agentic-blocks 0.1.7__py3-none-any.whl → 0.1.9__py3-none-any.whl

agentic_blocks/messages.py

@@ -205,6 +205,51 @@ class Messages:
 
         return False
 
+    def get_pending_tool_calls(self) -> List[Dict[str, Any]]:
+        """
+        Get pending tool calls that need execution, formatted for MCPClient.call_tool().
+
+        Returns:
+            List of dictionaries with 'tool_name', 'arguments', and 'tool_call_id' keys
+        """
+        pending_calls = []
+        
+        if not self.messages:
+            return pending_calls
+
+        last_message = self.messages[-1]
+
+        # Check if the last message is an assistant message with tool calls
+        if last_message.get("role") == "assistant" and "tool_calls" in last_message:
+            # Get tool call IDs that have responses
+            responded_tool_call_ids = set()
+            for msg in reversed(self.messages):
+                if msg.get("role") == "tool" and msg.get("tool_call_id"):
+                    responded_tool_call_ids.add(msg.get("tool_call_id"))
+
+            # Find tool calls that don't have responses
+            for tool_call in last_message["tool_calls"]:
+                tool_call_id = tool_call.get("id")
+                if tool_call_id not in responded_tool_call_ids:
+                    function_info = tool_call.get("function", {})
+                    tool_name = function_info.get("name")
+                    arguments_str = function_info.get("arguments", "{}")
+                    
+                    # Parse arguments JSON string to dict
+                    import json
+                    try:
+                        arguments = json.loads(arguments_str)
+                    except json.JSONDecodeError:
+                        arguments = {}
+                    
+                    pending_calls.append({
+                        "tool_name": tool_name,
+                        "arguments": arguments,
+                        "tool_call_id": tool_call_id
+                    })
+
+        return pending_calls
+
     def __str__(self) -> str:
         """Return messages in a simple, readable format."""
         if not self.messages:

{agentic_blocks-0.1.7.dist-info → agentic_blocks-0.1.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-blocks
-Version: 0.1.7
+Version: 0.1.9
 Summary: Simple building blocks for agentic AI systems with MCP client and conversation management
 Author-email: Magnus Bjelkenhed <bjelkenhed@gmail.com>
 License: MIT
@@ -23,6 +23,7 @@ Requires-Dist: mcp
 Requires-Dist: requests
 Requires-Dist: python-dotenv
 Requires-Dist: openai
+Requires-Dist: langchain-core
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Provides-Extra: dev
@@ -187,66 +188,119 @@ Or pass the API key directly:
 response = call_llm(messages, api_key="your_api_key_here")
 ```
 
-## Complete Example - Agent with MCP Tools and LLM
+## Complete Example - Tool Calling with Weather API
+
+This example demonstrates a complete workflow using function calling with an LLM. For a full interactive notebook version, see `notebooks/agentic_example.ipynb`.
 
 ```python
-from agentic_blocks import MCPClient, Messages, call_llm
-
-def simple_agent():
-    # Initialize MCP client and conversation
-    client = MCPClient("https://example.com/mcp/server/sse")
-    messages = Messages(
-        system_prompt="You are a helpful research assistant.",
-        add_date_and_time=True
-    )
-    
-    # Get available tools
-    tools = client.list_tools()
-    print(f"Connected to MCP server with {len(tools)} tools")
-    
-    # Simulate user query
-    user_query = "What's the latest news about AI?"
-    messages.add_user_message(user_query)
-    
-    # Agent decides to use a search tool
-    if tools:
-        search_tool = next((t for t in tools if "search" in t["function"]["name"]), None)
-        if search_tool:
-            # Add tool call to messages
-            tool_call = {
-                "id": "search_001",
-                "type": "function",
-                "function": {
-                    "name": search_tool["function"]["name"],
-                    "arguments": '{"query": "latest AI news"}'
-                }
+from agentic_blocks import call_llm, Messages
+
+# Define tools in OpenAI function calling format
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current weather information for a location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA"
+                    },
+                    "unit": {
+                        "type": "string", 
+                        "enum": ["celsius", "fahrenheit"],
+                        "description": "Temperature unit"
+                    }
+                },
+                "required": ["location"]
             }
-            messages.add_tool_call(tool_call)
-            
-            # Execute the tool
-            result = client.call_tool(
-                search_tool["function"]["name"], 
-                {"query": "latest AI news"}
-            )
-            
-            # Add tool response
-            if result["content"]:
-                response_text = result["content"][0]["text"]
-                messages.add_tool_response("search_001", response_text)
-            
-            # Use LLM to generate response based on search results
-            messages.add_user_message("Based on the search results, please summarize the key AI news.")
-            llm_response = call_llm(messages, temperature=0.7)
-            messages.add_assistant_message(llm_response)
-    
-    # Print conversation
-    print("\\nConversation:")
-    print(messages)
-    
-    return messages.get_messages()
+        }
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "calculate",
+            "description": "Perform a mathematical calculation",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "expression": {
+                        "type": "string",
+                        "description": "Mathematical expression to evaluate"
+                    }
+                },
+                "required": ["expression"]
+            }
+        }
+    }
+]
+
+# Create conversation with system and user prompts
+messages = Messages(
+    system_prompt="You are a helpful assistant with access to weather and calculation tools.",
+    user_prompt="What is the weather in Stockholm?"
+)
+
+# Call LLM with tools - it will decide which tools to call
+model = "gpt-4o-mini"  # or your preferred model
+response = call_llm(model=model, messages=messages, tools=tools)
+
+# Add the LLM's response (including any tool calls) to conversation
+messages.add_response_message(response)
 
