lidge-jun · mushikingh · Aug 1, 2026 · Aug 1, 2026 · Aug 1, 2026 · Aug 1, 2026
@@ -88,7 +88,46 @@ ocx logout <provider>
 | `kiro` | `kiro` | `https://runtime.us-east-1.kiro.dev` | Initial login imports the installed, signed-in `kiro-cli` session (on Unix, install with `curl -fsSL https://cli.kiro.dev/install | bash`; on Windows PowerShell, use `irm 'https://cli.kiro.dev/install.ps1' | iex`; then run `kiro-cli login`). **Add account** logs `kiro-cli` out, starts a fresh browser login that switches the account used by `kiro-cli`, and stores account-scoped profile metadata. Existing OpenCodex accounts are preserved, and cancellation or failure restores the previous `kiro-cli` session. |
 | `google-antigravity` | `google` | `https://daily-cloudcode-pa.googleapis.com` | Google OAuth over the Cloud Code Assist wire. |
 | `cursor` | `cursor` | `https://api2.cursor.sh` | Experimental PKCE login, live HTTP/2 transport, and account-filtered model discovery. |
-| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | Experimental. GitHub device flow + `copilot_internal` exchange (VS Code OAuth client). Requires an active Copilot subscription; not an official third-party API. |
+| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | Experimental. GitHub device flow + `copilot_internal` exchange (VS Code OAuth client). Requires an active Copilot subscription; not an official third-party API. The catalog is mixed-wire — see [GitHub Copilot model wires](#github-copilot-model-wires). |
+
+### GitHub Copilot model wires
+
+Copilot's catalog is not uniformly served by `/chat/completions`. The provider adapter stays
+`openai-chat`, which is correct for the Claude, Gemini, GPT-3.5/4 and `gpt-5-mini` entries, but the
+newer OpenAI models answer only on the Responses API. opencodex routes those over
+`openai-responses` automatically:
+
+`gpt-5.3-codex` · `gpt-5.4` · `gpt-5.4-mini` · `gpt-5.4-nano` · `gpt-5.5` · `gpt-5.6-luna` ·
+`gpt-5.6-sol` · `gpt-5.6-terra`
+
+Without this, a chat-completions request fails with
+`model "…" is not accessible via the /chat/completions endpoint`. `gpt-5.4` is subtler: a text-only
+request succeeds and only a real Codex request fails, because Codex supplies function tools plus a
+reasoning effort (`Function tools with reasoning_effort are not supported … use /v1/responses`).
+
+Unlike the DeepSeek default, which applies only to a Responses inbound, these apply to every
+inbound: Copilot serves no chat route at all for them, so a Chat Completions or Claude Code client
+is translated onto Responses too.
+
+An explicit [`modelAdapters`](/reference/configuration/) entry always wins, so you can move a model
+back onto chat completions — or route a new one onto Responses before the built-in map catches up:
+
+```json
+{
+  "providers": {
+    "github-copilot": {
+      "modelAdapters": { "gpt-5.4": "openai-chat" }
+    }
+  }
+}
+```
+
+Bare OpenAI model names such as `gpt-5.6-sol` are reserved for the canonical `openai` provider, so
+Copilot models must be selected with the provider prefix:
+
+```bash
+codex -m github-copilot/gpt-5.6-sol -c 'model_reasoning_effort="medium"'
+```
 
 For the canonical Kimi Coding Plan presets (`kimi` account login and `kimi-code` API key),
 opencodex forwards only a caller-supplied stable `prompt_cache_key` to the Chat Completions request;

@@ -85,7 +85,7 @@ ocx logout <provider>
 | `kiro` | `kiro` | `https://runtime.us-east-1.kiro.dev` | 初回ログインは、インストール済みでサインインした `kiro-cli` セッションを取り込みます（Unix では `curl -fsSL https://cli.kiro.dev/install | bash`、Windows PowerShell では `irm 'https://cli.kiro.dev/install.ps1' | iex` でインストールしてから `kiro-cli login` を実行）。**アカウントを追加**は `kiro-cli` をログアウトして新しいブラウザログインを開始し、`kiro-cli` 自体のアカウントを切り替えてアカウント別プロファイルメタデータを保存します。既存の OpenCodex アカウントは保持され、キャンセルまたは失敗時には以前の `kiro-cli` セッションが復元されます。 |
 | `google-antigravity` | `google` | `https://daily-cloudcode-pa.googleapis.com` | Google OAuth を Cloud Code Assist wire で使用。 |
 | `cursor` | `cursor` | `https://api2.cursor.sh` | 実験的 PKCE ログイン、HTTP/2 トランスポート、アカウント別モデル探索をサポート。 |
-| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | 実験的。GitHub デバイスフロー + `copilot_internal` 交換（VS Code OAuth クライアント）。有効な Copilot サブスクリプションが必要で、公式のサードパーティ API ではありません。 |
+| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | 実験的。GitHub デバイスフロー + `copilot_internal` 交換（VS Code OAuth クライアント）。有効な Copilot サブスクリプションが必要で、公式のサードパーティ API ではありません。カタログは wire が混在します: `gpt-5.3-codex`、`gpt-5.4`、`gpt-5.4-mini`、`gpt-5.4-nano`、`gpt-5.5`、`gpt-5.6-luna`、`gpt-5.6-sol`、`gpt-5.6-terra` は Chat Completions では `model "…" is not accessible via the /chat/completions endpoint` で失敗するため、opencodex がすべての inbound で `openai-responses` にルーティングします。`gpt-5.4` はテキストのみの要求なら成功しますが、Codex が function tool と reasoning effort を伴うと失敗します。その他のモデルは `openai-chat` のままで、明示的な `modelAdapters` が常に優先されます。bare な OpenAI 名は canonical `openai` 専用なので `github-copilot/gpt-5.6-sol` のように選択してください。 |
 
