From 49c5c7012f1f27d781079231dde92562ced68594 Mon Sep 17 00:00:00 2001 From: Yuxin Qiao <104957188+Yuxin-Qiao@users.noreply.github.com> Date: Sun, 4 Oct 2026 00:49:07 +0800 Subject: [PATCH] fix(responses): honor reset replay grants on translated dispatch --- .../fr/reference/configuration/providers.md | 2 +- .../ja/reference/configuration/providers.md | 2 +- .../ko/reference/configuration/providers.md | 2 +- .../docs/reference/configuration/providers.md | 2 +- .../ru/reference/configuration/providers.md | 2 +- .../tr/reference/configuration/providers.md | 2 +- .../reference/configuration/providers.md | 2 +- .../reference/configuration/providers.md | 2 +- scripts/test-layout/layout.json | 1 + src/server/responses/adapter-dispatch.ts | 28 ++++- src/types/provider.ts | 2 +- structure/transports/responses-failover.md | 2 +- tests/fixtures/test-layout-expected.json | 1 + .../responses-translated-reset.test.ts | 110 ++++++++++++++++++ 14 files changed, 146 insertions(+), 14 deletions(-) create mode 100644 tests/responses/responses-translated-reset.test.ts diff --git a/docs-site/src/content/docs/fr/reference/configuration/providers.md b/docs-site/src/content/docs/fr/reference/configuration/providers.md index b939aff7146..257562a75d0 100644 --- a/docs-site/src/content/docs/fr/reference/configuration/providers.md +++ b/docs-site/src/content/docs/fr/reference/configuration/providers.md @@ -143,7 +143,7 @@ sauvegarde dont le contenu diffère, puis réécrit en identifiants sans préfix | `responsesSnapshotRepair?` | `boolean` | Réparation côté client désactivée par défaut pour les instantanés du cycle de vie des réponses clairsemés dans SSE et JSON. Remplit les métadonnées d'état canonique, de sortie et d'outil manquantes tandis que l'inspection brute et la persistance restent inchangées. | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | Fournisseurs à clé API uniquement (`authMode: "key"`). Nouvelle tentative facultative sur la même cible après un 429 : lorsque `retryOn429` est absent, la fonctionnalité est désactivée ; la présence d'un objet l'active, sauf avec `enabled: false`. Après un 429, le proxy attend selon `Retry-After` reçu en amont ou selon l'intervalle fixe, puis relit la requête à l'identique avec la même clé avant tout basculement de clé. Ce comportement couvre la boucle principale de récupération d'un tour textuel, le protocole de transfert Responses, le pont d'images et de vidéos, le service auxiliaire de recherche Web et les continuations du terminal. Seules les réponses HTTP 429 reçues avant le début de la diffusion peuvent être relues ; les transports `runTurn` personnalisés ne font pas partie de la boucle de nouvelle tentative HTTP. `attempts` compte les relectures avec la même clé après le premier 429, soit `attempts` + 1 envois au total, et constitue un budget commun à toute la requête, partagé entre la boucle principale de récupération, la continuation de la garde du terminal et les nouvelles tentatives du pont. L'épuisement de `attempts` arrête uniquement les relectures supplémentaires avec la même clé : le basculement normal de clé ou la gestion de l'erreur finale s'applique ensuite selon les cibles disponibles. Sur le protocole de transfert authentifié par clé, aucun basculement n'est possible ; le 429 final est donc renvoyé sans modification. Codex ne retente jamais lui-même une requête après un 429 : cette option constitue ainsi la seule protection pour les fournisseurs à clé unique. Valeurs par défaut : `enabled: true`, `attempts: 3`, `intervalMs: 5000`, `maxIntervalMs: 60000` (chaque attente est plafonnée à `maxIntervalMs`, lui-même plafonné à 600000), `respectRetryAfter: true`. | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | Fournisseurs `openai-chat` et `openai-responses` authentifiés par clé uniquement. Les fournisseurs `authMode: "forward"` (le pool de comptes ChatGPT) ne lisent jamais cette option et conservent l'échelle par défaut. Nouvelle tentative facultative pour les états transitoires reçus en amont avant le début de la diffusion (500, 502, 503, 504, 520, 521, 522) : l'absence de l'option la désactive ; la présence d'un objet l'active, sauf avec `enabled: false`. Ce comportement couvre la requête Responses initiale, la continuation de la garde du terminal, le point de terminaison natif `/v1/chat/completions` et les réémissions liées à la récupération après un 429 ou à la récupération de compte. `attempts` représente le nombre TOTAL d'envois en amont autorisés pour une requête, premier envoi compris (de 1 à 10, valeur par défaut : 3). Il constitue un budget commun à la requête, partagé avec la récupération après une réinitialisation de connexion ; ainsi, `3` signifie qu'au plus trois requêtes réelles atteignent le fournisseur. Les attentes utilisent une temporisation exponentielle à base fixe de 400 ms, plafonnée à 5 s, et respectent `Retry-After`. Cette option est distincte de `retryOn429`, qui traite la limitation de débit ; les échecs en cours de diffusion ne sont jamais relus. | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Fournisseurs `openai-responses` natifs uniquement, `authMode: "forward"` compris. Remplacement facultatif d'un envoi qui a échoué alors que l'appelant n'avait rien observé : l'absence de l'option la désactive ; la présence d'un objet l'active, sauf avec `enabled: false`. Couvre les deux étapes ambiguës — une connexion rompue avant tout en-tête de réponse, et un corps SSE rompu après l'en-tête alors qu'il ne portait que des événements de contrôle. Une WebSocket canonique ChatGPT en amont qui s'est fermée ou a échoué après l'envoi de sa trame de création, avant tout événement Responses, est couverte de la même façon ; son remplacement est envoyé en HTTP. Seule une requête autonome est remplacée : `store: false`, `input` complet, ni `previous_response_id`, ni `conversation`, ni `stream_id`, et uniquement des outils exécutés par le client. `replacements` est le nombre d'envois de remplacement qu'UNE requête logique peut effectuer, toutes étapes et tous enfants de combo confondus (de 1 à 2, valeur par défaut : 1). Ce n'est ni un nombre de tentatives par étape ni un budget d'envoi : un remplacement doit toujours tenir dans l'allocation d'envois dont l'étape disposait déjà. Une requête qui a déjà émis une sortie ou un appel d'outil n'est jamais remplacée, quelle que soit cette valeur. L'inférence de remplacement peut tout de même être facturée si l'origine avait déjà démarré la première, d'où la désactivation par défaut. | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Fournisseurs `openai-responses` natifs, `authMode: "forward"` compris. Remplacement facultatif d'un envoi qui a échoué alors que l'appelant n'avait rien observé : l'absence de l'option la désactive ; la présence d'un objet l'active, sauf avec `enabled: false`. Couvre les deux étapes ambiguës — une connexion rompue avant tout en-tête de réponse, et un corps SSE rompu après l'en-tête alors qu'il ne portait que des événements de contrôle. Une WebSocket canonique ChatGPT en amont qui s'est fermée ou a échoué après l'envoi de sa trame de création, avant tout événement Responses, est couverte de la même façon ; son remplacement est envoyé en HTTP. Seule une requête autonome est remplacée : `store: false`, `input` complet, ni `previous_response_id`, ni `conversation`, ni `stream_id`, et uniquement des outils exécutés par le client. `replacements` est le nombre d'envois de remplacement qu'UNE requête logique peut effectuer, toutes étapes et tous enfants de combo confondus (de 1 à 2, valeur par défaut : 1). Ce n'est ni un nombre de tentatives par étape ni un budget d'envoi : un remplacement doit toujours tenir dans l'allocation d'envois dont l'étape disposait déjà. Une requête qui a déjà émis une sortie ou un appel d'outil n'est jamais remplacée, quelle que soit cette valeur. L'inférence de remplacement peut tout de même être facturée si l'origine avait déjà démarré la première, d'où la désactivation par défaut. Les requêtes Responses traduites vers chat prennent aussi en charge le remplacement avant les en-têtes, avec la même autorisation et le même budget ; les erreurs du flux traduit après les en-têtes restent exclues. | | `autoToolChoiceOnlyModels?