fix: carry Claude translated-lane and usage-metering fixes (VB)

docs-site/src/content/docs/guides/claude-code.md

@@ -960,7 +960,7 @@ The proxy translates every Anthropic Messages API request into the Codex Respons
 | User `tool_result` | `function_call_output` (`is_error` → `[tool error]` prefix) |
 | `tool_reference` in a tool result | Text `Tool loaded: <tool_name>` in the paired result; preserves loaded-tool names without adding declarations or enabling translated server-side deferral |
 | `thinking` / `redacted_thinking` replay | `reasoning` items with bounded `ocxr1` envelopes for signatures and redacted payloads |
-| Function tools | `{type: "function"}` (`web_search*` → `{type: "web_search"}`) |
+| Function tools | `{type: "function"}` (`web_search*` → `{type: "web_search"}`). On a route to `api.anthropic.com`, the typed `web_search_*` and `web_fetch_*` declarations are also sent to Anthropic as declared and run server-side, unless the web-search sidecar supplies `web_search` itself. Each search or fetch comes back to the client as its `server_tool_use` block and its `web_search_tool_result` or `web_fetch_tool_result` |
 | `tool_choice` | `auto`→`auto`, `none`→`none`, `any`→`required`, named function→`{type:"function",name}`, hosted WebSearch/web_search→`{type:"web_search"}` |
 | `max_tokens` | `max_output_tokens` |
 | `stop_sequences` | `stop` |

docs-site/src/content/docs/guides/web-dashboard.md

@@ -203,7 +203,11 @@ The **Usage** summary and Models/Providers tables show end-to-end output through
 
 The **Usage** Models and Providers tables show the estimated priced portion for each row. Requests
 without a matching price or usable usage are counted as excluded beside that amount when the proxy
-reports pricing coverage fields. A row with only excluded requests shows an em dash with that count
+reports pricing coverage fields. Usage that was only partly measured (`unreported` or `unsupported`)
+is not priced, and one excluded part excludes the whole request from that row's priced count. A
+leg that reached no upstream, or that upstream refused with an HTTP error before any output, spent
+nothing and does not; a leg whose response began (or ended without a status) but reported no usage
+may have been billed, so it does. A row with only excluded requests shows an em dash with that count
 instead of a zero-dollar estimate, and a displayed zero-dollar value is a confirmed priced estimate.
 An older proxy that reports no coverage fields keeps a bare em dash with no count, so missing
 coverage stays distinct from an all-excluded row and from a confirmed zero estimate.

docs-site/src/content/docs/ja/guides/claude-code.md

@@ -535,7 +535,7 @@ Messages → Responses に変換されるリクエストでは、Claude Code の
 | Assistant `tool_use` | `function_call`(`input` → JSON 文字列に変換した `arguments`) |
 | ユーザー `tool_result` | `function_call_output`(`is_error` → `[tool error]` 接頭辞) |
 | `thinking` / `redacted_thinking` 再生 | シグネチャと秘匿ペイロードを境界付き `ocxr1` エンベロープに保持した `reasoning` 項目 |
-| Function ツール | `{type: "function"}`(`web_search*` → `{type: "web_search"}`) |
+| Function ツール | `{type: "function"}`(`web_search*` → `{type: "web_search"}`). `api.anthropic.com` への翻訳ルートでは、型付き `web_search_*` と `web_fetch_*` 宣言も Anthropic に送信され、サーバー側で実行されます。ただし Web 検索サイドカーが `web_search` を提供する場合はそちらが優先されます。検索と取得の結果は `server_tool_use` と対応する `web_search_tool_result` / `web_fetch_tool_result` としてクライアントに返されます |
 | `tool_choice` | `auto`→`auto`、`none`→`none`、`any`→`required`、名前指定関数→`{type:"function",name}`、ホスト型 WebSearch/web_search→`{type:"web_search"}` |
 | `max_tokens` | `max_output_tokens` |
 | `stop_sequences` | `stop` |