 正規の Kimi Coding Plan プリセット（`kimi` アカウントログインと `kimi-code` API key）では、
 opencodex は呼び出し元が指定した安定した `prompt_cache_key` だけを Chat Completions リクエストへ

@@ -85,7 +85,7 @@ ocx logout <provider>
 | `kiro` | `kiro` | `https://runtime.us-east-1.kiro.dev` | 최초 로그인은 설치하고 로그인한 `kiro-cli` 세션을 가져옵니다(Unix에서는 `curl -fsSL https://cli.kiro.dev/install | bash`, Windows PowerShell에서는 `irm 'https://cli.kiro.dev/install.ps1' | iex`로 설치한 뒤 `kiro-cli login` 실행). **계정 추가**는 `kiro-cli`에서 로그아웃한 뒤 새 브라우저 로그인을 시작하여 `kiro-cli` 자체의 계정을 전환하고, 계정별 프로필 메타데이터를 저장합니다. 기존 OpenCodex 계정은 유지되며, 취소되거나 실패하면 이전 `kiro-cli` 세션을 복원합니다. |
 | `google-antigravity` | `google` | `https://daily-cloudcode-pa.googleapis.com` | Google OAuth를 Cloud Code Assist wire로 사용합니다. |
 | `cursor` | `cursor` | `https://api2.cursor.sh` | 실험적 PKCE 로그인, HTTP/2 전송, 계정별 모델 탐색을 지원합니다. |
-| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | 실험적. GitHub 디바이스 플로우 + `copilot_internal` 교환(VS Code OAuth 클라이언트). 활성 Copilot 구독 필요; 공식 서드파티 API가 아닙니다. |
+| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | 실험적. GitHub 디바이스 플로우 + `copilot_internal` 교환(VS Code OAuth 클라이언트). 활성 Copilot 구독 필요; 공식 서드파티 API가 아닙니다. 카탈로그는 wire가 섞여 있습니다: `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`는 Chat Completions에서 `model "…" is not accessible via the /chat/completions endpoint`로 실패하므로 opencodex가 모든 inbound에서 `openai-responses`로 라우팅합니다. `gpt-5.4`는 텍스트 전용 요청은 성공하지만 Codex가 function tool과 reasoning effort를 함께 보내면 실패합니다. 나머지 모델은 `openai-chat` 그대로이며, 명시적인 `modelAdapters` 항목이 항상 우선합니다. bare OpenAI 이름은 canonical `openai` 전용이므로 `github-copilot/gpt-5.6-sol`처럼 선택하세요. |
 
 정식 Kimi Coding Plan 프리셋(`kimi` 계정 로그인과 `kimi-code` API key)의 경우, opencodex는
 호출자가 제공한 안정적인 `prompt_cache_key`만 Chat Completions 요청으로 전달하며 직접 생성하지

