targeted_mutation(ControlPlaneMutation::CreateClientApiKey(key), audit)
+            .await
    }

    async fn update_client_api_key(
        &self,
-        expected_revision: Revision,
        key: UpdateClientApiKeyDetails,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision> {
-        self.apply_targeted_mutation(
-            expected_revision,
-            ControlPlaneMutation::UpdateClientApiKey(key),
-            audit,
-        )
-        .await
+        self.apply_targeted_mutation(ControlPlaneMutation::UpdateClientApiKey(key), audit)
+            .await
    }

    async fn set_client_api_key_enabled(
        &self,
-        expected_revision: Revision,
        id: &str,
        enabled: bool,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision> {
        self.apply_targeted_mutation(
-            expected_revision,
            ControlPlaneMutation::SetClientApiKeyEnabled {
                id: id.to_owned(),
                enabled,
@@ -229,12 +210,10 @@ impl ControlPlaneRepository for PgControlPlaneRepository {

    async fn delete_client_api_key(
        &self,
-        expected_revision: Revision,
        id: &str,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision> {
        self.apply_targeted_mutation(
-            expected_revision,
            ControlPlaneMutation::DeleteClientApiKey(id.to_owned()),
            audit,
        )
@@ -252,7 +231,6 @@ enum ControlPlaneMutation {
 impl PgControlPlaneRepository {
    async fn apply_targeted_mutation(
        &self,
-        expected_revision: Revision,
        mutation: ControlPlaneMutation,
        audit: AdminAuditEvent,
    ) -> StoreResult<Revision> {
@@ -262,8 +240,7 @@ impl PgControlPlaneRepository {
            .await
            .map_err(|_| postgres_unavailable("begin targeted control plane mutation"))?;
        let result = async {
-            let revision =
-                bump_config_revision_in_transaction(&mut transaction, expected_revision).await?;
+            let revision = bump_config_revision_in_transaction(&mut transaction).await?;
            match mutation {
                ControlPlaneMutation::CreateClientApiKey(key) => {
                    insert_client_api_key_in_transaction(&mut transaction, &key).await?;
@@ -125,7 +125,6 @@ impl UsageRecordFilter {
            (self.model.as_deref(), "model filter"),
            (self.outcome.as_deref(), "outcome filter"),
            (self.transport.as_deref(), "transport filter"),
-            (self.response_id.as_deref(), "response ID filter"),
            (
                self.upstream_request_id.as_deref(),
                "upstream request ID filter",
@@ -189,7 +188,6 @@ impl OpsErrorFilter {
            (self.operation.as_deref(), "operation filter"),
            (self.model.as_deref(), "model filter"),
            (self.transport.as_deref(), "transport filter"),
-            (self.response_id.as_deref(), "response ID filter"),
            (
                self.upstream_request_id.as_deref(),
                "upstream request ID filter",
@@ -371,6 +369,7 @@ pub struct CalculatedUsageBillingFact {
    pub bucket_start: DateTime<Utc>,
    pub provider_kind: String,
    pub upstream_model_id: String,
+    pub service_tier: Option<String>,
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
    pub cached_tokens: Option<u64>,
@@ -523,6 +522,7 @@ pub struct UsageRecord {
    pub upstream_transport: Option<String>,
    pub http_version: Option<String>,
    pub websocket_pool: Option<String>,
+    pub service_tier: Option<String>,
    pub provider_metadata_json: Option<String>,
    pub attempt_count: u32,
    pub upstream_send_state: String,
@@ -1380,6 +1380,7 @@ fn admin_calculated_usage_billing_fact(
        bucket_start: fact.bucket_start,
        provider_kind: fact.provider_kind,
        upstream_model_id: fact.upstream_model_id,
+        service_tier: fact.service_tier,
        input_tokens: fact.input_tokens,
        output_tokens: fact.output_tokens,
        cached_tokens: fact.cached_tokens,
@@ -1455,6 +1456,7 @@ fn admin_usage_record(record: UsageRecord) -> AdminStoreResult<admin_observabili
        upstream_transport: record.upstream_transport,
        http_version: record.http_version,
        websocket_pool: record.websocket_pool,
+        service_tier: record.service_tier,
        provider_metadata_json: record.provider_metadata_json,
        attempt_count: record.attempt_count,
        upstream_send_state: record.upstream_send_state,
@@ -1814,7 +1816,7 @@ async fn calculated_usage_billing_facts(
    query.push_bind(granularity.sql_interval());
    query.push(
        "::interval, mr.started_at, timestamptz '1970-01-01 00:00:00+00') as bucket_start,
-                mr.provider_kind, mr.upstream_model_id,
+                mr.provider_kind, mr.upstream_model_id, mr.service_tier,
                mr.input_tokens, mr.output_tokens, mr.cached_tokens, mr.cache_write_tokens,
                mr.cost_currency, mr.cost_amount::text as amount
         from model_requests mr where mr.started_at >= ",
@@ -1990,27 +1992,35 @@ async fn provider_account_metrics(
    observed_at: DateTime<Utc>,
 ) -> StoreResult<ProviderAccountMetrics> {
    let row = sqlx::query(
-        "select count(*)::bigint as total,
+        "with normalized as (
+           select enabled,
+                  case
+                    when not enabled then 'disabled'
+                    when availability = 'banned' then 'banned'
+                    when availability = 'quota_exhausted'
+                      or (
+                        availability = 'cooldown'
+                        and availability_reason = 'usage_limit_exhausted'
+                        and (cooldown_until is null or cooldown_until > $1)
+                      )
+                      then 'quota_exhausted'
+                    when availability in ('expired', 'invalid')
+                      or (access_token_expires_at is not null and access_token_expires_at <= $1)
+                      then 'expired'
+                    else 'active'
+                  end as status
+             from provider_accounts
+         )
+         select count(*)::bigint as total,
                count(*) filter (where enabled)::bigint as enabled,
-                count(*) filter (
-                  where not (
-                    enabled and availability = 'ready'
-                      and (access_token_expires_at is null or access_token_expires_at > $1)
-                  )
-                )::bigint as unavailable,
-                count(*) filter (
-                  where enabled and availability = 'ready'
-                    and (access_token_expires_at is null or access_token_expires_at > $1)
-                )::bigint as active,
-                count(*) filter (
-                  where availability = 'expired'
-                    or (access_token_expires_at is not null and access_token_expires_at <= $1)
-                )::bigint as expired,
-                count(*) filter (where availability = 'quota_exhausted')::bigint
-                  as quota_exhausted,
-                count(*) filter (where not enabled)::bigint as disabled,
-                count(*) filter (where availability = 'banned')::bigint as banned
-         from provider_accounts",
+                count(*) filter (where status in ('expired', 'disabled', 'banned'))::bigint
+                  as unavailable,
+                count(*) filter (where status = 'active')::bigint as active,
+                count(*) filter (where status = 'expired')::bigint as expired,
+                count(*) filter (where status = 'quota_exhausted')::bigint as quota_exhausted,
+                count(*) filter (where status = 'disabled')::bigint as disabled,
+                count(*) filter (where status = 'banned')::bigint as banned
+           from normalized",
    )
    .bind(observed_at)
    .fetch_one(pool)
@@ -2033,11 +2043,29 @@ async fn active_provider_account_ids(
    observed_at: DateTime<Utc>,
 ) -> StoreResult<Vec<String>> {
    sqlx::query(
-        "select id
-         from provider_accounts
-         where enabled and availability = 'ready'
-           and (access_token_expires_at is null or access_token_expires_at > $1)
-         order by id",
+        "with normalized as (
+           select id,
+                  case
+                    when not enabled then 'disabled'
+                    when availability = 'banned' then 'banned'
+                    when availability = 'quota_exhausted'
+                      or (
+                        availability = 'cooldown'
+                        and availability_reason = 'usage_limit_exhausted'
+                        and (cooldown_until is null or cooldown_until > $1)
+                      )
+                      then 'quota_exhausted'
+                    when availability in ('expired', 'invalid')
+                      or (access_token_expires_at is not null and access_token_expires_at <= $1)
+                      then 'expired'
+                    else 'active'
+                  end as status
+             from provider_accounts
+         )
+         select id
+           from normalized
+          where status = 'active'
+          order by id",
    )
    .bind(observed_at)
    .fetch_all(pool)
@@ -2234,9 +2262,9 @@ fn push_usage_filter(query: &mut QueryBuilder<Postgres>, filter: &UsageRecordFil
    }
    if let Some(value) = &filter.response_id {
        query.push(format!(" and ({alias}.client_response_id = "));
-        query.push_bind(value.clone());
+        query.push_bind(value.as_bytes().to_vec());
        query.push(format!(" or {alias}.upstream_response_id = "));
-        query.push_bind(value.clone());
+        query.push_bind(value.as_bytes().to_vec());
        query.push(")");
    }
    if let Some(value) = &filter.upstream_request_id {
@@ -2248,7 +2276,7 @@ fn push_usage_filter(query: &mut QueryBuilder<Postgres>, filter: &UsageRecordFil
            " and lower(concat_ws(' ', {alias}.id, {alias}.client_api_key_ref,
                    {alias}.requested_model_id, {alias}.provider_kind,
                    {alias}.provider_account_ref, {alias}.upstream_model_id,
-                    {alias}.client_response_id, {alias}.upstream_request_id,
+                    encode({alias}.client_response_id, 'escape'), {alias}.upstream_request_id,
                    {alias}.error_kind, {alias}.provider_error_code,
                    {alias}.error_message)) like "
        ));
@@ -2611,7 +2639,7 @@ const USAGE_RECORD_SELECT: &str =
            pa.name as provider_account_name, pa.email as provider_account_email,
            pa.authentication_kind as provider_account_authentication_kind,
            mr.upstream_model_id, mr.upstream_transport, mr.http_version, mr.websocket_pool,
-            mr.provider_observation_json,
+            mr.service_tier, mr.provider_observation_json,
            mr.attempt_count, mr.upstream_send_state, mr.downstream_committed_at,
            mr.outcome, mr.client_status_code, mr.upstream_status_code,
            mr.client_response_id, mr.upstream_request_id, mr.upstream_response_id,
@@ -3055,7 +3083,6 @@ fn push_ops_filter(statement: &mut QueryBuilder<Postgres>, filter: &OpsErrorFilt
        ("provider_kind", &filter.provider_kind),
        ("operation", &filter.operation),
        ("upstream_transport", &filter.transport),
-        ("client_response_id", &filter.response_id),
        ("upstream_request_id", &filter.upstream_request_id),
        ("failure_kind", &filter.failure_kind),
    ] {
@@ -3064,6 +3091,10 @@ fn push_ops_filter(statement: &mut QueryBuilder<Postgres>, filter: &OpsErrorFilt
            statement.push_bind(value.clone());
        }
    }
+    if let Some(value) = &filter.response_id {
+        statement.push(" and e.client_response_id = ");
+        statement.push_bind(value.as_bytes().to_vec());
+    }
    if let Some(model) = &filter.model {
        statement.push(" and e.upstream_model_id = ");
        statement.push_bind(model.clone());
@@ -3106,6 +3137,7 @@ fn usage_record_from_row(row: &sqlx::postgres::PgRow) -> StoreResult<UsageRecord
        upstream_transport: get(row, "upstream_transport")?,
        http_version: get(row, "http_version")?,
        websocket_pool: get(row, "websocket_pool")?,
+        service_tier: get(row, "service_tier")?,
        provider_metadata_json: get::<Option<serde_json::Value>>(row, "provider_observation_json")?
            .map(|value| serde_json::to_string(&value))
            .transpose()
@@ -3116,9 +3148,9 @@ fn usage_record_from_row(row: &sqlx::postgres::PgRow) -> StoreResult<UsageRecord
        outcome: get(row, "outcome")?,
        client_status_code: optional_status(row, "client_status_code")?,
        upstream_status_code: optional_status(row, "upstream_status_code")?,
-        client_response_id: get(row, "client_response_id")?,
+        client_response_id: opaque_response_id(row, "client_response_id")?,
        upstream_request_id: get(row, "upstream_request_id")?,
-        upstream_response_id: get(row, "upstream_response_id")?,
+        upstream_response_id: opaque_response_id(row, "upstream_response_id")?,
        error_kind: get(row, "error_kind")?,
        provider_error_code: get(row, "provider_error_code")?,
        error_message: get(row, "error_message")?,
@@ -3177,7 +3209,7 @@ fn ops_error_from_row(row: &sqlx::postgres::PgRow) -> StoreResult<OpsErrorRecord
        client_status_code: optional_status(row, "client_status_code")?,
        upstream_status_code: optional_status(row, "upstream_status_code")?,
        provider_error_code: get(row, "provider_error_code")?,
-        client_response_id: get(row, "client_response_id")?,
+        client_response_id: opaque_response_id(row, "client_response_id")?,
        upstream_request_id: get(row, "upstream_request_id")?,
        latency_ms: optional_unsigned(row, "latency_ms")?,
        message: get(row, "message")?,
@@ -3201,6 +3233,7 @@ fn calculated_usage_billing_fact_from_row(
        bucket_start: get(row, "bucket_start")?,
        provider_kind: get(row, "provider_kind")?,
        upstream_model_id: get(row, "upstream_model_id")?,
+        service_tier: get(row, "service_tier")?,
        input_tokens: optional_unsigned(row, "input_tokens")?,
        output_tokens: optional_unsigned(row, "output_tokens")?,
        cached_tokens: optional_unsigned(row, "cached_tokens")?,
@@ -3218,6 +3251,16 @@ fn optional_decimal(
        .transpose()
 }

