fix: Correct Gemini model name to 2.5 Flash

README.md

@@ -7,7 +7,7 @@ sdk: docker
 app_port: 7860
 pinned: true
 license: agpl-3.0
-short_description: MCP server for agent evaluation with Gemini 2.5 Pro
+short_description: MCP server for agent evaluation with Gemini 2.5 Flash
 tags:
   - building-mcp-track-enterprise
   - mcp
@@ -76,7 +76,7 @@ This MCP server is part of a complete agent evaluation ecosystem built on two fo
 2. **debug prompts**: Templates for debugging scenarios
 3. **optimization prompts**: Templates for optimization goals
 
-All analysis is powered by **Google Gemini 2.5 Pro** for intelligent, context-aware insights.
+All analysis is powered by **Google Gemini 2.5 Flash** for intelligent, context-aware insights.
 
 ## 🔗 Quick Links
 
@@ -115,7 +115,7 @@ All analysis is powered by **Google Gemini 2.5 Pro** for intelligent, context-aw
 - ✅ **Production-Ready**: Deployable to HuggingFace Spaces with SSE transport
 - ✅ **Testing Interface**: Beautiful Gradio UI for testing all components
 - ✅ **Enterprise Focus**: Cost optimization, debugging, decision support, and custom dataset generation
-- ✅ **Google Gemini Powered**: Leverages Gemini 2.5 Pro for intelligent analysis
+- ✅ **Google Gemini Powered**: Leverages Gemini 2.5 Flash for intelligent analysis
 - ✅ **17 Total Components**: 11 Tools + 3 Resources + 3 Prompts
 
 ### 🛠️ Eleven Production-Ready Tools
@@ -254,7 +254,7 @@ Loads SMOLTRACE datasets from HuggingFace and returns raw data as JSON:
 
 #### 8. generate_synthetic_dataset
 
-Generates domain-specific synthetic test datasets for SMOLTRACE evaluations using Google Gemini 2.5 Pro:
+Generates domain-specific synthetic test datasets for SMOLTRACE evaluations using Google Gemini 2.5 Flash:
 - AI-powered task generation tailored to your domain
 - Custom tool specifications
 - Configurable difficulty distribution (balanced, easy_only, medium_only, hard_only, progressive)
@@ -561,7 +561,7 @@ A: The MCP endpoint is publicly accessible. However, the tools may require Huggi
 ### Available MCP Components
 
