feat(xai): B2 — enable Priority Processing on the API-key transport (#1886, closes #1875)

devlog/_plan/260818_fastwire_b2_xai/evidence/README.md

@@ -0,0 +1,17 @@
+# FastWire B2 (xAI) — UI evidence
+
+`010_logs_priority_lower_bound.png` — Logs & Debug, three seeded `xai/grok-4.6` rows
+that exercise every branch of the new pricing path:
+
+| Row | Situation | Cost cell |
+| --- | --- | --- |
+| `req-standard` | no Fast requested | `~$0.0300` |
+| `req-priority` | response-confirmed priority, prompt under the long-context threshold | `~$0.0600` — exactly the documented 2x premium over the row above |
+| `req-longctx-priority` | response-confirmed priority, prompt at or above 200k | `≥$0.8760` — the published long-context rate, marked a lower bound because xAI publishes no combined price |
+
+The `≥` prefix is the visible change: a cost that is a known floor rather than an
+estimate now says so instead of rendering as `~$`. The detail drawer explains why
+via the `priority_lower_bound` estimate reason.
+
+Captured against a local proxy with a seeded `usage.jsonl`; no live xAI request was
+billed to produce it.

docs-site/src/content/docs/fr/guides/providers.md

@@ -115,7 +115,7 @@ ocx logout <provider>
 
 | Fournisseur | Adaptateur | URL de base | Remarques |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | Catalogue Grok découvert en direct en priorité ; `grok-4.5` est le modèle de repli par défaut. |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth utilise la passerelle d'abonnement Grok CLI distincte. Le remplacement par clé API utilise `https://api.x.ai/v1` et peut injecter Priority Processing. Catalogue Grok découvert en direct en priorité ; `grok-4.5` est le modèle de repli par défaut. |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Modèles Claude ; liste des modèles récupérée en direct depuis `/v1/models`. |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Modèles de programmation Kimi K2.7/K2.6/K2.5. |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Passerelle d'abonnement Nous Research (le même service en amont que celui utilisé par Hermes Agent). Connexion par autorisation d'appareil auprès de `portal.nousresearch.com` ; le jeton d'accès est le JWT d'inférence envoyé avec chaque requête. Le catalogue mixte de modèles payants et `:free` (`tencent/hy3:free`, `stepfun/step-3.7-flash:free`, ...) est découvert en direct pour le compte connecté. Les jetons d'actualisation sont à usage unique et renouvelés à chaque actualisation. |

docs-site/src/content/docs/guides/providers.md

@@ -110,7 +110,7 @@ ocx logout <provider>
 
 | Provider | Adapter | Base URL | Notes |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | Live-first Grok catalog; `grok-4.5` is the fallback default. |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth uses the separate Grok CLI subscription gateway. The API-key override uses `https://api.x.ai/v1` and may inject Priority Processing. Live-first Grok catalog; `grok-4.5` is the fallback default. |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Claude models; live model list fetched from `/v1/models`. |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Kimi K2.7/K2.6/K2.5 coding models. |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Nous Research subscription gateway (same backend Hermes Agent uses). Device-grant login against `portal.nousresearch.com`; the access token is the per-request inference JWT. Mixed paid + `:free` model catalog (`tencent/hy3:free`, `stepfun/step-3.7-flash:free`, ...) discovered live from the signed-in account. Refresh tokens are single-use and rotated on every refresh. |