docs-site/src/content/docs/ko/guides/claude-code.md

@@ -575,7 +575,7 @@ Messages → Responses로 변환되는 요청에서는 Claude Code의 `/effort`
 | 사용자 `tool_result` | `function_call_output`(`is_error` → `[tool error]` 접두사) |
 | 도구 결과의 `tool_reference` | 짝지어진 결과에 `Tool loaded: <tool_name>` 텍스트로 보존합니다. 도구 선언을 추가하거나 번역 경로의 서버 측 지연 로딩을 활성화하지는 않습니다. |
 | `thinking` / `redacted_thinking` 재생 | 서명과 비공개 페이로드를 제한된 `ocxr1` 봉투에 담은 `reasoning` 항목 |
-| Function 도구 | `{type: "function"}`(`web_search*` → `{type: "web_search"}`) |
+| Function 도구 | `{type: "function"}`(`web_search*` → `{type: "web_search"}`). `api.anthropic.com`으로 번역하여 보내는 경로에서는 타입이 지정된 `web_search_*`와 `web_fetch_*` 선언도 Anthropic에 전달되어 서버에서 실행됩니다. 웹 검색 사이드카가 `web_search`를 제공하면 사이드카가 우선합니다. 검색과 가져오기 결과는 `server_tool_use` 및 대응하는 `web_search_tool_result` / `web_fetch_tool_result` 블록으로 클라이언트에 반환됩니다 |
 | `tool_choice` | `auto`→`auto`, `none`→`none`, `any`→`required`, 이름 지정 함수→`{type:"function",name}`, 호스팅 WebSearch/web_search→`{type:"web_search"}` |
 | `max_tokens` | `max_output_tokens` |
 | `stop_sequences` | `stop` |

docs-site/src/content/docs/reference/configuration/providers.md

@@ -100,7 +100,7 @@ separate. Full request URLs such as `/api/v1/responses` are not provider base UR
 | `maxUpstreamBodyBytes?` | `number` | `0` | Opt-in ceiling, in bytes, on a serialized native Responses **passthrough** body. `0` or omitted disables it — no limit is inferred for any destination. When set, a built body above the ceiling is refused locally before the send: streaming turns receive a terminal `response.failed` / `context_length_exceeded` so the client compacts instead of resending, and non-streaming turns receive a `413` naming the size, the number of embedded `input_image` items, and roughly how many megabytes of image data they represent. Checked at every build and rebuild point, including OAuth-refresh replay and alternate-account retry. Translated adapter paths are not covered. There is deliberately no default: the only measured ceiling here belongs to the WebSocket transport, which already falls back to HTTP for oversized turns, so a default would refuse requests that currently succeed. Set it when your gateway has a known request-size limit and you would rather see an actionable local error than an opaque upstream failure. |
 | `maxInboundBodyBytes?` | `number` | `0` | Opt-in ceiling, in bytes, on a decompressed **inbound** data-plane request body — the mirror of `maxUpstreamBodyBytes` above. `0` or omitted keeps the built-in 256 MiB default. Raise it when a large-context session can no longer compact: Codex replays the whole history to the compaction model, so on the 922k-token opt-in window the compaction request is itself the one that crosses the limit, and the session is stuck at the only operation that would have shrunk it. Clamped to 1 MiB–512 MiB. The ceiling is not negotiable: the reader materializes the body several times over (wire bytes, decoded bytes, the decoded string, and the parsed object graph), so peak memory is a multiple of whatever is admitted, and an unbounded value would be a memory exhaustion lever. Applies to `/v1/responses`, `/v1/responses/compact`, `/v1/chat/completions`, and `/v1/messages`. The listener's accept size is fixed when the proxy binds, so a change takes effect on restart. A body above the limit is refused locally with HTTP 413 and `code: "inbound_body_too_large"`, which is deliberately distinct from the `context_length_exceeded` 413 a provider size refusal produces. |
 | `modelCacheTtlMs?` | `number` | `300000` | Freshness window for the per-provider `/models` cache. |
-| `cacheRetention?` | `"none" \| "short" \| "long"` | `"short"` | Anthropic prompt-cache policy: disabled, 5-minute ephemeral, or 1-hour extended. |
+| `cacheRetention?` | `"none" \| "short" \| "long"` | `"short"` | Anthropic prompt-cache policy: disabled, 5-minute ephemeral, or 1-hour extended. When unset, a `/v1/messages` request on a translated route whose own `cache_control` breakpoints all ask for `ttl: "1h"` is treated as `"long"`; a request that mixes 1h and 5m breakpoints keeps the 5-minute default, and an explicit value always wins. |
 | `tokenGuardian?` | `OcxTokenGuardianConfig` | off | Optional proactive OAuth refresh and Codex-account warmup policy. |
 
 Across these strategies, each account's effective threshold is its `codexAccountAutoSwitchThresholds` entry when present, otherwise global `autoSwitchThreshold`. A zero override disables only proactive usage switching; startup binding, hard-lock, cooldown, entitlement checks, and failure recovery remain enforced.

docs-site/src/content/docs/reference/management-api.md

@@ -290,10 +290,11 @@ upstream model evidence remains absent rather than being inferred from the reque
 
