chore(deps): bump dependencies (#612)

* fix(llms): gpt patch

* feat(llms): patch `hunyuan` models

* feat(llms): update model list

.agents/skills/submit-pr-from-current-changes/SKILL.md

@@ -24,6 +24,13 @@ Before attempting to push or open a PR, verify that the necessary tools are avai
 - Check that `gh` CLI is installed and authenticated (`gh auth status`). If not available, stop and ask the user to install and authenticate GitHub CLI first.
 - If the workflow uses MCP tools for GitHub operations, verify the MCP server is accessible.
 
+## Shell Permissions
+
+`gh` reads credentials from the OS keyring. A sandboxed shell cannot reach the keyring and will report a false auth failure.
+
+- Run every `gh` command (`gh auth status`, `gh pr create`, `gh pr view`, …) and every `git push` / `git fetch` that talks to GitHub with full permissions on the **first** attempt (`required_permissions: ["all"]` for the Shell tool). Do not probe these in the sandbox first.
+- Local read-only git inspection (`git status`, `git diff`, `git log`, `git branch`) may stay sandboxed.
+
 ## Procedure
 
 1. **Read contribution rules.** Read `CONTRIBUTING.md` and any package-level instructions (e.g. `packages/*/AGENTS.md`) relevant to the changed files.

.github/workflows/deploy-website.yml

@@ -3,7 +3,6 @@ name: Deploy Website
 on:
   push:
     branches: [main]
-  workflow_dispatch:
 
 jobs:
   deploy:

.github/workflows/main-ci.yml

@@ -7,7 +7,6 @@ permissions:
 on:
   push:
     branches: [main]
-  workflow_dispatch:
 
 jobs:
   test:

.github/workflows/release.yml

@@ -23,9 +23,9 @@ jobs:
           node-version: 24
           registry-url: 'https://registry.npmjs.org'
 
-      # Ensure npm 11.5.1 or later is installed
+      # Stay on the latest npm 11 release
       - name: Update npm
-        run: npm install -g npm@latest
+        run: npm install -g npm@11
 
       - name: Install dependencies
         run: npm ci

AGENTS.md

@@ -132,6 +132,7 @@ const pageInfo = await this.pageController.getPageInfo()
 - **Location**: co-located, `src/foo.test.ts` next to `src/foo.ts`
 - **Coverage today**: `packages/llms` only — other packages will follow incrementally
 - **Adding tests to a new package**: create `vitest.config.ts` in the package and add a `"test": "vitest run"` script. Root `npm test` and `node scripts/ci.js` pick it up through npm workspaces.
+- **Live tests** (hit real external APIs, slow/costly): name them `*.live.test.ts`, exclude them from the package's `test` script, and expose them via a `test:live` script. Root `npm run test:live` runs all of them; they never run in `npm test` or CI. Template: `packages/llms`.
 - **Template**: See @page-agent/llms
 
 ```bash

README.md

@@ -56,19 +56,18 @@ Fastest way to try PageAgent with our free Demo LLM:
 
 ```html
 <script
-    src="https://cdn.jsdelivr.net/npm/page-agent@1.12.0/dist/iife/page-agent.demo.js"
+    src="https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js"
     crossorigin="anonymous"
 ></script>
 ```
 
 > **⚠️ For technical evaluation only.** This demo CDN uses our free [testing LLM API](https://alibaba.github.io/page-agent/docs/features/models#free-testing-api). By using it, you agree to its [terms](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md).
+> Add `?autoInit=false` to load the script without creating the demo agent automatically. You can then instantiate it with `new window.PageAgent(...)`.
 
 | Mirrors | URL                                                                                 |
 | ------- | ----------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.12.0/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.12.0/files/dist/iife/page-agent.demo.js |
-
-Add `?autoInit=false` to load the script without creating the demo agent automatically. You can then instantiate it with `new window.PageAgent(...)`.
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js         |
+| China   | https://registry.npmmirror.com/page-agent/1.12.1/files/dist/iife/page-agent.demo.js |
 
 ### NPM Installation
 

docs/README-zh.md

@@ -55,19 +55,18 @@
 