+fn opaque_response_id(
+    row: &sqlx::postgres::PgRow,
+    column: &'static str,
+) -> StoreResult<Option<String>> {
+    get::<Option<Vec<u8>>>(row, column)?
+        .map(String::from_utf8)
+        .transpose()
+        .map_err(|_| invalid(column))
+}
+
 fn validate_account_ids(account_ids: &[String]) -> StoreResult<()> {
    let mut unique = BTreeSet::new();
    for account_id in account_ids {
@@ -12,8 +12,7 @@ use gateway_admin::{
    model::{
        MutationContext, Revision as AdminRevision,
        accounts::{
-            AccountAvailability as AdminAccountAvailability, AccountCost,
-            AccountListQuery as AdminAccountListQuery, AccountModelUsage, AccountPage,
+            AccountCost, AccountListQuery as AdminAccountListQuery, AccountModelUsage, AccountPage,
            AccountRecord, AccountRequestBucket, AccountSort as AdminAccountSort,
            AccountSortField as AdminAccountSortField, AccountStatus as AdminAccountStatus,
            AccountSummary, AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult,
@@ -35,12 +34,12 @@ use gateway_admin::{
 use sqlx::{PgPool, Postgres, Row, Transaction};

 use gateway_core::engine::credential::{
-    AccountAvailability as CoreAccountAvailability, AccountStateChange, CredentialCasOutcome,
-    CredentialCasUpdate, CredentialRevision as CoreCredentialRevision, LoadedCredential,
+    AccountAvailability, AccountStateChange, CredentialCasOutcome, CredentialCasUpdate,
+    CredentialRevision as CoreCredentialRevision, LoadedCredential,
    NewProviderAccount as CoreNewProviderAccount, OpaqueProviderData, PlaintextCredential,
    ProviderAccount as CoreProviderAccount, ProviderAccountId as CoreProviderAccountId,
-    ProviderAccountStore, ProviderAccountUpdate as CoreProviderAccountUpdate, QuotaObservation,
-    QuotaWriteOutcome,
+    ProviderAccountIdentity, ProviderAccountStore,
+    ProviderAccountUpdate as CoreProviderAccountUpdate, QuotaObservation, QuotaWriteOutcome,
 };
 use gateway_core::error::{StoreError as CoreStoreError, StoreErrorKind as CoreStoreErrorKind};
 use gateway_core::routing::ProviderKind;
@@ -121,43 +120,29 @@ impl ProviderAccountAdminScope {
    }
 }

-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum ProviderAccountAvailability {
-    Unknown,
-    Ready,
-    Cooldown,
-    QuotaExhausted,
-    Expired,
-    Banned,
-    Invalid,
+/// 解析数据库 availability 列；字符串映射本体唯一归属 gateway-core。
+fn parse_availability(value: &str) -> StoreResult<AccountAvailability> {
+    AccountAvailability::parse(value).ok_or_else(|| invalid("unknown availability value"))
 }

-impl ProviderAccountAvailability {
-    #[must_use]
-    pub const fn as_str(self) -> &'static str {
-        match self {
-            Self::Unknown => "unknown",
-            Self::Ready => "ready",
-            Self::Cooldown => "cooldown",
-            Self::QuotaExhausted => "quota_exhausted",
-            Self::Expired => "expired",
-            Self::Banned => "banned",
-            Self::Invalid => "invalid",
-        }
+fn validate_availability_cooldown(
+    availability: AccountAvailability,
+    has_cooldown_until: bool,
+) -> StoreResult<()> {
+    if availability == AccountAvailability::Cooldown && !has_cooldown_until {
+        return Err(invalid("cooldown availability requires cooldown_until"));
    }
-
-    fn parse(value: &str) -> StoreResult<Self> {
-        match value {
-            "unknown" => Ok(Self::Unknown),
-            "ready" => Ok(Self::Ready),
-            "cooldown" => Ok(Self::Cooldown),
-            "quota_exhausted" => Ok(Self::QuotaExhausted),
-            "expired" => Ok(Self::Expired),
-            "banned" => Ok(Self::Banned),
-            "invalid" => Ok(Self::Invalid),
-            _ => Err(invalid("unknown availability value")),
-        }
+    if has_cooldown_until
+        && !matches!(
+            availability,
+            AccountAvailability::Cooldown | AccountAvailability::QuotaExhausted
+        )
+    {
+        return Err(invalid(
+            "cooldown_until is only allowed for cooldown or quota_exhausted availability",
+        ));
    }
+    Ok(())
 }