 Failed request rows can include bounded `upstreamErrorType`, `upstreamErrorCode`, and
 `upstreamRequestId` diagnostics. On the Codex upstream WebSocket path, a bare error followed by
-EOF retains recognized rate-limit or overload codes in the synthesized failed terminal.
-Request logs record these as 429 for `rate_limit_exceeded` / `rate_limit_error`, or 503 for
-`server_is_overloaded` / `overloaded_error`. A recognized type without a code uses the same
-status. On the streaming path, an explicit unknown code records the 5xx status the Codex
+EOF retains recognized rate-limit, overload, or client-refusal codes in the synthesized failed terminal.
+Request logs record these as 429 for `rate_limit_exceeded` / `rate_limit_error`, 503 for
+`server_is_overloaded` / `overloaded_error`, and 400/401/403/404 for `invalid_request_error` /
+`authentication_error` / `permission_error` / `not_found_error`. A recognized type without a code
+uses the same status. On the streaming path, an explicit unknown code records the 5xx status the Codex
 WebSocket wrapper states as a top-level integer `status` or `status_code` (one of the two, not
 both); otherwise, and for buffered JSON callers, it remains a generic 502 failure. The client
 terminal keeps `upstream_server_error` for unknown codes either way. Bare-error status is provisional:

docs-site/src/content/docs/ru/guides/claude-code.md

@@ -571,7 +571,7 @@ Claude Code — это лишь учётные данные для доступ
 | `tool_use` ассистента | `function_call` (`input` → `arguments` в виде JSON-строки) |
 | `tool_result` пользователя | `function_call_output` (`is_error` → префикс `[tool error]`) |
 | Повтор `thinking` / `redacted_thinking` | Элементы `reasoning` с ограниченными конвертами `ocxr1` для подписей и скрытых данных |
-| Function-инструменты | `{type: "function"}` (`web_search*` → `{type: "web_search"}`) |
+| Function-инструменты | `{type: "function"}` (`web_search*` → `{type: "web_search"}`). На переведённом маршруте к `api.anthropic.com` типизированные объявления `web_search_*` и `web_fetch_*` также передаются Anthropic для выполнения на сервере, если только сайдкар веб-поиска сам не предоставляет `web_search`. Поиск и загрузка возвращаются клиенту как `server_tool_use` и соответствующий `web_search_tool_result` / `web_fetch_tool_result` |
 | `tool_choice` | `auto`→`auto`, `none`→`none`, `any`→`required`, именованная функция→`{type:"function",name}`, размещённый WebSearch/web_search→`{type:"web_search"}` |
 | `max_tokens` | `max_output_tokens` |
 | `stop_sequences` | `stop` |

docs-site/src/content/docs/zh-cn/guides/claude-code.md

@@ -497,7 +497,7 @@ Search 和图像描述沿用仓库已有的 Claude Code OAuth fingerprint 先例
 | Assistant `tool_use` | `function_call`（`input` → JSON 字符串化的 `arguments`） |
 | 用户 `tool_result` | `function_call_output`（`is_error` → `[tool error]` 前缀） |
 | 重放 `thinking` / `redacted_thinking` | `reasoning` 项；签名和脱敏载荷保存在有界 `ocxr1` 信封中 |
-| Function 工具 | `{type: "function"}`（`web_search*` → `{type: "web_search"}`） |
+| Function 工具 | `{type: "function"}`（`web_search*` → `{type: "web_search"}`）. 在到 `api.anthropic.com` 的转换路由上，带类型的 `web_search_*` 和 `web_fetch_*` 声明也会发送到 Anthropic 并在服务端执行；如果网页搜索边车提供了 `web_search`，则优先使用边车。搜索和抓取结果以 `server_tool_use` 及对应的 `web_search_tool_result` / `web_fetch_tool_result` 块返回客户端 |
 | `tool_choice` | `auto`→`auto`，`none`→`none`，`any`→`required`，指定函数→`{type:"function",name}`，托管 WebSearch/web_search→`{type:"web_search"}` |
 | `max_tokens` | `max_output_tokens` |
 | `stop_sequences` | `stop` |

scripts/test-layout/layout.json

@@ -77,6 +77,14 @@
     "owner-registry-acl.test.ts": "config",
     "minimax-combo-image-input.test.ts": "providers",
     "web-search-forced-declaration.test.ts": "web-search",
+  "usage-partly-measured-cost.test.ts": "usage",
+  "claude-gateway-output-cap.test.ts": "claude-integration",
+  "claude-client-refusal-status.test.ts": "claude-integration",
+  "claude-translated-cache-ttl.test.ts": "claude-integration",
+  "claude-translated-server-tools.test.ts": "claude-integration",
+    "web-search-loop-iteration-usage.test.ts": "web-search",
+    "web-search-loop-error-usage.test.ts": "web-search",
+    "web-search-rotation-usage-attribution.test.ts": "web-search",
     "claude-devin-output-order.test.ts": "claude-integration",
     "codex-config-preservation.test.ts": "codex-integration",
     "codex-credits.test.ts": "codex-integration",