Merge remote-tracking branch 'origin/main'

.github/ISSUE_TEMPLATE/request_new_features.md

@@ -1,14 +0,0 @@
----
-name: "🤔 Request new features"
-about: Suggest ideas or features you’d like to see implemented in OpenManus.
-title: ''
-labels: kind/features
-assignees: ''
----
-
-**Feature description**
-<!-- Provide a clear and concise description of the proposed feature -->
-
-**Your Feature**
-<!-- Explain your idea or implementation process. Optionally, include a Pull Request URL. -->
-<!-- Ensure accompanying docs/tests/examples are provided for review. -->

.github/ISSUE_TEMPLATE/request_new_features.yaml

@@ -0,0 +1,21 @@
+name: "🤔 Request new features"
+description: Suggest ideas or features you’d like to see implemented in OpenManus.
+labels: enhancement
+body:
+  - type: textarea
+    id: feature-description
+    attributes:
+      label: Feature description
+      description: |
+        Provide a clear and concise description of the proposed feature
+    validations:
+      required: true
+  - type: textarea
+    id: your-feature
+    attributes:
+      label: Your Feature
+      description: |
+        Explain your idea or implementation process, if any. Optionally, include a Pull Request URL.
+        Ensure accompanying docs/tests/examples are provided for review.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/show_me_the_bug.md

@@ -1,25 +0,0 @@
----
-name: "🪲 Show me the Bug"
-about: Report a bug encountered while using OpenManus and seek assistance.
-title: ''
-labels: kind/bug
-assignees: ''
----
-
-**Bug description**
-<!-- Clearly describe the bug you encountered -->
-
-**Bug solved method**
-<!-- If resolved, explain the solution. Optionally, include a Pull Request URL. -->
-<!-- If unresolved, provide additional details to aid investigation -->
-
-**Environment information**
-<!-- System: e.g., Ubuntu 22.04, Python: e.g., 3.12, OpenManus version: e.g., 0.1.0 -->
-
-- System version:
-- Python version:
-- OpenManus version or branch:
-- Installation method (e.g., `pip install -r requirements.txt` or `pip install -e .`):
-
-**Screenshots or logs**
-<!-- Attach screenshots or logs to help diagnose the issue -->

.github/ISSUE_TEMPLATE/show_me_the_bug.yaml

@@ -0,0 +1,44 @@
+name: "🪲 Show me the Bug"
+description: Report a bug encountered while using OpenManus and seek assistance.
+labels: bug
+body:
+  - type: textarea
+    id: bug-description
+    attributes:
+      label: Bug Description
+      description: |
+        Clearly describe the bug you encountered
+    validations:
+      required: true
+  - type: textarea
+    id: solve-method
+    attributes:
+      label: Bug solved method
+      description: |
+        If resolved, explain the solution. Optionally, include a Pull Request URL.
+        If unresolved, provide additional details to aid investigation
+    validations:
+      required: true
+  - type: textarea
+    id: environment-information
+    attributes:
+      label: Environment information
+      description: |
+        System: e.g., Ubuntu 22.04
+        Python: e.g., 3.12
+        OpenManus version: e.g., 0.1.0
+      value: |
+        - System version:
+        - Python version:
+        - OpenManus version or branch:
+        - Installation method (e.g., `pip install -r requirements.txt` or `pip install -e .`):
+    validations:
+      required: true
+  - type: textarea
+    id: extra-information
+    attributes:
+      label: Extra information
+      description: |
+        For example, attach screenshots or logs to help diagnose the issue
+    validations:
+      required: false