@@ -194,7 +194,7 @@ timing side channel을 막기 위해 상수 시간(`timingSafeEqual`)으로 비
 | `modelReasoningEfforts?` | `Record<string,string[]>` | 모델별 reasoning 레이블. 빈 배열은 해당 모델의 effort control을 숨깁니다. |
 | `modelSupportsReasoningSummaries?` | `Record<string,boolean>` | 모델별 reasoning summary capability. 모델 값을 `false`로 두면 summary 지원을 알리지 않고 `openai-responses` 요청 전에 summary-delivery 필드를 제거합니다. |
 | `modelReasoningSummaryDelivery?` | `Record<string,"sequential" \| "sequential_cutoff" \| "concurrent" \| "concurrent_cutoff">` | 모델별 Responses delivery enum입니다. 설정된 모델은 summary 지원을 유지하며 기존 `stream_options.reasoning_summary_delivery` 값만 바꿉니다. 같은 모델의 summary capability를 `false`로 설정할 수 없습니다. |
-| `modelAdapters?` | `Record<string,string>` | 여러 wire를 쓰는 모델이 한 게이트웨이에 섞여 있을 때의 모델별 wire 지정. 키는 upstream native 모델 ID이고 값은 `openai-chat` 또는 `openai-responses`만 허용합니다. `web_search` 같은 hosted tool 때문에 한 모델만 Responses API가 필요할 때 씁니다. upstream이 wire를 고정한 모델과 canonical ChatGPT forward provider에서는 override가 거부됩니다. |
+| `modelAdapters?` | `Record<string,string>` | 여러 wire를 쓰는 모델이 한 게이트웨이에 섞여 있을 때의 모델별 wire 지정. 키는 upstream native 모델 ID이고 값은 `openai-chat` 또는 `openai-responses`만 허용합니다. `web_search` 같은 hosted tool 때문에 한 모델만 Responses API가 필요할 때 씁니다. upstream이 wire를 고정한 모델과 canonical ChatGPT forward provider에서는 override가 거부됩니다. 일부 preset은 검증된 mixed-wire 경로를 자동 선택하는 registry 기본값을 가집니다(DeepSeek은 `deepseek-v4-flash`를 native Responses로, GitHub Copilot은 Responses 전용 GPT-5.3+ 모델을 모든 inbound에서 그렇게 보냅니다). 여기에 명시한 항목은 provider 전체 adapter와 같은 값이더라도 항상 우선하며, 모델을 기본값에서 빼는 방법입니다. |
 | `reasoningEffortMap?` | `Record<string,string>` | 프로바이더 단위 reasoning 레이블 wire alias. 업스트림이 다른 값을 요구할 때만 사용합니다. |
 | `modelReasoningEffortMap?` | `Record<string,Record<string,string>>` | 모델별 reasoning 레이블 wire alias. |
 | `noReasoningModels?` | `string[]` | reasoning/thinking 파라미터를 거부하는 모델. 어댑터가 `reasoning_effort`를 제거합니다. |

@@ -339,7 +339,7 @@ or bind the forward explicitly to loopback (`ssh -L 127.0.0.1:20100:localhost:10
 | `modelReasoningEfforts?` | `Record<string,string[]>` | Model-specific reasoning labels. An empty list hides the effort control for that model. |
 | `modelSupportsReasoningSummaries?` | `Record<string,boolean>` | Model-specific reasoning-summary capability. Set a model to `false` to stop advertising summaries and strip summary-delivery fields before an `openai-responses` request. |
 | `modelReasoningSummaryDelivery?` | `Record<string,"sequential" \| "sequential_cutoff" \| "concurrent" \| "concurrent_cutoff">` | Model-specific Responses delivery enum. A configured model stays summary-capable and only an existing `stream_options.reasoning_summary_delivery` is rewritten; do not combine it with a `false` summary capability for the same model. |
-| `modelAdapters?` | `Record<string,string>` | Per-model wire override for a gateway that fronts models speaking different wires. Keys are upstream native model ids; values must be `openai-chat` or `openai-responses`. Built-in registry defaults may select a verified mixed-wire route automatically (the DeepSeek preset sends `deepseek-v4-flash` over native Responses); an explicit entry wins and can opt a model back out. Models the upstream pins to a single wire, and the canonical ChatGPT forward provider, reject overrides. |
+| `modelAdapters?` | `Record<string,string>` | Per-model wire override for a gateway that fronts models speaking different wires. Keys are upstream native model ids; values must be `openai-chat` or `openai-responses`. Built-in registry defaults may select a verified mixed-wire route automatically (the DeepSeek preset sends `deepseek-v4-flash` over native Responses; the GitHub Copilot preset sends its Responses-only GPT-5.3+ models that way on every inbound); an explicit entry wins and can opt a model back out. Models the upstream pins to a single wire, and the canonical ChatGPT forward provider, reject overrides. |
 | `reasoningEffortMap?` | `Record<string,string>` | Provider-wide wire aliases for reasoning labels. Use only when the upstream expects a different value. |
 | `modelReasoningEffortMap?` | `Record<string,Record<string,string>>` | Model-specific wire aliases for reasoning labels. |
 | `noReasoningModels?` | `string[]` | Models that reject a reasoning/thinking param — the adapter drops `reasoning_effort` for them. |