` | `string[]` | Modèles dont `tool_choice` accepte uniquement `auto` ou `none` ; les choix forcés sont dévalorisés. | | `preserveReasoningContentModels?` | `string[]` | Modèles nécessitant un assistant préalable `reasoning_content` dans l'historique des discussions. Les enregistrements depuis le tableau de bord conservent la liste enregistrée, y compris `[]`. `PATCH /api/providers?name=` accepte un tableau ou `null` pour l'effacer. Une sauvegarde qui déplace le fournisseur vers un autre adaptateur, une autre URL de base ou un autre mode d'authentification ne la conserve pas (voir la section ci-dessous). | | `reasoningDetailsModels?` | `string[]` | Modèles dont le point de terminaison renvoie la réflexion sous forme de tableau structuré `reasoning_details` (MiniMax série M avec `reasoning_split`) ; les deltas de flux sont des instantanés cumulatifs comparés par préfixe, et la réflexion conservée est rejouée sous forme de tableau `reasoning_details` plutôt que de chaîne `reasoning_content`. | diff --git a/docs-site/src/content/docs/ja/reference/configuration/providers.md b/docs-site/src/content/docs/ja/reference/configuration/providers.md index e7f99b8cacb..e485938c7dc 100644 --- a/docs-site/src/content/docs/ja/reference/configuration/providers.md +++ b/docs-site/src/content/docs/ja/reference/configuration/providers.md @@ -135,7 +135,7 @@ account を削除しても mapping は保持され、同じ id を再追加す | `responsesSnapshotRepair?` | `boolean` | デフォルトで無効のクライアント向け修復です。SSE と JSON の Responses ライフサイクルで欠落した status、output、ツールメタデータを補完し、raw 検査と永続化は変更しません。 | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | API-key プロバイダーのみ(`authMode: "key"`)。オプトインの同一ターゲット 429 リトライ: `retryOn429` が無ければ無効で、オブジェクトがあれば `enabled: false` でない限り有効になります。429 時に待機(上流の `Retry-After` または固定間隔)してから、キー フェイルオーバーの前に同一キーで同一リクエストを再送します — メインのテキストターン回復ループ、Responses passthrough、画像/動画ブリッジ、web-search サイドカー、ターミナル継続要求をすべてカバーします。再送の対象はプリストリームの HTTP 429 応答のみで、カスタム `runTurn` トランスポートは HTTP リトライループの対象外です。`attempts` は最初の 429 以降の同一キー再送回数(合計送信数 = `attempts` + 1)で、メインの回復ループ・ターミナルガード継続・ブリッジ再試行で共有されるリクエスト単位の予算です。`attempts` を使い切っても同一キーでの再送が止まるだけで、通常のキー フェイルオーバーまたは最終エラー処理が利用可能なターゲットに応じて続きます — キー認証の passthrough ワイヤにはフェイルオーバーがないため、使い切った 429 はそのまま返ります。Codex 自体は 429 をリトライしないため、単一キーのプロバイダーでは唯一の防御です。デフォルト: `enabled: true`、`attempts: 3`、`intervalMs: 5000`、`maxIntervalMs: 60000`(1回の待機は `maxIntervalMs` で上限、その上限は 600000)、`respectRetryAfter: true`。 | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | キー認証の `openai-chat` および `openai-responses` プロバイダーのみ。`authMode: "forward"` のプロバイダー（ChatGPT アカウントプール）はこのオプションを読まず、既定の再試行段数を維持します。ストリーム開始前に上流から返される一時的なステータス（500、502、503、504、520、521、522）に対するオプトインの再試行です。設定がなければ無効で、オブジェクトを指定すると `enabled: false` でない限り有効になります。最初の Responses リクエスト、ターミナルガード継続、ネイティブの `/v1/chat/completions`、および 429／アカウント回復時の再取得が対象です。`attempts` は最初の送信を含め、1 回のリクエストで許可される上流への送信総数です（1～10、デフォルトは 3）。接続リセット回復と共有するリクエスト単位の単一予算であるため、`3` を指定した場合、プロバイダーに到達する実リクエストは最大 3 回です。待機には 400 ms を基準とする固定式の指数バックオフを使用し、上限は 5 秒で、`Retry-After` に従います。レート制限を扱う `retryOn429` とは別の機能であり、ストリーム開始後の失敗は再送されません。 | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | ネイティブ `openai-responses` プロバイダー専用で、`authMode: "forward"` も含みます。呼び出し側が何も観測しないまま失敗した送信を、オプトインで置き換えます。設定がなければ無効で、オブジェクトを指定すると `enabled: false` でない限り有効になります。レスポンスヘッダーが届く前に接続が切れた場合と、ヘッダー後に SSE 本文が制御イベントだけを運んだまま切れた場合の両方が対象です。canonical ChatGPT upstream WebSocket で create フレームの送信後、Responses イベントが届く前にソケットが閉じたかエラーになった場合も同じく対象で、その置き換えは HTTP で送信します。置き換えるのは自己完結したリクエストだけで、`store: false`、完全な `input`、`previous_response_id` / `conversation` / `stream_id` がないこと、クライアントが実行するツールのみ、が条件です。`replacements` は、すべてのレッグとすべてのコンボ子リクエストを合わせて 1 つの論理リクエストが行える置き換え送信の回数です（1..2、デフォルトは 1）。レッグ単位の再試行回数でも送信予算でもないため、置き換え送信もそのレッグがすでに持つ送信許容量に収まる必要があります。すでに出力やツール呼び出しを送ったリクエストは、この値に関わらず置き換えません。元の送信がすでに開始されていた場合は置き換えた推論も課金される可能性があるため、既定では無効です。 | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | ネイティブ `openai-responses` プロバイダーに適用され、、`authMode: "forward"` も含みます。呼び出し側が何も観測しないまま失敗した送信を、オプトインで置き換えます。設定がなければ無効で、オブジェクトを指定すると `enabled: false` でない限り有効になります。レスポンスヘッダーが届く前に接続が切れた場合と、ヘッダー後に SSE 本文が制御イベントだけを運んだまま切れた場合の両方が対象です。canonical ChatGPT upstream WebSocket で create フレームの送信後、Responses イベントが届く前にソケットが閉じたかエラーになった場合も同じく対象で、その置き換えは HTTP で送信します。置き換えるのは自己完結したリクエストだけで、`store: false`、完全な `input`、`previous_response_id` / `conversation` / `stream_id` がないこと、クライアントが実行するツールのみ、が条件です。`replacements` は、すべてのレッグとすべてのコンボ子リクエストを合わせて 1 つの論理リクエストが行える置き換え送信の回数です（1..2、デフォルトは 1）。レッグ単位の再試行回数でも送信予算でもないため、置き換え送信もそのレッグがすでに持つ送信許容量に収まる必要があります。すでに出力やツール呼び出しを送ったリクエストは、この値に関わらず置き換えません。元の送信がすでに開始されていた場合は置き換えた推論も課金される可能性があるため、既定では無効です。 Responses から chat への変換経路でも、同じ許可と送信予算でヘッダー受信前の切断を置き換えます。変換ストリームのヘッダー受信後の障害は対象外です。 | | `autoToolChoiceOnlyModels?` | `string[]` | `tool_choice` が `auto` または `none` のみを受け入れるモデル。強制的な選択は格下げされます。 | | `preserveReasoningContentModels?` | `string[]` |チャット履歴に以前のアシスタント `reasoning_content` が必要なモデル。ダッシュボードから保存しても、保存済みのリスト（`[]` を含む）は保持されます。`PATCH /api/providers?name=` は配列、または消去するための `null` を受け付けます。 アダプター、ベース URL、または認証モードを変えて別の宛先に移す保存では保持されません（下の節を参照）。 | | `reasoningDetailsModels?` | `string[]` | thinking を構造化された `reasoning_details` 配列で返すモデル（`reasoning_split` 使用の MiniMax M シリーズ）。ストリーム差分は累積スナップショットとして prefix-diff され、保持された reasoning は `reasoning_content` 文字列ではなく `reasoning_details` 配列としてリプレイされます。 | diff --git a/docs-site/src/content/docs/ko/reference/configuration/providers.md b/docs-site/src/content/docs/ko/reference/configuration/providers.md index 1f15a246edc..c5eb3fca4f6 100644 --- a/docs-site/src/content/docs/ko/reference/configuration/providers.md +++ b/docs-site/src/content/docs/ko/reference/configuration/providers.md @@ -135,7 +135,7 @@ managed map을 활성화하면 privacy-safe selector를 만들고, 이후 계정 | `responsesSnapshotRepair?` | `boolean` | 기본값이 꺼진 클라이언트용 복구입니다. SSE와 JSON의 Responses 수명 주기에서 누락된 status, output, 도구 메타데이터를 채우며 raw 검사와 영속화는 변경하지 않습니다. | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | API-key 프로바이더 전용(`authMode: "key"`). 동일 대상 429 재시도: `retryOn429`가 없으면 기능이 꺼져 있고, 객체가 있으면 `enabled: false`가 아닌 한 활성화됩니다. 429 시 대기(업스트림 `Retry-After` 또는 고정 간격) 후 키 장애 조치 전에 동일 키로 동일 요청을 재전송합니다 — 일반 텍스트 턴 복구 루프, Responses passthrough, 이미지/비디오 브리지, web-search 사이드카, 터미널 연속 요청을 모두 포함합니다. 재전송 대상은 프리스트림 HTTP 429 응답뿐이며, 커스텀 `runTurn` 전송은 HTTP 재시도 루프에서 제외됩니다. `attempts`는 첫 429 이후의 동일 키 재전송 횟수(총 전송 = `attempts` + 1)이며, 메인 복구 루프·터미널 가드 연속 요청·브리지 재시도가 공유하는 요청 단위 예산입니다. `attempts`를 모두 소진해도 동일 키 재전송만 중단되며, 이후에는 일반 키 장애 조치 또는 최종 오류 처리가 사용 가능한 대상에 따라 진행됩니다 — 키 인증 passthrough 와이어에는 장애 조치가 없으므로 소진된 429가 그대로 반환됩니다. Codex 자체는 429를 재시도하지 않으므로 단일 키 프로바이더의 유일한 방어선입니다. 기본값: `enabled: true`, `attempts: 3`, `intervalMs: 5000`, `maxIntervalMs: 60000`(단일 대기는 `maxIntervalMs`로 상한, 그 자체는 600000으로 상한), `respectRetryAfter: true`. | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | 키 인증 `openai-chat` 및 `openai-responses` 프로바이더 전용입니다. `authMode: "forward"` 프로바이더(ChatGPT 계정 풀)는 이 옵션을 읽지 않고 기본 재시도 단계를 유지합니다. 스트림 시작 전의 일시적인 업스트림 상태(500, 502, 503, 504, 520, 521, 522)를 선택적으로 재시도합니다. 