.github/workflows/pr-autodiff.yaml

@@ -15,21 +15,20 @@ jobs:
       (github.event_name == 'pull_request') ||
       (github.event_name == 'issue_comment' &&
        contains(github.event.comment.body, '!pr-diff') &&
-       (github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'OWNER') &&
+       (github.event.comment.author_association == 'CONTRIBUTOR' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'OWNER') &&
        github.event.issue.pull_request)
     steps:
       - name: Get PR head SHA
         id: get-pr-sha
         run: |
-          if [ "${{ github.event_name }}" == "pull_request" ]; then
+          PR_URL="${{ github.event.issue.pull_request.url || github.event.pull_request.url }}"
-            echo "pr_sha=${{ github.event.pull_request.head.sha }}" >> $GITHUB_OUTPUT
+          # https://api.github.com/repos/OpenManus/pulls/1
-            echo "Retrieved PR head SHA: ${{ github.event.pull_request.head.sha }}"
+          RESPONSE=$(curl -s -H "Authorization: Bearer ${{ secrets.GITHUB_TOKEN }}" $PR_URL)
-          else
+          SHA=$(echo $RESPONSE | jq -r '.head.sha')
-            PR_URL="${{ github.event.issue.pull_request.url }}"
+          TARGET_BRANCH=$(echo $RESPONSE | jq -r '.base.ref')
-            SHA=$(curl -s -H "Authorization: Bearer ${{ secrets.GITHUB_TOKEN }}" $PR_URL | jq -r '.head.sha')
+          echo "pr_sha=$SHA" >> $GITHUB_OUTPUT
-            echo "pr_sha=$SHA" >> $GITHUB_OUTPUT
+          echo "target_branch=$TARGET_BRANCH" >> $GITHUB_OUTPUT
-            echo "Retrieved PR head SHA from API: $SHA"
+          echo "Retrieved PR head SHA from API: $SHA, target branch: $TARGET_BRANCH"
-          fi
       - name: Check out code
         uses: actions/checkout@v4
         with:
@@ -49,6 +48,7 @@ jobs:
           OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}
           GH_TOKEN: ${{ github.token }}
           PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}
+          TARGET_BRANCH: ${{ steps.get-pr-sha.outputs.target_branch }}
         run: |-
           cat << 'EOF' > /tmp/_workflow_core.py
           import os
@@ -59,7 +59,7 @@ jobs:
 
           def get_diff():
               result = subprocess.run(
-                  ['git', 'diff', 'origin/main...HEAD'],
+                  ['git', 'diff', 'origin/' + os.getenv('TARGET_BRANCH') + '...HEAD'],
                   capture_output=True, text=True, check=True)
               return '\n'.join(
                   line for line in result.stdout.split('\n')
@@ -86,6 +86,17 @@ jobs:
 
               ### Spelling/Offensive Content Check
               - No spelling mistakes or offensive content found in the code or comments.
+
+              ## 中文（简体）
+              - 新增了 `ABC` 类
+              - `foo` 模块中的 `f()` 行为已修复
+
+              ### 评论高亮
+              - `config.toml` 需要正确配置才能确保新功能正常运行。
+
+              ### 内容检查
+              - 没有发现代码或注释中的拼写错误或不当措辞。
+
           3. Highlight non-English comments
           4. Check for spelling/offensive content'''
 

app/agent/toolcall.py

@@ -71,40 +71,42 @@ class ToolCallAgent(ReActAgent):
                 return False
             raise
 
-        self.tool_calls = response.tool_calls
+        self.tool_calls = tool_calls = (
+            response.tool_calls if response and response.tool_calls else []
+        )
+        content = response.content if response and response.content else ""
 
         # Log response info
-        logger.info(f"✨ {self.name}'s thoughts: {response.content}")
+        logger.info(f"✨ {self.name}'s thoughts: {content}")
         logger.info(
-            f"🛠️ {self.name} selected {len(response.tool_calls) if response.tool_calls else 0} tools to use"
+            f"🛠️ {self.name} selected {len(tool_calls) if tool_calls else 0} tools to use"
         )
-        if response.tool_calls:
+        if tool_calls:
             logger.info(
-                f"🧰 Tools being prepared: {[call.function.name for call in response.tool_calls]}"
+                f"🧰 Tools being prepared: {[call.function.name for call in tool_calls]}"
-            )
-            logger.info(
-                f"🔧 Tool arguments: {response.tool_calls[0].function.arguments}"
             )
+            logger.info(f"🔧 Tool arguments: {tool_calls[0].function.arguments}")
 
         try:
+            if response is None:
+                raise RuntimeError("No response received from the LLM")
+
             # Handle different tool_choices modes
             if self.tool_choices == ToolChoice.NONE:
-                if response.tool_calls:
+                if tool_calls:
                     logger.warning(
                         f"🤔 Hmm, {self.name} tried to use tools when they weren't available!"
                     )
-                if response.content:
+                if content:
-                    self.memory.add_message(Message.assistant_message(response.content))
+                    self.memory.add_message(Message.assistant_message(content))
                     return True
                 return False
 
             # Create and add assistant message
             assistant_msg = (
-                Message.from_tool_calls(
+                Message.from_tool_calls(content=content, tool_calls=self.tool_calls)
-                    content=response.content, tool_calls=self.tool_calls
-                )
                 if self.tool_calls
-                else Message.assistant_message(response.content)
+                else Message.assistant_message(content)
             )
             self.memory.add_message(assistant_msg)
 
@@ -113,7 +115,7 @@ class ToolCallAgent(ReActAgent):
 