 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -175,7 +160,7 @@ pub struct ProviderAccountSummary {
    pub access_token_expires_at: Option<DateTime<Utc>>,
    pub next_refresh_at: Option<DateTime<Utc>>,
    pub enabled: bool,
-    pub availability: ProviderAccountAvailability,
+    pub availability: AccountAvailability,
    pub availability_reason: Option<String>,
    pub cooldown_until: Option<DateTime<Utc>>,
    pub availability_observed_at: DateTime<Utc>,
@@ -220,7 +205,7 @@ pub struct NewProviderAccount {
    pub access_token_expires_at: Option<DateTime<Utc>>,
    pub next_refresh_at: Option<DateTime<Utc>>,
    pub enabled: bool,
-    pub availability: ProviderAccountAvailability,
+    pub availability: AccountAvailability,
    pub availability_reason: Option<String>,
    pub cooldown_until: Option<DateTime<Utc>>,
    pub availability_observed_at: DateTime<Utc>,
@@ -259,13 +244,7 @@ impl NewProviderAccount {
        if !self.has_refresh_token && self.next_refresh_at.is_some() {
            return Err(invalid("next_refresh_at requires a refresh token"));
        }
-        if (self.availability == ProviderAccountAvailability::Cooldown)
-            != self.cooldown_until.is_some()
-        {
-            return Err(invalid(
-                "cooldown_until must be present exactly for cooldown availability",
-            ));
-        }
+        validate_availability_cooldown(self.availability, self.cooldown_until.is_some())?;
        validate_object_size(
            "provider_credentials_json",
            &self.provider_credentials_json,
@@ -333,6 +312,7 @@ impl ImportProviderAccounts {
 pub struct RotateProviderAccount {
    pub scope: ProviderAccountAdminScope,
    pub profile: UpdateProviderAccount,
+    pub replacement_identity: Option<ProviderAccountIdentity>,
    pub credential: ProviderCredentialUpdate,
    pub audit: AdminAuditEvent,
 }
@@ -343,6 +323,7 @@ impl fmt::Debug for RotateProviderAccount {
            .debug_struct("RotateProviderAccount")
            .field("scope", &self.scope)
            .field("profile", &self.profile)
+            .field("replacement_identity", &self.replacement_identity)
            .field("credential", &self.credential)
            .field("audit", &self.audit)
            .finish()
@@ -394,7 +375,7 @@ impl fmt::Debug for ProviderCredentialUpdate {
 #[derive(Debug, Clone, PartialEq)]
 pub struct ProviderAccountObservation {
    pub account_id: String,
-    pub availability: ProviderAccountAvailability,
+    pub availability: AccountAvailability,
    pub availability_reason: Option<String>,
    pub cooldown_until: Option<DateTime<Utc>>,
    pub provider_quota_json: Option<JsonObject>,
@@ -406,7 +387,7 @@ pub struct ProviderAccountObservation {
 pub struct ProviderAccountStateUpdate {
    pub account_id: String,
    pub expected_revision: Revision,
-    pub availability: ProviderAccountAvailability,
+    pub availability: AccountAvailability,
    pub availability_reason: Option<String>,
    pub cooldown_until: Option<DateTime<Utc>>,
    pub availability_observed_at: DateTime<Utc>,
@@ -415,13 +396,7 @@ pub struct ProviderAccountStateUpdate {
 impl ProviderAccountStateUpdate {
    pub fn validate(&self) -> StoreResult<()> {
        require_nonempty(ENTITY, "account_id", &self.account_id)?;
-        if (self.availability == ProviderAccountAvailability::Cooldown)
-            != self.cooldown_until.is_some()
-        {
-            return Err(invalid(
-                "cooldown availability and cooldown_until must agree",
-            ));
-        }
+        validate_availability_cooldown(self.availability, self.cooldown_until.is_some())?;
        Ok(())
    }
 }
@@ -429,13 +404,7 @@ impl ProviderAccountStateUpdate {
 impl ProviderAccountObservation {
    pub fn validate(&self) -> StoreResult<()> {
        require_nonempty(ENTITY, "account_id", &self.account_id)?;
-        if (self.availability == ProviderAccountAvailability::Cooldown)
-            != self.cooldown_until.is_some()
-        {
-            return Err(invalid(
-                "cooldown availability and cooldown_until must agree",
-            ));
-        }
+        validate_availability_cooldown(self.availability, self.cooldown_until.is_some())?;
        if self.provider_quota_json.is_some() != self.quota_observed_at.is_some() {
            return Err(invalid("quota JSON and quota_observed_at must agree"));
        }
@@ -485,25 +454,21 @@ pub trait ProviderAccountAdminRepository: Send + Sync {

    async fn import_provider_accounts(
        &self,
-        expected_config_revision: Revision,
        command: ImportProviderAccounts,
    ) -> StoreResult<ProviderAccountAdminImport>;

    async fn rotate_provider_account(
        &self,
-        expected_config_revision: Revision,
        command: RotateProviderAccount,
    ) -> StoreResult<ProviderAccountAdminRotation>;

    async fn set_provider_account_enabled_admin(
        &self,
-        expected_config_revision: Revision,
        command: SetProviderAccountEnabled,
    ) -> StoreResult<Revision>;

    async fn delete_provider_accounts_admin(
        &self,
-        expected_config_revision: Revision,
        command: DeleteProviderAccounts,
    ) -> StoreResult<Revision>;
 }
@@ -657,8 +622,14 @@ impl ProviderAccountRepository for PgProviderAccountRepository {
        update.validate()?;
        let result = sqlx::query(
            "update provider_accounts
-             set availability = $3, availability_reason = $4, cooldown_until = $5,
-                 availability_observed_at = $6, updated_at = greatest(now(), $6)
+             set availability = case when enabled then $3 else availability end,
+                 availability_reason = case when enabled then $4 else availability_reason end,
+                 cooldown_until = case when enabled then $5 else cooldown_until end,
+                 availability_observed_at = case
+                     when enabled then $6
+                     else availability_observed_at
+                 end,
+                 updated_at = case when enabled then greatest(now(), $6) else updated_at end
             where id = $1 and credential_revision = $2",
        )
        .bind(update.account_id)
@@ -767,7 +738,6 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {

    async fn import_provider_accounts(
        &self,
-        expected_config_revision: Revision,
        command: ImportProviderAccounts,
    ) -> StoreResult<ProviderAccountAdminImport> {
        command.validate()?;
@@ -777,9 +747,7 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {
            .await
            .map_err(|_| postgres_unavailable("begin provider account admin import"))?;
        let result = async {
-            let revision =
-                bump_config_revision_in_transaction(&mut transaction, expected_config_revision)
-                    .await?;
+            let revision = bump_config_revision_in_transaction(&mut transaction).await?;
            let mut account_ids = Vec::with_capacity(command.accounts.len());
            for account in &command.accounts {
                account_ids
@@ -798,12 +766,17 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {

    async fn rotate_provider_account(
        &self,
-        expected_config_revision: Revision,
        command: RotateProviderAccount,
    ) -> StoreResult<ProviderAccountAdminRotation> {
        command.scope.validate()?;
        require_nonempty(ENTITY, "account_id", &command.profile.id)?;
        require_nonempty(ENTITY, "name", &command.profile.name)?;
+        if let Some(identity) = &command.replacement_identity {
+            require_nonempty(ENTITY, "upstream_user_id", identity.upstream_user_id())?;
+            if let Some(account_id) = identity.upstream_account_id() {
+                require_nonempty(ENTITY, "upstream_account_id", account_id)?;
+            }
+        }
        if command.profile.id != command.credential.account_id {
            return Err(invalid("rotated profile and credential account IDs differ"));
        }
@@ -814,13 +787,12 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {
            .await
            .map_err(|_| postgres_unavailable("begin provider account admin rotation"))?;
        let result = async {
-            let config_revision =
-                bump_config_revision_in_transaction(&mut transaction, expected_config_revision)
-                    .await?;
+            let config_revision = bump_config_revision_in_transaction(&mut transaction).await?;
            let credential_revision = rotate_provider_account_in_transaction(
                &mut transaction,
                &command.scope,
                &command.profile,
+                command.replacement_identity.as_ref(),
                &command.credential,
            )
            .await?;
@@ -841,7 +813,6 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {

    async fn set_provider_account_enabled_admin(
        &self,
-        expected_config_revision: Revision,
        command: SetProviderAccountEnabled,
    ) -> StoreResult<Revision> {
        command.scope.validate()?;
@@ -852,9 +823,7 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {
            .await
            .map_err(|_| postgres_unavailable("begin provider account admin state change"))?;
        let result = async {
-            let revision =
-                bump_config_revision_in_transaction(&mut transaction, expected_config_revision)
-                    .await?;
+            let revision = bump_config_revision_in_transaction(&mut transaction).await?;
            set_provider_account_enabled_in_transaction(
                &mut transaction,
                &command.scope,
@@ -872,7 +841,6 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {

    async fn delete_provider_accounts_admin(
        &self,
-        expected_config_revision: Revision,
        command: DeleteProviderAccounts,
    ) -> StoreResult<Revision> {
        command.scope.validate()?;
@@ -883,9 +851,7 @@ impl ProviderAccountAdminRepository for PgProviderAccountRepository {
            .await
            .map_err(|_| postgres_unavailable("begin provider account admin deletion"))?;
        let result = async {
-            let revision =
-                bump_config_revision_in_transaction(&mut transaction, expected_config_revision)
-                    .await?;
+            let revision = bump_config_revision_in_transaction(&mut transaction).await?;
            delete_provider_accounts_in_transaction(
                &mut transaction,
                &command.scope,
@@ -1032,7 +998,6 @@ impl PgAdminAccountStore {

    async fn commit_prepared_import(
        &self,
-        expected_config_revision: AdminRevision,
        prepared: PreparedCredentialImport,
        context: &MutationContext,
        action: &str,
@@ -1046,22 +1011,19 @@ impl PgAdminAccountStore {
            .map_err(|error| admin_store_error(ENTITY, error))?;
        let imported = self
            .accounts
-            .import_provider_accounts(
-                store_revision(expected_config_revision)?,
-                ImportProviderAccounts {
-                    scope: ProviderAccountAdminScope {
-                        provider_kind: provider_kind.clone(),
-                    },
-                    accounts,
-                    audit: mutation_audit(
-                        context,
-                        action,
-                        "provider_account",
-                        &provider_kind,
-                        vec!["credentials".to_owned()],
-                    ),
+            .import_provider_accounts(ImportProviderAccounts {
+                scope: ProviderAccountAdminScope {
+                    provider_kind: provider_kind.clone(),
                },
-            )
+                accounts,
+                audit: mutation_audit(
+                    context,
+                    action,
+                    "provider_account",
+                    &provider_kind,
+                    vec!["credentials".to_owned()],
+                ),
+            })
            .await
            .map_err(|error| admin_store_error(ENTITY, error))?;
        Ok(CredentialImportResult {
@@ -1083,7 +1045,6 @@ impl PgAdminAccountStore {