이 옵션이 없으면 꺼져 있고, 객체가 있으면 `enabled: false`가 아닌 한 활성화됩니다. 최초 Responses 요청, 터미널 가드 연속 요청, 네이티브 `/v1/chat/completions`, 429/계정 복구 재조회를 포함합니다. `attempts`는 최초 전송을 포함하여 요청 하나에 허용되는 업스트림 전송의 총횟수(1..10, 기본값 3)입니다. 연결 재설정 복구와 요청 단위 예산 하나를 공유하므로 `3`이면 실제로 프로바이더에 도달하는 요청은 최대 세 번입니다. 대기에는 400ms로 고정된 지수 백오프를 사용하고 상한은 5초이며 `Retry-After`를 따릅니다. 속도 제한을 처리하는 `retryOn429`와는 별개이며, 스트림 도중의 실패는 절대 재전송하지 않습니다. | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | 네이티브 `openai-responses` 프로바이더 전용이며 `authMode: "forward"`도 포함합니다. 호출자가 아무것도 관측하지 못한 채 실패한 전송을 선택적으로 대체합니다. 이 옵션이 없으면 꺼져 있고, 객체가 있으면 `enabled: false`가 아닌 한 활성화됩니다. 응답 헤더가 오기 전에 연결이 끊어진 경우와, 헤더 이후 SSE 본문이 제어 이벤트만 실은 채 끊어진 경우를 모두 다룹니다. canonical ChatGPT 업스트림 WebSocket에서 create 프레임을 보낸 뒤 Responses 이벤트가 오기 전에 소켓이 닫히거나 오류가 난 경우도 같은 방식으로 다루며, 이때 대체 전송은 HTTP로 보냅니다. 자체 완결된 요청만 대체합니다. `store: false`, 완전한 `input`, `previous_response_id`·`conversation`·`stream_id` 없음, 클라이언트가 실행하는 도구만 해당합니다. `replacements`는 모든 구간과 모든 콤보 자식을 합쳐 논리 요청 하나가 만들 수 있는 대체 전송 횟수입니다(1..2, 기본값 1). 구간별 재시도 횟수도 전송 예산도 아니므로, 대체 전송도 해당 구간이 이미 가진 전송 허용량 안에 들어가야 합니다. 이미 출력이나 도구 호출을 내보낸 요청은 이 값과 무관하게 대체하지 않습니다. 원본 전송이 이미 시작됐다면 대체한 추론도 과금될 수 있어서 기본값은 꺼짐입니다. | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | 네이티브 `openai-responses` 프로바이더에 적용되며 `authMode: "forward"`도 포함합니다. 호출자가 아무것도 관측하지 못한 채 실패한 전송을 선택적으로 대체합니다. 이 옵션이 없으면 꺼져 있고, 객체가 있으면 `enabled: false`가 아닌 한 활성화됩니다. 응답 헤더가 오기 전에 연결이 끊어진 경우와, 헤더 이후 SSE 본문이 제어 이벤트만 실은 채 끊어진 경우를 모두 다룹니다. canonical ChatGPT 업스트림 WebSocket에서 create 프레임을 보낸 뒤 Responses 이벤트가 오기 전에 소켓이 닫히거나 오류가 난 경우도 같은 방식으로 다루며, 이때 대체 전송은 HTTP로 보냅니다. 자체 완결된 요청만 대체합니다. `store: false`, 완전한 `input`, `previous_response_id`·`conversation`·`stream_id` 없음, 클라이언트가 실행하는 도구만 해당합니다. `replacements`는 모든 구간과 모든 콤보 자식을 합쳐 논리 요청 하나가 만들 수 있는 대체 전송 횟수입니다(1..2, 기본값 1). 구간별 재시도 횟수도 전송 예산도 아니므로, 대체 전송도 해당 구간이 이미 가진 전송 허용량 안에 들어가야 합니다. 이미 출력이나 도구 호출을 내보낸 요청은 이 값과 무관하게 대체하지 않습니다. 원본 전송이 이미 시작됐다면 대체한 추론도 과금될 수 있어서 기본값은 꺼짐입니다. Responses에서 chat으로 변환하는 요청도 같은 권한과 전송 예산으로 헤더 수신 전 연결 종료를 대체합니다. 변환 스트림의 헤더 수신 후 오류는 포함하지 않습니다. | | `autoToolChoiceOnlyModels?` | `string[]` | `tool_choice`가 `auto` 또는 `none`만 받는 모델입니다. 강제 선택은 낮은 수준으로 바뀝니다. | | `preserveReasoningContentModels?` | `string[]` | chat 기록에서 이전 assistant `reasoning_content`가 필요한 모델입니다. 대시보드에서 저장해도 저장된 목록(`[]` 포함)은 유지됩니다. `PATCH /api/providers?name=`는 배열 또는 지우기 위한 `null`을 받습니다. 어댑터, 기본 URL, 인증 모드를 바꿔 다른 목적지로 옮기는 저장에서는 유지되지 않습니다(아래 절 참고). | | `reasoningDetailsModels?` | `string[]` | thinking을 구조화된 `reasoning_details` 배열로 반환하는 모델(`reasoning_split` 사용 MiniMax M 시리즈). 스트림 델타는 누적 스냅샷이라 prefix-diff로 처리하고, 보존된 reasoning은 `reasoning_content` 문자열 대신 `reasoning_details` 배열로 리플레이합니다. | diff --git a/docs-site/src/content/docs/reference/configuration/providers.md b/docs-site/src/content/docs/reference/configuration/providers.md index 729d00601ff..364f8b8220f 100644 --- a/docs-site/src/content/docs/reference/configuration/providers.md +++ b/docs-site/src/content/docs/reference/configuration/providers.md @@ -288,7 +288,7 @@ Providers can expose a built-in shorthand, such as `agy` for `google-antigravity | `webSearchBridge?` | `{ enabled?: boolean; backend?: "ollama" \| "openai" \| "anthropic" \| "xai" \| "gemini" \| "exa"; maxSearches?: number; timeoutMs?: number; endpoint?: string }` | Key-auth `openai-responses` passthrough providers only. Off by default. Codex always declares the hosted `web_search` tool, and the passthrough relays it on the assumption the destination executes it. A gateway that does not run hosted search answers with a `function_call` named `web_search` that nothing runs, and the undeclared-tool guard ends the turn. With `enabled: true` and an explicit `backend` OpenCodex intercepts that call, runs the search itself, feeds the result back to the same upstream, and shows Codex a hosted `web_search_call` cell. Never armed for `authMode: "forward"` (ChatGPT already searches) or for a provider that executes hosted search upstream. `backend` is required; there is no implicit default and a missing credential for the named backend leaves the bridge disarmed rather than falling through to another paid search. `ollama` reuses this provider's own API key on `POST /api/web_search`, so the origin must be `https://ollama.com` unless the operator names `endpoint` explicitly. `openai` / `anthropic` / `xai` / `gemini` / `exa` reuse the matching sidecar executor and that executor's own credential (`webSearchSidecar.exaApiKey` for Exa). The search model comes from `webSearchSidecar.model` only when `webSearchSidecar.backend` resolves to the same backend this bridge names; otherwise the bridge runs that backend's own default, because a model chosen for one vendor is rejected by another. An unset `webSearchSidecar.backend` resolves to `openai`, so an unset-backend model reaches an `openai` bridge and no other. There is no per-provider bridge model override. Streaming turns only. A turn that mixes `web_search` with another client tool call still fails closed rather than dropping the client's call. Assistant text such as XML-like `` prose is not executed. Defaults: `maxSearches: 3` (1..10), `timeoutMs: 60000` (1000..600000). | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | API-key providers only (`authMode: "key"`). Opt-in same-target 429 retry: when `retryOn429` is absent the feature is off, except that key-auth OpenCode Go and Command Code (canonical endpoints) fall back to a patient policy (6 replays, 10 s interval, 60 s cap); object presence enables it unless `enabled: false`, which also turns that fallback off. On 429 the proxy waits (upstream `Retry-After` or the fixed interval) and replays the identical request on the same key before any key failover — across the main text-turn recovery loop, the Responses passthrough wire, the image/video bridge, the web-search sidecar, and terminal continuations. Only pre-stream HTTP 429 responses are eligible for replay; custom `runTurn` transports are outside the HTTP retry loop. `attempts` counts same-key replays after the first 429 (total sends = `attempts` + 1) and is one request-wide budget shared by the main recovery loop, the terminal-guard continuation, and bridge retries. Exhausting `attempts` only stops further same-key replays: normal key failover or final-error handling then applies per the available targets — on the key-auth passthrough wire there is no failover, so the exhausted 429 surfaces as-is. Codex itself never retries 429, so this is the only defense for single-key providers. Defaults: `enabled: true`, `attempts: 3`, `intervalMs: 5000`, `maxIntervalMs: 60000` (any single wait is capped at `maxIntervalMs`, itself capped at 600000), `respectRetryAfter: true`. | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | Key-auth `openai-chat` and `openai-responses` providers only. `authMode: "forward"` providers (the ChatGPT account pool) never read this option and keep the default ladder. Opt-in retry for pre-stream transient upstream statuses (500, 502, 503, 504, 520, 521, 522): absent means off, object presence enables it unless `enabled: false`. Covers the initial Responses request, the Responses passthrough lane and each of its recovery legs (OAuth-401 replay, same-target 429 replay, validated rebuild), the terminal-guard continuation, and native `/v1/chat/completions`. `attempts` is the TOTAL number of upstream sends allowed for one request including the first (1..10, default 3) — it is one budget shared with connection-reset recovery, so `3` means at most three real requests reach the provider. On the Responses