 ```html
 <script
-    src="https://cdn.jsdelivr.net/npm/page-agent@1.12.0/dist/iife/page-agent.demo.js"
+    src="https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js"
     crossorigin="anonymous"
 ></script>
 ```
 
 > **⚠️ 仅用于技术评估。** 该 Demo CDN 使用了免费的[测试 LLM API](https://alibaba.github.io/page-agent/docs/features/models#free-testing-api)，使用即表示您同意其[条款](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md)。
+> 在 URL 后添加 `?autoInit=false` 可只加载脚本，不自动创建 Demo Agent；之后可通过 `new window.PageAgent(...)` 手动初始化。
 
 | Mirrors | URL                                                                                 |
 | ------- | ----------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.12.0/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.12.0/files/dist/iife/page-agent.demo.js |
-
-在 URL 后添加 `?autoInit=false` 可只加载脚本，不自动创建 Demo Agent；之后可通过 `new window.PageAgent(...)` 手动初始化。
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js         |
+| China   | https://registry.npmmirror.com/page-agent/1.12.1/files/dist/iife/page-agent.demo.js |
 
 ### NPM 安装
 

package.json

@@ -1,7 +1,7 @@
 {
     "name": "root",
     "private": true,
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "workspaces": [
         "packages/page-controller",
@@ -37,20 +37,21 @@
         "postpublish": "npm run postpublish --workspaces --if-present",
         "typecheck": "tsc --noEmit -p tsconfig.typecheck.json && tsc --noEmit -p packages/extension/tsconfig.json",
         "test": "npm test --workspaces --if-present",
+        "test:live": "npm run test:live --workspaces --if-present",
         "lint": "eslint .",
         "ci": "node scripts/ci.js",
         "cleanup": "rm -rf packages/*/dist && rm -rf packages/*/.output",
         "prepare": "husky || true"
     },
     "devDependencies": {
-        "@commitlint/cli": "^21.2.0",
+        "@commitlint/cli": "^21.2.1",
         "@commitlint/config-conventional": "^21.2.0",
-        "@eslint-react/eslint-plugin": "^5.11.2",
+        "@eslint-react/eslint-plugin": "^5.13.2",
         "@eslint/js": "^10.0.1",
         "@microsoft/api-extractor": "^7.58.9",
         "@tailwindcss/vite": "^4.3.2",
         "@trivago/prettier-plugin-sort-imports": "^6.0.2",
-        "@types/node": "^26.1.0",
+        "@types/node": "^26.1.1",
         "@vitejs/plugin-react": "^6.0.3",
         "chalk": "^5.6.2",
         "concurrently": "^10.0.3",
@@ -60,11 +61,11 @@
         "happy-dom": "^20.10.6",
         "husky": "^9.1.7",
         "lint-staged": "^17.0.8",
-        "prettier": "^3.9.4",
+        "prettier": "^3.9.5",
         "typescript": "^6.0.3",
         "typescript-eslint": "^8.63.0",
         "unplugin-dts": "^1.0.3",
-        "vite": "^8.1.3",
+        "vite": "^8.1.4",
         "vite-plugin-css-injected-by-js": "^5.0.1",
         "vitest": "^4.1.10"
     },

packages/core/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/core",
     "private": false,
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "main": "./src/PageAgentCore.ts",
     "types": "./src/PageAgentCore.ts",
@@ -55,8 +55,8 @@
     },
     "dependencies": {
         "chalk": "^5.6.2",
-        "@page-agent/llms": "1.12.0",
-        "@page-agent/page-controller": "1.12.0"
+        "@page-agent/llms": "1.12.1",
+        "@page-agent/page-controller": "1.12.1"
     },
     "peerDependencies": {
         "zod": "^3.25.0 || ^4.0.0"

packages/extension/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/ext",
     "private": true,