    async fn commit_prepared_rotation(
        &self,
-        expected_config_revision: AdminRevision,
        prepared: PreparedCredentialRotationFacts,
        context: &MutationContext,
        action: &str,
@@ -1094,36 +1055,32 @@ impl PgAdminAccountStore {
        };
        let rotation = self
            .accounts
-            .rotate_provider_account(
-                store_revision(expected_config_revision)?,
-                RotateProviderAccount {
-                    scope,
-                    profile: UpdateProviderAccount {
-                        id: account_id.as_str().to_owned(),
-                        name: prepared.name,
-                        email: prepared.email,
-                        plan_type: prepared.plan_type,
-                    },
-                    credential: ProviderCredentialUpdate {
-                        account_id: account_id.as_str().to_owned(),
-                        expected_revision: store_revision(prepared.expected_credential_revision)?,
-                        provider_credentials_json: provider_document_json(
-                            prepared.provider_material,
-                        )
-                        .map_err(|error| admin_store_error(ENTITY, error))?,
-                        has_refresh_token: prepared.has_refresh_token,
-                        access_token_expires_at: prepared.access_token_expires_at,
-                        next_refresh_at: prepared.next_refresh_at,
-                    },
-                    audit: mutation_audit(
-                        context,
-                        action,
-                        "provider_account",
-                        account_id.as_str(),
-                        vec!["credentials".to_owned()],
-                    ),
+            .rotate_provider_account(RotateProviderAccount {
+                scope,
+                profile: UpdateProviderAccount {
+                    id: account_id.as_str().to_owned(),
+                    name: prepared.name,
+                    email: prepared.email,
+                    plan_type: prepared.plan_type,
                },
-            )
+                replacement_identity: prepared.replacement_identity,
+                credential: ProviderCredentialUpdate {
+                    account_id: account_id.as_str().to_owned(),
+                    expected_revision: store_revision(prepared.expected_credential_revision)?,
+                    provider_credentials_json: provider_document_json(prepared.provider_material)
+                        .map_err(|error| admin_store_error(ENTITY, error))?,
+                    has_refresh_token: prepared.has_refresh_token,
+                    access_token_expires_at: prepared.access_token_expires_at,
+                    next_refresh_at: prepared.next_refresh_at,
+                },
+                audit: mutation_audit(
+                    context,
+                    action,
+                    "provider_account",
+                    account_id.as_str(),
+                    vec!["credentials".to_owned()],
+                ),
+            })
            .await
            .map_err(|error| admin_store_error(ENTITY, error))?;
        Ok(CredentialMutationResult {
@@ -1251,9 +1208,10 @@ impl AccountStore for PgAdminAccountStore {
            .into_iter()
            .filter(|account| account.provider_kind == provider_kind.as_str())
            .filter(|account| {
-                query.availability.as_ref().is_none_or(|expected| {
-                    expected.matches(admin_account_availability(account.availability))
-                })
+                query
+                    .availability
+                    .as_ref()
+                    .is_none_or(|expected| expected.matches(account.availability))
            })
            .filter(|account| {
                query
@@ -1383,13 +1341,8 @@ impl AccountStore for PgAdminAccountStore {
        command: CredentialImportCommit,
        context: &MutationContext,
    ) -> AdminStoreResult<CredentialImportResult> {
-        self.commit_prepared_import(
-            command.expected_config_revision,
-            command.prepared,
-            context,
-            "import_document",
-        )
-        .await
+        self.commit_prepared_import(command.prepared, context, "import_document")
+            .await
    }

    async fn commit_authorization(
@@ -1397,13 +1350,11 @@ impl AccountStore for PgAdminAccountStore {
        command: AuthorizationCommit,
        context: &MutationContext,
    ) -> AdminStoreResult<CredentialMutationResult> {
-        let expected_config_revision = command.pending.expected_config_revision();
        match command.credential {
            AuthorizationCredentialCommit::Create(credential) => {
                let account_id = credential.account_id.clone();
                let result = self
                    .commit_prepared_import(
-                        expected_config_revision,
                        PreparedCredentialImport {
                            provider_kind: credential.provider_kind.clone(),
                            credentials: vec![credential],
@@ -1431,13 +1382,8 @@ impl AccountStore for PgAdminAccountStore {
                })
            }
            AuthorizationCredentialCommit::Reauthorize(prepared) => {
-                self.commit_prepared_rotation(
-                    expected_config_revision,
-                    prepared,
-                    context,
-                    "reauthorize",
-                )
-                .await
+                self.commit_prepared_rotation(prepared, context, "reauthorize")
+                    .await
            }
        }
    }
@@ -1447,13 +1393,8 @@ impl AccountStore for PgAdminAccountStore {
        command: CredentialRotationCommit,
        context: &MutationContext,
    ) -> AdminStoreResult<CredentialMutationResult> {
-        self.commit_prepared_rotation(
-            command.expected_config_revision,
-            command.prepared,
-            context,
-            "rotate_credential",
-        )
-        .await
+        self.commit_prepared_rotation(command.prepared, context, "rotate_credential")
+            .await
    }

    async fn commit_credential_refresh(
@@ -1461,13 +1402,8 @@ impl AccountStore for PgAdminAccountStore {
        command: CredentialRotationCommit,
        context: &MutationContext,
    ) -> AdminStoreResult<CredentialMutationResult> {
-        self.commit_prepared_rotation(
-            command.expected_config_revision,
-            command.prepared,
-            context,
-            "refresh_credential",
-        )
-        .await
+        self.commit_prepared_rotation(command.prepared, context, "refresh_credential")
+            .await
    }

    async fn set_account_enabled(
@@ -1478,21 +1414,18 @@ impl AccountStore for PgAdminAccountStore {
        let scope = self.required_scope(&command.account_id).await?;
        let action = if command.enabled { "enable" } else { "disable" };
        self.accounts
-            .set_provider_account_enabled_admin(
-                store_revision(command.expected_config_revision)?,
-                SetProviderAccountEnabled {
-                    scope,
-                    account_id: command.account_id.clone(),
-                    enabled: command.enabled,
-                    audit: mutation_audit(
-                        context,
-                        action,
-                        "provider_account",
-                        &command.account_id,
-                        vec!["enabled".to_owned()],
-                    ),
-                },
-            )
+            .set_provider_account_enabled_admin(SetProviderAccountEnabled {
+                scope,
+                account_id: command.account_id.clone(),
+                enabled: command.enabled,
+                audit: mutation_audit(
+                    context,
+                    action,
+                    "provider_account",
+                    &command.account_id,
+                    vec!["enabled".to_owned()],
+                ),
+            })
            .await
            .map_err(|error| admin_store_error(ENTITY, error))
            .and_then(admin_revision)
@@ -1517,20 +1450,17 @@ impl AccountStore for PgAdminAccountStore {
            "provider_accounts".to_owned()
        };
        self.accounts
-            .delete_provider_accounts_admin(
-                store_revision(command.expected_config_revision)?,
-                DeleteProviderAccounts {
-                    scope,
-                    account_ids: command.account_ids,
-                    audit: mutation_audit(
-                        context,
-                        "delete",
-                        "provider_account",
-                        &audit_target,
-                        Vec::new(),
-                    ),
-                },
-            )
+            .delete_provider_accounts_admin(DeleteProviderAccounts {
+                scope,
+                account_ids: command.account_ids,
+                audit: mutation_audit(
+                    context,
+                    "delete",
+                    "provider_account",
+                    &audit_target,
+                    Vec::new(),
+                ),
+            })
            .await
            .map_err(|error| admin_store_error(ENTITY, error))
            .and_then(admin_revision)
@@ -1656,12 +1586,16 @@ fn admin_account_status(
 ) -> AdminAccountStatus {
    if !account.enabled {
        AdminAccountStatus::Disabled
-    } else if account.availability == ProviderAccountAvailability::Banned {
+    } else if account.availability == AccountAvailability::Banned {
        AdminAccountStatus::Banned
-    } else if account.availability == ProviderAccountAvailability::QuotaExhausted {
+    } else if account.availability == AccountAvailability::QuotaExhausted
+        || (account.availability == AccountAvailability::Cooldown
+            && account.availability_reason.as_deref() == Some("usage_limit_exhausted")
+            && account.cooldown_until.is_none_or(|until| until > now))
+    {
        AdminAccountStatus::QuotaExhausted
-    } else if account.availability == ProviderAccountAvailability::Expired
-        || account.availability == ProviderAccountAvailability::Invalid
+    } else if account.availability == AccountAvailability::Expired
+        || account.availability == AccountAvailability::Invalid
        || account
            .access_token_expires_at
            .is_some_and(|expires_at| expires_at <= now)
@@ -1786,7 +1720,7 @@ fn admin_account_record(summary: ProviderAccountSummary) -> AdminStoreResult<Acc
        access_token_expires_at: summary.access_token_expires_at,
        next_refresh_at: summary.next_refresh_at,
        enabled: summary.enabled,
-        availability: admin_account_availability(summary.availability),
+        availability: summary.availability,
        availability_reason: summary.availability_reason,
        cooldown_until: summary.cooldown_until,
        availability_observed_at: summary.availability_observed_at,
@@ -1811,7 +1745,7 @@ fn prepared_account(credential: PreparedCredentialCreate) -> StoreResult<NewProv
        access_token_expires_at: credential.access_token_expires_at,
        next_refresh_at: credential.next_refresh_at,
        enabled: credential.enabled,
-        availability: provider_account_availability(credential.availability),
+        availability: credential.availability,
        availability_reason: credential.availability_reason,
        cooldown_until: credential.cooldown_until,
        availability_observed_at: credential.availability_observed_at,
@@ -1826,34 +1760,6 @@ fn provider_document_json(document: ProviderDocument) -> StoreResult<JsonObject>
    )
 }

