refactor(core): remove non-OpenAI SDK support and upgrade to OpenAI 6.x (#1325)

* refactor(core): remove non-OpenAI SDK support and upgrade to OpenAI 6.x

This commit removes support for Anthropic SDK and Azure OpenAI, simplifying
the codebase to use only the standard OpenAI SDK with OpenAI-style APIs.

Changes:
- Remove Anthropic SDK (@anthropic-ai/sdk) dependency
- Remove Azure OpenAI specific code and @azure/identity dependency
- Remove langsmith wrapper support
- Remove proxy agent support (https-proxy-agent, socks-proxy-agent)
- Upgrade OpenAI SDK from 4.81.0 to 6.3.0
- Simplify createChatClient function to only create standard OpenAI clients
- Remove 'style' parameter from createChatClient return type
- Remove all Anthropic-specific message handling code
- Add openai 6.3.0 as devDependency to @midscene/shared

Benefits:
- Cleaner, more maintainable codebase
- Reduced dependencies (removed 5 packages)
- All AI providers can now be accessed through OpenAI-compatible APIs

Breaking Changes:
- Anthropic SDK mode no longer supported
- Azure OpenAI specific configuration removed
- MIDSCENE_LANGSMITH_DEBUG no longer supported
- httpAgent/socksProxy removed from createChatClient

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

* refactor(core): model provider documentation and remove Azure and Anthropic configurations

* Apply suggestion from @Copilot

Co-authored-by: Copilot <[email protected]>

* feat(core): add proxy support for OpenAI client with HTTP and SOCKS configurations

* feat(core): add qwen-vl specific configuration for high resolution images

---------

Co-authored-by: Claude <[email protected]>
Co-authored-by: yuyutaotao <[email protected]>
Co-authored-by: Copilot <[email protected]>

Author: 4 people

apps/site/docs/en/model-provider.mdx

@@ -43,7 +43,6 @@ Some advanced configs are also supported. Usually you don't need to use them.
 
 | Name | Description |
 |------|-------------|
-| `OPENAI_USE_AZURE` | Optional. Set to "true" to use Azure OpenAI Service. See more details in the following section. |
 | `MIDSCENE_OPENAI_INIT_CONFIG_JSON` | Optional. Custom JSON config for OpenAI SDK initialization |
 | `MIDSCENE_OPENAI_HTTP_PROXY` | Optional. HTTP/HTTPS proxy configuration (e.g. `http://127.0.0.1:8080` or `https://proxy.example.com:8080`). This option has higher priority than `MIDSCENE_OPENAI_SOCKS_PROXY` |
 | `MIDSCENE_OPENAI_SOCKS_PROXY` | Optional. SOCKS proxy configuration (e.g. "socks5://127.0.0.1:1080") |
@@ -99,34 +98,6 @@ Import the dotenv module in your script. It will automatically read the environm
 import 'dotenv/config';
 ```
 
-## Using Azure OpenAI Service
-
-There are some extra configs when using Azure OpenAI Service.
-
-### Use ADT token provider
-
-This mode cannot be used in Chrome extension.
-
-```bash
-# this is always true when using Azure OpenAI Service
-export MIDSCENE_USE_AZURE_OPENAI=1
-
-export MIDSCENE_AZURE_OPENAI_SCOPE="https://cognitiveservices.azure.com/.default"
-export AZURE_OPENAI_ENDPOINT="..."
-export AZURE_OPENAI_API_VERSION="2024-05-01-preview"
-export AZURE_OPENAI_DEPLOYMENT="gpt-4o"
-```
-
-### Use keyless authentication
-
-```bash
-export MIDSCENE_USE_AZURE_OPENAI=1
-export AZURE_OPENAI_ENDPOINT="..."
-export AZURE_OPENAI_KEY="..."
-export AZURE_OPENAI_API_VERSION="2024-05-01-preview"
-export AZURE_OPENAI_DEPLOYMENT="gpt-4o"
-```
-
 ## Set config by JavaScript
 
 You can also override the config by javascript. Remember to call this before running Midscene codes.
@@ -188,18 +159,6 @@ export MIDSCENE_MODEL_NAME="ui-tars-72b-sft"
 export MIDSCENE_USE_VLM_UI_TARS=1
 ```
 