passthrough lane the configured value is additionally intersected with the request-wide send allowance, so a value below that allowance narrows the ladder exactly while a value above it does not raise the bound. Waits use a fixed 400 ms exponential backoff capped at 5 s and honor `Retry-After`. Separate from `retryOn429`, which handles rate limiting; mid-stream failures are never replayed. | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Native `openai-responses` providers, including `authMode: "forward"`. Opt-in replacement of a send that failed while the caller had observed nothing: absent means off, object presence enables it unless `enabled: false`. Covers both ambiguous stages — a connection that died before any response header, and an SSE body that died after the header while carrying only control events. A canonical ChatGPT upstream WebSocket that closed or errored after its create frame left, before any Responses event, is covered the same way, and its replacement is sent over HTTP. Only a self-contained request is ever replaced: `store: false`, complete `input`, no `previous_response_id`, `conversation` or `stream_id`, and only client-executed tools. `replacements` is the number of replacement sends ONE logical request may make across every leg and every combo child (1..2, default 1) — not a per-leg retry count and not a send budget, so a replacement still has to fit inside the send allowance the leg already had. A request that already emitted output or a tool call is never replaced, whatever this is set to. The replacement inference may still be billed if the origin had already started the first one, which is why this is off by default. | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | `openai-responses` providers, including `authMode: "forward"`. Opt-in replacement of a send that failed while the caller had observed nothing: absent means off, object presence enables it unless `enabled: false`. Covers both ambiguous stages — a connection that died before any response header, and an SSE body that died after the header while carrying only control events. A canonical ChatGPT upstream WebSocket that closed or errored after its create frame left, before any Responses event, is covered the same way, and its replacement is sent over HTTP. Only a self-contained request is ever replaced: `store: false`, complete `input`, no `previous_response_id`, `conversation` or `stream_id`, and only client-executed tools. `replacements` is the number of replacement sends ONE logical request may make across every leg and every combo child (1..2, default 1) — not a per-leg retry count and not a send budget, so a replacement still has to fit inside the send allowance the leg already had. A request that already emitted output or a tool call is never replaced, whatever this is set to. The replacement inference may still be billed if the origin had already started the first one, which is why this is off by default. Translated Responses-to-chat requests also support pre-header reset replacement under the same grant and send budget; their post-header stream failures are not covered. | | `autoToolChoiceOnlyModels?` | `string[]` | Models whose `tool_choice` accepts only `auto` or `none`; forced choices are downgraded. | | `preserveReasoningContentModels?` | `string[]` | Models requiring prior assistant `reasoning_content` in chat history. A provider save that keeps the destination keeps the stored list, including `[]`; see [What a provider save keeps](#what-a-provider-save-keeps). `PATCH /api/providers?name=` accepts an array or `null` to clear it. | | `inlineThinkTagModels?` | `string[]` | Opt-in recovery for `openai-chat` gateways without a server-side reasoning parser. A leading `` / `` / `` block (optionally after whitespace) activates splitting in streamed and buffered replies. All answer whitespace is preserved. Subsequent tags are delimiters anywhere, including same-line interleaving and code fences; this mode does not interpret Markdown. Ordinary text or a code fence before the first tag keeps the whole reply untouched. Off by default; prefer structured upstream reasoning or `reasoningSplitModels` where supported. | diff --git a/docs-site/src/content/docs/ru/reference/configuration/providers.md b/docs-site/src/content/docs/ru/reference/configuration/providers.md index 1d36ca37398..33af2422715 100644 --- a/docs-site/src/content/docs/ru/reference/configuration/providers.md +++ b/docs-site/src/content/docs/ru/reference/configuration/providers.md @@ -148,7 +148,7 @@ cross-route credential fallback не существует. Строки API GPT- | `responsesSnapshotRepair?` | `boolean` | По умолчанию выключенная клиентская repair для неполных lifecycle snapshot'ов Responses в SSE и JSON. Добавляет отсутствующие status, output и tool metadata, не меняя raw inspection и persistence. | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | Только для провайдеров с API-ключом (`authMode: "key"`). Опциональный повтор при 429 на том же таргете: если `retryOn429` отсутствует, функция выключена; наличие объекта включает её, если только `enabled: false`. При 429: ожидание (`Retry-After` апстрима или фиксированный интервал) и повтор идентичного запроса на том же ключе до любого фейловера ключей — покрывает основной цикл восстановления текстовых ходов, passthrough-канал Responses, мост изображений/видео, sidecar web-search и терминальные продолжения. Повтор допустим только для HTTP 429, полученных до начала потока; пользовательские транспорты `runTurn` не входят в цикл HTTP-повторов. `attempts` — это число повторов на том же ключе после первого 429 (всего отправок = `attempts` + 1) и единый бюджет на запрос, общий для основного цикла восстановления, терминального продолжения и повторов моста. Исчерпание `attempts` лишь останавливает дальнейшие повторы на том же ключе; далее применяется обычный фейловер ключей или финальная обработка ошибки в зависимости от доступных таргетов — на passthrough-канале с ключевой аутентификацией фейловера нет, поэтому исчерпанный 429 возвращается как есть. Codex сам никогда не повторяет 429, поэтому это единственная защита для провайдеров с одним ключом. По умолчанию: `enabled: true`, `attempts: 3`, `intervalMs: 5000`, `maxIntervalMs: 60000` (любое ожидание ограничено `maxIntervalMs`, который сам ограничен 600000), `respectRetryAfter: true`. | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | Только для провайдеров `openai-chat` и `openai-responses` с аутентификацией по ключу. Провайдеры с `authMode: "forward"` (пул аккаунтов ChatGPT) никогда не читают эту настройку и сохраняют число повторов по умолчанию. Опциональный повтор при временных статусах апстрима до начала потока (500, 502, 503, 504, 520, 521, 522): если параметр отсутствует, функция выключена; наличие объекта включает её, если только `enabled: false`. Покрывает исходный запрос `Responses`, продолжение терминального предохранителя, нативный `/v1/chat/completions`, а также повторные запросы при восстановлении после 429 или ошибки учётной записи. `attempts` — ОБЩЕЕ число разрешённых отправок в апстрим для одного запроса, включая первую (1..10, по умолчанию 3). Это единый бюджет на запрос, общий с восстановлением после сброса соединения, поэтому `3` означает, что до провайдера дойдут не более трёх реальных запросов. Ожидание использует экспоненциальную задержку с фиксированной начальной величиной 400 мс, ограниченную 5 с, и учитывает `Retry-After`. Параметр не связан с `retryOn429`, который обрабатывает ограничение частоты запросов; сбои после начала потока никогда не