-const fn provider_account_availability(
-    availability: AdminAccountAvailability,
-) -> ProviderAccountAvailability {
-    match availability {
-        AdminAccountAvailability::Unknown => ProviderAccountAvailability::Unknown,
-        AdminAccountAvailability::Ready => ProviderAccountAvailability::Ready,
-        AdminAccountAvailability::Cooldown => ProviderAccountAvailability::Cooldown,
-        AdminAccountAvailability::QuotaExhausted => ProviderAccountAvailability::QuotaExhausted,
-        AdminAccountAvailability::Expired => ProviderAccountAvailability::Expired,
-        AdminAccountAvailability::Banned => ProviderAccountAvailability::Banned,
-        AdminAccountAvailability::Invalid => ProviderAccountAvailability::Invalid,
-    }
-}
-
-const fn admin_account_availability(
-    availability: ProviderAccountAvailability,
-) -> AdminAccountAvailability {
-    match availability {
-        ProviderAccountAvailability::Unknown => AdminAccountAvailability::Unknown,
-        ProviderAccountAvailability::Ready => AdminAccountAvailability::Ready,
-        ProviderAccountAvailability::Cooldown => AdminAccountAvailability::Cooldown,
-        ProviderAccountAvailability::QuotaExhausted => AdminAccountAvailability::QuotaExhausted,
-        ProviderAccountAvailability::Expired => AdminAccountAvailability::Expired,
-        ProviderAccountAvailability::Banned => AdminAccountAvailability::Banned,
-        ProviderAccountAvailability::Invalid => AdminAccountAvailability::Invalid,
-    }
-}
-
 fn admin_account_usage(usage: ProviderAccountUsageObservation) -> AdminStoreResult<AccountUsage> {
    Ok(AccountUsage {
        account_id: usage.account_id,
@@ -2093,8 +1999,13 @@ async fn rotate_provider_account_in_transaction(
    transaction: &mut Transaction<'_, Postgres>,
    scope: &ProviderAccountAdminScope,
    profile: &UpdateProviderAccount,
+    replacement_identity: Option<&ProviderAccountIdentity>,
    update: &ProviderCredentialUpdate,
 ) -> StoreResult<Revision> {
+    let replace_identity = replacement_identity.is_some();
+    let upstream_user_id = replacement_identity.map(ProviderAccountIdentity::upstream_user_id);
+    let upstream_account_id =
+        replacement_identity.and_then(ProviderAccountIdentity::upstream_account_id);
    let next = sqlx::query_scalar::<_, i64>(
        "update provider_accounts
         set name = $4,
@@ -2105,6 +2016,28 @@ async fn rotate_provider_account_in_transaction(
             has_refresh_token = $8,
             access_token_expires_at = $9,
             next_refresh_at = $10,
+             upstream_user_id = case when $11::boolean then $12::text else upstream_user_id end,
+             upstream_account_id = case when $11::boolean then $13::text else upstream_account_id end,
+             availability = case
+                 when not enabled then availability
+                 when availability <> 'quota_exhausted' then 'ready'
+                 else availability
+             end,
+             availability_reason = case
+                 when not enabled then availability_reason
+                 when availability <> 'quota_exhausted' then null
+                 else availability_reason
+             end,
+             cooldown_until = case
+                 when not enabled then cooldown_until
+                 when availability <> 'quota_exhausted' then null
+                 else cooldown_until
+             end,
+             availability_observed_at = case
+                 when not enabled then availability_observed_at
+                 when availability <> 'quota_exhausted' then now()
+                 else availability_observed_at
+             end,
             updated_at = now()
         where id = $1 and provider_kind = $2
           and credential_revision = $3
@@ -2120,9 +2053,25 @@ async fn rotate_provider_account_in_transaction(
    .bind(update.has_refresh_token)
    .bind(update.access_token_expires_at)
    .bind(update.next_refresh_at)
+    .bind(replace_identity)
+    .bind(upstream_user_id)
+    .bind(upstream_account_id)
    .fetch_optional(&mut **transaction)
    .await
-    .map_err(|_| postgres_unavailable("rotate provider account in admin transaction"))?
+    .map_err(|error| {
+        if error
+            .as_database_error()
+            .is_some_and(sqlx::error::DatabaseError::is_unique_violation)
+        {
+            StoreError::Conflict {
+                entity: ENTITY,
+                id: update.account_id.clone(),
+                kind: ConflictKind::InvalidTransition,
+            }
+        } else {
+            postgres_unavailable("rotate provider account in admin transaction")
+        }
+    })?
    .ok_or_else(|| StoreError::Conflict {
        entity: ENTITY,
        id: update.account_id.clone(),
@@ -2268,7 +2217,7 @@ impl ProviderAccountStore for PgProviderAccountRepository {
                .map(DateTime::<Utc>::from),
            next_refresh_at: account.account.next_refresh_at().map(DateTime::<Utc>::from),
            enabled: account.account.enabled(),
-            availability: availability_from_core(account.account.availability()),
+            availability: account.account.availability(),
            availability_reason: None,
            cooldown_until: account.account.cooldown_until().map(DateTime::<Utc>::from),
            availability_observed_at: Utc::now(),
@@ -2313,15 +2262,23 @@ impl ProviderAccountStore for PgProviderAccountRepository {
        &self,
        account: &CoreProviderAccountId,
        expected_revision: CoreCredentialRevision,
+    ) -> Result<LoadedCredential, CoreStoreError> {
+        let loaded = self.load_current_credential(account).await?;
+        if loaded.account.revision().get() != expected_revision.get() {
+            return Err(CoreStoreError::new(CoreStoreErrorKind::Conflict));
+        }
+        Ok(loaded)
+    }
+
+    async fn load_current_credential(
+        &self,
+        account: &CoreProviderAccountId,
    ) -> Result<LoadedCredential, CoreStoreError> {
        let record = self
            .load_provider_account(account.as_str())
            .await
            .map_err(core_store_error)?
            .ok_or_else(|| CoreStoreError::new(CoreStoreErrorKind::InvalidData))?;
-        if record.summary.credential_revision.get() != expected_revision.get() {
-            return Err(CoreStoreError::new(CoreStoreErrorKind::Conflict));
-        }
        Ok(LoadedCredential {
            account: core_account_from_summary(record.summary)?,
            credential: PlaintextCredential::new(record.provider_credentials_json.fields().clone()),
@@ -2470,7 +2427,7 @@ impl ProviderAccountStore for PgProviderAccountRepository {
                account_id: change.account_id.as_str().to_owned(),
                expected_revision: Revision::new(change.expected_revision.get())
                    .map_err(core_store_error)?,
-                availability: availability_from_core(change.availability),
+                availability: change.availability,
                availability_reason: change.reason,
                cooldown_until: change.cooldown_until.map(DateTime::<Utc>::from),
                availability_observed_at: DateTime::<Utc>::from(change.observed_at),
@@ -2581,7 +2538,7 @@ fn core_account_from_summary(
    )
    .with_runtime_state(
        summary.enabled,
-        availability_to_core(summary.availability),
+        summary.availability,
        summary.cooldown_until.map(Into::into),
    )
    .with_refresh_schedule(
@@ -2590,30 +2547,6 @@ fn core_account_from_summary(
    ))
 }

-const fn availability_to_core(value: ProviderAccountAvailability) -> CoreAccountAvailability {
-    match value {
-        ProviderAccountAvailability::Unknown => CoreAccountAvailability::Unknown,
-        ProviderAccountAvailability::Ready => CoreAccountAvailability::Ready,
-        ProviderAccountAvailability::Cooldown => CoreAccountAvailability::Cooldown,
-        ProviderAccountAvailability::QuotaExhausted => CoreAccountAvailability::QuotaExhausted,
-        ProviderAccountAvailability::Expired => CoreAccountAvailability::Expired,
-        ProviderAccountAvailability::Banned => CoreAccountAvailability::Banned,
-        ProviderAccountAvailability::Invalid => CoreAccountAvailability::Invalid,
-    }
-}
-
-const fn availability_from_core(value: CoreAccountAvailability) -> ProviderAccountAvailability {
-    match value {
-        CoreAccountAvailability::Unknown => ProviderAccountAvailability::Unknown,
-        CoreAccountAvailability::Ready => ProviderAccountAvailability::Ready,
-        CoreAccountAvailability::Cooldown => ProviderAccountAvailability::Cooldown,
-        CoreAccountAvailability::QuotaExhausted => ProviderAccountAvailability::QuotaExhausted,
-        CoreAccountAvailability::Expired => ProviderAccountAvailability::Expired,
-        CoreAccountAvailability::Banned => ProviderAccountAvailability::Banned,
-        CoreAccountAvailability::Invalid => ProviderAccountAvailability::Invalid,
-    }
-}
-
 fn core_store_error(error: StoreError) -> CoreStoreError {
    let kind = match error {
        StoreError::Unavailable { .. } => CoreStoreErrorKind::Unavailable,
@@ -2654,7 +2587,7 @@ fn account_summary_from_row(row: sqlx::postgres::PgRow) -> StoreResult<ProviderA
        access_token_expires_at: get(&row, "access_token_expires_at")?,
        next_refresh_at: get(&row, "next_refresh_at")?,
        enabled: get(&row, "enabled")?,
-        availability: ProviderAccountAvailability::parse(&availability)?,
+        availability: parse_availability(&availability)?,
        availability_reason: get(&row, "availability_reason")?,
        cooldown_until: get(&row, "cooldown_until")?,
        availability_observed_at: get(&row, "availability_observed_at")?,
@@ -12,7 +12,7 @@ use gateway_core::provider_ports::{
    ProviderRefreshPolicy, ProviderRuntimePolicyPort, ProviderStoreError, ProviderStoreErrorKind,
 };

-use crate::{ConflictKind, Revision, StoreError, StoreResult, postgres_unavailable};
+use crate::{Revision, StoreError, StoreResult, postgres_unavailable};

 #[derive(Clone, PartialEq, Eq)]
 pub struct RuntimeSettings {
@@ -111,11 +111,8 @@ impl RuntimeSettingsUpdate {
 pub trait RuntimeSettingsRepository: Send + Sync {
    async fn load_runtime_settings(&self) -> StoreResult<RuntimeSettings>;

-    async fn update_runtime_settings(
-        &self,
-        expected_revision: Revision,
-        update: RuntimeSettingsUpdate,
-    ) -> StoreResult<Revision>;
+    async fn update_runtime_settings(&self, update: RuntimeSettingsUpdate)
+    -> StoreResult<Revision>;
 }

