Removed LLM call

app.py

@@ -1,9 +1,9 @@
 """
 app.py — Data Analyst Duo MCP (no OpenAI) Gradio Space
+Shows preview table, stats, corr, plus full JSON histories.
 """
 
 import os
-import json
 import uuid
 import logging
 import datetime
@@ -12,14 +12,14 @@ import pandas as pd
 import numpy as np
 import gradio as gr
 
-# ——— Logging setup —————————————————————————————————————
+# ——— Logging ——————————————————————————————————————————————
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s %(levelname)s:%(name)s: %(message)s"
 )
 logger = logging.getLogger("DataAnalystDuo")
 
-# ——— MCP Core —————————————————————————————————————
+# ——— MCP Core ——————————————————————————————————————————————
 class MCPMessage:
     def __init__(self, sender, message_type, content):
         self.id = str(uuid.uuid4())
@@ -86,19 +86,20 @@ class MCPAgent:
     def get_history(self):
         return self.history
 
-# ——— ComputeAgent —————————————————————————————————————
+# ——— ComputeAgent ——————————————————————————————————————————————
 class ComputeAgent(MCPAgent):
     def __init__(self):
         super().__init__("ComputeAgent", "Loads & computes data")
         self.df = None
-        self.register_tool(MCPTool("load_dataset", "Load CSV from URL", self._load))
-        self.register_tool(MCPTool("compute_statistics", "Descriptive stats", self._stats))
-        self.register_tool(MCPTool("compute_correlation", "Correlation matrix", self._corr))
+        self.register_tool(MCPTool("load_dataset", "Load CSV", self._load))
+        self.register_tool(MCPTool("compute_statistics", "Stats", self._stats))
+        self.register_tool(MCPTool("compute_correlation", "Corr", self._corr))
 
     def _load(self, params):
         url = params.get("url", "").strip()
-        if not url or url.lower() == "default":
-            url = "https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv"
+        if not url:
+            # default to diamonds dataset
+            url = "https://raw.githubusercontent.com/mwaskom/seaborn-data/master/diamonds.csv"
         try:
             self.df = pd.read_csv(url)
             return {
@@ -114,24 +115,16 @@ class ComputeAgent(MCPAgent):
     def _stats(self, params):
         if self.df is None:
             return {"status": "error", "message": "No data loaded"}
-        try:
-            cols = list(self.df.select_dtypes(include=[np.number]).columns)
-            stats = self.df[cols].describe().to_dict()
-            return {"status": "success", "statistics": stats}
-        except Exception as e:
-            logger.exception("Stats failed")
-            return {"status": "error", "message": str(e)}
+        cols = self.df.select_dtypes(include=[np.number]).columns
+        stats = self.df[cols].describe().to_dict()
+        return {"status": "success", "statistics": stats}
 
     def _corr(self, params):
         if self.df is None:
             return {"status": "error", "message": "No data loaded"}
-        try:
-            cols = list(self.df.select_dtypes(include=[np.number]).columns)
-            corr = self.df[cols].corr().to_dict()
-            return {"status": "success", "correlation_matrix": corr}
-        except Exception as e:
-            logger.exception("Corr failed")
-            return {"status": "error", "message": str(e)}
+        cols = self.df.select_dtypes(include=[np.number]).columns
+        corr = self.df[cols].corr().to_dict()
+        return {"status": "success", "correlation_matrix": corr}
 
     def handle_message(self, m):
         if m.message_type == "request_data_load":
@@ -144,35 +137,26 @@ class ComputeAgent(MCPAgent):
             res = self._corr(m.content)
             self.send_message(m.sender, "correlation_result", res)
 
-# ——— InterpretAgent (stubs) —————————————————————————————————
+# ——— InterpretAgent (stubs) ——————————————————————————————————————
 class InterpretAgent(MCPAgent):
     def __init__(self):
-        super().__init__("InterpretAgent", "Interprets & reports (no LLM)")
+        super().__init__("InterpretAgent", "Stubbed interp")
         self.data_info = None
         self.stats = None
         self.corr = None
         self.register_tool(MCPTool("interpret_statistics", "", self._int_stats))
         self.register_tool(MCPTool("interpret_correlation", "", self._int_corr))
-        self.register_tool(MCPTool("llm_interpret", "LLM stub", self._llm_interpret))
-        self.register_tool(MCPTool("llm_report", "LLM stub", self._llm_report))
+        self.register_tool(MCPTool("llm_interpret", "stub", self._llm_stub))
+        self.register_tool(MCPTool("llm_report", "stub", self._llm_stub))
 
     def _int_stats(self, params):
-        ins = []
-        for col, vals in self.stats.get("statistics", {}).items():
-            if "mean" in vals:
-                ins.append(f"{col} avg={vals['mean']:.2f}")
-            if "min" in vals and "max" in vals:
-                ins.append(f"{col} ∈ [{vals['min']:.2f},{vals['max']:.2f}]")
-        return {"status": "success", "insights": ins[:3], "summary": "Rule-based insights"}
+        return {"status": "skipped", "insights": []}
 
     def _int_corr(self, params):
-        return {"status": "success", "insights": ["Correlation computed"], "summary": "Rule-based corr"}
+        return {"status": "skipped", "insights": []}
 