docs-site/src/content/docs/ja/guides/providers.md

@@ -105,7 +105,7 @@ ocx logout <provider>
 
 | プロバイダー | アダプター | ベース URL | 備考 |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | ライブ一覧を優先し、フォールバックのデフォルトモデルは `grok-4.5`。 |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth は独立した Grok CLI サブスクリプションゲートウェイを使用します。API キーのオーバーライドは `https://api.x.ai/v1` を使用し、Priority Processing を注入する場合があります。ライブ一覧を優先し、フォールバックのデフォルトモデルは `grok-4.5`。 |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Claude モデル; ライブモデル一覧は `/v1/models` から取得。 |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Kimi K2.7/K2.6/K2.5 コーディングモデル。 |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Nous Research サブスクリプションゲートウェイ（Hermes Agent と同じバックエンド）。`portal.nousresearch.com` へのデバイスグラントログイン; access トークンはリクエストごとの inference JWT。有料 + `:free` モデルの混在カタログ（`tencent/hy3:free`、`stepfun/step-3.7-flash:free` など）はサインイン中のアカウントからライブ探索されます。Refresh トークンは単回使用で、更新のたびにローテーションされます。 |

docs-site/src/content/docs/ko/guides/providers.md

@@ -104,7 +104,7 @@ ocx logout <provider>
 
 | 프로바이더 | 어댑터 | 베이스 URL | 비고 |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | 실시간 목록을 우선 사용하며, 폴백 기본 모델은 `grok-4.5`입니다. |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth는 별도의 Grok CLI 구독 게이트웨이를 사용합니다. API 키 오버라이드는 `https://api.x.ai/v1`을 사용하며 Priority Processing을 주입할 수 있습니다. 실시간 목록을 우선 사용하며, 폴백 기본 모델은 `grok-4.5`입니다. |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Claude 모델; 실시간 모델 목록은 `/v1/models`에서 가져옵니다. |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Kimi K2.7/K2.6/K2.5 코딩 모델. |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Nous Research 구독 게이트웨이(Hermes Agent와 동일한 백엔드). `portal.nousresearch.com`에 대한 디바이스 그랜트 로그인; access 토큰은 요청별 inference JWT. 유료 + `:free` 모델 혼합 카탈로그(`tencent/hy3:free`, `stepfun/step-3.7-flash:free` 등)는 로그인한 계정에서 실시간으로 발견됩니다. Refresh 토큰은 단회 사용이며, 갱신할 때마다 회전됩니다. |

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

@@ -87,7 +87,7 @@ differing backup and rewrites known legacy namespaced selected ids to bare ids.
 | `modelMaxInputTokens?` | `Record<string, number>` | Positive per-model max input limits used for catalog auto-compaction hints. |
 | `defaultMaxOutputTokens?` | `number` | Provider-wide `openai-chat` fallback when the client omits `max_output_tokens`. |
 | `modelMaxOutputTokens?` | `Record<string, number>` | Positive per-model `openai-chat` fallback budgets; exact/pattern matches beat the provider default. |
-| `modelCosts?` | `Record<string, Cost4>` | Per-model display prices (USD per 1M tokens), keyed by that provider's exact upstream model id — not a provider identifier or a routed `provider/model` label, e.g. `{ "deepseek-v4-flash": { "input": 0.14, "output": 0.28, "cacheRead": 0.0028, "cacheWrite": 0 } }`. Any model id is a valid key — custom providers may target any OpenAI-compatible endpoint through the `openai-chat` adapter, and local or internal provider ids work even when they are absent from the built-in catalogs. User-configured prices win over the built-in catalogs in the Logs `~$` and Usage estimates; historical entries are repriced from the current overlay, so editing a price can move past totals. The fallback order is user `modelCosts` → jawcode catalog → expected-price overlay → model-level vendor fallback, and an all-zero entry falls through to the next source in that sequence. Each rate must be a non-negative finite number at most 1,000,000 (USD per 1M tokens); out-of-range rows are rejected by the management boundary and dropped on load. Display-time estimation only: overlays never affect routing, account selection, quotas, or billing. |
+| `modelCosts?` | `Record<string, Cost4>` | Per-model display prices (USD per 1M tokens), keyed by that provider's exact upstream model id — not a provider identifier or a routed `provider/model` label, e.g. `{ "deepseek-v4-flash": { "input": 0.14, "output": 0.28, "cacheRead": 0.0028, "cacheWrite": 0 } }`. Any model id is a valid key — custom providers may target any OpenAI-compatible endpoint through the `openai-chat` adapter, and local or internal provider ids work even when they are absent from the built-in catalogs. User-configured prices win over the built-in catalogs in the Logs `~$` and Usage estimates; historical entries are repriced from the current overlay, so editing a price can move past totals. The fallback order is user `modelCosts` → exact official correction → jawcode catalog → expected-price overlay → model-level vendor fallback, and an all-zero entry falls through to the next source in that sequence. Each rate must be a non-negative finite number at most 1,000,000 (USD per 1M tokens); out-of-range rows are rejected by the management boundary and dropped on load. Display-time estimation only: overlays never affect routing, account selection, quotas, or billing. |
 | `headers?` | `Record<string, string>` | Extra upstream headers. Authorization, cookies, API-key headers, embedded newlines, and invalid names are rejected. |
 | `openRouterRouting?` | `OpenRouterProviderRouting` | Default OpenRouter `order`, `only`, and `allowFallbacks` preferences; valid only for canonical OpenRouter with `openai-chat`. |
 | `modelOpenRouterRouting?` | `Record<string, OpenRouterProviderRouting>` | Exact model-id overrides that replace the provider-wide OpenRouter preference. |
@@ -152,6 +152,25 @@ contract; existing configurations see these migration deltas:
 