воспроизводятся. | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Только для нативных провайдеров `openai-responses`, включая `authMode: "forward"`. Необязательная замена отправки, которая завершилась неудачей, когда вызывающая сторона ещё ничего не наблюдала: если параметр отсутствует, функция выключена; наличие объекта включает её, если только `enabled: false`. Покрывает обе неоднозначные стадии — обрыв соединения до любого заголовка ответа и обрыв тела SSE после заголовка, когда оно несло только управляющие события. Так же покрывается upstream WebSocket canonical ChatGPT, который закрылся или завершился ошибкой после отправки кадра create и до любого события Responses; замена в этом случае отправляется по HTTP. Заменяется только самодостаточный запрос: `store: false`, полный `input`, отсутствие `previous_response_id`, `conversation` и `stream_id`, и только инструменты, исполняемые клиентом. `replacements` — число замещающих отправок, которые ОДИН логический запрос может сделать по всем участкам и всем дочерним запросам комбо (1..2, по умолчанию 1). Это не число повторов на участок и не бюджет отправок, поэтому замена всё равно должна поместиться в уже имеющийся у участка лимит отправок. Запрос, который уже выдал вывод или вызов инструмента, не заменяется никогда, каким бы ни было это значение. Замещающий вывод модели всё равно может быть оплачен, если источник уже начал первый, поэтому параметр выключен по умолчанию. | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Для нативных провайдеров `openai-responses`, включая `authMode: "forward"`. Необязательная замена отправки, которая завершилась неудачей, когда вызывающая сторона ещё ничего не наблюдала: если параметр отсутствует, функция выключена; наличие объекта включает её, если только `enabled: false`. Покрывает обе неоднозначные стадии — обрыв соединения до любого заголовка ответа и обрыв тела SSE после заголовка, когда оно несло только управляющие события. Так же покрывается upstream WebSocket canonical ChatGPT, который закрылся или завершился ошибкой после отправки кадра create и до любого события Responses; замена в этом случае отправляется по HTTP. Заменяется только самодостаточный запрос: `store: false`, полный `input`, отсутствие `previous_response_id`, `conversation` и `stream_id`, и только инструменты, исполняемые клиентом. `replacements` — число замещающих отправок, которые ОДИН логический запрос может сделать по всем участкам и всем дочерним запросам комбо (1..2, по умолчанию 1). Это не число повторов на участок и не бюджет отправок, поэтому замена всё равно должна поместиться в уже имеющийся у участка лимит отправок. Запрос, который уже выдал вывод или вызов инструмента, не заменяется никогда, каким бы ни было это значение. Замещающий вывод модели всё равно может быть оплачен, если источник уже начал первый, поэтому параметр выключен по умолчанию. Переведённые запросы Responses→chat также поддерживают замену до заголовков с тем же разрешением и бюджетом отправок; сбои переведённого потока после заголовков не покрываются. | | `autoToolChoiceOnlyModels?` | `string[]` | Модели, у которых `tool_choice` принимает только `auto` или `none`; forced choice понижается. | | `preserveReasoningContentModels?` | `string[]` | Модели, которым нужен предыдущий assistant `reasoning_content` в chat history. Сохранение в дашборде не меняет записанный список, в том числе `[]`. `PATCH /api/providers?name=` принимает массив или `null`, чтобы его очистить. Сохранение, которое переносит провайдера на другой адаптер, базовый URL или режим аутентификации, список не сохраняет (см. раздел ниже). | | `reasoningDetailsModels?` | `string[]` | Модели, чей endpoint возвращает thinking как структурированный массив `reasoning_details` (MiniMax M-series с `reasoning_split`); потоковые дельты — кумулятивные снимки, сравниваемые по префиксу, а сохранённый reasoning воспроизводится массивом `reasoning_details` вместо строки `reasoning_content`. | diff --git a/docs-site/src/content/docs/tr/reference/configuration/providers.md b/docs-site/src/content/docs/tr/reference/configuration/providers.md index 0d7bb915565..6291b03b6cb 100644 --- a/docs-site/src/content/docs/tr/reference/configuration/providers.md +++ b/docs-site/src/content/docs/tr/reference/configuration/providers.md @@ -149,7 +149,7 @@ alanlı seçilmiş kimlikleri yalın kimliklere yeniden yazar. | `responsesSnapshotRepair?` | `boolean` | SSE ve JSON'daki seyrek Responses yaşam döngüsü anlık görüntüleri için varsayılan olarak devre dışı bırakılmış istemciye yönelik onarım. Ham inceleme ve kalıcılık değişmeden kalırken eksik kurallı durumu, çıktıyı ve araç meta verilerini doldurur. | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | Yalnızca API anahtarı sağlayıcıları (`authMode: "key"`). İsteğe bağlı aynı hedef 429 yeniden denemesi: `retryOn429` olmadığında özellik kapalıdır; nesnenin varlığı `enabled: false` olmadığı sürece özelliği etkinleştirir. 429'da proxy bekler (yukarı akış `Retry-After` veya sabit aralık) ve herhangi bir anahtar yük devretmesinden önce aynı istek üzerinde aynı anahtarla aynı isteği yeniden oynatır — ana metin turu kurtarma döngüsü, Responses doğrudan geçiş hattı, görsel/video köprüsü, web araması sidecar'ı ve terminal devamları genelinde. Yalnızca akış öncesi HTTP 429 yanıtları yeniden oynatma için uygundur; özel `runTurn` aktarımları HTTP yeniden deneme döngüsünün dışındadır. `attempts`, ilk 429'dan sonraki aynı anahtar yeniden oynatmalarını sayar (toplam gönderim = `attempts` + 1) ve ana kurtarma döngüsü, terminal koruma devamı ve köprü yeniden denemeleri tarafından paylaşılan tek bir istek genelinde bütçedir. `attempts`'ı tüketmek yalnızca daha fazla aynı anahtar yeniden oynatmasını durdurur: normal anahtar yük devretmesi veya nihai hata işleme daha sonra kullanılabilir hedeflere göre geçerli olur — anahtar kimlik doğrulamalı doğrudan geçiş hattında yük devretme yoktur, bu nedenle tükenen 429 olduğu gibi görünür. Codex'in kendisi 429'u asla yeniden denemez, bu nedenle tek anahtarlı sağlayıcılar için tek savunma budur. Varsayılanlar: `enabled: true`, `attempts: 3`, `intervalMs: 5000`, `maxIntervalMs: 60000` (tek bir bekleme `maxIntervalMs` ile sınırlandırılır, kendisi de 600000 ile sınırlandırılır), `respectRetryAfter: true`. | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | Yalnızca anahtarla kimlik doğrulanan `openai-chat` ve `openai-responses` sağlayıcıları. `authMode: "forward"` sağlayıcıları (ChatGPT hesap havuzu) bu seçeneği hiç okumaz ve varsayılan merdiveni korur. Akış öncesi geçici yukarı akış durumları (500, 502, 503, 504, 520, 521, 522) için isteğe bağlı yeniden deneme: seçenek belirtilmezse kapalıdır; nesnenin varlığı, `enabled: false` olmadığı sürece özelliği etkinleştirir. İlk Responses isteğini, terminal koruma devamını, yerel `/v1/chat/completions` isteklerini ve 429/hesap kurtarma yeniden getirmelerini kapsar. `attempts`, bir istek için ilk gönderim dahil izin verilen yukarı akış gönderimlerinin TOPLAM sayısıdır (1..10, varsayılan 3) — bağlantı sıfırlama kurtarmasıyla paylaşılan, istek kapsamlı tek bütçedir; dolayısıyla `3`, sağlayıcıya en fazla üç gerçek isteğin ulaşması anlamına gelir. Beklemelerde 400 ms'lik sabit üstel geri çekilme uygulanır, süre 5 sn ile sınırlandırılır ve `Retry-After` dikkate alınır. Hız sınırlamasını işleyen `retryOn429` seçeneğinden ayrıdır; akış ortası hataları hiçbir zaman yeniden oynatılmaz. | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Yalnızca yerel `openai-responses` sağlayıcıları, `authMode: "forward"` dahil. Çağıranın hiçbir şey gözlemlemediği bir