autowing 0.1.0__tar.gz

autowing-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

autowing-0.1.0/PKG-INFO

@@ -0,0 +1,37 @@
+Metadata-Version: 2.1
+Name: autowing
+Version: 0.1.0
+Summary: auto-wing is a tool that uses LLM to assist automated testing.
+Author: defnngj
+Author-email: defnngj@gmail.com
+Requires-Python: >=3.12,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: dashscope (>=1.22.1,<2.0.0)
+Requires-Dist: openai (>=1.60.1,<2.0.0)
+Requires-Dist: pytest-playwright (>=0.6.2,<0.7.0)
+Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
+Requires-Dist: selenium (>=4.28.1,<5.0.0)
+Description-Content-Type: text/markdown
+
+# auto-wing
+
+![](auto-wing.png)
+
+> auto-wing is a tool that uses LLM to assist automated testing, give your automated testing wings.
+
+auto-wing是一个利用LLM辅助自动化测试的工具, 为你的自动化测试插上翅膀。
+
+
+### Features
+
+⭐ 支持多种操作：`ai_action`、`ai_query`、`ai_assert`等。
+
+⭐ 支持多模型：`openai`、`qwen` 和 `deepseek`。
+
+⭐ 支持 `playwright`、`selenium`等。
+
+⭐ 方便的和现有自动化项目集成。
+
+### 安装
+

autowing-0.1.0/README.md

@@ -0,0 +1,20 @@
+# auto-wing
+
+![](auto-wing.png)
+
+> auto-wing is a tool that uses LLM to assist automated testing, give your automated testing wings.
+
+auto-wing是一个利用LLM辅助自动化测试的工具, 为你的自动化测试插上翅膀。
+
+
+### Features
+
+⭐ 支持多种操作：`ai_action`、`ai_query`、`ai_assert`等。
+
+⭐ 支持多模型：`openai`、`qwen` 和 `deepseek`。
+
+⭐ 支持 `playwright`、`selenium`等。
+
+⭐ 方便的和现有自动化项目集成。
+
+### 安装

autowing-0.1.0/autowing/core/ai_context.py

@@ -0,0 +1,46 @@
+from typing import Any, Dict, Optional
+import json
+
+
+class AiContext:
+    """
+    A class for managing AI context data.
+    Provides storage and retrieval of context information used in AI operations.
+    """
+
+    def __init__(self):
+        """
+        Initialize an empty context storage.
+        """
+        self._context: Dict[str, Any] = {}
+        
+    def set_context(self, key: str, value: Any) -> None:
+        """
+        Store a value in the context.
+
+        Args:
+            key (str): The key under which to store the value
+            value (Any): The value to store
+        """
+        self._context[key] = value
+
+    def get_context(self, key: str) -> Optional[Any]:
+        """
+        Retrieve a value from the context.
+
+        Args:
+            key (str): The key of the value to retrieve
+
+        Returns:
+            Optional[Any]: The stored value, or None if the key doesn't exist
+        """
+        return self._context.get(key)
+
+    def to_json(self) -> str:
+        """
+        Convert the context to a JSON string.
+
+        Returns:
+            str: JSON string representation of the context
+        """
+        return json.dumps(self._context)

autowing-0.1.0/autowing/core/llm/base.py

@@ -0,0 +1,53 @@
+from abc import ABC, abstractmethod
+from typing import Dict, Any, Optional
+
+
+class BaseLLMClient(ABC):
+    """
+    Abstract base class for Language Model clients.
+    Defines the interface that all LLM clients must implement.
+    """
+
+    @abstractmethod
+    def complete(self, prompt: str, context: Optional[Dict[str, Any]] = None) -> str:
+        """
+        Generate a completion for the given prompt with optional context.
+
+        Args:
+            prompt (str): The input text to generate completion for
+            context (Optional[Dict[str, Any]]): Additional context information for the completion
+
+        Returns:
+            str: The generated completion text
+
+        Raises:
+            NotImplementedError: If the subclass doesn't implement this method
+        """
+        pass
+
+    @abstractmethod
+    def complete_with_vision(self, prompt: Dict[str, Any]) -> str:
+        """
+        Generate a completion for vision-based tasks.
+
+        Args:
+            prompt (Dict[str, Any]): A dictionary containing the prompt and image data
+                                   in the format required by the specific model
+
+        Returns:
+            str: The generated completion text
+
+        Raises:
+            NotImplementedError: If the subclass doesn't implement this method
+        """
+        pass
+
+    @classmethod
+    def get_model_name(cls) -> str:
+        """
+        Get the standardized name of the model.
+
+        Returns:
+            str: The model name in lowercase, with 'client' suffix removed
+        """
+        return cls.__name__.lower().replace('client', '')