 #[derive(Clone)]
@@ -169,7 +166,6 @@ impl RuntimeSettingsRepository for PgRuntimeSettingsRepository {

    async fn update_runtime_settings(
        &self,
-        expected_revision: Revision,
        update: RuntimeSettingsUpdate,
    ) -> StoreResult<Revision> {
        let mut transaction = self
@@ -177,9 +173,7 @@ impl RuntimeSettingsRepository for PgRuntimeSettingsRepository {
            .begin()
            .await
            .map_err(|_| postgres_unavailable("begin runtime settings update"))?;
-        let revision =
-            update_runtime_settings_in_transaction(&mut transaction, expected_revision, &update)
-                .await?;
+        let revision = update_runtime_settings_in_transaction(&mut transaction, &update).await?;
        transaction
            .commit()
            .await
@@ -228,30 +222,43 @@ pub(crate) async fn load_runtime_settings_in_transaction(

 pub(crate) async fn update_runtime_settings_in_transaction(
    transaction: &mut Transaction<'_, Postgres>,
-    expected_revision: Revision,
    update: &RuntimeSettingsUpdate,
 ) -> StoreResult<Revision> {
    update.validate()?;
+    let refresh_margin_seconds =
+        i64::try_from(update.refresh_margin_seconds).map_err(|_| invalid_numeric())?;
+    let previous_refresh_margin_seconds = sqlx::query_scalar::<_, i64>(
+        "select refresh_margin_seconds
+         from runtime_settings
+         where id = 1
+         for update",
+    )
+    .fetch_optional(&mut **transaction)
+    .await
+    .map_err(|_| postgres_unavailable("lock runtime settings for update"))?
+    .ok_or_else(|| StoreError::NotFound {
+        entity: "runtime settings",
+        id: "1".to_owned(),
+    })?;
    let next = sqlx::query_scalar::<_, i64>(
        "update runtime_settings
             set config_revision = config_revision + 1,
-                 admin_api_key = $2,
-                 refresh_margin_seconds = $3,
-                 refresh_concurrency = $4,
-                 max_concurrent_per_account = $5,
-                 request_interval_ms = $6,
-                 rotation_strategy = $7,
-                 model_mappings_json = $8,
-                 usage_retention_days = $9,
-                 ops_event_retention_days = $10,
-                 audit_retention_days = $11,
-                 updated_at = now()
-             where id = 1 and config_revision = $1
-             returning config_revision",
+	                 admin_api_key = $1,
+	                 refresh_margin_seconds = $2,
+	                 refresh_concurrency = $3,
+	                 max_concurrent_per_account = $4,
+	                 request_interval_ms = $5,
+	                 rotation_strategy = $6,
+	                 model_mappings_json = $7,
+	                 usage_retention_days = $8,
+	                 ops_event_retention_days = $9,
+	                 audit_retention_days = $10,
+	             updated_at = now()
+	             where id = 1
+	             returning config_revision",
    )
-    .bind(i64::try_from(expected_revision.get()).map_err(|_| invalid_numeric())?)
    .bind(update.admin_api_key.as_deref())
-    .bind(i64::try_from(update.refresh_margin_seconds).map_err(|_| invalid_numeric())?)
+    .bind(refresh_margin_seconds)
    .bind(i64::from(update.refresh_concurrency))
    .bind(i64::from(update.max_concurrent_per_account))
    .bind(i64::try_from(update.request_interval_ms).map_err(|_| invalid_numeric())?)
@@ -263,32 +270,54 @@ pub(crate) async fn update_runtime_settings_in_transaction(
    .fetch_optional(&mut **transaction)
    .await
    .map_err(|_| postgres_unavailable("update runtime settings in transaction"))?
-    .ok_or_else(|| StoreError::Conflict {
+    .ok_or_else(|| StoreError::NotFound {
        entity: "runtime settings",
        id: "1".to_owned(),
-        kind: ConflictKind::StaleRevision,
    })?;
+    if previous_refresh_margin_seconds != refresh_margin_seconds {
+        reschedule_provider_refreshes_in_transaction(transaction, refresh_margin_seconds).await?;
+    }
    Revision::new(u64::try_from(next).map_err(|_| invalid_numeric())?)
 }

+async fn reschedule_provider_refreshes_in_transaction(
+    transaction: &mut Transaction<'_, Postgres>,
+    refresh_margin_seconds: i64,
+) -> StoreResult<()> {
+    sqlx::query(
+        "update provider_accounts
+         set next_refresh_at = case
+               when access_token_expires_at <= now()
+                 or extract(epoch from (access_token_expires_at - now())) <= $1
+               then now()
+               else access_token_expires_at - ($1::double precision * interval '1 second')
+             end,
+             updated_at = now()
+         where has_refresh_token
+           and access_token_expires_at is not null",
+    )
+    .bind(refresh_margin_seconds)
+    .execute(&mut **transaction)
+    .await
+    .map_err(|_| postgres_unavailable("reschedule provider credential refreshes"))?;
+    Ok(())
+}
+
 pub(crate) async fn bump_config_revision_in_transaction(
    transaction: &mut Transaction<'_, Postgres>,
-    expected_revision: Revision,
 ) -> StoreResult<Revision> {
    let next = sqlx::query_scalar::<_, i64>(
        "update runtime_settings
         set config_revision = config_revision + 1, updated_at = now()
-         where id = 1 and config_revision = $1
+         where id = 1
         returning config_revision",
    )
-    .bind(i64::try_from(expected_revision.get()).map_err(|_| invalid_numeric())?)
    .fetch_optional(&mut **transaction)
    .await
    .map_err(|_| postgres_unavailable("bump config revision in transaction"))?
-    .ok_or_else(|| StoreError::Conflict {
+    .ok_or_else(|| StoreError::NotFound {
        entity: "runtime settings",
        id: "1".to_owned(),
-        kind: ConflictKind::StaleRevision,
    })?;
    Revision::new(u64::try_from(next).map_err(|_| invalid_numeric())?)
 }
@@ -0,0 +1,254 @@
+//! 可由 TTL 或后续反馈收敛的 Redis 写副作用队列。
+//!
+//! Continuation affinity 决定下一轮 Provider 与账号，必须在响应 ID 可复用前
+//! 获得 Redis 确认，因此不属于本模块的可丢失副作用。
+
+use std::num::NonZeroUsize;
+use std::sync::Arc;
+
+use futures::future::{BoxFuture, ready};
+use gateway_core::engine::admission::{
+    ClientAdmissionDecision, ClientAdmissionError, ClientAdmissionPort, ClientAdmissionRecovery,
+    ClientAdmissionRequest, ClientAdmissionRestoreResult,
+};
+use gateway_core::engine::execution::{
+    ProviderCircuitDecision, ProviderCircuitError, ProviderCircuitPort,
+};
+use gateway_core::engine::{CancellationToken, ModelRequestId};
+use gateway_core::policy::ClientApiKeyId;
+use gateway_core::routing::ProviderKind;
+use gateway_core::task::{DaemonTask, WorkerTaskError};
+use tokio::sync::{Mutex, mpsc};
+
+const DEFAULT_QUEUE_CAPACITY: usize = 4_096;
+
+/// 准入读取保持强一致；终态释放只做有界入队，Redis 失败由 worker 吸收。
+#[derive(Clone)]
+pub struct BufferedClientAdmissionPort {
+    inner: Arc<dyn ClientAdmissionPort>,
+    sender: mpsc::Sender<AdmissionRelease>,
+}
+
+impl BufferedClientAdmissionPort {
+    #[must_use]
+    pub fn new(inner: Arc<dyn ClientAdmissionPort>) -> (Self, ClientAdmissionReleaseWriter) {
+        Self::with_capacity(
+            inner,
+            NonZeroUsize::new(DEFAULT_QUEUE_CAPACITY).expect("queue capacity is non-zero"),
+        )
+    }
+
+    #[must_use]
+    pub fn with_capacity(
+        inner: Arc<dyn ClientAdmissionPort>,
+        capacity: NonZeroUsize,
+    ) -> (Self, ClientAdmissionReleaseWriter) {
+        let (sender, receiver) = mpsc::channel(capacity.get());
+        (
+            Self {
+                inner: Arc::clone(&inner),
+                sender,
+            },
+            ClientAdmissionReleaseWriter {
+                inner,
+                receiver: Mutex::new(receiver),
+            },
+        )
+    }
+
+    fn enqueue(&self, release: AdmissionRelease) -> bool {
+        match self.sender.try_send(release) {
+            Ok(()) => true,
+            Err(error) => {
+                let reason = match error {
+                    mpsc::error::TrySendError::Full(_) => "full",
+                    mpsc::error::TrySendError::Closed(_) => "closed",
+                };
+                tracing::warn!(
+                    operation = "release_client_admission",
+                    reason,
+                    "Redis 协调队列不可用，已丢弃本次准入释放；租约将由 TTL 收敛"
+                );
+                false
+            }
+        }
+    }
+}
+
+impl ClientAdmissionPort for BufferedClientAdmissionPort {
+    fn admit(
+        &self,
+        request: ClientAdmissionRequest,
+    ) -> BoxFuture<'_, Result<ClientAdmissionDecision, ClientAdmissionError>> {
+        self.inner.admit(request)
+    }
+
+    fn release<'a>(
+        &'a self,
+        client_api_key_id: &'a ClientApiKeyId,
+        model_request_id: &'a ModelRequestId,
+    ) -> BoxFuture<'a, Result<bool, ClientAdmissionError>> {
+        let enqueued = self.enqueue(AdmissionRelease {
+            client_api_key_id: client_api_key_id.clone(),
+            model_request_id: model_request_id.clone(),
+        });
+        Box::pin(ready(Ok(enqueued)))
+    }
+
+    fn restore(
+        &self,
+        recovery: ClientAdmissionRecovery,
+    ) -> BoxFuture<'_, Result<ClientAdmissionRestoreResult, ClientAdmissionError>> {
+        self.inner.restore(recovery)
+    }
+}
+
+struct AdmissionRelease {
+    client_api_key_id: ClientApiKeyId,
+    model_request_id: ModelRequestId,
+}
+
+pub struct ClientAdmissionReleaseWriter {
+    inner: Arc<dyn ClientAdmissionPort>,
+    receiver: Mutex<mpsc::Receiver<AdmissionRelease>>,
+}
+
+impl DaemonTask for ClientAdmissionReleaseWriter {
+    fn run(&self, cancellation: CancellationToken) -> BoxFuture<'_, Result<(), WorkerTaskError>> {
+        Box::pin(async move {
+            let mut receiver = self.receiver.lock().await;
+            loop {
+                let release = tokio::select! {
+                    () = cancellation.cancelled() => return Ok(()),
+                    release = receiver.recv() => release,
+                };
+                let Some(release) = release else {
+                    return Err(WorkerTaskError::safe(
+                        "client admission release queue closed",
+                    ));
+                };
+                if let Err(error) = self
+                    .inner
+                    .release(&release.client_api_key_id, &release.model_request_id)
+                    .await
+                {
+                    tracing::warn!(%error, "Client admission 后台释放失败，依赖租约 TTL 收敛");
+                }
+            }
+        })
+    }
+}
+
+/// Circuit decision 仍直读 Redis；success/failure feedback 只做有界入队。
+#[derive(Clone)]
+pub struct BufferedProviderCircuitPort {
+    inner: Arc<dyn ProviderCircuitPort>,
+    sender: mpsc::Sender<CircuitFeedback>,
+}
+
+impl BufferedProviderCircuitPort {
+    #[must_use]
+    pub fn new(inner: Arc<dyn ProviderCircuitPort>) -> (Self, ProviderCircuitFeedbackWriter) {
+        Self::with_capacity(
+            inner,
+            NonZeroUsize::new(DEFAULT_QUEUE_CAPACITY).expect("queue capacity is non-zero"),
+        )
+    }
+
+    #[must_use]
+    pub fn with_capacity(
+        inner: Arc<dyn ProviderCircuitPort>,
+        capacity: NonZeroUsize,
+    ) -> (Self, ProviderCircuitFeedbackWriter) {
+        let (sender, receiver) = mpsc::channel(capacity.get());
+        (
+            Self {
+                inner: Arc::clone(&inner),
+                sender,
+            },
+            ProviderCircuitFeedbackWriter {
+                inner,
+                receiver: Mutex::new(receiver),
+            },
+        )
+    }
+
+    fn enqueue(&self, feedback: CircuitFeedback) {
+        if let Err(error) = self.sender.try_send(feedback) {
+            let reason = match error {
+                mpsc::error::TrySendError::Full(_) => "full",
+                mpsc::error::TrySendError::Closed(_) => "closed",
+            };
+            tracing::warn!(
+                operation = "record_provider_circuit_feedback",
+                reason,
+                "Redis 协调队列不可用，已丢弃本次 circuit feedback"
+            );
+        }
+    }
+}
+
+impl ProviderCircuitPort for BufferedProviderCircuitPort {
+    fn decision<'a>(
+        &'a self,
+        provider_kind: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<ProviderCircuitDecision, ProviderCircuitError>> {
+        self.inner.decision(provider_kind)
+    }
+
+    fn observe_failure<'a>(
+        &'a self,
+        provider_kind: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<(), ProviderCircuitError>> {
+        self.enqueue(CircuitFeedback::Failure(provider_kind.clone()));
+        Box::pin(ready(Ok(())))
+    }
+
+    fn observe_success<'a>(
+        &'a self,
+        provider_kind: &'a ProviderKind,
+    ) -> BoxFuture<'a, Result<(), ProviderCircuitError>> {
+        self.enqueue(CircuitFeedback::Success(provider_kind.clone()));
+        Box::pin(ready(Ok(())))
+    }
+}
+
+enum CircuitFeedback {
+    Failure(ProviderKind),
+    Success(ProviderKind),
+}
+
+pub struct ProviderCircuitFeedbackWriter {
+    inner: Arc<dyn ProviderCircuitPort>,
+    receiver: Mutex<mpsc::Receiver<CircuitFeedback>>,
+}
+
+impl DaemonTask for ProviderCircuitFeedbackWriter {
+    fn run(&self, cancellation: CancellationToken) -> BoxFuture<'_, Result<(), WorkerTaskError>> {
+        Box::pin(async move {
+            let mut receiver = self.receiver.lock().await;
+            loop {
+                let feedback = tokio::select! {
+                    () = cancellation.cancelled() => return Ok(()),
+                    feedback = receiver.recv() => feedback,
+                };
+                let Some(feedback) = feedback else {
+                    return Err(WorkerTaskError::safe(
+                        "provider circuit feedback queue closed",
+                    ));
+                };
+                let result = match feedback {
+                    CircuitFeedback::Failure(provider) => {
+                        self.inner.observe_failure(&provider).await
+                    }
+                    CircuitFeedback::Success(provider) => {
+                        self.inner.observe_success(&provider).await
+                    }
+                };
+                if let Err(error) = result {
+                    tracing::warn!(%error, "Provider circuit feedback 后台写入失败");
+                }
+            }
+        })
+    }
+}
@@ -13,7 +13,8 @@ use gateway_core::{
    },
    error::StoreError as CoreStoreError,
    provider_ports::{
-        ProviderCooldown, ProviderCooldownPort, ProviderStoreError, ProviderStoreErrorKind,
+        ProviderCooldown, ProviderCooldownPort, ProviderCooldownScope, ProviderScopedCooldown,
+        ProviderStoreError, ProviderStoreErrorKind,
    },
    routing::ProviderKind,
 };
@@ -104,24 +105,35 @@ impl RedisCredentialCooldownRepository {
        let fingerprint = resource_fingerprint("credential cooldown", provider_account_id)?;
        Ok(format!("{}:account:{fingerprint}:cooldown", self.namespace))
    }
-}

