@bitkyc08/opencodex 2.7.33 → 2.7.34-preview.20260723

package/README.ja.md

@@ -233,7 +233,7 @@ opencodex は 2 つの動作を分離して保持します:
 | Ollama / vLLM / LM Studio(ローカル) | `openai-chat` | key(通常は空欄) |
 | 任意の OpenAI 互換エンドポイント | `openai-chat` | key |
 
-このほか DeepSeek、Groq、OpenRouter、Together、Fireworks、Cerebras、Mistral、Hugging Face、NVIDIA NIM、MiniMax、Qwen Cloud などがあります。完全な一覧は `ocx init` または[プロバイダードキュメント](https://lidge-jun.github.io/opencodex/ja/reference/configuration/)で確認してください。
+このほか DeepSeek、Groq、OpenRouter、Together、Fireworks、Cerebras、Mistral、Hugging Face、NVIDIA NIM、MiniMax、Qwen Cloud、Tencent Cloud Coding Plan、SiliconFlow などがあります。完全な一覧は `ocx init` または[プロバイダードキュメント](https://lidge-jun.github.io/opencodex/ja/reference/configuration/)で確認してください。
 
 Cursor サポートは段階的な実験的ブリッジです: `ocx init` とダッシュボードの Add Provider ピッカーに Cursor の静的公開モデルカタログを持つローカル config として表示されます。Cursor アクセストークンを設定するとライブ
 HTTP/2 トランスポートが有効になります。Cursor サーバー駆動のネイティブ

package/README.ko.md

@@ -232,7 +232,7 @@ opencodex는 두 가지 동작을 분리해서 유지합니다:
 | Ollama / vLLM / LM Studio (로컬) | `openai-chat` | key (보통 비워둠) |
 | 모든 OpenAI 호환 엔드포인트 | `openai-chat` | key |
 
-그 외에 DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud 등이 있습니다. 전체 목록은 `ocx init` 또는 [프로바이더 문서](https://lidge-jun.github.io/opencodex/ko/reference/configuration/)에서 확인하세요.
+그 외에 DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud, Tencent Cloud Coding Plan, SiliconFlow 등이 있습니다. 전체 목록은 `ocx init` 또는 [프로바이더 문서](https://lidge-jun.github.io/opencodex/ko/reference/configuration/)에서 확인하세요.
 
 ## CLI
 

package/README.md

@@ -158,6 +158,11 @@ codex -m "ollama/llama3" "Refactor this function"
 
 When you omit the `provider/` prefix, opencodex routes to the default provider — or auto-matches based on the model name pattern (e.g., `claude-*` routes to Anthropic, `gpt-*` routes to OpenAI).
 
+Combo aliases are exact public model ids and may be bare names or use a custom namespace. If a
+combo alias exactly matches a configured non-OpenAI `provider/model` selector, the combo
+intentionally takes precedence in routing, `/v1/models`, and the Codex catalog. Renaming that
+alias or deleting the combo immediately restores the physical provider selector.
+
 Routed models also appear in the **Codex App** model picker with per-model reasoning effort controls:
 