autowing-0.1.0/autowing/core/llm/deepseek_client.py

@@ -0,0 +1,151 @@
+import os
+from typing import Optional, Dict, Any, List
+import json
+from openai import OpenAI
+from autowing.core.llm.base import BaseLLMClient
+
+
+class DeepSeekClient(BaseLLMClient):
+    """
+    A client for interacting with the DeepSeek AI model.
+    Implements the BaseLLMClient interface for text completion and vision tasks.
+    """
+
+    def __init__(self, api_key: Optional[str] = None):
+        """
+        Initialize the DeepSeek client.
+
+        Args:
+            api_key (Optional[str]): The API key for DeepSeek. If not provided,
+                                   will try to get from DEEPSEEK_API_KEY environment variable.
+
+        Raises:
+            ValueError: If no API key is provided or found in environment variables.
+        """
+        self.api_key = api_key or os.getenv("DEEPSEEK_API_KEY")
+        if not self.api_key:
+            raise ValueError("DeepSeek API key is required")
+
+        self.base_url = os.getenv("DEEPSEEK_BASE_URL", "https://api.deepseek.com")
+        self.model_name = os.getenv("DEEPSEEK_MODEL_NAME", "deepseek-chat")
+
+        self.client = OpenAI(
+            api_key=self.api_key,
+            base_url=self.base_url
+        )
+
+    def _truncate_text(self, text: str, max_length: int = 30000) -> str:
+        """
+        Truncate text to fit within model's length limits.
+
+        Args:
+            text (str): The input text to truncate
+            max_length (int): Maximum allowed length for the text. Defaults to 30000.
+
+        Returns:
+            str: Truncated text with ellipsis if needed
+        """
+        if len(text) > max_length:
+            return text[:max_length] + "..."
+        return text
+
+    def _format_messages(self, prompt: str, context: Optional[Dict[str, Any]] = None) -> List[Dict[str, str]]:
+        """
+        Format messages for the DeepSeek API.
+
+        Args:
+            prompt (str): The main prompt text
+            context (Optional[Dict[str, Any]]): Additional context information
+
+        Returns:
+            List[Dict[str, str]]: Formatted messages list ready for API submission
+        """
+        # Add system message
+        messages = [{
+            "role": "system",
+            "content": (
+                "You are a web automation assistant. "
+                "Analyze the page structure and provide precise element locators. "
+                "Return responses in the requested format."
+            )
+        }]
+
+        # Add context (if any)
+        if context:
+            context_str = json.dumps(context, ensure_ascii=False)
+            messages.append({
+                "role": "user",
+                "content": f"Page context: {self._truncate_text(context_str)}"
+            })
+
+        # Add main prompt
+        messages.append({
+            "role": "user",
+            "content": self._truncate_text(prompt)
+        })
+
+        return messages
+
+    def complete(self, prompt: str, context: Optional[Dict[str, Any]] = None) -> str:
+        """
+        Send a completion request to the DeepSeek API.
+
+        Args:
+            prompt (str): The text prompt to complete
+            context (Optional[Dict[str, Any]]): Additional context for the completion
+
+        Returns:
+            str: The model's response text
+
+        Raises:
+            Exception: If there's an error communicating with the DeepSeek API
+        """
+        try:
+            messages = self._format_messages(prompt, context)
+
+            response = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=messages,
+                temperature=0.7,
+                max_tokens=2000
+            )
+
+            return response.choices[0].message.content
+        except Exception as e:
+            raise Exception(f"DeepSeek API error: {str(e)}")
+
+    def complete_with_vision(self, prompt: Dict[str, Any]) -> str:
+        """
+        Send a vision-based completion request to the DeepSeek API.
+
+        Args:
+            prompt (Dict[str, Any]): A dictionary containing messages and image data
+                                   in the format expected by the API
+
+        Returns:
+            str: The model's response text
+
+        Raises:
+            Exception: If there's an error communicating with the DeepSeek API
+        """
+        try:
+            # Make sure the message length is within the limit
+            messages = prompt["messages"]
+            for msg in messages:
+                if isinstance(msg.get("content"), str):
+                    msg["content"] = self._truncate_text(msg["content"])
+                elif isinstance(msg.get("content"), list):
+                    for item in msg["content"]:
+                        if isinstance(item.get("text"), str):
+                            item["text"] = self._truncate_text(item["text"])
+
+            response = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=messages,
+                temperature=0.7,
+                max_tokens=2000
+            )
+
+            return response.choices[0].message.content
+        except Exception as e:
+            raise Exception(f"DeepSeek API error: {str(e)}") 