-#[async_trait]
-impl CredentialCooldownRepository for RedisCredentialCooldownRepository {
-    async fn cache_credential_cooldown(&self, cooldown: &CredentialCooldown) -> StoreResult<bool> {
-        require_nonempty(
-            "credential cooldown",
-            "provider_account_id",
-            &cooldown.provider_account_id,
-        )?;
-        let until_ms = cooldown.cooldown_until.timestamp_millis();
+    fn scoped_key(
+        &self,
+        provider_account_id: &str,
+        scope: &ProviderCooldownScope,
+    ) -> StoreResult<String> {
+        let account_fingerprint = resource_fingerprint("credential cooldown", provider_account_id)?;
+        let scope_fingerprint = resource_fingerprint("credential cooldown scope", scope.value())?;
+        Ok(format!(
+            "{}:account:{account_fingerprint}:cooldown:{}:{scope_fingerprint}",
+            self.namespace,
+            scope.kind(),
+        ))
+    }
+
+    async fn cache_at_key(
+        &self,
+        key: String,
+        credential_revision: Revision,
+        cooldown_until: DateTime<Utc>,
+    ) -> StoreResult<bool> {
+        let until_ms = cooldown_until.timestamp_millis();
        if until_ms <= 0 {
            return Err(invalid("cooldown expiry must be positive"));
        }
        let mut connection = self.connection.clone();
        let written = Script::new(WRITE_SCRIPT)
-            .key(self.key(&cooldown.provider_account_id)?)
-            .arg(cooldown.credential_revision.get())
+            .key(key)
+            .arg(credential_revision.get())
            .arg(until_ms)
            .invoke_async::<i64>(&mut connection)
            .await
@@ -129,18 +141,10 @@ impl CredentialCooldownRepository for RedisCredentialCooldownRepository {
        Ok(written == 1)
    }

-    async fn read_credential_cooldown(
-        &self,
-        provider_account_id: &str,
-    ) -> StoreResult<Option<CredentialCooldown>> {
-        require_nonempty(
-            "credential cooldown",
-            "provider_account_id",
-            provider_account_id,
-        )?;
+    async fn read_at_key(&self, key: String) -> StoreResult<Option<(Revision, DateTime<Utc>)>> {
        let mut connection = self.connection.clone();
        let (present, revision, until_ms): (i64, String, String) = Script::new(READ_SCRIPT)
-            .key(self.key(provider_account_id)?)
+            .key(key)
            .invoke_async(&mut connection)
            .await
            .map_err(|_| redis_unavailable("read credential cooldown"))?;
@@ -155,11 +159,59 @@ impl CredentialCooldownRepository for RedisCredentialCooldownRepository {
            .map_err(|_| invalid("cached cooldown expiry is invalid"))?;
        let cooldown_until = DateTime::from_timestamp_millis(until_ms)
            .ok_or_else(|| invalid("cached cooldown expiry is invalid"))?;
-        Ok(Some(CredentialCooldown {
-            provider_account_id: provider_account_id.to_owned(),
-            credential_revision: Revision::new(revision)?,
-            cooldown_until,
-        }))
+        Ok(Some((Revision::new(revision)?, cooldown_until)))
+    }
+
+    async fn invalidate_at_key(
+        &self,
+        key: String,
+        through_revision: Revision,
+    ) -> StoreResult<bool> {
+        let mut connection = self.connection.clone();
+        let removed = Script::new(INVALIDATE_SCRIPT)
+            .key(key)
+            .arg(through_revision.get())
+            .invoke_async::<i64>(&mut connection)
+            .await
+            .map_err(|_| redis_unavailable("invalidate credential cooldown"))?;
+        Ok(removed == 1)
+    }
+}
+
+#[async_trait]
+impl CredentialCooldownRepository for RedisCredentialCooldownRepository {
+    async fn cache_credential_cooldown(&self, cooldown: &CredentialCooldown) -> StoreResult<bool> {
+        require_nonempty(
+            "credential cooldown",
+            "provider_account_id",
+            &cooldown.provider_account_id,
+        )?;
+        self.cache_at_key(
+            self.key(&cooldown.provider_account_id)?,
+            cooldown.credential_revision,
+            cooldown.cooldown_until,
+        )
+        .await
+    }
+
+    async fn read_credential_cooldown(
+        &self,
+        provider_account_id: &str,
+    ) -> StoreResult<Option<CredentialCooldown>> {
+        require_nonempty(
+            "credential cooldown",
+            "provider_account_id",
+            provider_account_id,
+        )?;
+        self.read_at_key(self.key(provider_account_id)?)
+            .await
+            .map(|value| {
+                value.map(|(credential_revision, cooldown_until)| CredentialCooldown {
+                    provider_account_id: provider_account_id.to_owned(),
+                    credential_revision,
+                    cooldown_until,
+                })
+            })
    }

    async fn invalidate_credential_cooldown(
@@ -172,14 +224,8 @@ impl CredentialCooldownRepository for RedisCredentialCooldownRepository {
            "provider_account_id",
            provider_account_id,
        )?;
-        let mut connection = self.connection.clone();
-        let removed = Script::new(INVALIDATE_SCRIPT)
-            .key(self.key(provider_account_id)?)
-            .arg(through_revision.get())
-            .invoke_async::<i64>(&mut connection)
+        self.invalidate_at_key(self.key(provider_account_id)?, through_revision)
            .await
-            .map_err(|_| redis_unavailable("invalidate credential cooldown"))?;
-        Ok(removed == 1)
    }
 }