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "scripts": {
         "dev": "wxt",
@@ -10,12 +10,12 @@
         "postinstall": "wxt prepare"
     },
     "devDependencies": {
-        "@radix-ui/react-hover-card": "^1.1.18",
+        "@radix-ui/react-hover-card": "^1.1.19",
         "@radix-ui/react-icons": "^1.3.2",
         "@radix-ui/react-label": "^2.1.11",
         "@radix-ui/react-separator": "^1.1.11",
         "@radix-ui/react-slot": "^1.3.0",
-        "@radix-ui/react-switch": "^1.3.2",
+        "@radix-ui/react-switch": "^1.3.3",
         "@tailwindcss/vite": "^4.3.2",
         "@types/chrome": "^0.2.2",
         "@types/react": "^19.2.17",
@@ -24,7 +24,7 @@
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
         "idb": "^8.0.3",
-        "lucide-react": "^1.23.0",
+        "lucide-react": "^1.24.0",
         "motion": "^12.42.2",
         "next-themes": "^0.4.6",
         "react": "^19.2.7",
@@ -38,10 +38,10 @@
         "wxt": "^0.20.27"
     },
     "dependencies": {
-        "@page-agent/core": "1.12.0",
-        "@page-agent/llms": "1.12.0",
-        "@page-agent/page-controller": "1.12.0",
-        "@page-agent/ui": "1.12.0",
+        "@page-agent/core": "1.12.1",
+        "@page-agent/llms": "1.12.1",
+        "@page-agent/page-controller": "1.12.1",
+        "@page-agent/ui": "1.12.1",
         "ai-motion": "^0.4.8",
         "chalk": "^5.6.2"
     },

packages/llms/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/llms",
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "main": "./src/index.ts",
     "types": "./src/index.ts",
@@ -43,7 +43,8 @@
     "homepage": "https://alibaba.github.io/page-agent/",
     "scripts": {
         "build": "vite build",
-        "test": "vitest run",
+        "test": "vitest run --project llms",
+        "test:live": "vitest run --project llms:live",
         "prepublishOnly": "node ../../scripts/pre-publish.js",
         "postpublish": "node ../../scripts/post-publish.js"
     },

packages/llms/src/models.live.test.ts

@@ -10,9 +10,10 @@
  * Tests `OpenAIClient` directly (not the `LLM` retry wrapper), so a failure
  * always reflects the very first request/response — no retry can mask it.
  *
- * Each provider's tests skip (not fail) when its `TESTING_*_KEY` env var is
- * absent, so this stays CI-safe. To actually run these, put keys in the
- * repo-root `.env`:
+ * Per the `*.live.test.ts` convention this suite is excluded from `npm test`
+ * (slow, costs tokens) — run it manually with `npm run test:live`. Each
+ * provider's tests skip (not fail) when its `TESTING_*_KEY` env var is
+ * absent. Keys live in the repo-root `.env`:
  *
  *   TESTING_OPENROUTER_KEY=...
  *   TESTING_DEEPSEEK_KEY=...
@@ -50,6 +51,9 @@ const MODEL_GROUPS: Record<string, string[]> = {
 		'qwen3-max',
 	],
 	OpenAI: [
+		'gpt-5.6-sol',
+		'gpt-5.6-terra',
+		'gpt-5.6-luna',
 		'gpt-5.5',
 		'gpt-5.4',
 		'gpt-5.4-mini',
@@ -79,7 +83,8 @@ const MODEL_GROUPS: Record<string, string[]> = {
 		'claude-haiku-4-5',
 	],
 	MiniMax: ['MiniMax-M3', 'MiniMax-M2.7', 'MiniMax-M2.5'],
-	xAI: ['grok-4.3', 'grok-build-0.1'],
+	xAI: ['grok-4.5', 'grok-4.3', 'grok-build-0.1'],
+	Tencent: ['hy3'],
 	MoonshotAI: ['kimi-k2.7-code', 'kimi-k2.6', 'kimi-k2.5'],
 	'Z.AI': ['glm-5.2', 'glm-5.1', 'glm-5', 'glm-4.7'],
 }
@@ -97,6 +102,7 @@ const OPENROUTER_VENDOR_SLUG: Record<string, string> = {
 	Anthropic: 'anthropic',
 	MiniMax: 'minimax',
 	xAI: 'x-ai',
+	Tencent: 'tencent',
 	MoonshotAI: 'moonshotai',