autowing-0.1.0/autowing/core/llm/factory.py

@@ -0,0 +1,48 @@
+import os
+from typing import Type
+from autowing.core.llm.base import BaseLLMClient
+from autowing.core.llm.openai_client import OpenAIClient
+from autowing.core.llm.qwen_client import QwenClient
+from autowing.core.llm.deepseek_client import DeepSeekClient
+
+
+class LLMFactory:
+    """
+    Factory class for creating Language Model clients.
+    Provides centralized management of different LLM implementations.
+    """
+
+    _models = {
+        'openai': OpenAIClient,
+        'qwen': QwenClient,
+        'deepseek': DeepSeekClient
+    }
+
+    @classmethod
+    def create(cls) -> BaseLLMClient:
+        """
+        Create an instance of the configured LLM client.
+
+        Returns:
+            BaseLLMClient: An instance of the specified LLM client
+
+        Raises:
+            ValueError: If the specified model provider is not supported
+        """
+        model_name = os.getenv("AUTOWING_MODEL_PROVIDER", "deepseek").lower()
+        if model_name not in cls._models:
+            raise ValueError(f"Unsupported model provider: {model_name}")
+
+        model_class = cls._models[model_name]
+        return model_class()
+    
+    @classmethod
+    def register_model(cls, name: str, model_class: Type[BaseLLMClient]) -> None:
+        """
+        Register a new LLM client implementation.
+
+        Args:
+            name (str): The name to register the model under
+            model_class (Type[BaseLLMClient]): The class implementing the BaseLLMClient interface
+        """
+        cls._models[name.lower()] = model_class 

autowing-0.1.0/autowing/core/llm/openai_client.py

@@ -0,0 +1,85 @@
+import os
+from typing import Optional, Dict, Any
+from openai import OpenAI
+from autowing.core.llm.base import BaseLLMClient
+
+
+class OpenAIClient(BaseLLMClient):
+    """
+    OpenAI API client implementation.
+    Provides access to OpenAI's GPT and vision models.
+    """
+
+    def __init__(self, api_key: Optional[str] = None, base_url: Optional[str] = None):
+        """
+        Initialize the OpenAI client.
+
+        Args:
+            api_key (Optional[str]): OpenAI API key. If not provided, will try to get from OPENAI_API_KEY env var
+            base_url (Optional[str]): Custom base URL for API requests
+
+        Raises:
+            ValueError: If no API key is provided or found in environment variables
+        """
+        self.api_key = api_key or os.getenv("OPENAI_API_KEY")
+        if not self.api_key:
+            raise ValueError("OpenAI API key is required")
+            
+        self.base_url = base_url or os.getenv("OPENAI_BASE_URL")
+        self.model_name = os.getenv("MIDSCENE_MODEL_NAME", "gpt-4-vision-preview")
+        
+        client_kwargs = {"api_key": self.api_key}
+        if self.base_url:
+            client_kwargs["base_url"] = self.base_url
+            
+        self.client = OpenAI(**client_kwargs)
+        
+    def complete(self, prompt: str, context: Optional[Dict[str, Any]] = None) -> str:
+        """
+        Generate a completion using GPT-4.
+
+        Args:
+            prompt (str): The text prompt to complete
+            context (Optional[Dict[str, Any]]): Additional context for the completion
+
+        Returns:
+            str: The model's response text
+
+        Raises:
+            Exception: If there's an error communicating with the OpenAI API
+        """
+        try:
+            response = self.client.chat.completions.create(
+                model="gpt-4",
+                messages=[
+                    {"role": "system", "content": "You are a helpful AI assistant for web automation."},
+                    {"role": "user", "content": prompt}
+                ]
+            )
+            return response.choices[0].message.content
+        except Exception as e:
+            raise Exception(f"OpenAI API error: {str(e)}")
+            
+    def complete_with_vision(self, prompt: Dict[str, Any]) -> str:
+        """
+        Generate a completion for vision tasks using GPT-4 Vision.
+
+        Args:
+            prompt (Dict[str, Any]): A dictionary containing messages and image data
+                                   in the format required by the GPT-4 Vision API
+
+        Returns:
+            str: The model's response text
+
+        Raises:
+            Exception: If there's an error communicating with the OpenAI Vision API
+        """
+        try:
+            response = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=prompt["messages"],
+                max_tokens=1000
+            )
+            return response.choices[0].message.content
+        except Exception as e:
+            raise Exception(f"OpenAI Vision API error: {str(e)}")