anda başarısız olan gönderimin isteğe bağlı olarak değiştirilmesi: seçenek belirtilmezse kapalıdır; nesnenin varlığı, `enabled: false` olmadığı sürece özelliği etkinleştirir. İki belirsiz aşamayı da kapsar: yanıt başlığı gelmeden kopan bağlantı ve başlıktan sonra yalnızca denetim olayları taşırken kopan SSE gövdesi. Kanonik ChatGPT upstream WebSocket'i create çerçevesi gönderildikten sonra, herhangi bir Responses olayından önce kapanır veya hata verirse aynı şekilde kapsanır ve değiştirme gönderimi HTTP üzerinden yapılır. Yalnızca kendi kendine yeten bir istek değiştirilir: `store: false`, eksiksiz `input`, `previous_response_id`, `conversation` veya `stream_id` bulunmaması ve yalnızca istemcinin yürüttüğü araçlar. `replacements`, BİR mantıksal isteğin tüm bacaklar ve tüm combo alt istekleri boyunca yapabileceği değiştirme gönderimi sayısıdır (1..2, varsayılan 1). Bacak başına yeniden deneme sayısı da gönderim bütçesi de değildir; bu yüzden bir değiştirme gönderimi, ilgili bacağın hâlihazırda sahip olduğu gönderim payına sığmak zorundadır. Halihazırda çıktı veya araç çağrısı üretmiş bir istek, bu değer ne olursa olsun asla değiştirilmez. Kaynak ilk çıkarımı zaten başlatmışsa değiştirilen çıkarım yine ücretlendirilebilir; bu nedenle varsayılan olarak kapalıdır. | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | Yerel `openai-responses` sağlayıcıları, `authMode: "forward"` dahil. Çağıranın hiçbir şey gözlemlemediği bir anda başarısız olan gönderimin isteğe bağlı olarak değiştirilmesi: seçenek belirtilmezse kapalıdır; nesnenin varlığı, `enabled: false` olmadığı sürece özelliği etkinleştirir. İki belirsiz aşamayı da kapsar: yanıt başlığı gelmeden kopan bağlantı ve başlıktan sonra yalnızca denetim olayları taşırken kopan SSE gövdesi. Kanonik ChatGPT upstream WebSocket'i create çerçevesi gönderildikten sonra, herhangi bir Responses olayından önce kapanır veya hata verirse aynı şekilde kapsanır ve değiştirme gönderimi HTTP üzerinden yapılır. Yalnızca kendi kendine yeten bir istek değiştirilir: `store: false`, eksiksiz `input`, `previous_response_id`, `conversation` veya `stream_id` bulunmaması ve yalnızca istemcinin yürüttüğü araçlar. `replacements`, BİR mantıksal isteğin tüm bacaklar ve tüm combo alt istekleri boyunca yapabileceği değiştirme gönderimi sayısıdır (1..2, varsayılan 1). Bacak başına yeniden deneme sayısı da gönderim bütçesi de değildir; bu yüzden bir değiştirme gönderimi, ilgili bacağın hâlihazırda sahip olduğu gönderim payına sığmak zorundadır. Halihazırda çıktı veya araç çağrısı üretmiş bir istek, bu değer ne olursa olsun asla değiştirilmez. Kaynak ilk çıkarımı zaten başlatmışsa değiştirilen çıkarım yine ücretlendirilebilir; bu nedenle varsayılan olarak kapalıdır. Responses→chat çevirisinde de aynı izin ve gönderim bütçesiyle başlık öncesi kopma için değiştirme desteklenir; çevrilmiş akışın başlıklardan sonraki hataları kapsam dışıdır. | | `autoToolChoiceOnlyModels?` | `string[]` | `tool_choice`'u yalnızca `auto` veya `none` kabul eden modeller; zorunlu seçimlerin derecesi düşürülür. | | `preserveReasoningContentModels?` | `string[]` | Sohbet geçmişinde önceki asistan `reasoning_content`'ini gerektiren modeller. Dashboard üzerinden yapılan kayıtlar, `[]` dahil saklanan listeyi korur. `PATCH /api/providers?name=`, bir dizi veya temizlemek için `null` kabul eder. Sağlayıcıyı başka bir bağdaştırıcıya, temel URL'ye veya kimlik doğrulama moduna taşıyan bir kayıt listeyi korumaz (aşağıdaki bölüme bakın). | | `reasoningDetailsModels?` | `string[]` | Thinking'i yapılandırılmış bir `reasoning_details` dizisi olarak döndüren modeller (`reasoning_split` ile MiniMax M-serisi); akış deltaları önek farkıyla işlenen kümülatif anlık görüntülerdir ve korunan reasoning, `reasoning_content` dizesi yerine `reasoning_details` dizisi olarak yeniden oynatılır. | diff --git a/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md b/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md index 0edbc641cad..a55e83d9f2f 100644 --- a/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md +++ b/docs-site/src/content/docs/zh-cn/reference/configuration/providers.md @@ -136,7 +136,7 @@ selector，而不是分配一个新名称。 | `responsesSnapshotRepair?` | `boolean` | 默认关闭的客户端修复，用于补全 SSE 与 JSON 中稀疏 Responses 生命周期快照缺失的 status、output 和工具元数据；原始检查与持久化保持不变。 | | `retryOn429?` | `{ enabled?: boolean; attempts?: number; intervalMs?: number; maxIntervalMs?: number; respectRetryAfter?: boolean }` | 仅限 API-key 提供商（`authMode: "key"`）。可选的同目标 429 重试：未配置 `retryOn429` 时功能关闭；对象存在即启用，除非 `enabled: false`。收到 429 时等待（上游 `Retry-After` 或固定间隔）后在相同 key 上重放完全相同请求，再进入任何 key 故障转移——覆盖主文本恢复循环、Responses passthrough、图像/视频桥、web-search 侧车与终结续接。重放仅适用于流开始前的 HTTP 429 响应；自定义 `runTurn` 传输不在 HTTP 重试循环范围内。`attempts` 是首个 429 之后的同 key 重放次数（总发送次数 = `attempts` + 1），是主恢复循环、终结守卫续接与桥接重试共享的按请求统一预算；`attempts` 耗尽只会停止进一步的同 key 重放：随后按可用目标进行正常的 key 故障转移或最终错误处理——key 认证的 passthrough 线路上没有故障转移，因此耗尽的 429 会原样透出。Codex 自身从不重试 429，因此这是单 key 提供商唯一的防线。默认值：`enabled: true`、`attempts: 3`、`intervalMs: 5000`、`maxIntervalMs: 60000`（单次等待以 `maxIntervalMs` 为上限，其本身上限 600000）、`respectRetryAfter: true`。 | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | 仅限使用 key 认证的 `openai-chat` 与 `openai-responses` 提供商。`authMode: "forward"` 的提供商（ChatGPT 账号池）从不读取此选项，保持默认重试次数。可选的流开始前上游瞬态状态码（500、502、503、504、520、521、522）重试：未配置时关闭；对象存在即启用，除非 `enabled: false`。覆盖初始 Responses 请求、终结守卫续接、原生 `/v1/chat/completions`，以及 429/账户恢复重新获取。`attempts` 是单个请求允许向上游发送的总次数，包含首次发送（1..10，默认 3）；它是与连接重置恢复共享的按请求预算，因此 `3` 表示最多只有三个实际请求到达提供商。等待采用固定 400 毫秒的指数退避，上限为 5 秒，并遵循 `Retry-After`。此选项独立于处理速率限制的 `retryOn429`；流开始后的故障绝不会重放。 | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | 仅限原生 `openai-responses` 提供商，包含 `authMode: "forward"`。可选地替换一次在调用方尚未观察到任何内容时就失败的发送：未配置时关闭；对象存在即启用，除非 `enabled: false`。涵盖两个不确定阶段——响应头到达前连接断开，以及响应头之后 SSE 正文只承载控制事件时断开。canonical ChatGPT 上游 WebSocket 在 create 帧发出之后、任何 Responses 事件到达之前关闭或出错时，也按同样方式处理，其替换发送走 HTTP。只有自包含的请求才会被替换：`store: false`、完整的 `input`、没有 `previous_response_id`／`conversation`／`stream_id`，且只使用由客户端执行的工具。`replacements` 是单个逻辑请求在所有环节和所有组合子请求中可以进行的替换发送次数（1..2，默认 1）；它既不是按环节的重试次数，也不是发送预算，因此替换发送仍必须落在该环节已有的发送额度之内。已经产生输出或工具调用的请求，无论此值为何都不会被替换。如果上游已经开始了第一次推理，被替换的推理仍可能计费，因此该选项默认关闭。 | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | 原生 `openai-responses` 提供商，包含 `authMode: "forward"`。可选地替换一次在调用方尚未观察到任何内容时就失败的发送：未配置时关闭；对象存在即启用，除非 `enabled: false`。涵盖两个不确定阶段——响应头到达前连接断开，以及响应头之后 SSE 正文只承载控制事件时断开。canonical ChatGPT 上游 WebSocket 在 create 帧发出之后、任何 Responses 事件到达之前关闭或出错时，也按同样方式处理，其替换发送走 HTTP。只有自包含的请求才会被替换：`store: false`、完整的 `input`、没有 `previous_response_id`／`conversation`／`stream_id`，且只使用由客户端执行的工具。`replacements` 是单个逻辑请求在所有环节和所有组合子请求中可以进行的替换发送次数（1..2，默认 1）；它既不是按环节的重试次数，也不是发送预算，因此替换发送仍必须落在该环节已有的发送额度之内。已经产生输出或工具调用的请求，无论此值为何都不会被替换。如果上游已经开始了第一次推理，被替换的推理仍可能计费，因此该选项默认关闭。 Responses 转 chat 的请求也支持响应头之前断线的替换发送，使用同一授权和发送预算；不覆盖转换流在响应头之后的故障。 | | `autoToolChoiceOnlyModels?` | `string[]` | `tool_choice` 只接受 `auto` 或 `none` 的模型；强制选择会被降级。 | | `preserveReasoningContentModels?` | `string[]` | 需要在聊天历史中保留先前 assistant `reasoning_content` 的模型。从仪表板保存时会保留已存储的列表（包括 `[]`）。`PATCH /api/providers?name=` 接受数组，或传入 `null` 清除该字段。将提供方改到其他适配器、base URL 或认证模式的保存不会保留该列表（见下文）。 | | `reasoningDetailsModels?` | `string[]` | 以结构化 `reasoning_details` 数组返回思考内容的模型（启用 `reasoning_split` 的 MiniMax M 系列）；流式增量为累积快照，按前缀差分处理，保留的推理以 `reasoning_details` 数组而非 `reasoning_content` 字符串回放。 | diff --git a/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md b/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md index e2834a0d8bd..e1608c92b3c 100644 --- a/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md +++ b/docs-site/src/content/docs/zh-tw/reference/configuration/providers.md @@ -107,7 +107,7 @@ ocx models provider openrouter on | `parallelToolCalls?