             # For 'auto' mode, continue with content if no commands but content exists
             if self.tool_choices == ToolChoice.AUTO and not self.tool_calls:
-                return bool(response.content)
+                return bool(content)
 
             return bool(self.tool_calls)
         except Exception as e:
@@ -209,7 +211,7 @@ class ToolCallAgent(ReActAgent):
             return f"Error: {error_msg}"
         except Exception as e:
             error_msg = f"⚠️ Tool '{name}' encountered a problem: {str(e)}"
-            logger.error(error_msg)
+            logger.exception(error_msg)
             return f"Error: {error_msg}"
 
     async def _handle_special_tool(self, name: str, result: Any, **kwargs):

app/llm.py

@@ -10,6 +10,7 @@ from openai import (
     OpenAIError,
     RateLimitError,
 )
+from openai.types.chat.chat_completion_message import ChatCompletionMessage
 from tenacity import (
     retry,
     retry_if_exception_type,
@@ -421,9 +422,9 @@ class LLM:
 
             if not stream:
                 # Non-streaming request
-                params["stream"] = False
+                response = await self.client.chat.completions.create(
-
+                    **params, stream=False
-                response = await self.client.chat.completions.create(**params)
+                )
 
                 if not response.choices or not response.choices[0].message.content:
                     raise ValueError("Empty or invalid response from LLM")
@@ -438,8 +439,7 @@ class LLM:
             # Streaming request, For streaming, update estimated token count before making the request
             self.update_token_count(input_tokens)
 
-            params["stream"] = True
+            response = await self.client.chat.completions.create(**params, stream=True)
-            response = await self.client.chat.completions.create(**params)
 
             collected_messages = []
             completion_text = ""
@@ -466,11 +466,11 @@ class LLM:
         except TokenLimitExceeded:
             # Re-raise token limit errors without logging
             raise
-        except ValueError as ve:
+        except ValueError:
-            logger.error(f"Validation error: {ve}")
+            logger.exception(f"Validation error")
             raise
         except OpenAIError as oe:
-            logger.error(f"OpenAI API error: {oe}")
+            logger.exception(f"OpenAI API error")
             if isinstance(oe, AuthenticationError):
                 logger.error("Authentication failed. Check API key.")
             elif isinstance(oe, RateLimitError):
@@ -478,8 +478,8 @@ class LLM:
             elif isinstance(oe, APIError):
                 logger.error(f"API error: {oe}")
             raise
-        except Exception as e:
+        except Exception:
-            logger.error(f"Unexpected error in ask: {e}")
+            logger.exception(f"Unexpected error in ask")
             raise
 
     @retry(
@@ -654,7 +654,7 @@ class LLM:
         tool_choice: TOOL_CHOICE_TYPE = ToolChoice.AUTO,  # type: ignore
         temperature: Optional[float] = None,
         **kwargs,
-    ):
+    ) -> ChatCompletionMessage | None:
         """
         Ask LLM using functions/tools and return the response.
 
@@ -732,12 +732,15 @@ class LLM:
                     temperature if temperature is not None else self.temperature
                 )
 
-            response = await self.client.chat.completions.create(**params)
+            response: ChatCompletion = await self.client.chat.completions.create(
+                **params, stream=False
+            )
 
             # Check if response is valid
             if not response.choices or not response.choices[0].message:
                 print(response)
-                raise ValueError("Invalid or empty response from LLM")
+                # raise ValueError("Invalid or empty response from LLM")
+                return None
 
             # Update token counts
             self.update_token_count(

app/tool/browser_use_tool.py

@@ -1,4 +1,5 @@
 import asyncio
+import base64
 import json
 from typing import Generic, Optional, TypeVar
 
@@ -552,7 +553,16 @@ Page content:
                 viewport_height = ctx.config.browser_window_size.get("height", 0)
 
             # Take a screenshot for the state
-            screenshot = await ctx.take_screenshot(full_page=True)
+            page = await ctx.get_current_page()
+
+            await page.bring_to_front()
+            await page.wait_for_load_state()
+
+            screenshot = await page.screenshot(
+                full_page=True, animations="disabled", type="jpeg", quality=100
+            )
+
+            screenshot = base64.b64encode(screenshot).decode("utf-8")
 
             # Build the state info with all required fields
             state_info = {

app/tool/file_operators.py

@@ -42,17 +42,19 @@ class FileOperator(Protocol):
 class LocalFileOperator(FileOperator):
     """File operations implementation for local filesystem."""
 
+    encoding: str = "utf-8"
+
     async def read_file(self, path: PathLike) -> str:
         """Read content from a local file."""
         try:
-            return Path(path).read_text()
+            return Path(path).read_text(encoding=self.encoding)
         except Exception as e:
             raise ToolError(f"Failed to read {path}: {str(e)}") from None
 
     async def write_file(self, path: PathLike, content: str) -> None:
         """Write content to a local file."""
         try:
-            Path(path).write_text(content)
+            Path(path).write_text(content, encoding=self.encoding)
         except Exception as e:
             raise ToolError(f"Failed to write to {path}: {str(e)}") from None