 	'Z.AI': 'z-ai',
 }
@@ -106,7 +112,7 @@ const OPENROUTER_VENDOR_SLUG: Record<string, string> = {
  * `<vendor-slug>/<lowercased-name>` heuristic — dated snapshots, "-preview"
  * suffixes, "v"-prefixed versions, or dots instead of hyphens in the
  * version number. Verified against `GET https://openrouter.ai/api/v1/models`
- * on 2026-07-03; re-check when models are added to `MODEL_GROUPS`.
+ * on 2026-07-10; re-check when models are added to `MODEL_GROUPS`.
  */
 const OPENROUTER_ID_OVERRIDES: Record<string, string> = {
 	'qwen3.6-max': 'qwen/qwen3.6-max-preview',

packages/llms/src/utils.ts

@@ -62,17 +62,26 @@ export function modelPatch(body: Record<string, any>, baseURL?: string) {
 	if (modelName.startsWith('gpt')) {
 		if (modelName.startsWith('gpt-5')) {
 			body.verbosity = 'low'
-
-			// gpt-5 gpt-5-mini gpt-5-nano only supports "minimal";
-			// 5.1+ supports "none".
-			body.reasoning_effort = /^gpt-5(-|$)/.test(modelName) ? 'minimal' : 'none'
-			debug(`Patch GPT-5: verbosity=low, reasoning_effort=${body.reasoning_effort}`)
 		}
 
+		// Since gpt-5.4, /chat/completions rejects any explicit reasoning_effort
+		// when function tools are present. Newer models are expected to follow.
+		// - gpt-5.1 / gpt-5.2 can fully disable reasoning
+		// - gpt-5 / -mini / -nano bottom out at "minimal"
+		// - everything else (gpt-4.x, chat-latest, gpt-5.4+) must not receive it
 		if (modelName.includes('chat-latest')) {
-			debug('Omitting reasoning_effort and temperature for chat-latest')
+			debug('Patch chat-latest: omit reasoning_effort and temperature')
 			delete body.reasoning_effort
 			delete body.temperature
+		} else if (/^gpt-5[12](-|$)/.test(modelName)) {
+			debug('Patch GPT-5.1/5.2: reasoning_effort=none')
+			body.reasoning_effort = 'none'
+		} else if (/^gpt-5(-|$)/.test(modelName)) {
+			debug('Patch GPT-5: reasoning_effort=minimal')
+			body.reasoning_effort = 'minimal'
+		} else {
+			debug('Patch GPT: omit reasoning_effort')
+			delete body.reasoning_effort
 		}
 	}
 
@@ -125,6 +134,12 @@ export function modelPatch(body: Record<string, any>, baseURL?: string) {
 		body.thinking = { type: 'disabled' }
 	}
 
+	if (modelName.startsWith('hy')) {
+		debug('Patch Hunyuan: disable thinking, reasoning_effort=low')
+		body.thinking = { type: 'disabled' }
+		body.reasoning_effort = 'low'
+	}
+
 	if (modelName.startsWith('grok')) {
 		if (/^grok-4-?3/.test(modelName)) {
 			debug('Patch Grok 4.3: reasoning_effort=none')

packages/llms/vitest.config.js

@@ -1,12 +1,27 @@
-import { defineConfig } from 'vitest/config'
+import { configDefaults, defineConfig } from 'vitest/config'
 
+// Convention: `*.live.test.ts` hits real provider APIs (slow, costs tokens)
+// and only runs via `npm run test:live`. Everything else runs on `npm test`.
 export default defineConfig({
 	test: {
-		name: 'llms',
-		include: ['src/**/*.test.ts'],
-		// Keep live provider suites under OpenRouter's ~20 req/min free-route cap.
-		maxConcurrency: 2,
 		// Suppress console output from passing tests; failed tests still get their logs.
 		silent: 'passed-only',
+		projects: [
+			{
+				test: {
+					name: 'llms',
+					include: ['src/**/*.test.ts'],
+					exclude: [...configDefaults.exclude, 'src/**/*.live.test.ts'],
+				},
+			},
+			{
+				test: {
+					name: 'llms:live',
+					include: ['src/**/*.live.test.ts'],
+					// Keep live provider suites under OpenRouter's ~20 req/min free-route cap.
+					maxConcurrency: 2,
+				},