` | `boolean` | 切換平行工具呼叫。OpenAI Chat 預設開啟；非 chat adapter 僅在明確 `true` 時廣告。 | | `responsesItemIdRepair?` | `{ message?: string[]; reasoning?: string[]; repairMissingTerminalIds?: boolean }` | 預設停用的下游 SSE 修復，用於精確佔位 id 與缺失的終端 id。Function-call id 永不被重寫。 | | `transientRetryOn5xx?` | `{ enabled?: boolean; attempts?: number }` | 僅限使用金鑰認證的 `openai-chat` 與 `openai-responses` 供應商。`authMode: "forward"` 的供應商（ChatGPT 帳號池）從不讀取此選項，維持預設重試次數。選擇性重試串流開始前的暫時性上游狀態（500、502、503、504、520、521、522）：未設定時停用；只要有此物件即啟用，除非 `enabled: false`。涵蓋初始 `Responses` 請求、終止防護續接、原生 `/v1/chat/completions`，以及 429／帳號復原的重新擷取。`attempts` 是單一請求允許傳送至上游的總次數，包含第一次（1..10，預設 3）；這是與連線重設復原共用的單一請求範圍預算，因此 `3` 表示最多只有三個實際請求會送達供應商。等待採固定 400 毫秒、上限 5 秒的指數退避，並遵循 `Retry-After`。此機制獨立於處理速率限制的 `retryOn429`；串流中的失敗絕不重播。 | -| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | 僅限原生 `openai-responses` 供應商，包含 `authMode: "forward"`。可選擇性地替換一次在呼叫端尚未觀察到任何內容時就失敗的傳送：未設定時停用；只要有此物件即啟用，除非 `enabled: false`。涵蓋兩個不確定階段——回應標頭抵達前連線中斷，以及標頭之後 SSE 內文只載有控制事件時中斷。canonical ChatGPT upstream WebSocket 在 create 訊框送出之後、任何 Responses 事件抵達之前關閉或出錯時，也以相同方式處理，其替換傳送改走 HTTP。只有自我完備的請求才會被替換：`store: false`、完整的 `input`、沒有 `previous_response_id`／`conversation`／`stream_id`，且僅使用由用戶端執行的工具。`replacements` 是單一邏輯請求在所有環節與所有組合子請求中可進行的替換傳送次數（1..2，預設 1）；它既不是各環節的重試次數，也不是傳送預算，因此替換傳送仍必須落在該環節既有的傳送額度之內。已經產生輸出或工具呼叫的請求，無論此值為何都不會被替換。若上游已經開始第一次推論，被替換的推論仍可能計費，因此此選項預設停用。 | +| `retryOnReset?` | `{ enabled?: boolean; replacements?: number }` | 原生 `openai-responses` 供應商，包含 `authMode: "forward"`。可選擇性地替換一次在呼叫端尚未觀察到任何內容時就失敗的傳送：未設定時停用；只要有此物件即啟用，除非 `enabled: false`。涵蓋兩個不確定階段——回應標頭抵達前連線中斷，以及標頭之後 SSE 內文只載有控制事件時中斷。canonical ChatGPT upstream WebSocket 在 create 訊框送出之後、任何 Responses 事件抵達之前關閉或出錯時，也以相同方式處理，其替換傳送改走 HTTP。只有自我完備的請求才會被替換：`store: false`、完整的 `input`、沒有 `previous_response_id`／`conversation`／`stream_id`，且僅使用由用戶端執行的工具。`replacements` 是單一邏輯請求在所有環節與所有組合子請求中可進行的替換傳送次數（1..2，預設 1）；它既不是各環節的重試次數，也不是傳送預算，因此替換傳送仍必須落在該環節既有的傳送額度之內。已經產生輸出或工具呼叫的請求，無論此值為何都不會被替換。若上游已經開始第一次推論，被替換的推論仍可能計費，因此此選項預設停用。 Responses 轉 chat 的請求也支援回應標頭之前斷線的替換傳送，使用同一授權和傳送預算；不涵蓋轉換串流在回應標頭之後的故障。 | | `autoToolChoiceOnlyModels?` | `string[]` | 其 `tool_choice` 僅接受 `auto` 或 `none` 的模型；強制選擇被降級。 | | `preserveReasoningContentModels?` | `string[]` | 需要在 chat 歷史中保留先前 assistant `reasoning_content` 的模型。從儀表板儲存時會保留已儲存的清單（包括 `[]`）。`PATCH /api/providers?name=` 接受陣列，或傳入 `null` 清除該欄位。將供應商改到其他轉接器、base URL 或驗證模式的儲存不會保留該清單（見下文）。 | | `reasoningDetailsModels?` | `string[]` | 以結構化 `reasoning_details` 陣列回傳思考內容的模型（啟用 `reasoning_split` 的 MiniMax M 系列）；串流增量為累積快照，以前綴差分處理，保留的推理以 `reasoning_details` 陣列而非 `reasoning_content` 字串重播。 | diff --git a/scripts/test-layout/layout.json b/scripts/test-layout/layout.json index 65b171af7b1..fd62cc5e33f 100644 --- a/scripts/test-layout/layout.json +++ b/scripts/test-layout/layout.json @@ -1537,6 +1537,7 @@ "responses-reasoning-effort-downgrade.test.ts": "responses", "responses-reasoning-summary-passthrough.test.ts": "responses", "responses-reset-replay.test.ts": "responses", + "responses-translated-reset.test.ts": "responses", "responses-routed-web-search-fields.test.ts": "responses", "responses-self-named-namespace-scrub.test.ts": "responses", "responses-send-budget-counts.test.ts": "responses", diff --git a/src/server/responses/adapter-dispatch.ts b/src/server/responses/adapter-dispatch.ts index ffc991fb755..b00991dda7d 100644 --- a/src/server/responses/adapter-dispatch.ts +++ b/src/server/responses/adapter-dispatch.ts @@ -1,5 +1,8 @@ import { classifyAnthropic429 } from "../../oauth/anthropic-rate-limit-policy"; import { rotateAnthropicAccountOnResponse } from "../../oauth/anthropic-account-refusal"; +import { authorizeResendForRecovery } from "../../lib/request-resend-gate"; +import { ambiguousResendAllowanceFor, selfContainedResponsesBody } from "./reset-replay"; +import { transientSendCapFor } from "./request-send-budget"; import { isNonReplayableResponse } from "../../lib/upstream-retry"; import { isLocalUpstream } from "../../lib/local-upstream"; import type { ResponsesRequestContext, ResponsesAdmissionState } from "./core-options"; @@ -25,6 +28,7 @@ import { withProviderRequestSlot } from "../../providers/request-pacing"; import { providerFetch, fetchWithHeaderTimeout, safeHostLabel } from "./fetch-helpers"; import { transientRetryPolicyFor, + resetReplayPolicyFor, rateLimitRetryPolicyFor, hasKeyPoolFailover, rotateProviderTransportOn401, @@ -156,6 +160,8 @@ export async function prepareAdapterExchange( | "reserveCredentialHop" | "pendingHopPermit" | "workflowRootId" + | "claimAmbiguousResend" + | "sendsUsed" >, ) { const { options, config, logCtx, req } = requestContext; @@ -189,9 +195,18 @@ export async function prepareAdapterExchange( recoveryClassFor, sendBudgetExhausted, reserveCredentialHop, + claimAmbiguousResend, } = sendBudgetState; + let selfContainedJudgment: boolean | undefined; + const requestIsSelfContained = (): boolean => + selfContainedJudgment ??= selfContainedResponsesBody(parsed._rawBody); + const claimPreHeaderResend = (): boolean => authorizeResendForRecovery( + "pre-header", "connection-reset", + ambiguousResendAllowanceFor(route.provider, requestIsSelfContained, claimAmbiguousResend), + ).allowed; + const upstream = new AbortController(); const cleanupUpstreamAbort = linkAbortSignal(upstream, options.abortSignal); const connectMs = config.connectTimeoutMs ?? 200_000; @@ -367,6 +382,7 @@ export async function prepareAdapterExchange( { abortSignal: upstream.signal, label: safeHostLabel(builtInitialRequest.url), + claimAmbiguousResend: claimPreHeaderResend, ...(transientPolicy || compactPrepaid // Draws the remainder, not the raw policy. A combo child inherits the parent's // holder but used to take a fresh full allowance on its own first send, so the @@ -378,7 +394,10 @@ export async function prepareAdapterExchange( remainingTransientSendBudget(transientPolicy?.attempts ?? 1) + (compactPrepaid ? 1 : 0)), onSendsConsumed: noteTransientSends, } - : {}), + : resetReplayPolicyFor(route.provider) ? { + attempts: remainingTransientSendBudget(transientSendCapFor(undefined, sendBudgetState.sendsUsed)), + onSendsConsumed: noteTransientSends, + } : {}), }, ); } @@ -548,9 +567,9 @@ export async function prepareAdapterExchange( // Same rule as the passthrough rebuild: spend the base allowance first, then the one // shared final-recovery reserve, so a recovery that follows a spent streak still gets // its single send instead of dying at three. - const refetchAllowance = refetchTransientPolicy + const refetchAllowance = refetchTransientPolicy || resetReplayPolicyFor(route.provider) ? recoverySendAllowance( - refetchTransientPolicy.attempts, + refetchTransientPolicy?.attempts ?? transientSendCapFor(undefined, sendBudgetState.sendsUsed), recoveryClassFor(recovery), `${route.providerName}|${route.modelId}|${recovery}`, ) @@ -566,7 +585,7 @@ export async function prepareAdapterExchange( // can be refused above before it does. use() past the first attempt is a no-op. onDispatch?.(); if (preserveFailureResponse) replacementAdmitted = true; - if (!refetchTransientPolicy) chargeFastDowngradeWorkflowSend(); + if (!refetchAllowance) chargeFastDowngradeWorkflowSend(); return fetchWithHeaderTimeout(retryRequest.url, applyUpstreamRecoveryInit({ method: retryRequest.method, headers: retryRequest.headers, body: retryRequest.body, @@ -580,6 +599,7 @@ export async function prepareAdapterExchange( { abortSignal: upstream.signal, label: safeHostLabel(retryRequest.url), + claimAmbiguousResend: claimPreHeaderResend, ...