Update fallback model references to use openai-codex/gpt-5.4 in README, guide, and setup script

README.md

@@ -29,12 +29,12 @@ This Space runs the [OpenClaw](https://github.com/openclaw/openclaw) gateway so
    - **`SUPABASE_KEY`** — (recommended) Supabase service key or project API key with insert/update access to your sync table.
    - **`OPENCLAW_MODEL_PRIMARY`** — (recommended) Primary model ref. This repo now defaults to `huggingface/Qwen/Qwen3-8B`.
    - **`OPENCLAW_MODEL_FALLBACK_1`** — (recommended) First fallback model ref. Default is `huggingface/deepseek-ai/DeepSeek-R1`.
-   - **`OPENCLAW_MODEL_FALLBACK_2`** — (recommended) Second fallback model ref. Default is `gpt-codex`.
+   - **`OPENCLAW_MODEL_FALLBACK_2`** — (recommended) Second fallback model ref. Default is `openai-codex/gpt-5.4`.
    - **`OPENCLAW_GATEWAY_TRUSTED_PROXIES`** — (optional) Comma-separated proxy IPs (e.g. `10.20.31.87,10.20.26.157`). The startup script writes this into `gateway.trustedProxies`; set if you see “Proxy headers detected from untrusted address” or pairing/unauthorized. Use **Variables** if you prefer (IPs need not be secret).
    - **`OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS`** — (optional) Comma-separated origins (e.g. `https://your-space.hf.space`). Written to `gateway.controlUi.allowedOrigins` so only those origins can open the Control UI; useful to lock down to your Space URL.
    - **`TELEGRAM_BOT_TOKEN`** — (optional) Telegram BotFather token. This is the only Telegram setting you need for a minimal setup.
    - **`OPENCLAW_TELEGRAM_DM_POLICY`** / **`OPENCLAW_TELEGRAM_ALLOW_FROM`** / **`OPENCLAW_TELEGRAM_GROUP_POLICY`** / **`OPENCLAW_TELEGRAM_GROUP_ALLOW_FROM`** / **`OPENCLAW_TELEGRAM_REQUIRE_MENTION`** — (optional) Advanced Telegram access-control settings.
-4. **Build and run** — push to the Space repo; the Space will build and start the gateway. Startup writes config so the default model chain is `Qwen3-8B -> DeepSeek-R1 -> gpt-codex`, the Control UI accepts token-only connections (no device pairing), and Supabase sync starts automatically when `SUPABASE_URL` + `SUPABASE_KEY` are present.
+4. **Build and run** — push to the Space repo; the Space will build and start the gateway. Startup writes config so the default model chain is `Qwen3-8B -> DeepSeek-R1 -> openai-codex/gpt-5.4`, the Control UI accepts token-only connections (no device pairing), and Supabase sync starts automatically when `SUPABASE_URL` + `SUPABASE_KEY` are present.
 
 When the logs show `listening on ws://0.0.0.0:7860`, open your Space’s URL (e.g. `https://your-username-openclaw-gateway.hf.space`) and paste the gateway token in **Settings → token** (or use `https://your-space.hf.space#token=YOUR_TOKEN`).
 
@@ -42,11 +42,11 @@ When the logs show `listening on ws://0.0.0.0:7860`, open your Space’s URL (e.
 
 - **Default behavior in this repo** is now:
   - primary: `huggingface/Qwen/Qwen3-8B`
-  - fallbacks: `huggingface/deepseek-ai/DeepSeek-R1`, `gpt-codex`
+  - fallbacks: `huggingface/deepseek-ai/DeepSeek-R1`, `openai-codex/gpt-5.4`
 - **The startup script now writes both `primary` and `fallbacks`.**
-- **Codex fallback only works if Codex itself is already authenticated and usable.** If `gpt-codex` still lacks auth, fallback will still fail when traffic reaches it.
+- **Codex fallback only works if Codex itself is already authenticated and usable.** If `openai-codex/gpt-5.4` still lacks auth, fallback will still fail when traffic reaches it.
 - **OpenCode Zen** also works well in Hugging Face Spaces. Set `OPENCODE_API_KEY` and use a default model such as `opencode/claude-opus-4-6`.
-- **Codex auth remains the special case**: if your `gpt-codex` path depends on OAuth-backed credentials, use a separate environment that can complete the login flow first, or expect the Codex fallback to fail.
+- **Codex auth remains the special case**: if your `openai-codex/gpt-5.4` path depends on OAuth-backed credentials, use a separate environment that can complete the login flow first, or expect the Codex fallback to fail.
 - **Telegram minimal setup** only needs `TELEGRAM_BOT_TOKEN`.
 - **Telegram advanced settings** are optional and only needed when you want allowlists, group restrictions, or mention-only behavior.
 