autowing-0.1.0/autowing/core/llm/qwen_client.py

@@ -0,0 +1,152 @@
+import os
+import json
+from typing import Optional, Dict, Any, List
+from openai import OpenAI
+from autowing.core.llm.base import BaseLLMClient
+
+
+class QwenClient(BaseLLMClient):
+    """
+    Qwen (DashScope) API client implementation.
+    Provides access to Alibaba Cloud's Qwen language model through OpenAI-compatible interface.
+    """
+
+    def __init__(self, api_key: Optional[str] = None):
+        """
+        Initialize the Qwen client.
+
+        Args:
+            api_key (Optional[str]): DashScope API key. If not provided, will try to get from DASHSCOPE_API_KEY env var
+
+        Raises:
+            ValueError: If no API key is provided or found in environment variables
+        """
+        self.api_key = api_key or os.getenv("DASHSCOPE_API_KEY")
+        if not self.api_key:
+            raise ValueError("DashScope API key is required")
+
+        # 使用兼容模式的 URL
+        self.base_url = os.getenv("OPENAI_BASE_URL", "https://dashscope.aliyuncs.com/compatible-mode/v1")
+        self.model_name = os.getenv("MIDSCENE_MODEL_NAME", "qwen-vl-max-latest")
+
+        # 使用 OpenAI 客户端，但配置为千问的 URL
+        self.client = OpenAI(
+            api_key=self.api_key,
+            base_url=self.base_url
+        )
+
+    def _truncate_text(self, text: str, max_length: int = 30000) -> str:
+        """
+        Truncate text to fit within model's length limits.
+
+        Args:
+            text (str): The input text to truncate
+            max_length (int): Maximum allowed length for the text. Defaults to 30000
+
+        Returns:
+            str: Truncated text with ellipsis if needed
+        """
+        if len(text) > max_length:
+            return text[:max_length] + "..."
+        return text
+
+    def _format_messages(self, prompt: str, context: Optional[Dict[str, Any]] = None) -> List[Dict[str, str]]:
+        """
+        Format messages for the Qwen API.
+
+        Args:
+            prompt (str): The main prompt text
+            context (Optional[Dict[str, Any]]): Additional context information
+
+        Returns:
+            List[Dict[str, str]]: Formatted messages list ready for API submission
+        """
+        # Add system message
+        messages = [{
+            "role": "system",
+            "content": (
+                "You are a web automation assistant. "
+                "Analyze the page structure and provide precise element locators. "
+                "Return responses in the requested format."
+            )
+        }]
+
+        # Add context (if any)
+        if context:
+            context_str = json.dumps(context, ensure_ascii=False)
+            messages.append({
+                "role": "user",
+                "content": f"Page context: {self._truncate_text(context_str)}"
+            })
+
+        # Add main prompt
+        messages.append({
+            "role": "user",
+            "content": self._truncate_text(prompt)
+        })
+
+        return messages
+
+    def complete(self, prompt: str, context: Optional[Dict[str, Any]] = None) -> str:
+        """
+        Generate a completion using Qwen model.
+
+        Args:
+            prompt (str): The text prompt to complete
+            context (Optional[Dict[str, Any]]): Additional context for the completion
+
+        Returns:
+            str: The model's response text
+
+        Raises:
+            Exception: If there's an error communicating with the Qwen API
+        """
+        try:
+            messages = self._format_messages(prompt, context)
+
+            response = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=messages,
+                temperature=0.7,
+                max_tokens=2000
+            )
+
+            return response.choices[0].message.content
+        except Exception as e:
+            raise Exception(f"Qwen API error: {str(e)}")
+
+    def complete_with_vision(self, prompt: Dict[str, Any]) -> str:
+        """
+        Generate a completion for vision tasks using Qwen-VL model.
+
+        Args:
+            prompt (Dict[str, Any]): A dictionary containing messages and image data
+                                   in the format required by the Qwen-VL API
+
+        Returns:
+            str: The model's response text
+
+        Raises:
+            Exception: If there's an error communicating with the Qwen API
+        """
+        try:
+            # Make sure the message length is within the limit
+            messages = prompt["messages"]
+            for msg in messages:
+                if isinstance(msg.get("content"), str):
+                    msg["content"] = self._truncate_text(msg["content"])
+                elif isinstance(msg.get("content"), list):
+                    for item in msg["content"]:
+                        if isinstance(item.get("text"), str):
+                            item["text"] = self._truncate_text(item["text"])
+
+            response = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=messages,
+                temperature=0.7,
+                max_tokens=2000
+            )
+
+            return response.choices[0].message.content
+        except Exception as e:
+            raise Exception(f"Qwen API error: {str(e)}")