(refetchAllowance ? { attempts: refetchAllowance.attempts, diff --git a/src/types/provider.ts b/src/types/provider.ts index adfa680e808..5e2f5f88fd5 100644 --- a/src/types/provider.ts +++ b/src/types/provider.ts @@ -1012,7 +1012,7 @@ export interface OcxProviderConfig { /** * Opt-in replacement of a native Responses send that died while the caller had observed * nothing (`providers..retryOnReset`). Disabled unless present; a bare `{}` opts in - * with defaults. Native Responses sends only, and only for self-contained requests. + * with defaults. Includes pre-header translated Responses-to-chat sends; only self-contained requests. */ retryOnReset?: ResetReplayPolicy; /** diff --git a/structure/transports/responses-failover.md b/structure/transports/responses-failover.md index 4ed2e4972dc..2ebee5073fa 100644 --- a/structure/transports/responses-failover.md +++ b/structure/transports/responses-failover.md @@ -83,7 +83,7 @@ counter rather than holding a second. A replacement never widens a send budget: fit inside the allowance the leg already had, and it is charged to the same counter every other send goes through. -The number of replacements is the request's as well. A leg reads it from `route.provider`, which +Translated Responses-to-chat dispatch asks the same pre-header gate for initial and rebuilt sends, charging opted-in sends to the shared budget; post-header translated-stream recovery and adapter-owned fetch policies are outside this opt-in. The number of replacements is the request's as well. A leg reads it from `route.provider`, which credential rotation, OAuth refresh, transport resolution and each combo target reassign inside one request, so the grant is held to the smallest ceiling any leg has presented rather than to whatever the asking leg presents. Otherwise a request that had already spent the one replacement a diff --git a/tests/fixtures/test-layout-expected.json b/tests/fixtures/test-layout-expected.json index b163ec3b090..1017a2144bf 100644 --- a/tests/fixtures/test-layout-expected.json +++ b/tests/fixtures/test-layout-expected.json @@ -1549,6 +1549,7 @@ "responses-reasoning-effort-downgrade.test.ts": "responses", "responses-reasoning-summary-passthrough.test.ts": "responses", "responses-reset-replay.test.ts": "responses", + "responses-translated-reset.test.ts": "responses", "responses-routed-web-search-fields.test.ts": "responses", "responses-self-named-namespace-scrub.test.ts": "responses", "responses-send-budget-counts.test.ts": "responses", diff --git a/tests/responses/responses-translated-reset.test.ts b/tests/responses/responses-translated-reset.test.ts new file mode 100644 index 00000000000..3e63fe7c0d6 --- /dev/null +++ b/tests/responses/responses-translated-reset.test.ts @@ -0,0 +1,110 @@ +import { describe, expect, test } from "bun:test"; +import { mkdtempSync, rmSync } from "node:fs"; +import { tmpdir } from "node:os"; +import { join } from "node:path"; +import { handleResponses } from "../../src/server/responses"; +import { createRequestExecutionBudget } from "../../src/lib/request-execution-budget"; +import type { OcxConfig, OcxProviderConfig } from "../../src/types"; +import { acquireOwnedSpendHome } from "../helpers/owned-spend-home"; + +async function probe(options: { + provider?: Partial; + body?: Record; + resets?: number; + exhausted?: boolean; + abort?: boolean; + spentGrant?: boolean; + downgrade?: boolean; +}) { + const home = mkdtempSync(join(tmpdir(), "ocx-translated-reset-")); + const oldHome = process.env.OPENCODEX_HOME; + const oldFetch = globalThis.fetch; + process.env.OPENCODEX_HOME = home; + const release = acquireOwnedSpendHome(); + const budget = createRequestExecutionBudget(); + if (options.exhausted) budget.used = 3; + if (options.spentGrant) budget.claimAmbiguousResend(1); + const abort = new AbortController(); + const bodies: string[] = []; + globalThis.fetch = (async (_input, init) => { + bodies.push(String(init?.body)); + if (options.abort) abort.abort(); + if (options.downgrade && bodies.length === 1) { + return Response.json({ error: { type: "invalid_request_error", param: "reasoning_effort", + message: "reasoning_effort max is not supported for this model" } }, { status: 400 }); + } + if (bodies.length <= (options.resets ?? 1) + (options.downgrade ? 1 : 0)) { + throw Object.assign(new Error("synthetic pre-header reset"), { code: "ECONNRESET" }); + } + return Response.json({ id: "chat-test", choices: [{ index: 0, + message: { role: "assistant", content: "ok" }, finish_reason: "stop" }] }); + }) as typeof fetch; + try { + const config = { port: 0, defaultProvider: "mock", providers: { + mock: { adapter: "openai-chat", baseUrl: "https://synthetic.invalid/v1", apiKey: "synthetic", + models: ["test"], retryOnReset: {}, ...options.provider }, + } } as OcxConfig; + const response = await handleResponses(new Request("http://localhost/v1/responses", { + method: "POST", headers: { "content-type": "application/json" }, + body: JSON.stringify({ model: "mock/test", input: "hello", store: false, stream: false, ...options.body }), + }), config, { model: "", provider: "" }, { sendBudget: budget, abortSignal: abort.signal }); + return { status: response.status, text: await response.text(), bodies, used: budget.used }; + } finally { + globalThis.fetch = oldFetch; + release(); + if (oldHome === undefined) delete process.env.OPENCODEX_HOME; + else process.env.OPENCODEX_HOME = oldHome; + rmSync(home, { recursive: true, force: true }); + } +} + +describe("translated Responses pre-header reset replay (#6510)", () => { + test("a bare opt-in replays identical chat bytes once and charges both sends", async () => { + const result = await probe({}); + expect(result.status, result.text).toBe(200); + expect(result.bodies).toHaveLength(2); + expect(result.bodies[0]).toBe(result.bodies[1]); + expect(result.used).toBe(2); + }); + + test.each([ + ["absent opt-in", { provider: { retryOnReset: undefined } }], + ["disabled opt-in", { provider: { retryOnReset: { enabled: false } } }], + ["stored turn", { body: { store: true } }], + ["spent request-wide replacement", { spentGrant: true }], + ["exact one-send policy", { provider: { transientRetryOn5xx: { attempts: 1 } } }], + ] as const)("%s does not fund a duplicate turn", async (_name, options) => { + const result = await probe(options); + expect(result.status).toBe(429); + expect(result.text).toContain("upstream_reset_replay_refused"); + expect(result.bodies).toHaveLength(1); + }); + + test("a reset during a rebuilt effort-downgrade send uses the same grant", async () => { + const result = await probe({ downgrade: true, provider: { reasoningEfforts: ["high", "max"] }, + body: { reasoning: { effort: "max" } } }); + expect(result.status, result.text).toBe(200); + expect(result.bodies).toHaveLength(3); + expect(result.bodies[1]).toBe(result.bodies[2]); + expect(result.used).toBe(3); + }); + + test("repeated resets exhaust the grant after two sends", async () => { + const result = await probe({ resets: 10 }); + expect(result.status).toBe(429); + expect(result.bodies).toHaveLength(2); + expect(result.used).toBe(2); + }); + + test("exhausted send budget blocks dispatch", async () => { + const result = await probe({ exhausted: true }); + expect(result.status).toBe(429); + expect(result.bodies).toHaveLength(0); + }); + + test("cancellation never spends the replacement", async () => { + const result = await probe({ abort: true }); + expect(result.status).toBe(499); + expect(result.bodies).toHaveLength(1); + }); +});