 Explicit capability `false` and Responses caller-tier forwarding retain their existing contracts.
 
+### xAI Priority Processing
+
+The built-in `xai` preset advertises and injects Fast only when its effective transport uses
+`authMode: "key"`. API-key mode targets `https://api.x.ai/v1` through the `openai-chat` adapter and
+sends `service_tier: "priority"` through Chat Completions. `ocx login xai`
+instead stores OAuth credentials for the separate Grok CLI subscription-gateway flow, so OAuth
+remains unclassified: its catalog rows do not advertise Fast and the proxy does not inject a tier.
+
+xAI charges Priority Processing at 2× the standard token price for input, output, cached, and
+reasoning tokens; cache discounts are applied before the multiplier. Cost estimates use that premium
+only when xAI's response confirms `service_tier: "priority"`. A missing or unparsed response tier is
+not confirmation, and an echoed `default` is a downgrade; all three stay at the standard price.
+
+For `grok-4.6`, the standard rate per 1M tokens is $2.00 input, $0.50 cached input, and $6.00
+output. A prompt of at least 200,000 tokens reprices the whole request at $4.00 / $1.00 / $12.00.
+xAI has not published how that long-context band combines with Priority Processing. When a
+long-context response confirms `priority`, the dashboard therefore shows the published long-context
+cost with a `≥` marker and a lower-bound explanation; it never invents a stacked multiplier.
+
 ### OpenRouter Fast
 
 The canonical `https://openrouter.ai/api/v1` preset advertises Fast only for these exact

docs-site/src/content/docs/ru/guides/providers.md

@@ -114,7 +114,7 @@ ocx logout <provider>
 
 | Провайдер | Адаптер | Базовый URL | Примечания |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | Каталог Grok загружается в реальном времени; фолбэк по умолчанию — `grok-4.5`. |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth использует отдельный шлюз подписки Grok CLI. Переопределение с API-ключом использует `https://api.x.ai/v1` и может добавлять Priority Processing. Каталог Grok загружается в реальном времени; фолбэк по умолчанию — `grok-4.5`. |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Модели Claude; актуальный список моделей загружается из `/v1/models`. |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Модели Kimi K2.7/K2.6/K2.5 для кодинга. |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Шлюз подписки Nous Research (тот же бэкенд, что использует Hermes Agent). Вход по device grant против `portal.nousresearch.com`; access-токен — это JWT для каждого запроса к inference. Смешанный каталог платных + `:free` моделей (`tencent/hy3:free`, `stepfun/step-3.7-flash:free`, …) обнаруживается вживую по авторизованному аккаунту. Refresh-токены одноразовые и ротируются при каждом обновлении. |

