add locally mermaid validation

Author: anhnh2002

README.md

@@ -1,102 +1,15 @@
+install Node
+```bash
+# macos
+brew install node
+
+# linux
+sudo apt update && apt install -y nodejs npm
+```
+
 ```bash
 python3.12 -m venv .venv
 source .venv/bin/activate
 pip install -r requirements.txt
 python run_web_app.py
 ```
-
-Check networking for Mermaid validator
-```python
-import mermaid as md
-
-error_mermaid = """
-graph TB
-    subgraph "Core Agent System"
-        A[DefaultAgent] --> B[Agent Execution]
-        B --> C[Step Processing]
-        C --> D[Action Execution]
-    end
-    
-    subgraph "Hook System"
-        E[CombinedAgentHook] --> F[Hook 1]
-        E --> G[Hook 2]
-        E --> H[Hook N]
-    end
-    
-    subgraph "Event Flow"
-        I[on_init] --> J[on_run_start]
-        J --> K[on_step_start]
-        K --> L[on_actions_generated]
-        L --> M[on_action_started]
-        M --> N[on_action_executed]
-        N --> O[on_step_done]
-        O --> P{More Steps?}
-        P -->|Yes| K
-        P -->|No| Q[on_run_done]
-    end
-    
-    A -.-> E : uses hooks
-    B -.-> I
-    C -.-> K
-    D -.-> M
-    
-    style E fill:#e1f5fe
-    style A fill:#f3e5f5
-"""
-
-true_mermaid = """
-graph TB
-    subgraph "CLI Configuration Module"
-        A[Main CLI Entry Point<br/>sweagent.run.run.main] --> B[Command Router]
-        C[BasicCLI Configuration System<br/>sweagent.run.common.BasicCLI] --> D[Config Validation]
-        
-        B --> E[Execution Commands]
-        B --> F[Analysis Commands]
-        B --> G[Inspector Commands]
-        
-        E --> H[Single Execution<br/>run]
-        E --> I[Batch Execution<br/>run-batch]
-        E --> J[Replay Execution<br/>run-replay]
-        E --> K[Shell Execution<br/>shell]
-        
-        F --> L[Merge Predictions<br/>merge-preds]
-        F --> M[Extract Predictions<br/>extract-pred]
-        F --> N[Compare Runs<br/>compare-runs]
-        F --> O[Quick Stats<br/>quick-stats]
-        F --> P[Remove Unfinished<br/>remove-unfinished]
-        
-        G --> Q[Terminal Inspector<br/>inspect]
-        G --> R[Web Inspector<br/>inspector]
-    end
-    
-    subgraph "External Dependencies"
-        S[execution_engines.md]
-        T[inspector_tools.md]
-        U[analysis_utilities.md]
-    end
-    
-    H --> S
-    I --> S
-    J --> S
-    K --> S
-    Q --> T
-    R --> T
-    L --> U
-    M --> U
-    N --> U
-    O --> U
-    P --> U
-    
-    style A fill:#e1f5fe
-    style C fill:#e8f5e8
-    style B fill:#fff3e0
-"""
-
-render = md.Mermaid(error_mermaid)
-print(render.svg_response.text[:50])
-# => Parse error on line 26:\n...  end    A -.-> E : use
-
-render = md.Mermaid(true_mermaid)
-print(render.svg_response.text[:50])
-# => <svg id="mermaid-svg" width="100%" xmlns="http://w
-```