-if __name__ == "__main__":
-    simple_agent()
+# Display the conversation so far
+for message in messages.get_messages():
+    print(message)
+
+# Check if there are pending tool calls that need execution
+print("Has pending tool calls:", messages.has_pending_tool_calls())
+
+# In a real implementation, you would:
+# 1. Execute the actual tool calls (get_weather, calculate, etc.)
+# 2. Add tool responses using messages.add_tool_response()
+# 3. Call the LLM again to get the final user-facing response
+```
+
+**Expected Output:**
+```
+{'role': 'system', 'content': 'You are a helpful assistant with access to weather and calculation tools.'}
+{'role': 'user', 'content': 'What is the weather in Stockholm?'}
+{'role': 'assistant', 'content': '', 'tool_calls': [{'id': 'call_abc123', 'type': 'function', 'function': {'name': 'get_weather', 'arguments': '{"location": "Stockholm, Sweden", "unit": "celsius"}'}}]}
+Has pending tool calls: True
+```
+
+**Key Features Demonstrated:**
+- **Messages management**: Clean conversation history with system/user prompts
+- **Tool calling**: LLM automatically decides to call the `get_weather` function
+- **Response handling**: `add_response_message()` handles both content and tool calls
+- **Pending detection**: `has_pending_tool_calls()` identifies when tools need execution
+
+**Next Steps:**
+After the LLM makes tool calls, you would implement the actual tool functions and continue the conversation:
+
+```python
+# Implement actual weather function
+def get_weather(location, unit="celsius"):
+    # Your weather API implementation here
+    return f"The weather in {location} is sunny, 22°{unit[0].upper()}"
+
+# Execute pending tool calls
+if messages.has_pending_tool_calls():
+    last_message = messages.get_messages()[-1]
+    for tool_call in last_message.get("tool_calls", []):
+        if tool_call["function"]["name"] == "get_weather":
+            import json
+            args = json.loads(tool_call["function"]["arguments"])
+            result = get_weather(**args)
+            messages.add_tool_response(tool_call["id"], result)
+    
+    # Get final response from LLM
+    final_response = call_llm(model=model, messages=messages)
+    messages.add_assistant_message(final_response)
+    print(f"Final response: {final_response}")
 ```
 
 ## Development Principles
@@ -284,6 +338,8 @@ Messages(system_prompt=None, user_prompt=None, add_date_and_time=False)
 - `add_user_message(content: str)`: Add user message
 - `add_assistant_message(content: str)`: Add assistant message
 - `add_tool_call(tool_call: Dict)`: Add tool call to assistant message
+- `add_tool_calls(tool_calls)`: Add multiple tool calls from ChatCompletionMessageFunctionToolCall objects
+- `add_response_message(message)`: Add ChatCompletionMessage response to conversation
 - `add_tool_response(call_id: str, content: str)`: Add tool response
 - `get_messages() -> List[Dict]`: Get all messages
 - `has_pending_tool_calls() -> bool`: Check for pending tool calls

agentic_blocks-0.1.9.dist-info/RECORD

@@ -0,0 +1,9 @@
+agentic_blocks/__init__.py,sha256=LJy2tzTwX9ZjPw8dqkXOWiude7ZDDIaBIvaLC8U4d_Y,435
+agentic_blocks/llm.py,sha256=CznQ5iNFz_nQsGqjSmtZbCz1YyL6ha1qvnaoFOwsJtk,4868
+agentic_blocks/mcp_client.py,sha256=15mIN_Qw0OVNJAvfgO3jVZS4-AU4TtvEQSFDlL9ruqA,9773
+agentic_blocks/messages.py,sha256=dxaR_-IiH8n7pZygFDiUt8n7mMOm--FRuN-xCQEuewo,11758
+agentic_blocks-0.1.9.dist-info/licenses/LICENSE,sha256=r4IcBaAjTv3-yfjXgDPuRD953Qci0Y0nQn5JfHwLyBY,1073
+agentic_blocks-0.1.9.dist-info/METADATA,sha256=RTvQSPxogrsYO0Scv0sxZp-0BsG3EKnovV38F-VhM0g,11943
+agentic_blocks-0.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+agentic_blocks-0.1.9.dist-info/top_level.txt,sha256=-1a4RAemqicXLU1rRzw4QHV3KlNeQDNxVs3m2gAT238,15
+agentic_blocks-0.1.9.dist-info/RECORD,,

agentic_blocks-0.1.7.dist-info/RECORD

@@ -1,9 +0,0 @@
-agentic_blocks/__init__.py,sha256=LJy2tzTwX9ZjPw8dqkXOWiude7ZDDIaBIvaLC8U4d_Y,435
-agentic_blocks/llm.py,sha256=CznQ5iNFz_nQsGqjSmtZbCz1YyL6ha1qvnaoFOwsJtk,4868
-agentic_blocks/mcp_client.py,sha256=15mIN_Qw0OVNJAvfgO3jVZS4-AU4TtvEQSFDlL9ruqA,9773
-agentic_blocks/messages.py,sha256=WhZDFYb9afvJH9YcieTvEbPdSOkRcclFkCSiMM-9YjY,9904
-agentic_blocks-0.1.7.dist-info/licenses/LICENSE,sha256=r4IcBaAjTv3-yfjXgDPuRD953Qci0Y0nQn5JfHwLyBY,1073
-agentic_blocks-0.1.7.dist-info/METADATA,sha256=wQIebdtAorFhdsiVKrLi-M_3C60S7qI1oZ9l2ivlLQs,9445
-agentic_blocks-0.1.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-agentic_blocks-0.1.7.dist-info/top_level.txt,sha256=-1a4RAemqicXLU1rRzw4QHV3KlNeQDNxVs3m2gAT238,15
-agentic_blocks-0.1.7.dist-info/RECORD,,