docs-site/src/content/docs/tr/guides/providers.md

@@ -129,7 +129,7 @@ ocx logout <saglayici>
 
 | Sağlayıcı | Adaptör | Temel URL | Notlar |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | Canlı öncelikli Grok kataloğu; `grok-4.5` geri dönüş varsayılanıdır. |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth ayrı Grok CLI abonelik ağ geçidini kullanır. API anahtarı geçersiz kılması `https://api.x.ai/v1` kullanır ve Priority Processing ekleyebilir. Canlı öncelikli Grok kataloğu; `grok-4.5` geri dönüş varsayılanıdır. |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Claude modelleri; canlı model listesi `/v1/models` üzerinden getirilir. |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Kimi K2.7/K2.6/K2.5 kodlama modelleri. |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Nous Research abonelik ağ geçidi (Hermes Agent'ın kullandığı aynı arka uç). `portal.nousresearch.com`'a karşı cihaz yetkilendirmesi girişi; erişim belirteci istek başına çıkarım JWT'sidir. Oturum açmış hesaptan canlı olarak keşfedilen karışık ücretli + `:free` model kataloğu (`tencent/hy3:free`, `stepfun/step-3.7-flash:free`, ...). Yenileme belirteçleri tek kullanımlıktır ve her yenilemede döndürülür. |

docs-site/src/content/docs/zh-cn/guides/providers.md

@@ -95,7 +95,7 @@ ocx logout <provider>
 
 | 提供商 | Adapter | 基础 URL | 备注 |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | 优先使用实时 Grok 目录；回退默认模型为 `grok-4.5`。 |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth 使用独立的 Grok CLI 订阅网关。API 密钥覆盖模式使用 `https://api.x.ai/v1`，并可能注入 Priority Processing。优先使用实时 Grok 目录；回退默认模型为 `grok-4.5`。 |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Claude 模型；实时模型列表从 `/v1/models` 获取。 |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Kimi K2.7/K2.6/K2.5 编程模型。 |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Nous Research 订阅网关（与 Hermes Agent 使用同一后端）。通过设备授权登录 `portal.nousresearch.com`；access 令牌是每个请求的 inference JWT。付费 + `:free` 模型混合目录（`tencent/hy3:free`、`stepfun/step-3.7-flash:free` 等）会从已登录账户实时发现。Refresh 令牌是单次使用，每次刷新都会轮换。 |

docs-site/src/content/docs/zh-tw/guides/providers.md

@@ -103,7 +103,7 @@ ocx logout <provider>
 
 | 供應商 | Adapter | Base URL | 備註 |
 | --- | --- | --- | --- |
-| `xai` | `openai-chat` | `https://api.x.ai/v1` | 優先使用即時 Grok catalog；fallback 預設為 `grok-4.5`。 |
+| `xai` | `openai-chat` | `https://cli-chat-proxy.grok.com/v1` | OAuth 使用獨立的 Grok CLI 訂閱 gateway。API key 覆寫使用 `https://api.x.ai/v1`，並可能注入 Priority Processing。優先使用即時 Grok catalog；fallback 預設為 `grok-4.5`。 |
 | `anthropic` | `anthropic` | `https://api.anthropic.com` | Claude 模型；即時模型列表從 `/v1/models` 取得。 |
 | `kimi` | `openai-chat` | `https://api.kimi.com/coding/v1` | Kimi K2.7/K2.6/K2.5 coding 模型。 |
 | `nous` | `openai-chat` | `https://inference-api.nousresearch.com/v1` | Nous Research 訂閱 gateway（Hermes Agent 使用相同 backend）。透過 `portal.nousresearch.com` 做 device-grant 登入；access token 是每次請求使用的 inference JWT。混合付費與 `:free` 模型 catalog（`tencent/hy3:free`、`stepfun/step-3.7-flash:free` 等）會從已登入帳號即時探索。Refresh token 為單次使用，每次 refresh 都會輪換。 |