 Current Codex builds can expose `low`, `medium`, `high`, `xhigh`, `max`, and `ultra` reasoning
@@ -229,7 +234,7 @@ next Codex session. opencodex keeps these behaviors:
 - **Log in once, skip the API key.** OAuth support for xAI, Anthropic, and Kimi means you can authenticate with your existing account. Tokens auto-refresh. Or forward your `codex login`, paste an API key, or use `${ENV_VAR}` references — your call.
 - **Works everywhere Codex does.** Injects into Codex CLI, TUI, App, and SDK automatically. Routed models show up in Codex's model picker just like native ones.
 - **History-safe injection.** On local installs the proxy points Codex's own built-in `openai` provider at itself via a single `openai_base_url` line — new threads keep their native provider tag, so ongoing chat history is never remapped and an unclean shutdown can't hide it. (Threads re-tagged by older versions are migrated back once on the first start; remote/LAN binds use a dedicated provider entry instead, since they need an API-key header.)
-- **Delegate to the right model.** Feature up to five routed or native models in Codex's subagent picker from the dashboard or config — route complex tasks to a reasoning model, fast tasks to a cheap one. On the v2 multi-agent surface (GPT-5.6 Sol/Terra) the proxy injects compact delegation guidance: a preferred sub-agent model and effort (`injectionModel` / `injectionEffort`), the featured-model roster with the effort ladder each supports, and the `fork_turns` rules that let cross-model `spawn_agent` calls apply their overrides. Known limitation: when a native parent spawns a routed child, the task body can currently arrive backend-encrypted and be lost ([#92](https://github.com/lidge-jun/opencodex/issues/92)) — use the v1 surface for reliable cross-provider delegation. Want your own wording? Set `injectionPrompt` with `{{model}}` / `{{effort}}` / `{{roster}}` placeholders.
+- **Delegate to the right model.** Feature up to five routed or native models in Codex's subagent picker from the dashboard or config — route complex tasks to a reasoning model, fast tasks to a cheap one. On the v2 multi-agent surface (GPT-5.6 Sol/Terra) the proxy injects compact, schema-agnostic delegation guidance: an eligible preferred sub-agent model and effort (`injectionModel` / `injectionEffort`), the configured intersection of Codex's picker-visible, v2-compatible, priority-sorted first five with available effort ladders, and the `fork_turns` rules that let cross-model `spawn_agent` calls apply their overrides. Known limitation: when a native parent spawns a routed child, the task body can currently arrive backend-encrypted and be lost ([#92](https://github.com/lidge-jun/opencodex/issues/92)) — use the v1 surface for reliable cross-provider delegation. Want your own wording? Set `injectionPrompt` with `{{model}}` / `{{effort}}` / `{{roster}}` placeholders.
 - **Prepare for preview-gated OpenAI rollouts.** GPT-5.6 Sol/Terra/Luna entries preserve the upstream effort ladders. Direct/Multi use the 372k Codex contract; OpenAI API and OpenRouter use 1.05M metadata when upstream access is available.
 - **Give any model superpowers.** Non-OpenAI models get real web search and image understanding via a `gpt-5.4-mini` sidecar over your ChatGPT login.
 - **Generate images natively.** Codex's standalone `image_gen` tool uses `POST /v1/images/generations` for generation and `POST /v1/images/edits` for edits; it is separate from the hosted Responses `image_generation` tool.
@@ -254,14 +259,17 @@ next Codex session. opencodex keeps these behaviors:
 | Ollama / vLLM / LM Studio (local) | `openai-chat` | key (usually blank) |
 | Any OpenAI-compatible endpoint | `openai-chat` | key |
 
-Plus DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud, and more. See the full list with `ocx init` or in the [provider docs](https://lidge-jun.github.io/opencodex/reference/configuration/).
+Plus DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud, Tencent Cloud Coding Plan, SiliconFlow, and more. See the full list with `ocx init` or in the [provider docs](https://lidge-jun.github.io/opencodex/reference/configuration/).
 