 **Tools** (9):
-1. **analyze_leaderboard**: AI-powered leaderboard analysis with Gemini 2.5 Pro
+1. **analyze_leaderboard**: AI-powered leaderboard analysis with Gemini 2.5 Flash
 2. **debug_trace**: Trace debugging with AI insights
 3. **estimate_cost**: Cost estimation with optimization recommendations
 4. **compare_runs**: Compare two evaluation runs with AI-powered analysis
@@ -588,7 +588,7 @@ See full API documentation in the Gradio interface under "📖 API Documentation
 ```
 TraceMind-mcp-server/
 ├── app.py                      # Gradio UI + MCP server (mcp_server=True)
-├── gemini_client.py            # Google Gemini 2.5 Pro integration
+├── gemini_client.py            # Google Gemini 2.5 Flash integration
 ├── mcp_tools.py                # 7 tool implementations
 ├── requirements.txt            # Python dependencies
 ├── .env.example                # Environment variable template
@@ -598,7 +598,7 @@ TraceMind-mcp-server/
 
 **Key Technologies**:
 - **Gradio 6 with MCP support**: `gradio[mcp]` provides native MCP server capabilities
-- **Google Gemini 2.5 Pro**: Latest AI model for intelligent analysis
+- **Google Gemini 2.5 Flash**: Latest AI model for intelligent analysis
 - **HuggingFace Datasets**: Data source for evaluations
 - **Streamable HTTP Transport**: Modern streaming protocol for MCP communication (recommended)
 - **SSE Transport**: Server-Sent Events for legacy MCP compatibility (deprecated)
@@ -699,7 +699,7 @@ Note: This requires actual trace data from an evaluation run. For testing purpos
 - Integrates with enterprise data infrastructure (HuggingFace datasets)
 
 **Technology Stack**
-- **AI Analysis**: Google Gemini 2.5 Pro for all intelligent insights
+- **AI Analysis**: Google Gemini 2.5 Flash for all intelligent insights
 - **MCP Framework**: Gradio 6 with native MCP support
 - **Data Source**: HuggingFace Datasets
 - **Transport**: Streamable HTTP (recommended) and SSE (deprecated)
@@ -727,7 +727,7 @@ Main Gradio application with:
 - API documentation
 
 ### gemini_client.py
-Google Gemini 2.5 Pro client that:
+Google Gemini 2.5 Flash client that:
 - Handles API authentication
 - Provides specialized analysis methods for different data types
 - Formats prompts for optimal results
@@ -842,7 +842,7 @@ gemini_client = GeminiClient(model_name="gemini-2.5-flash-latest")
 Special thanks to the sponsors of **MCP's 1st Birthday Hackathon** (November 14-30, 2025):
 
 - **🤗 HuggingFace** - Hosting platform and dataset infrastructure
-- **🧠 Google Gemini** - AI analysis powered by Gemini 2.5 Pro API
+- **🧠 Google Gemini** - AI analysis powered by Gemini 2.5 Flash API
 - **⚡ Modal** - Serverless infrastructure partner
 - **🏢 Anthropic** - MCP protocol creators
 - **🎨 Gradio** - Native MCP framework support
@@ -901,7 +901,7 @@ For issues or questions:
   - 3 data resources (leaderboard, trace, cost data)
   - 3 prompt templates (analysis, debug, optimization)
 - Gradio native MCP support with decorators (`@gr.mcp.*`)
-- Google Gemini 2.5 Pro integration for all AI analysis
+- Google Gemini 2.5 Flash integration for all AI analysis
 - Live HuggingFace dataset integration
 - **Performance Optimizations**:
   - get_top_performers: 90% token reduction vs full leaderboard

app.py

@@ -22,7 +22,7 @@ Architecture:
          → MCP Endpoint (Gradio SSE)
          → TraceMind MCP Server (this file)
          → Tools (mcp_tools.py)
-         → Google Gemini 2.5 Pro API
+         → Google Gemini 2.5 Flash API
 
 For Track 1: Building MCP Servers - Enterprise Category
 https://huggingface.co/MCP-1st-Birthday
@@ -139,7 +139,7 @@ def create_gradio_ui():
             #### 🤖 TraceMind MCP Server (This Project)
             **Track 1: Building MCP (Enterprise)**
             - Provides AI-powered MCP tools for analyzing evaluation data
-            - Uses Google Gemini 2.5 Pro for intelligent insights
+            - Uses Google Gemini 2.5 Flash for intelligent insights
             - 11 tools + 3 resources + 3 prompts
             - [HF Space](https://huggingface.co/spaces/MCP-1st-Birthday/TraceMind-mcp-server)
 
@@ -170,7 +170,7 @@ def create_gradio_ui():
 
             TraceMind MCP Server provides intelligent analysis tools for agent evaluation data through the Model Context Protocol (MCP).
 
-            **Powered by**: Google Gemini 2.5 Pro
+            **Powered by**: Google Gemini 2.5 Flash
 
             **🎬 [Quick Demo (5 min)](https://www.loom.com/share/d4d0003f06fa4327b46ba5c081bdf835)** | **📺 [Full Demo (20 min)](https://www.loom.com/share/de559bb0aef749559c79117b7f951250)**
 
@@ -265,7 +265,7 @@ def create_gradio_ui():
                     Analyze agent evaluation leaderboard and generate AI-powered insights.
 
                     This tool loads agent evaluation data from HuggingFace datasets and uses
-                    Google Gemini 2.5 Pro to provide intelligent analysis of top performers,
+                    Google Gemini 2.5 Flash to provide intelligent analysis of top performers,
                     trends, cost/performance trade-offs, and actionable recommendations.
 
                     Args:
@@ -327,7 +327,7 @@ def create_gradio_ui():
                     Debug a specific agent execution trace using OpenTelemetry data.
 
                     This tool analyzes OpenTelemetry trace data from agent executions and uses
-                    Google Gemini 2.5 Pro to answer specific questions about the execution flow,
+                    Google Gemini 2.5 Flash to answer specific questions about the execution flow,
                     identify bottlenecks, explain agent behavior, and provide debugging insights.
 
                     Args:
@@ -409,7 +409,7 @@ def create_gradio_ui():