@@ -62,7 +62,7 @@ TELEGRAM_BOT_TOKEN=<botfather token>
 Variables
 OPENCLAW_MODEL_PRIMARY=huggingface/Qwen/Qwen3-8B
 OPENCLAW_MODEL_FALLBACK_1=huggingface/deepseek-ai/DeepSeek-R1
-OPENCLAW_MODEL_FALLBACK_2=gpt-codex
+OPENCLAW_MODEL_FALLBACK_2=openai-codex/gpt-5.4
 OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS=https://your-space.hf.space
 OPENCLAW_SUPABASE_TABLE=openclaw_state
 OPENCLAW_SYNC_INTERVAL_MS=300000

guide.md

@@ -8,14 +8,14 @@
 
 1. `huggingface/Qwen/Qwen3-8B`
 2. `huggingface/deepseek-ai/DeepSeek-R1`
-3. `gpt-codex`
+3. `openai-codex/gpt-5.4`
 
 注意：
 
 - `Qwen` 是 primary
 - `DeepSeek` 是第一個 fallback
-- `gpt-codex` 是第二個 fallback
-- `gpt-codex` 只有在它本身已經可用時，fallback 才會成功
+- `openai-codex/gpt-5.4` 是第二個 fallback
+- `openai-codex/gpt-5.4` 只有在它本身已經可用時，fallback 才會成功
 
 ## 你在 HF Space 要放的檔案
 
@@ -53,7 +53,7 @@ TELEGRAM_BOT_TOKEN=<你的 telegram bot token>
 ```text
 OPENCLAW_MODEL_PRIMARY=huggingface/Qwen/Qwen3-8B
 OPENCLAW_MODEL_FALLBACK_1=huggingface/deepseek-ai/DeepSeek-R1
-OPENCLAW_MODEL_FALLBACK_2=gpt-codex
+OPENCLAW_MODEL_FALLBACK_2=openai-codex/gpt-5.4
 OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS=https://你的-space-url.hf.space
 OPENCLAW_SUPABASE_TABLE=openclaw_state
 OPENCLAW_SYNC_INTERVAL_MS=300000
@@ -101,7 +101,7 @@ TELEGRAM_BOT_TOKEN=<你的 bot token>
 原因：
 
 - OpenClaw 狀態會存在 `/data/.openclaw`
-- 如果之後 `gpt-codex` 要用到持久化 auth，沒有 persistent storage 會不穩
+- 如果之後 `openai-codex/gpt-5.4` 要用到持久化 auth，沒有 persistent storage 會不穩
 
 ## 部署後怎麼檢查
 
@@ -119,9 +119,9 @@ TELEGRAM_BOT_TOKEN=<你的 bot token>
 2. 可以用 `OPENCLAW_GATEWAY_TOKEN` 登入
 3. Supabase 的 `openclaw_state` 有同步資料
 
-## 關於 `gpt-codex`
+## 關於 `openai-codex/gpt-5.4`
 
-目前 `gpt-codex` 是 fallback，不是 primary。
+目前 `openai-codex/gpt-5.4` 是 fallback，不是 primary。
 
 這樣做的好處是：
 
@@ -131,7 +131,7 @@ TELEGRAM_BOT_TOKEN=<你的 bot token>
 
 但要注意：
 
-- 如果 `gpt-codex` 還沒完成它需要的登入或授權
+- 如果 `openai-codex/gpt-5.4` 還沒完成它需要的登入或授權
 - 真正切到第三個 fallback 時，仍然可能失敗
 
 所以目前最穩的理解方式是：
@@ -155,7 +155,7 @@ SUPABASE_KEY
 ```text
 OPENCLAW_MODEL_PRIMARY=huggingface/Qwen/Qwen3-8B
 OPENCLAW_MODEL_FALLBACK_1=huggingface/deepseek-ai/DeepSeek-R1
-OPENCLAW_MODEL_FALLBACK_2=gpt-codex
+OPENCLAW_MODEL_FALLBACK_2=openai-codex/gpt-5.4
 ```
 
 ### 建議 Variables

setup-hf-config.mjs

@@ -67,7 +67,7 @@ const defaultModel =
 const fallbackModels =
   fallbackModelsFromIndexedEnv.length > 0
     ? fallbackModelsFromIndexedEnv
-    : ["huggingface/deepseek-ai/DeepSeek-R1", "gpt-codex"];
+    : ["huggingface/deepseek-ai/DeepSeek-R1", "openai-codex/gpt-5.4"];
 const gatewayToken = readGatewayToken();
 const gatewayPassword = process.env.OPENCLAW_GATEWAY_PASSWORD?.trim();
 const telegramBotToken = process.env.TELEGRAM_BOT_TOKEN?.trim();