+			},
+		],
 	},
 })

packages/mcp/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/mcp",
     "private": false,
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "bin": {
         "page-agent-mcp": "src/index.js"

packages/page-agent/package.json

@@ -1,7 +1,7 @@
 {
     "name": "page-agent",
     "private": false,
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "main": "./src/PageAgent.ts",
     "types": "./src/PageAgent.ts",
@@ -54,10 +54,10 @@
         "postpublish": "node ../../scripts/post-publish.js"
     },
     "dependencies": {
-        "@page-agent/core": "1.12.0",
-        "@page-agent/llms": "1.12.0",
-        "@page-agent/page-controller": "1.12.0",
-        "@page-agent/ui": "1.12.0",
+        "@page-agent/core": "1.12.1",
+        "@page-agent/llms": "1.12.1",
+        "@page-agent/page-controller": "1.12.1",
+        "@page-agent/ui": "1.12.1",
         "chalk": "^5.6.2"
     },
     "peerDependencies": {

packages/page-controller/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/page-controller",
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "main": "./src/PageController.ts",
     "types": "./src/PageController.ts",

packages/ui/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/ui",
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "main": "./src/index.ts",
     "types": "./src/index.ts",

packages/website/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/website",
     "private": true,
-    "version": "1.12.0",
+    "version": "1.12.1",
     "type": "module",
     "scripts": {
         "dev": "vite --host 0.0.0.0",
@@ -12,13 +12,13 @@
         "@radix-ui/react-icons": "^1.3.2",
         "@radix-ui/react-separator": "^1.1.11",
         "@radix-ui/react-slot": "^1.3.0",
-        "@radix-ui/react-switch": "^1.3.2",
-        "@radix-ui/react-tooltip": "^1.2.11",
+        "@radix-ui/react-switch": "^1.3.3",
+        "@radix-ui/react-tooltip": "^1.2.12",
         "@types/react": "^19.2.17",
         "@types/react-dom": "^19.2.3",
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
-        "lucide-react": "^1.23.0",
+        "lucide-react": "^1.24.0",
         "motion": "^12.42.2",
         "next-themes": "^0.4.6",
         "react": "^19.2.7",

packages/website/src/constants.ts

@@ -1,8 +1,8 @@
 // Demo build (auto-init with demo LLM, for quick testing)
 export const CDN_DEMO_URL =
-	'https://cdn.jsdelivr.net/npm/page-agent@1.12.0/dist/iife/page-agent.demo.js'
+	'https://cdn.jsdelivr.net/npm/page-agent@1.12.1/dist/iife/page-agent.demo.js'
 export const CDN_DEMO_CN_URL =
-	'https://registry.npmmirror.com/page-agent/1.12.0/files/dist/iife/page-agent.demo.js'
+	'https://registry.npmmirror.com/page-agent/1.12.1/files/dist/iife/page-agent.demo.js'
 
 // Demo LLM for website testing (homepage quick trial uses flash)
 export const DEMO_MODEL = 'qwen3.5-flash'

packages/website/src/pages/docs/features/models/page.tsx

@@ -29,6 +29,9 @@ const MODEL_GROUPS: Record<string, string[]> = {
 		// 'qwen3-coder-next', // low success rate
 	],
 	OpenAI: [
+		'gpt-5.6-sol',
+		'gpt-5.6-terra',
+		'gpt-5.6-luna',
 		'gpt-5.5',
 		'gpt-5.4',
 		'gpt-5.4-mini',
@@ -63,7 +66,8 @@ const MODEL_GROUPS: Record<string, string[]> = {
 		'MiniMax-M2.7',
 		'MiniMax-M2.5',
 	],
-	xAI: ['grok-4.3', 'grok-build-0.1'],
+	xAI: ['grok-4.5', 'grok-4.3', 'grok-build-0.1'],
+	Tencent: ['hy3'],
 	MoonshotAI: ['kimi-k2.7-code', 'kimi-k2.6', 'kimi-k2.5'],
 	'Z.AI': ['glm-5.2', 'glm-5.1', 'glm-5', 'glm-4.7'],
 }