gui/src/i18n/de.ts

@@ -717,7 +717,7 @@ export const de: Record<TKey, string> = {
   "logs.detail.estimate.cache_detail_missing": "Cache-Details fehlen; Eingabe ist als Obergrenze geschätzt.",
   "logs.detail.estimate.expected_price_overlay": "Ein verifizierter Expected-Listenpreis wurde verwendet.",
   "logs.detail.estimate.provider_cost_overlay": "Ein vom Anbieter konfiguriertes Preis-Overlay wurde verwendet.",
-  "logs.detail.estimate.priority_lower_bound": "Der bestätigte OpenRouter-Priority-Preis ist nicht verfügbar; die angezeigte Standardpreisschätzung ist eine bekannte Untergrenze.",
+  "logs.detail.estimate.priority_lower_bound": "Der bestätigte Priority-Preis ist nicht verfügbar; die angezeigte Schätzung ist eine bekannte Untergrenze.",
   "logs.col.error": "Fehler",
   "logs.col.upstreamReason": "Upstream-Grund",
   "logs.col.duration": "Dauer",

gui/src/i18n/en.ts

@@ -750,7 +750,7 @@ export const en = {
   "logs.detail.estimate.cache_detail_missing": "Cache details were unavailable; input is an upper-bound estimate.",
   "logs.detail.estimate.expected_price_overlay": "A verified expected list price was used.",
   "logs.detail.estimate.provider_cost_overlay": "A provider-configured price overlay was used.",
-  "logs.detail.estimate.priority_lower_bound": "The confirmed OpenRouter priority price is unavailable; the displayed standard-price estimate is a known lower bound.",
+  "logs.detail.estimate.priority_lower_bound": "The confirmed Priority price is unavailable; the displayed estimate is a known lower bound.",
   "logs.col.error": "Error",
   "logs.col.upstreamReason": "Upstream reason",
   "logs.col.duration": "Duration",

gui/src/i18n/fr.ts

@@ -731,7 +731,7 @@ export const fr: Record<TKey, string> = {
   "logs.detail.estimate.cache_detail_missing": "Les détails du cache n’étaient pas disponibles ; l’entrée est une estimation de la limite supérieure.",
   "logs.detail.estimate.expected_price_overlay": "Un tarif catalogue attendu et vérifié a été utilisé.",
   "logs.detail.estimate.provider_cost_overlay": "Un remplacement de tarif configuré pour le fournisseur a été utilisé.",
-  "logs.detail.estimate.priority_lower_bound": "Le tarif Priority OpenRouter confirmé n’est pas disponible ; l’estimation au tarif standard affichée est une borne inférieure connue.",
+  "logs.detail.estimate.priority_lower_bound": "Le tarif Priority confirmé n’est pas disponible ; l’estimation affichée est une borne inférieure connue.",
   "logs.col.error": "Erreur",
   "logs.col.upstreamReason": "Motif en amont",
   "logs.col.duration": "Durée",

gui/src/i18n/ja.ts

@@ -693,7 +693,7 @@ export const ja: Record<TKey, string> = {
   "logs.detail.estimate.cache_detail_missing": "キャッシュの詳細が利用できませんでした; 入力は上限の推定です。",
   "logs.detail.estimate.expected_price_overlay": "検証済みの予想定価が使用されました。",
   "logs.detail.estimate.provider_cost_overlay": "プロバイダー設定の価格オーバーレイが使用されました。",
-  "logs.detail.estimate.priority_lower_bound": "確認済みの OpenRouter Priority 価格は取得できないため、表示される標準価格の見積もりは既知の下限です。",
+  "logs.detail.estimate.priority_lower_bound": "確認済みの Priority 価格を利用できないため、表示される見積もりは既知の下限です。",
   "logs.col.error": "エラー",
   "logs.col.upstreamReason": "上流の理由",
   "logs.col.duration": "所要時間",