fix(agent): resolve math agent error by fixing streaming response handling and server URL

attached_assets/Pasted--Math-Agent-System-Initialized-Available-operations-2025-04-20-11-05-16-WARNING-swarms-stru-1745147277404.txt

@@ -0,0 +1,47 @@
+
+Math Agent System Initialized
+
+Available operations:2025-04-20 11:05:16 | WARNING  | swarms.structs.agent:llm_handling:646 - Model name is not provided, using gpt-4o-mini. You can configure any model from litellm if desired.
+
+Math Agent: add, multiply, divide
+
+Enter your query (or 'exit' to quit): add 2 and 4
+╭─────────────────────────────────────────────────────── Agent Name: Math Agent [Max Loops: 1] ───────────────────────────────────────────────────────╮
+│ Math Agent: <litellm.litellm_core_utils.streaming_handler.CustomStreamWrapper object at 0x7fb9d6ddcdf0>                                             │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+2025-04-20 11:05:28 | ERROR    | swarms.structs.agent:mcp_execution_flow:2807 - MCP flow failed: Expecting value: line 1 column 1 (char 0)
+╭─────────────────────────────────────────────── Agent Name: Math Agent - Tool Executor [Max Loops: 1] ───────────────────────────────────────────────╮
+│ Math Agent - Tool Executor: [MCP-error] Expecting value: line 1 column 1 (char 0)                                                                   │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+╭────────────────────────────────────────────── Agent Name: Math Agent - Agent Analysis [Max Loops: 1] ───────────────────────────────────────────────╮
+│ Math Agent - Agent Analysis: <litellm.litellm_core_utils.streaming_handler.CustomStreamWrapper object at 0x7fb9d6e14d30>                            │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+
+Math Agent Response: System: : Your Name: Math Agent 
+
+ Your Description: Specialized agent for mathematical computations 
+
+ You are a specialized math agent that can perform calculations by calling external math service APIs.
+Key responsibilities:
+1. Understand mathematical queries and break them down into basic operations
+2. Use available math tools (add, multiply, divide) appropriately
+3. Provide clear explanations of calculations
+4. Handle errors gracefully if operations fail
+
+Remember to use the available MCP tools for calculations rather than doing them directly.
+
+
+Human:: add 2 and 4
+
+
+Math Agent: <litellm.litellm_core_utils.streaming_handler.CustomStreamWrapper object at 0x7fb9d6ddcdf0>
+
+
+Tool Executor: [MCP-error] Expecting value: line 1 column 1 (char 0)
+
+
+Math Agent: <litellm.litellm_core_utils.streaming_handler.CustomStreamWrapper object at 0x7fb9d6e14d30>
+
+
+
+Enter your query (or 'exit' to quit): 

attached_assets/Pasted--What-happened-1-The-LLM-is-returning-a-streaming-wrapper-instead-of-text-Because--1745147257835.txt

@@ -0,0 +1,123 @@
+### What happened?
+
+1. **The LLM is returning a streaming wrapper instead of text**  
+   Because `streaming_on=True`, LiteLLM gives you a `CustomStreamWrapper` object.  
+   Your helper `parse_llm_output()` doesn’t know how to turn that object into a string, so the
+   agent stores the wrapper itself.
+
+2. **`mcp_execution_flow()` received an empty string**  
+   When the agent tried to forward the tool‑call to your Fast‑MCP server it called
+   `json.loads(<empty‑string>)`, which raised  
+   *“Expecting value: line 1 column 1 (char 0)”*.
+
+   That means the HTTP call to `http://0.0.0.0:8000/mcp` returned **no body** –
+   usually because the path is wrong or the server crashed.
+
+---
+
+### Fast MCP mock‑server: correct URL
+
+`FastMCP.run(transport="sse", port=8000)` serves SSE on  
+`http://<host>:8000/stream` **and** accepts JSON‑RPC over POST on the root
+`http://<host>:8000/`.
+
+So point the client at the root (no `/mcp` suffix):
+
+```python
+math_server = MCPServerSseParams(
+    url="http://0.0.0.0:8000",         # <── just the origin
+    headers={"Content-Type": "application/json"},
+    timeout=5.0,
+    sse_read_timeout=30.0,
+)
+```
+
+---
+
+### Stop streaming while you debug
+
+```python
+math_agent = Agent(
+    agent_name="Math Agent",
+    agent_description="Specialized agent for mathematical computations",
+    system_prompt=MATH_AGENT_PROMPT,
+    max_loops=1,
+    mcp_servers=[math_server],
+    streaming_on=False,          #  <── turn off for now
+)
+```
+
+(You can turn it back on when everything works and you extend
+`parse_llm_output()` to unwrap streams.)
+
+---
+
+### Make sure the LLM actually *produces* a tool call
+
+LLMs won’t invent a JSON‑RPC envelope unless you ask them.
+Add a very small system hint that mirrors the MCP schema, e.g.
+
+```python
+TOOL_CALL_INSTRUCTION = """
+When you want to use a math tool, reply with a JSON object only:
+
+{"tool_name": "<add|multiply|divide>", "a": <int>, "b": <int>}
+"""
+
+math_agent.short_memory.add(role="system", content=TOOL_CALL_INSTRUCTION)
+```
+
+Now “**add 2 and 4**” should yield
+
+```json
+{"tool_name":"add","a":2,"b":4}
+```
+
+which your `mcp_execution_flow()` can forward.
+
+---
+
+### Fix the empty‑body crash guard (optional)
+
+Inside `mcp_execution_flow()` (or `mcp_flow`) you can protect yourself:
+
+```python
+resp = client.post(...)
+if not resp.text:
+    raise RuntimeError("MCP server returned empty body")
+```
+
+That turns an unhelpful JSON decode error into a clear MCP‑connection error.
+
+---
+
+### Quick test commands
+
+```bash
+# 1. Start mock server in one shell
+python mock_math_server.py      # “Starting Mock Math Server on port 8000…”
+
+# 2. In another shell, make sure it answers
+curl -X POST http://0.0.0.0:8000 \
+     -H "Content-Type: application/json" \
+     -d '{"tool_name":"add","a":2,"b":4}'
+# → {"result":6}
+
+# 3. Run your client
+python mcp_client.py
+```
+
+If you now type `add 2 and 4`, the agent should respond **6** (with your
+explanation string) instead of the stream‑object dump.
+
+---
+
+#### Next steps
+
+* Re‑enable `streaming_on=True` and add handling of LiteLLM’s stream wrapper in
+  `parse_llm_output()`.
+* Return the math result to the user in natural language (e.g. “2 + 4 = 6”).
+* Add error handling in the mock server (e.g. divide‑by‑zero already covered).
+
+That should give you a clean smoke‑test of **Fast MCP + Swarms Agent** without
+the function‑calling “craziness”.