                     Estimate the cost, duration, and CO2 emissions of running agent evaluations.
 
                     This tool predicts costs before running evaluations by calculating LLM API costs,
-                    HuggingFace Jobs compute costs, and CO2 emissions. Uses Google Gemini 2.5 Pro
+                    HuggingFace Jobs compute costs, and CO2 emissions. Uses Google Gemini 2.5 Flash
                     to provide detailed cost breakdown and optimization recommendations.
 
                     Args:
@@ -486,7 +486,7 @@ def create_gradio_ui():
                     Compare two evaluation runs and generate AI-powered comparative analysis.
 
                     This tool fetches data for two evaluation runs from the leaderboard and uses
-                    Google Gemini 2.5 Pro to provide intelligent comparison across multiple dimensions:
+                    Google Gemini 2.5 Flash to provide intelligent comparison across multiple dimensions:
                     success rate, cost efficiency, speed, environmental impact, and use case recommendations.
 
                     Args:
@@ -1683,7 +1683,7 @@ if __name__ == "__main__":
     logger.info("  ✓ 7 AI-Powered Tools (Leaderboard + Trace + Cost + Dataset)")
     logger.info("  ✓ 3 Real-Time Resources (leaderboard, trace, cost data)")
     logger.info("  ✓ 3 Prompt Templates (analysis, debug, optimization)")
-    logger.info("  ✓ Google Gemini 2.5 Pro - Intelligent Analysis")
+    logger.info("  ✓ Google Gemini 2.5 Flash - Intelligent Analysis")
     logger.info("  ✓ HuggingFace Dataset Integration")
     logger.info("  ✓ SMOLTRACE Format Support")
     logger.info("  ✓ Synthetic Dataset Generation")

gemini_client.py

@@ -1,7 +1,7 @@
 """
 Gemini Client for TraceMind MCP Server
 
-Handles all interactions with Google Gemini 2.5 Pro API
+Handles all interactions with Google Gemini 2.5 Flash API
 """
 
 import os

mcp_tools.py

@@ -27,7 +27,7 @@ docstrings, and type hints.
     debug_prompt - Standardized templates for debugging scenarios
     optimization_prompt - Standardized templates for optimization goals
 
-All AI analysis powered by Google Gemini 2.5 Pro.
+All AI analysis powered by Google Gemini 2.5 Flash.
 Track 1: Building MCP Servers - Enterprise Category
 """
 
@@ -61,7 +61,7 @@ async def analyze_leaderboard(
     DO NOT use the leaderboard:// resource for questions - use this tool instead!
     The resource only returns raw JSON data without any analysis.
 
-    This tool uses Google Gemini 2.5 Pro to provide intelligent analysis of
+    This tool uses Google Gemini 2.5 Flash to provide intelligent analysis of
     agent evaluation results, including top performers, trends, cost/performance
     trade-offs, and actionable recommendations.
 
@@ -166,7 +166,7 @@ async def debug_trace(
     DO NOT use the trace:// resource for questions - use this tool instead!
     The resource only returns raw OTEL JSON data without any analysis.
 
-    This tool uses Google Gemini 2.5 Pro to analyze OpenTelemetry trace data and
+    This tool uses Google Gemini 2.5 Flash to analyze OpenTelemetry trace data and
     provide intelligent debugging insights, step-by-step breakdowns, and answers
     to specific questions about execution flow.
 
@@ -267,7 +267,7 @@ async def estimate_cost(
     DO NOT use the cost:// resource for estimates - use this tool instead!
     The resource only returns raw pricing tables without calculations.
 
-    This tool uses Google Gemini 2.5 Pro to calculate LLM API costs, HuggingFace
+    This tool uses Google Gemini 2.5 Flash to calculate LLM API costs, HuggingFace
     Jobs compute costs, CO2 emissions, and provide intelligent cost breakdowns with
     optimization recommendations.
 
@@ -490,7 +490,7 @@ async def compare_runs(
     Compare two evaluation runs and generate AI-powered comparative analysis.
 
     This tool fetches data for two evaluation runs from the leaderboard and uses
-    Google Gemini 2.5 Pro to provide intelligent comparison across multiple dimensions:
+    Google Gemini 2.5 Flash to provide intelligent comparison across multiple dimensions:
     success rate, cost efficiency, speed, environmental impact, and use case recommendations.
 
     Args:
@@ -693,7 +693,7 @@ async def analyze_results(
     - Analyze which types of tasks work well vs poorly
 
     This tool analyzes individual test case results (not aggregate leaderboard data)
-    and uses Google Gemini 2.5 Pro to provide actionable optimization recommendations.
+    and uses Google Gemini 2.5 Flash to provide actionable optimization recommendations.
 
     Args:
         results_repo (str): HuggingFace dataset repository containing results (e.g., "username/smoltrace-results-gpt4-20251114")
@@ -1462,7 +1462,7 @@ async def generate_synthetic_dataset(
     """
     Generate domain-specific synthetic test datasets for SMOLTRACE evaluations using AI.
 
-    This tool uses Google Gemini 2.5 Pro to create realistic, domain-specific evaluation
+    This tool uses Google Gemini 2.5 Flash to create realistic, domain-specific evaluation
     tasks that follow the SMOLTRACE task dataset format. Perfect for creating custom
     benchmarks when standard datasets don't fit your use case.
 
@@ -2158,7 +2158,7 @@ Start your response with the YAML content immediately."""
                 "agent_type": agent_type,
                 "template_name": template_name,
                 "base_template_url": template_url,
-                "customization_method": "Google Gemini 2.5 Pro"
+                "customization_method": "Google Gemini 2.5 Flash"
             },
             "prompt_template": customized_template,
             "usage_instructions": f"""