requirements.txt

@@ -1,18 +1,21 @@
 ag-ui-protocol==0.1.8
+aiodns==3.5.0
 aiohappyeyeballs==2.6.1
 aiohttp==3.12.15
 aiosignal==1.4.0
 annotated-types==0.7.0
-anthropic==0.60.0
+anthropic==0.67.0
 anyio==4.10.0
 appnope==0.1.4
 argcomplete==3.6.2
 asttokens==3.0.0
 attrs==25.3.0
 boto3==1.40.2
 botocore==1.40.2
+Brotli==1.1.0
 cachetools==5.5.2
 certifi==2025.8.3
+cffi==2.0.0
 charset-normalizer==3.4.2
 click==8.2.1
 cohere==5.16.2
@@ -25,11 +28,15 @@ eval_type_backport==0.2.2
 executing==2.2.0
 fastapi==0.116.1
 fastavro==1.12.0
+fastuuid==0.12.0
 filelock==3.18.0
 frozenlist==1.7.0
 fsspec==2025.7.0
+genai-prices==0.0.27
+gitdb==4.0.12
+GitPython==3.1.40
 google-auth==2.40.3
-google-genai==1.28.0
+google-genai==1.36.0
 googleapis-common-protos==1.70.0
 griffe==1.9.0
 groq==0.30.0
@@ -41,6 +48,7 @@ httpx-sse==0.4.0
 huggingface-hub==0.34.3
 idna==3.10
 importlib_metadata==8.7.0
+invoke==2.2.0
 ipykernel==6.30.1
 ipython==9.4.0
 ipython_pygments_lexers==1.1.1
@@ -52,29 +60,39 @@ jsonschema==4.25.0
 jsonschema-specifications==2025.4.1
 jupyter_client==8.6.3
 jupyter_core==5.8.1
+litellm==1.77.0
 logfire==4.1.0
 logfire-api==4.1.0
+loguru==0.7.3
 markdown-it-py==3.0.0
 MarkupSafe==3.0.2
 matplotlib-inline==0.1.7
 mcp==1.12.3
 mdurl==0.1.2
+mermaid-parser-py==0.0.2
 mermaid-py==0.8.0
-mistralai==1.9.3
+mistralai==1.9.10
 multidict==6.6.3
 nest-asyncio==1.6.0
-openai==1.98.0
+networkx==3.5
+nexus-rpc==1.1.0
+openai==1.107.1
+openai-agents==0.3.0
 opentelemetry-api==1.36.0
 opentelemetry-exporter-otlp-proto-common==1.36.0
 opentelemetry-exporter-otlp-proto-http==1.36.0
 opentelemetry-instrumentation==0.57b0
+opentelemetry-instrumentation-httpx==0.57b0
 opentelemetry-proto==1.36.0
 opentelemetry-sdk==1.36.0
 opentelemetry-semantic-conventions==0.57b0
+opentelemetry-util-http==0.57b0
 packaging==25.0
 parso==0.8.4
+pathspec==0.12.1
 pexpect==4.9.0
 platformdirs==4.3.8
+pminit==1.2.0
 prompt_toolkit==3.0.51
 propcache==0.3.2
 protobuf==6.31.1
@@ -83,17 +101,22 @@ ptyprocess==0.7.0
 pure_eval==0.2.3
 pyasn1==0.6.1
 pyasn1_modules==0.4.2
+pycares==4.11.0
+pycparser==2.23
 pydantic==2.11.7
-pydantic-ai==0.5.0
+pydantic-ai==1.0.5
 pydantic-ai-slim==0.5.0
-pydantic-evals==0.5.0
-pydantic-graph==0.5.0
+pydantic-evals==1.0.5
+pydantic-graph==1.0.5
 pydantic-settings==2.10.1
 pydantic_core==2.33.2
 Pygments==2.19.2
+pyperclip==1.9.0
 python-dateutil==2.9.0.post0
 python-dotenv==1.1.1
 python-multipart==0.0.20
+pythonmonkey==1.2.0
+pytz==2025.2
 PyYAML==6.0.2
 pyzmq==27.0.1
 referencing==0.36.2
@@ -104,26 +127,18 @@ rpds-py==0.26.0
 rsa==4.9.1
 s3transfer==0.13.1
 six==1.17.0
+smmap==5.0.2
 sniffio==1.3.1
 sse-starlette==3.0.2
 stack-data==0.6.3
 starlette==0.47.2
+temporalio==1.17.0
 tenacity==8.5.0
 tiktoken==0.10.0
 tokenizers==0.21.4
 tornado==6.5.1
 tqdm==4.67.1
 traitlets==5.14.3
-types-requests==2.32.4.20250611
-typing-inspection==0.4.1
-typing_extensions==4.14.1
-urllib3==2.5.0
-uvicorn==0.35.0
-wcwidth==0.2.13
-websockets==15.0.1
-wrapt==1.17.2
-yarl==1.20.1
-zipp==3.23.0
 tree-sitter==0.23.2
 tree-sitter-c==0.21.4
 tree-sitter-c-sharp==0.23.1
@@ -135,6 +150,14 @@ tree-sitter-language-pack==0.8.0
 tree-sitter-python==0.23.6
 tree-sitter-typescript==0.21.2
 tree-sitter-yaml==0.7.1
-pathspec==0.12.1
-python-multipart
-gitpython==3.1.40
+types-protobuf==6.30.2.20250822
+types-requests==2.32.4.20250611
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+urllib3==2.5.0
+uvicorn==0.35.0
+wcwidth==0.2.13
+websockets==15.0.1
+wrapt==1.17.2
+yarl==1.20.1
+zipp==3.23.0