-    def _llm_interpret(self, params):
-        return {"status": "skipped", "insights": [], "summary": "LLM removed"}
-
-    def _llm_report(self, params):
-        return {"status": "skipped", "report_md": ""}
+    def _llm_stub(self, params):
+        return {"status": "skipped"}
 
     def handle_message(self, m):
         if m.message_type == "data_load_result":
@@ -180,17 +164,14 @@ class InterpretAgent(MCPAgent):
             self.send_message(m.sender, "ack", {"status": "loaded"})
         elif m.message_type == "statistics_result":
             self.stats = m.content
-            llm_res = self._llm_interpret({})
-            self.send_message(m.sender, "llm_statistics_interpretation", llm_res)
+            self.send_message(m.sender, "llm_statistics_interpretation", {"status": "skipped"})
         elif m.message_type == "correlation_result":
             self.corr = m.content
-            llm_res = self._llm_interpret({})
-            self.send_message(m.sender, "llm_correlation_interpretation", llm_res)
+            self.send_message(m.sender, "llm_correlation_interpretation", {"status": "skipped"})
         elif m.message_type == "request_report":
-            llm_res = self._llm_report({})
-            self.send_message(m.sender, "report_result", llm_res)
+            self.send_message(m.sender, "report_result", {"status": "skipped"})
 
-# ——— Orchestration —————————————————————————————————————
+# ——— Orchestration ——————————————————————————————————————————
 class DataAnalystDuo:
     def __init__(self):
         self.C = ComputeAgent()
@@ -199,41 +180,53 @@ class DataAnalystDuo:
         self.I.connect(self.C)
 
     def run(self, url):
-        # 1) load data
+        # 1) load
         self.I.send_message("ComputeAgent", "request_data_load", {"url": url})
         self.C.process(); self.I.process()
         # 2) stats
         self.I.send_message("ComputeAgent", "request_statistics", {})
         self.C.process(); self.I.process()
-        # 3) correlation
+        # 3) corr
         self.I.send_message("ComputeAgent", "request_correlation", {})
         self.C.process(); self.I.process()
         # 4) report
-        self.C.send_message("InterpretAgent", "request_report", {"report_title": "Analysis Report"})
+        self.C.send_message("InterpretAgent", "request_report", {})
         self.I.process(); self.C.process()
-        # return two separate objects
-        return self.C.get_history(), self.I.get_history()
 
-# ——— Gradio app entrypoint —————————————————————————————————
+        hist_c = self.C.get_history()
+        hist_i = self.I.get_history()
+
+        # extract results
+        load = next(m["message"]["content"] for m in hist_c if m["message"]["message_type"]=="data_load_result")
+        stats = next(m["message"]["content"] for m in hist_c if m["message"]["message_type"]=="statistics_result")
+        corr = next(m["message"]["content"] for m in hist_c if m["message"]["message_type"]=="correlation_result")
+
+        # build preview DataFrame
+        preview_df = pd.DataFrame(load.get("preview", []))
+
+        return preview_df, stats, corr, hist_c, hist_i
+
+# ——— Gradio app —————————————————————————————————————————————
 def run_analysis(url: str):
-    compute_hist, interpret_hist = DataAnalystDuo().run(url)
-    return compute_hist, interpret_hist
+    return DataAnalystDuo().run(url)
 
 demo = gr.Interface(
     fn=run_analysis,
-    inputs=gr.Textbox(label="CSV URL", placeholder="https://..."),
+    inputs=[gr.Textbox(label="CSV URL", placeholder="https://...")],
     outputs=[
-        gr.JSON(label="Compute & Data-Load History"),
-        gr.JSON(label="Interpret & Report History"),
+        gr.Dataframe(label="Preview (first 5 rows)"),
+        gr.JSON(label="Statistics"),
+        gr.JSON(label="Correlation Matrix"),
+        gr.JSON(label="Compute History"),
+        gr.JSON(label="Interpret History"),
     ],
     title="Data Analyst Duo",
-    description="Load a CSV URL and see compute + interpretation steps"
+    description="Paste any CSV URL (e.g. diamonds.csv) to see data + stats + agent history"
 )
 
 if __name__ == "__main__":
-    port = int(os.environ.get("PORT", 7860))
     demo.launch(
         server_name="0.0.0.0",
-        server_port=port,
+        server_port=int(os.environ.get("PORT", 7860)),
         share=True
     )