autowing-0.1.0/autowing/playwright/fixture.py

@@ -0,0 +1,248 @@
+from typing import Any, Dict
+import json
+from playwright.sync_api import Page
+from autowing.core.llm.factory import LLMFactory
+
+
+class PlaywrightAiFixture:
+    """
+    A fixture class that combines Playwright with AI capabilities for web automation.
+    Provides AI-driven interaction with web pages using various LLM providers.
+    """
+
+    def __init__(self, page: Page):
+        """
+        Initialize the AI-powered Playwright fixture.
+
+        Args:
+            page (Page): The Playwright page object to automate
+        """
+        self.page = page
+        self.llm_client = LLMFactory.create()
+
+    def _get_page_context(self) -> Dict[str, Any]:
+        """
+        Extract context information from the current page.
+        Collects information about visible elements and page metadata.
+
+        Returns:
+            Dict[str, Any]: A dictionary containing page URL, title, and information about
+                           visible interactive elements
+        """
+        # 获取页面基本信息
+        basic_info = {
+            "url": self.page.url,
+            "title": self.page.title()
+        }
+        
+        # 获取关键元素信息
+        elements_info = self.page.evaluate("""() => {
+            const getVisibleElements = () => {
+                const elements = [];
+                const selectors = [
+                    'input', 'button', 'a', '[role="button"]',
+                    '[role="link"]', '[role="searchbox"]', 'textarea'
+                ];
+                
+                for (const selector of selectors) {
+                    document.querySelectorAll(selector).forEach(el => {
+                        if (el.offsetWidth > 0 && el.offsetHeight > 0) {
+                            elements.push({
+                                tag: el.tagName.toLowerCase(),
+                                type: el.getAttribute('type'),
+                                placeholder: el.getAttribute('placeholder'),
+                                value: el.value,
+                                text: el.textContent?.trim(),
+                                aria: el.getAttribute('aria-label'),
+                                id: el.id,
+                                name: el.getAttribute('name'),
+                                class: el.className
+                            });
+                        }
+                    });
+                }
+                return elements;
+            };
+            return getVisibleElements();
+        }""")
+        
+        return {
+            **basic_info,
+            "elements": elements_info
+        }
+        
+    def ai_action(self, prompt: str) -> None:
+        """
+        Execute an AI-driven action on the page based on the given prompt.
+        The AI will analyze the page context and perform the requested action.
+
+        Args:
+            prompt (str): Natural language description of the action to perform
+
+        Raises:
+            ValueError: If the AI response cannot be parsed or contains invalid instructions
+            Exception: If the requested action cannot be performed
+        """
+        context = self._get_page_context()
+        
+        # 构建提示，明确要求JSON格式的响应
+        action_prompt = f"""
+You are a web automation assistant. Based on the following page context, provide instructions for the requested action.
+
+Current page context:
+URL: {context['url']}
+Title: {context['title']}
+
+Available elements:
+{json.dumps(context['elements'], indent=2)}
+
+User request: {prompt}
+
+Return ONLY a JSON object with the following structure, no other text:
+{{
+    "selector": "CSS selector or XPath to locate the element",
+    "action": "fill",
+    "value": "text to input",
+    "key": "key to press if needed"
+}}
+
+Example response:
+{{
+    "selector": "#search-input",
+    "action": "fill",
+    "value": "search text",
+    "key": "Enter"
+}}
+"""
+        
+        response = self.llm_client.complete(action_prompt)
+        
+        try:
+            # 尝试提取JSON部分
+            json_str = response
