fix(math): resolve calculation error by fixing async handling in mcp_execution_flow

attached_assets/Pasted--Math-Agent-System-Initialized-Available-operations-Math-Agent-add-multiply-divide-2025-04-1745148921482.txt

@@ -0,0 +1,54 @@
+
+Math Agent System Initialized
+
+Available operations:
+Math Agent: add, multiply, divide
+2025-04-20 11:34:49 | WARNING  | swarms.structs.agent:llm_handling:647 - Model name is not provided, using gpt-4o-mini. You can configure any model from litellm if desired.
+
+Enter your query (or 'exit' to quit): AD D4 AND 5
+╭─────────────────────────────────────────────────────── Agent Name Math Agent [Max Loops: 1 ] ───────────────────────────────────────────────────────╮
+│ Math Agent: It seems like you want to add the numbers 4 and 5 together. I will use the addition tool to perform this calculation.                   │
+│                                                                                                                                                     │
+│ {"tool_name": "add", "a": 4, "b": 5}                                                                                                                │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+2025-04-20 11:34:55 | ERROR    | swarms.tools.mcp_integration:process_param:360 - Error processing parameter: {'url': 'http://0.0.0.0:8000', 'headers': {'Content-Type': 'application/json'}, 'timeout': 5.0, 'sse_read_timeout': 30.0}, error: __aenter__
+╭─────────────────────────────────────────────── Agent Name Math Agent - Tool Executor [Max Loops: 1 ] ───────────────────────────────────────────────╮
+│ Math Agent - Tool Executor: No result returned from MCP server                                                                                      │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+╭────────────────────────────────────────────── Agent Name Math Agent - Agent Analysis [Max Loops: 1 ] ───────────────────────────────────────────────╮
+│ Math Agent - Agent Analysis: It seems there was an issue with the MCP server not returning a result. Please provide me with a mathematical query or │
+│ operation you'd like to perform, and I'll attempt to process it again.                                                                              │
+╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+
+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.
+When you want to use a math tool, reply with a JSON object only:
+{"tool_name": "<add|multiply|divide>", "a": <int>, "b": <int>}
+
+
+Human:: AD D4 AND 5
+
+
+Math Agent: It seems like you want to add the numbers 4 and 5 together. I will use the addition tool to perform this calculation.
+
+{"tool_name": "add", "a": 4, "b": 5}
+
+
+Tool Executor: No result returned from MCP server
+
+
+Math Agent: It seems there was an issue with the MCP server not returning a result. Please provide me with a mathematical query or operation you'd like to perform, and I'll attempt to process it again.
+
+
+
+Enter your query (or 'exit' to quit): 

attached_assets/Pasted-You-ve-fixed-the-RuntimeWarning-by-wrapping-the-coroutine-but-now-the-call-never-actually-reaches-1745149021528.txt

@@ -0,0 +1,114 @@
+You’ve fixed the *RuntimeWarning* by wrapping the coroutine, but now the call never actually reaches the mock server.  
+Two things are still wrong:
+
+| symptom | real cause |
+|---------|------------|
+| **`__aenter__`** error from `process_param` | `MCPServerSse` *is* an async‑context‑manager; you must use **`async with`** (or call its `connect/cleanup` explicitly). |
+| **“No result returned from MCP server”** | we never awaited `call_tool`, so the request was never sent; the wrapper returned `None`. |
+
+Below is a minimal, fully‑working patch set.  
+Apply it and the *Math‑Mock‑Server* will answer correctly (e.g. `add 4 and 19834 → 19838`).
+
+---
+
+## 1 ▪ `tools/mcp_integration.py`
+
+```python
+# keep the import you already added
+import asyncio
+
+# ────────────────────────────────────────────────────────────
+# 1. async helper that really talks to one MCP server
+async def _call_one_server(param: MCPServerSseParams,
+                           payload: dict[str, any]) -> str:
+    async with MCPServerSse(param, cache_tools_list=True) as srv:
+        # ↓ fast‑mcp returns a pydantic model; make it json‑serialisable
+        res = await srv.call_tool(payload)
+        try:
+            return res.model_dump()            # fast‑mcp ≥0.2
+        except AttributeError:
+            return res                         # plain dict / str
+
+# 2. public sync wrapper – what the Agent imports & uses
+def batch_mcp_flow(params: list[MCPServerSseParams],
+                   payload: dict[str, any]) -> list[str]:
+    """Blocking helper – fan‑out to every MCP server given in *params*."""
+    return asyncio.run(_batch(params, payload))
+
+
+# 3. little async fan‑out
+async def _batch(params: list[MCPServerSseParams],
+                 payload: dict[str, any]) -> list[str]:
+    coros = [_call_one_server(p, payload) for p in params]
+    return await asyncio.gather(*coros)
+```
+
+---
+
+## 2 ▪ `structs/agent.py`
+
+Replace **only** the `mcp_execution_flow` method with the synchronous
+wrapper that now returns the real value (note: `payload` is a *string* here):
+
+```python
+    # inside class Agent
+    def mcp_execution_flow(self, response: str) -> str:
+        """
+        Forward the JSON tool‑call coming from the LLM to all MCP servers
+        listed in self.mcp_servers.
+        """
+        try:
+            payload = json.loads(response)          # {"tool_name": …}
+            results = batch_mcp_flow(self.mcp_servers, payload)
+            # `batch_mcp_flow` already blocks, so results is a list[str]
+            return any_to_str(results[0] if len(results) == 1 else results)
+        except Exception as err:
+            logger.error(f"MCP flow failed: {err}")
+            return f"[MCP-error] {err}"
+```
+
+*(you may keep the rest of your big `Agent` class unchanged)*
+
+---
+
+## 3 ▪ client‑side tiny polish
+
+When you start the mock server you exposed SSE at `http://0.0.0.0:8000`.
+That’s fine – the fast‑mcp helper discovers the SSE endpoint automatically,
+so the URL in `MCPServerSseParams` is correct.
+
+---
+
+## 4 ▪ Quick smoke‑test
+
+1. **Start the mock server** (in one shell):
+
+   ```bash
+   python math_mock_server.py       # prints “Starting Mock Math Server…”
+   ```
+
+2. **Run the client** (your `mcp_client.py`) in another shell:
+
+   ```
+   Enter your query (or 'exit' to quit): add 4 and 19834
+   Math Agent Response: 19838
+   ```
+
+No warning, no `[MCP‑error]`, and you get the right answer.
+
+---
+
+### Why this works
+
+* `async with MCPServerSse(...) as srv:` guarantees `connect()` and `cleanup()` are
+  called and awaited.
+* `await srv.call_tool(payload)` actually sends the JSON‑RPC request.
+* `asyncio.run()` in the wrapper lets the rest of your Agent stay 100 % synchronous.
+* Any exception bubbles up, gets logged, and your Agent sees
+  `[MCP‑error] …` instead of mysterious `None`.
+
+You can now add more servers to `self.mcp_servers` – they’ll all be invoked in
+parallel, and the first element of the returned list will always hold the
+result from the first server (adapt as needed).
+
+Happy calculating!