src/agent_tools/str_replace_editor.py

@@ -15,7 +15,14 @@
 from typing import List, Optional, Tuple, Literal
 import io
 
+import logging
+
+# Configure logging and monitoring
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
 from pydantic_ai import RunContext, Tool
+
 from .deps import CodeWikiDeps
 from utils import validate_mermaid_diagrams
 
@@ -755,7 +762,8 @@ async def str_replace_editor(
     result = "\n".join(tool.logs)
 
     if command != "view" and path.endswith(".md"):
-        result = result + "\n---------- Mermaid validation ----------\n" + validate_mermaid_diagrams(absolute_path, path)
+        mermaid_validation = await validate_mermaid_diagrams(absolute_path, path)
+        result = result + "\n---------- Mermaid validation ----------\n" + mermaid_validation
 
     return result
 

src/cluster_modules.py

@@ -12,9 +12,19 @@ def format_potential_core_components(leaf_nodes: List[str], components: Dict[str
     """
     Format the potential core components into a string that can be used in the prompt.
     """
+    # Filter out any invalid leaf nodes that don't exist in components
+    valid_leaf_nodes = []
+    for leaf_node in leaf_nodes:
+        if leaf_node in components:
+            valid_leaf_nodes.append(leaf_node)
+        else:
+            import logging
+            logger = logging.getLogger(__name__)
+            logger.warning(f"Skipping invalid leaf node '{leaf_node}' - not found in components")
+    
     #group leaf nodes by file
     leaf_nodes_by_file = defaultdict(list)
-    for leaf_node in leaf_nodes:
+    for leaf_node in valid_leaf_nodes:
         leaf_nodes_by_file[components[leaf_node].relative_path].append(leaf_node)
 
     potential_core_components = ""
@@ -49,7 +59,27 @@ def cluster_modules(
     response = call_llm(prompt, model=MAIN_MODEL)
 
     #parse the response
-    module_tree = eval(response.split("<GROUPED_COMPONENTS>")[1].split("</GROUPED_COMPONENTS>")[0])
+    try:
+        if "<GROUPED_COMPONENTS>" not in response or "</GROUPED_COMPONENTS>" not in response:
+            import logging
+            logger = logging.getLogger(__name__)
+            logger.error(f"Invalid LLM response format - missing component tags: {response[:200]}...")
+            return {}
+        
+        response_content = response.split("<GROUPED_COMPONENTS>")[1].split("</GROUPED_COMPONENTS>")[0]
+        module_tree = eval(response_content)
+        
+        if not isinstance(module_tree, dict):
+            import logging
+            logger = logging.getLogger(__name__)
+            logger.error(f"Invalid module tree format - expected dict, got {type(module_tree)}")
+            return {}
+            
+    except Exception as e:
+        import logging
+        logger = logging.getLogger(__name__)
+        logger.error(f"Failed to parse LLM response: {e}. Response: {response[:200]}...")
+        return {}
 
     # check if the module tree is valid
     if len(module_tree) <= 1:
@@ -66,10 +96,21 @@ def cluster_modules(
             value[module_name] = module_info
 
     for module_name, module_info in module_tree.items():
-        sub_leaf_nodes = module_info["components"]
+        sub_leaf_nodes = module_info.get("components", [])
+        
+        # Filter sub_leaf_nodes to ensure they exist in components
+        valid_sub_leaf_nodes = []
+        for node in sub_leaf_nodes:
+            if node in components:
+                valid_sub_leaf_nodes.append(node)
+            else:
+                import logging
+                logger = logging.getLogger(__name__)
+                logger.warning(f"Skipping invalid sub leaf node '{node}' in module '{module_name}' - not found in components")
+        
         current_module_path.append(module_name)
         module_info["children"] = {}
-        module_info["children"] = cluster_modules(sub_leaf_nodes, components, current_module_tree, module_name, current_module_path)
+        module_info["children"] = cluster_modules(valid_sub_leaf_nodes, components, current_module_tree, module_name, current_module_path)
         current_module_path.pop()
 
     return module_tree