-## Example: config `claude-3-opus-20240229` from Anthropic
-
-When configuring `MIDSCENE_USE_ANTHROPIC_SDK=1`, Midscene will use Anthropic SDK (`@anthropic-ai/sdk`) to call the model.
-
-Configure the environment variables:
-
-```bash
-export MIDSCENE_USE_ANTHROPIC_SDK=1
-export ANTHROPIC_API_KEY="....."
-export MIDSCENE_MODEL_NAME="claude-3-opus-20240229"
-```
-
 ## Example: config request headers (like for openrouter)
 
 ```bash

apps/site/docs/zh/model-provider.mdx

@@ -46,7 +46,6 @@ Midscene 默认集成了 OpenAI SDK 调用 AI 服务。使用这个 SDK 限定
 
 | 名称 | 描述 |
 |------|-------------|
-| `OPENAI_USE_AZURE` | 可选。设置为 "true" 以使用 Azure OpenAI Service。更多详情请参阅后文 |
 | `MIDSCENE_OPENAI_INIT_CONFIG_JSON` | 可选。OpenAI SDK 的初始化配置 JSON |
 | `MIDSCENE_OPENAI_HTTP_PROXY` | 可选。HTTP/HTTPS 代理配置 (如 `http://127.0.0.1:8080` 或 `https://proxy.example.com:8080`)。这个选项优先级高于 `MIDSCENE_OPENAI_SOCKS_PROXY` |
 | `MIDSCENE_OPENAI_SOCKS_PROXY` | 可选。SOCKS 代理配置 (如 "socks5://127.0.0.1:1080") |
@@ -102,32 +101,6 @@ OPENAI_API_KEY="sk-abcdefghijklmnopqrstuvwxyz"
 import 'dotenv/config';
 ```
 
-## 使用 Azure OpenAI 服务时的配置
-
-### 使用 ADT token provider
-
-此种模式无法运行在浏览器插件中。
-
-```bash
-# 使用 Azure OpenAI 服务时，配置为 1
-export MIDSCENE_USE_AZURE_OPENAI=1
-
-export MIDSCENE_AZURE_OPENAI_SCOPE="https://cognitiveservices.azure.com/.default"
-export AZURE_OPENAI_ENDPOINT="..."
-export AZURE_OPENAI_API_VERSION="2024-05-01-preview"
-export AZURE_OPENAI_DEPLOYMENT="gpt-4o"
-```
-
-### 使用 keyless 模式
-
-```bash
-export MIDSCENE_USE_AZURE_OPENAI=1
-export AZURE_OPENAI_ENDPOINT="..."
-export AZURE_OPENAI_KEY="..."
-export AZURE_OPENAI_API_VERSION="2024-05-01-preview"
-export AZURE_OPENAI_DEPLOYMENT="gpt-4o"
-```
-
 ## 使用 Javascript 配置 AI 服务
 
 你也可以在运行 Midscene 代码之前，使用 Javascript 来配置 AI 服务。
@@ -186,17 +159,5 @@ export MIDSCENE_MODEL_NAME="ui-tars-72b-sft"
 export MIDSCENE_USE_VLM_UI_TARS=1
 ```
 
-## 示例：使用 Anthropic 的 `claude-3-opus-20240229` 模型
-
-当配置 `MIDSCENE_USE_ANTHROPIC_SDK=1` 时，Midscene 会使用 Anthropic SDK (`@anthropic-ai/sdk`) 来调用模型。
-
-配置环境变量：
-
-```bash
-export MIDSCENE_USE_ANTHROPIC_SDK=1
-export ANTHROPIC_API_KEY="....."
-export MIDSCENE_MODEL_NAME="claude-3-opus-20240229"
-```
-
 
 <TroubleshootingLLMConnectivity />

package-lock.json

@@ -72,17 +72,14 @@
     "test:parse-action": "npm run test:ai -- tests/ai/parse-action.test.ts"
   },
   "dependencies": {
-    "@anthropic-ai/sdk": "0.33.1",
-    "@azure/identity": "4.5.0",
     "@langchain/core": "0.3.26",
     "@midscene/recorder": "workspace:*",
     "@midscene/shared": "workspace:*",
     "@ui-tars/action-parser": "1.2.3",
     "dotenv": "^16.4.5",
     "https-proxy-agent": "7.0.2",
     "jsonrepair": "3.12.0",
-    "langsmith": "0.3.7",
-    "openai": "4.81.0",
+    "openai": "6.3.0",
     "socks-proxy-agent": "8.0.4",
     "zod": "3.24.3",
     "semver": "7.5.2",