+            if '```json' in response:
+                json_str = response.split('```json')[1].split('```')[0].strip()
+            elif '```' in response:
+                json_str = response.split('```')[1].split('```')[0].strip()
+                
+            instruction = json.loads(json_str)
+            selector = instruction.get('selector')
+            action = instruction.get('action')
+            
+            if not selector or not action:
+                raise ValueError("Invalid instruction format")
+                
+            # 执行操作
+            element = self.page.locator(selector)
+            if action == 'click':
+                element.click()
+            elif action == 'fill':
+                element.fill(instruction.get('value', ''))
+                if instruction.get('key'):
+                    element.press(instruction.get('key'))
+            elif action == 'press':
+                element.press(instruction.get('key', 'Enter'))
+            else:
+                raise ValueError(f"Unsupported action: {action}")
+                
+        except json.JSONDecodeError:
+            raise ValueError(f"Failed to parse instruction: {response}")
+            
+    def ai_query(self, prompt: str) -> Any:
+        """
+        Query information from the page using AI analysis.
+
+        Args:
+            prompt (str): Natural language query about the page content
+
+        Returns:
+            Any: The query results as parsed from the AI response
+
+        Raises:
+            ValueError: If the AI response cannot be parsed into valid JSON
+        """
+        context = self._get_page_context()
+        
+        query_prompt = f"""
+You are a web automation assistant. Based on the following page context, answer the query.
+
+Current page context:
+URL: {context['url']}
+Title: {context['title']}
+
+Available elements:
+{json.dumps(context['elements'], indent=2)}
+
+Query: {prompt}
+
+Return ONLY a JSON array of results, no other text.
+"""
+        
+        response = self.llm_client.complete(query_prompt)
+        
+        try:
+            # 尝试提取JSON部分
+            json_str = response
+            if '```json' in response:
+                json_str = response.split('```json')[1].split('```')[0].strip()
+            elif '```' in response:
+                json_str = response.split('```')[1].split('```')[0].strip()
+                
+            return json.loads(json_str)
+        except json.JSONDecodeError:
+            raise ValueError(f"Failed to parse query results: {response}")
+            
+    def ai_assert(self, prompt: str) -> bool:
+        """
+        Verify a condition on the page using AI analysis.
+
+        Args:
+            prompt (str): Natural language description of the condition to verify
+
+        Returns:
+            bool: True if the condition is met, False otherwise
+
+        Raises:
+            ValueError: If the AI response cannot be parsed as a boolean value
+        """
+        context = self._get_page_context()
+        
+        assert_prompt = f"""
+You are a web automation assistant. Based on the following page context, verify the assertion.
+
+Current page context:
+URL: {context['url']}
+Title: {context['title']}
+
+Available elements:
+{json.dumps(context['elements'], indent=2)}
+
+Assertion to verify: {prompt}
+
+Return ONLY true or false as a JSON boolean, no other text.
+Example: true
+"""
+        
+        response = self.llm_client.complete(assert_prompt)
+        
+        try:
+            # 尝试提取JSON部分
+            json_str = response.lower().strip()
+            if 'true' in json_str:
+                return True
+            if 'false' in json_str:
+                return False
+            raise ValueError("Invalid assertion response")
+        except Exception:
+            raise ValueError(f"Failed to parse assertion result: {response}")
+
+
+def create_fixture():
+    """
+    Create a PlaywrightAiFixture factory.
+
+    Returns:
+        Callable[[Page], PlaywrightAiFixture]: A factory function that creates
+        PlaywrightAiFixture instances
+    """
+    return PlaywrightAiFixture