@@ -91,7 +91,7 @@ ocx logout <provider>
 | `kiro` | `kiro` | `https://runtime.us-east-1.kiro.dev` | Первый вход импортирует существующую сессию после установки Kiro CLI (в Unix: `curl -fsSL https://cli.kiro.dev/install | bash`; в Windows PowerShell: `irm 'https://cli.kiro.dev/install.ps1' | iex`; затем выполните `kiro-cli login`). **Добавить аккаунт** выполняет выход из `kiro-cli`, запускает новый вход через браузер, переключает аккаунт самого `kiro-cli` и сохраняет метаданные профиля отдельно для каждого аккаунта. Существующие аккаунты OpenCodex сохраняются; при отмене или сбое восстанавливается предыдущая сессия `kiro-cli`. |
 | `google-antigravity` | `google` | `https://daily-cloudcode-pa.googleapis.com` | Google OAuth поверх протокола Cloud Code Assist. |
 | `cursor` | `cursor` | `https://api2.cursor.sh` | Экспериментальный PKCE-вход, живой транспорт HTTP/2 и обнаружение моделей с фильтрацией по аккаунту. |
-| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | Экспериментально. Device flow GitHub + обмен `copilot_internal` (OAuth-клиент VS Code). Требуется активная подписка Copilot; это не официальный сторонний API. |
+| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | Экспериментально. Device flow GitHub + обмен `copilot_internal` (OAuth-клиент VS Code). Требуется активная подписка Copilot; это не официальный сторонний API. Каталог смешанный по wire: `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra` падают на Chat Completions с `model "…" is not accessible via the /chat/completions endpoint`, поэтому opencodex маршрутизирует их через `openai-responses` на любом inbound. У `gpt-5.4` текстовый запрос проходит, но запрос Codex с function tools и reasoning effort — нет. Остальные модели остаются на `openai-chat`, а явная запись `modelAdapters` всегда важнее. Голые имена OpenAI зарезервированы за каноническим `openai`, выбирайте `github-copilot/gpt-5.6-sol`. |
 
 Для канонических пресетов Kimi Coding Plan (вход через аккаунт `kimi` и API-ключ `kimi-code`)
 opencodex передаёт в запрос Chat Completions только стабильный `prompt_cache_key`, предоставленный

@@ -79,7 +79,7 @@ ocx logout <provider>
 | `kiro` | `kiro` | `https://runtime.us-east-1.kiro.dev` | 首次登录会导入已安装并已登录的 Kiro CLI 会话（Unix 使用 `curl -fsSL https://cli.kiro.dev/install | bash`；Windows PowerShell 使用 `irm 'https://cli.kiro.dev/install.ps1' | iex`；然后运行 `kiro-cli login`）。**添加账户**会先退出 `kiro-cli`，再启动新的浏览器登录，从而切换 `kiro-cli` 自身使用的账户，并保存账户范围的配置文件元数据。现有 OpenCodex 账户会保留；如果取消或失败，则恢复之前的 `kiro-cli` 会话。 |
 | `google-antigravity` | `google` | `https://daily-cloudcode-pa.googleapis.com` | 通过 Cloud Code Assist 协议使用 Google OAuth。 |
 | `cursor` | `cursor` | `https://api2.cursor.sh` | 实验性 PKCE 登录、HTTP/2 传输和按账号筛选的模型发现。 |
-| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | 实验性。GitHub 设备流 + `copilot_internal` 交换（VS Code OAuth 客户端）。需要有效的 Copilot 订阅；不是官方第三方 API。 |
+| `github-copilot` | `openai-chat` | `https://api.githubcopilot.com` | 实验性。GitHub 设备流 + `copilot_internal` 交换（VS Code OAuth 客户端）。需要有效的 Copilot 订阅；不是官方第三方 API。目录混用多种 wire：`gpt-5.3-codex`、`gpt-5.4`、`gpt-5.4-mini`、`gpt-5.4-nano`、`gpt-5.5`、`gpt-5.6-luna`、`gpt-5.6-sol`、`gpt-5.6-terra` 在 Chat Completions 上会返回 `model "…" is not accessible via the /chat/completions endpoint`，因此 opencodex 会在所有 inbound 上将它们路由到 `openai-responses`。`gpt-5.4` 的纯文本请求可以成功，但 Codex 携带 function tools 和 reasoning effort 的请求会失败。其余模型保持 `openai-chat`，显式的 `modelAdapters` 始终优先。裸 OpenAI 名称保留给 canonical `openai`，请使用 `github-copilot/gpt-5.6-sol`。 |
 
 对于规范的 Kimi Coding Plan 预设（`kimi` 账号登录和 `kimi-code` API key），opencodex
 只会把调用方提供的稳定 `prompt_cache_key` 转发到 Chat Completions 请求，绝不自行生成。Kimi