@@ -241,6 +287,69 @@ impl ProviderCooldownPort for RedisCredentialCooldownRepository {
            .map_err(|_| provider_unavailable("clear credential cooldown"))
        })
    }
+
+    fn put_scoped_if_later(
+        &self,
+        cooldown: ProviderScopedCooldown,
+    ) -> futures::future::BoxFuture<'_, Result<bool, ProviderStoreError>> {
+        Box::pin(async move {
+            let revision = Revision::new(cooldown.credential_revision().get())
+                .map_err(|_| provider_invalid("encode scoped credential cooldown"))?;
+            self.cache_at_key(
+                self.scoped_key(cooldown.account_id().as_str(), cooldown.scope())
+                    .map_err(|_| provider_invalid("encode scoped credential cooldown"))?,
+                revision,
+                cooldown.until().into(),
+            )
+            .await
+            .map_err(|_| provider_unavailable("cache scoped credential cooldown"))
+        })
+    }
+
+    fn read_scoped<'a>(
+        &'a self,
+        account_id: &'a ProviderAccountId,
+        scope: &'a ProviderCooldownScope,
+    ) -> futures::future::BoxFuture<'a, Result<Option<ProviderScopedCooldown>, ProviderStoreError>>
+    {
+        Box::pin(async move {
+            self.read_at_key(
+                self.scoped_key(account_id.as_str(), scope)
+                    .map_err(|_| provider_invalid("encode scoped credential cooldown"))?,
+            )
+            .await
+            .map_err(|_| provider_unavailable("read scoped credential cooldown"))?
+            .map(|(revision, until)| {
+                Ok(ProviderScopedCooldown::new(
+                    account_id.clone(),
+                    CredentialRevision::new(revision.get())
+                        .map_err(|_| provider_invalid("decode scoped credential cooldown"))?,
+                    scope.clone(),
+                    until.into(),
+                ))
+            })
+            .transpose()
+        })
+    }
+
+    fn clear_scoped<'a>(
+        &'a self,
+        account_id: &'a ProviderAccountId,
+        scope: &'a ProviderCooldownScope,
+        through_revision: CredentialRevision,
+    ) -> futures::future::BoxFuture<'a, Result<bool, ProviderStoreError>> {
+        Box::pin(async move {
+            let revision = Revision::new(through_revision.get())
+                .map_err(|_| provider_invalid("encode scoped cooldown revision"))?;
+            self.invalidate_at_key(
+                self.scoped_key(account_id.as_str(), scope)
+                    .map_err(|_| provider_invalid("encode scoped credential cooldown"))?,
+                revision,
+            )
+            .await
+            .map_err(|_| provider_unavailable("clear scoped credential cooldown"))
+        })
+    }
 }

 /// 账号状态写入到可丢失 cooldown cache 的桥接 adapter。
@@ -348,6 +457,13 @@ impl ProviderAccountStore for CooldownCachingProviderAccountStore {
            .await
    }

+    async fn load_current_credential(
+        &self,
+        account: &ProviderAccountId,
+    ) -> Result<LoadedCredential, CoreStoreError> {
+        self.authoritative.load_current_credential(account).await
+    }
+
    async fn compare_and_swap_credential(
        &self,
        update: CredentialCasUpdate,
@@ -388,6 +504,12 @@ impl ProviderAccountStore for CooldownCachingProviderAccountStore {
        let availability = change.availability;
        let cooldown_until = change.cooldown_until;
        self.authoritative.apply_state_change(change).await?;
+        let Some(account) = self.authoritative.get_account(&account_id).await? else {
+            return Ok(());
+        };
+        if !account.enabled() {
+            return Ok(());
+        }
        self.mirror(
            &account_id,
            credential_revision,
@@ -55,10 +55,7 @@ impl CredentialStateCache {
            "provider_account_id",
            &self.provider_account_id,
        )?;
-        if !matches!(
-            self.availability.as_str(),
-            "unknown" | "ready" | "cooldown" | "quota_exhausted" | "expired" | "banned" | "invalid"
-        ) {
+        if AccountAvailability::parse(&self.availability).is_none() {
            return Err(invalid("availability is not registered"));
        }
        Ok(())
@@ -8,6 +8,7 @@ use sha2::{Digest, Sha256};
 use async_trait::async_trait;

 mod client_admission;
+mod coordination_buffer;
 mod credential_cooldown;
 mod credential_leases;
 mod credential_state;
@@ -20,6 +21,7 @@ mod runtime_change;
 pub(crate) mod worker_lease;

 pub use client_admission::*;
+pub use coordination_buffer::*;
 pub use credential_cooldown::*;
 pub use credential_leases::*;
 pub use credential_state::*;
@@ -12,7 +12,6 @@ use gateway_core::engine::continuation::{
    NativeContinuationStoreError, PreviousResponseId,
 };
 use gateway_core::engine::credential::ProviderAccountId;
-use gateway_core::error::SafeUpstreamValue;
 use gateway_core::operation::ProviderSessionState;
 use gateway_core::routing::ProviderKind;
 use redis::aio::ConnectionManager;
@@ -25,6 +24,7 @@ use super::{namespace, resource_fingerprint};
 const CONTINUATION_TTL: Duration = Duration::from_secs(4 * 60 * 60);
 const MAX_CONTINUATIONS: usize = 65_536;
 const MAX_RECORD_BYTES: usize = 64 * 1024;
+const MAX_INDEX_CLEANUP_PER_RECORD: usize = 64;

 const RECORD_SCRIPT: &str = r#"
 local entry_key = KEYS[1]
@@ -36,12 +36,13 @@ local ttl_seconds = tonumber(ARGV[4])
 local cutoff = tonumber(ARGV[5])
 local max_entries = tonumber(ARGV[6])
 local entry_prefix = ARGV[7]
+local cleanup_limit = tonumber(ARGV[8])

 redis.call('SET', entry_key, payload, 'EX', ttl_seconds)
 redis.call('ZADD', index_key, score, entry_id)
 redis.call('EXPIRE', index_key, ttl_seconds)

-local stale = redis.call('ZRANGEBYSCORE', index_key, '-inf', cutoff)
+local stale = redis.call('ZRANGEBYSCORE', index_key, '-inf', cutoff, 'LIMIT', 0, cleanup_limit)
 for _, stale_id in ipairs(stale) do
  redis.call('UNLINK', entry_prefix .. '{' .. stale_id .. '}')
  redis.call('ZREM', index_key, stale_id)
@@ -49,6 +50,9 @@ end

 local count = redis.call('ZCARD', index_key)
 local excess = count - max_entries
+if excess > cleanup_limit then
+  excess = cleanup_limit
+end
 if excess > 0 then
  local oldest = redis.call('ZRANGE', index_key, 0, excess - 1)
  for _, old_id in ipairs(oldest) do
@@ -60,7 +64,7 @@ end
 return 1
 "#;

-/// Redis-backed, best-effort native response continuation affinity.
+/// 基于 Redis 的 best-effort 原生响应 continuation 亲和。
 #[derive(Clone)]
 pub struct RedisNativeContinuationRepository {
    connection: ConnectionManager,
@@ -110,6 +114,9 @@ impl NativeContinuationPort for RedisNativeContinuationRepository {
        previous_response_id: &'a PreviousResponseId,
    ) -> BoxFuture<'a, Result<Option<NativeContinuationPin>, NativeContinuationStoreError>> {
        Box::pin(async move {
+            if previous_response_id.as_str().is_empty() {
+                return Ok(None);
+            }
            let fingerprint = self.entry_fingerprint(previous_response_id.as_str())?;
            let mut connection = self.connection.clone();
            let payload = redis::cmd("GET")
@@ -128,6 +135,9 @@ impl NativeContinuationPort for RedisNativeContinuationRepository {
        pin: NativeContinuationPin,
    ) -> BoxFuture<'a, Result<(), NativeContinuationStoreError>> {
        Box::pin(async move {
+            if pin.previous_response_id().as_str().is_empty() {
+                return Ok(());
+            }
            let fingerprint = self.entry_fingerprint(pin.previous_response_id().as_str())?;
            let payload = encode_pin(&pin)?;
            if payload.len() > MAX_RECORD_BYTES {
@@ -153,6 +163,7 @@ impl NativeContinuationPort for RedisNativeContinuationRepository {
                .arg(cutoff)
                .arg(MAX_CONTINUATIONS)
                .arg(self.entry_prefix())
+                .arg(MAX_INDEX_CLEANUP_PER_RECORD)
                .invoke_async::<i64>(&mut connection)
                .await
                .map_err(|_| NativeContinuationStoreError)?;
@@ -186,8 +197,7 @@ fn decode_pin(
        serde_json::from_str(payload).map_err(|_| NativeContinuationStoreError)?;
    let provider = ProviderKind::new(wire.provider).map_err(|_| NativeContinuationStoreError)?;
    let account = ProviderAccountId::new(wire.account).map_err(|_| NativeContinuationStoreError)?;
-    let upstream_response_id = SafeUpstreamValue::new(wire.upstream_response_id)
-        .map_err(|_| NativeContinuationStoreError)?;
+    let upstream_response_id = PreviousResponseId::new(wire.upstream_response_id);
    let scope = parse_scope(&wire.scope)?;
    let mut pin = NativeContinuationPin::new(
        previous_response_id.clone(),
--- a/Show More
+++ b/Show More