autowing-0.1.0/autowing/selenium/fixture.py

@@ -0,0 +1,262 @@
+from typing import Any, Dict
+import json
+from selenium.webdriver.remote.webdriver import WebDriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.keys import Keys
+from selenium.common.exceptions import TimeoutException
+from autowing.core.llm.factory import LLMFactory
+
+
+class SeleniumAiFixture:
+    """
+    A fixture class that combines Selenium with AI capabilities for web automation.
+    Provides AI-driven interaction with web pages using various LLM providers.
+    Maintains API compatibility with PlaywrightAiFixture.
+    """
+
+    def __init__(self, driver: WebDriver):
+        """
+        Initialize the AI-powered Selenium fixture.
+
+        Args:
+            driver (WebDriver): The Selenium WebDriver instance to automate
+        """
+        self.driver = driver
+        self.llm_client = LLMFactory.create()
+        self.wait = WebDriverWait(self.driver, 10)  # Default timeout of 10 seconds
+
+    def _get_page_context(self) -> Dict[str, Any]:
+        """
+        Extract context information from the current page.
+        Collects information about visible elements and page metadata.
+
+        Returns:
+            Dict[str, Any]: A dictionary containing page URL, title, and information about
+                           visible interactive elements
+        """
+        # Get basic page info
+        basic_info = {
+            "url": self.driver.current_url,
+            "title": self.driver.title
+        }
+        
+        # Get key elements info using JavaScript
+        elements_info = self.driver.execute_script("""
+            const getVisibleElements = () => {
+                const elements = [];
+                const selectors = [
+                    'input', 'button', 'a', '[role="button"]',
+                    '[role="link"]', '[role="searchbox"]', 'textarea'
+                ];
+                
+                for (const selector of selectors) {
+                    document.querySelectorAll(selector).forEach(el => {
+                        if (el.offsetWidth > 0 && el.offsetHeight > 0) {
+                            elements.push({
+                                tag: el.tagName.toLowerCase(),
+                                type: el.getAttribute('type'),
+                                placeholder: el.getAttribute('placeholder'),
+                                value: el.value,
+                                text: el.textContent?.trim(),
+                                aria: el.getAttribute('aria-label'),
+                                id: el.id,
+                                name: el.getAttribute('name'),
+                                class: el.className
+                            });
+                        }
+                    });
+                }
+                return elements;
+            };
+            return getVisibleElements();
+        """)
+        
+        return {
+            **basic_info,
+            "elements": elements_info
+        }
+
+    def ai_action(self, prompt: str) -> None:
+        """
+        Execute an AI-driven action on the page based on the given prompt.
+        The AI will analyze the page context and perform the requested action.
+
+        Args:
+            prompt (str): Natural language description of the action to perform
+
+        Raises:
+            ValueError: If the AI response cannot be parsed or contains invalid instructions
+            TimeoutException: If the element cannot be found or interacted with
+            Exception: If the requested action cannot be performed
+        """
+        context = self._get_page_context()
+        
+        action_prompt = f"""
+You are a web automation assistant. Based on the following page context, provide instructions for the requested action.
+
+Current page context:
+URL: {context['url']}
+Title: {context['title']}
+
+Available elements:
+{json.dumps(context['elements'], indent=2)}
+
+User request: {prompt}
+
+Return ONLY a JSON object with the following structure, no other text:
+{{
+    "selector": "CSS selector or XPath to locate the element",
+    "action": "fill",
+    "value": "text to input",
+    "key": "key to press if needed"
+}}
+
+Example response:
+{{
+    "selector": "#search-input",
+    "action": "fill",
+    "value": "search text",
+    "key": "Enter"
+}}
+"""
+        
+        response = self.llm_client.complete(action_prompt)
+        
+        try:
+            # Try to extract JSON part
+            json_str = response
+            if '```json' in response:
+                json_str = response.split('```json')[1].split('```')[0].strip()
+            elif '```' in response:
+                json_str = response.split('```')[1].split('```')[0].strip()