 Cursor support is a staged experimental bridge: it appears in `ocx init` and the dashboard Add
 Provider picker as a local config with Cursor's static public model catalog. Live
 HTTP/2 transport is enabled when a Cursor access token is configured. Cursor server-driven native
 read/write/delete/ls/grep/shell/fetch execution is disabled by default because it bypasses Codex's
-approval and sandbox path; set `unsafeAllowNativeLocalExec: true` only for trusted local
-experiments.
+approval and sandbox path. Request text such as a Codex `danger-full-access` sandbox marker never
+authorizes native local exec; set `nativeLocalExec: "on"` only for trusted local experiments where
+every data-plane caller is trusted. `nativeLocalExec: "codex-sandbox"` is accepted for backwards
+compatibility but fails closed like `off`; legacy `unsafeAllowNativeLocalExec: true` remains an
+explicit operator opt-in.
 MCP, screen recording, and computer-use are exposed through executor hooks; when no local executor
 is configured, opencodex returns typed no-executor results instead of policy-blocking the request.
 Cursor OAuth and live model discovery are enabled for the experimental Cursor adapter.
@@ -345,13 +353,16 @@ Here's a typical multi-provider setup:
 }
 ```
 
-Provider entries can also annotate routed catalog metadata. Use `contextWindow` for a provider-wide
-Codex-visible context cap, `modelContextWindows` for model-specific caps, and
+Provider entries can also annotate routed catalog metadata and output defaults. Use `contextWindow`
+for a provider-wide Codex-visible context cap, `modelContextWindows` for model-specific caps, and
 `modelInputModalities` for model-specific catalog input hints such as `["text"]` or
-`["text", "image"]`. Context values cap live `/models` metadata; they never raise a smaller live
-context window. The bundled GPT-5.6 Sol/Terra/Luna fallback metadata uses a 1,050,000-token context
-window for OpenAI API key and OpenRouter catalog entries; it does not bypass upstream preview
-access. See the configuration reference for the full field list.
+`["text", "image"]`. For OpenAI-compatible chat providers whose upstream default response budget is
+too small, set `defaultMaxOutputTokens` or per-model `modelMaxOutputTokens`; explicit
+`max_output_tokens` from the client still wins, and unset configs still omit `max_tokens`. Context
+values cap live `/models` metadata; they never raise a smaller live context window. The bundled
+GPT-5.6 Sol/Terra/Luna fallback metadata uses a 1,050,000-token context window for OpenAI API key
+and OpenRouter catalog entries; it does not bypass upstream preview access. See the configuration
+reference for the full field list.
 
 > **GLM-5.2 1M context via Z.AI:** through the `openai-chat` adapter, both `glm-5.2`
 > and `glm-5.2[1m]` work — opencodex strips the trailing `[1m]` suffix before

package/README.ru.md

@@ -262,7 +262,7 @@ OpenAI API-ключа и OpenRouter (`gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-lu
 | Ollama / vLLM / LM Studio (локально) | `openai-chat` | key (обычно пустой) |
 | Любой OpenAI-совместимый эндпоинт | `openai-chat` | key |
 
-А также DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud и другие. Полный список — в `ocx init` или в [документации по провайдерам](https://lidge-jun.github.io/opencodex/reference/configuration/).
+А также DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud, Tencent Cloud Coding Plan, SiliconFlow и другие. Полный список — в `ocx init` или в [документации по провайдерам](https://lidge-jun.github.io/opencodex/reference/configuration/).
 
 Поддержка Cursor — поэтапный экспериментальный мост: он появляется в `ocx init` и в селекторе
 Add Provider панели управления как локальная конфигурация со статическим публичным каталогом

package/README.zh-CN.md

@@ -225,7 +225,7 @@ opencodex 保持两种独立行为：
 | Ollama / vLLM / LM Studio（本地） | `openai-chat` | key（通常留空） |
 | 任意 OpenAI 兼容端点 | `openai-chat` | key |
 
-此外还有 DeepSeek、Groq、OpenRouter、Together、Fireworks、Cerebras、Mistral、Hugging Face、NVIDIA NIM、MiniMax、Qwen Cloud 等等。完整列表可通过 `ocx init` 查看，或参阅 [provider 文档](https://lidge-jun.github.io/opencodex/zh-cn/reference/configuration/)。
+此外还有 DeepSeek、Groq、OpenRouter、Together、Fireworks、Cerebras、Mistral、Hugging Face、NVIDIA NIM、MiniMax、Qwen Cloud、腾讯云 Coding Plan、SiliconFlow 等等。完整列表可通过 `ocx init` 查看，或参阅 [provider 文档](https://lidge-jun.github.io/opencodex/zh-cn/reference/configuration/)。
 
 ## CLI