+                
+            instruction = json.loads(json_str)
+            selector = instruction.get('selector')
+            action = instruction.get('action')
+            
+            if not selector or not action:
+                raise ValueError("Invalid instruction format")
+                
+            # Execute the action
+            element = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, selector)))
+            
+            if action == 'click':
+                element.click()
+            elif action == 'fill':
+                element.clear()
+                element.send_keys(instruction.get('value', ''))
+                if instruction.get('key'):
+                    key_attr = getattr(Keys, instruction['key'].upper(), None)
+                    if key_attr:
+                        element.send_keys(key_attr)
+            elif action == 'press':
+                key_attr = getattr(Keys, instruction.get('key', 'ENTER').upper())
+                element.send_keys(key_attr)
+            else:
+                raise ValueError(f"Unsupported action: {action}")
+                
+        except json.JSONDecodeError:
+            raise ValueError(f"Failed to parse instruction: {response}")
+        except TimeoutException:
+            raise TimeoutException(f"Element not found: {selector}")
+            
+    def ai_query(self, prompt: str) -> Any:
+        """
+        Query information from the page using AI analysis.
+
+        Args:
+            prompt (str): Natural language query about the page content
+
+        Returns:
+            Any: The query results as parsed from the AI response
+
+        Raises:
+            ValueError: If the AI response cannot be parsed into valid JSON
+        """
+        context = self._get_page_context()
+        
+        query_prompt = f"""
+You are a web automation assistant. Based on the following page context, answer the query.
+
+Current page context:
+URL: {context['url']}
+Title: {context['title']}
+
+Available elements:
+{json.dumps(context['elements'], indent=2)}
+
+Query: {prompt}
+
+Return ONLY a JSON array of results, no other text.
+"""
+        
+        response = self.llm_client.complete(query_prompt)
+        
+        try:
+            # Try to extract JSON part
+            json_str = response
+            if '```json' in response:
+                json_str = response.split('```json')[1].split('```')[0].strip()
+            elif '```' in response:
+                json_str = response.split('```')[1].split('```')[0].strip()
+                
+            return json.loads(json_str)
+        except json.JSONDecodeError:
+            raise ValueError(f"Failed to parse query results: {response}")
+            
+    def ai_assert(self, prompt: str) -> bool:
+        """
+        Verify a condition on the page using AI analysis.
+
+        Args:
+            prompt (str): Natural language description of the condition to verify
+
+        Returns:
+            bool: True if the condition is met, False otherwise
+
+        Raises:
+            ValueError: If the AI response cannot be parsed as a boolean value
+        """
+        context = self._get_page_context()
+        
+        assert_prompt = f"""
+You are a web automation assistant. Based on the following page context, verify the assertion.
+
+Current page context:
+URL: {context['url']}
+Title: {context['title']}
+
+Available elements:
+{json.dumps(context['elements'], indent=2)}
+
+Assertion to verify: {prompt}
+
+Return ONLY true or false as a JSON boolean, no other text.
+Example: true
+"""
+        
+        response = self.llm_client.complete(assert_prompt)
+        
+        try:
+            # Try to extract JSON part
+            json_str = response.lower().strip()
+            if 'true' in json_str:
+                return True
+            if 'false' in json_str:
+                return False
+            raise ValueError("Invalid assertion response")
+        except Exception:
+            raise ValueError(f"Failed to parse assertion result: {response}")
+
+
+def create_fixture():
+    """
+    Create a SeleniumAiFixture factory.
+
+    Returns:
+        Callable[[WebDriver], SeleniumAiFixture]: A factory function that creates
+        SeleniumAiFixture instances
+    """
+    return SeleniumAiFixture

autowing-0.1.0/pyproject.toml

@@ -0,0 +1,18 @@
+[tool.poetry]
+name = "autowing"
+version = "0.1.0"
+description = "auto-wing is a tool that uses LLM to assist automated testing."
+authors = ["defnngj <defnngj@gmail.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.12"
+openai = "^1.60.1"
+dashscope = "^1.22.1"
+pytest-playwright = "^0.6.2"
+selenium = "^4.28.1"
+python-dotenv = "^1.0.1"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"