docs: Update README to reflect correct Gemini 1.5 Pro model

- Updated all references from Gemini 2.5 Pro to Gemini 1.5 Pro (002)
- Corrected context window size from 1M to 2M tokens
- Aligned documentation with actual model availability

This open source MCP server bridges the gap between Claude Code and Gemini,
enabling multi-model workflows for complex distributed system debugging.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: haasonsaas

README.md

@@ -4,24 +4,24 @@
 [![MCP Compatible](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://modelcontextprotocol.com)
 [![Node.js Version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen)](https://nodejs.org)
 
-An MCP server that pairs Claude Code with Google's Gemini AI for complementary code analysis. This server enables a multi-model workflow where Claude Code handles tight terminal integration and multi-file refactoring, while Gemini leverages its massive context window (1M tokens) and code execution capabilities for distributed system debugging and long-trace analysis.
+An MCP server that pairs Claude Code with Google's Gemini AI for complementary code analysis. This server enables a multi-model workflow where Claude Code handles tight terminal integration and multi-file refactoring, while Gemini leverages its massive context window (2M tokens) and code execution capabilities for distributed system debugging and long-trace analysis.
 
 ## Core Value
 
 Both Claude and Gemini can handle deep semantic reasoning and distributed system bugs. This server enables an intelligent routing strategy where:
 - **Claude Code** excels at local-context operations, incremental patches, and CLI-native workflows
-- **Gemini 2.5 Pro** shines with huge-context sweeps, synthetic test execution, and analyzing failures that span logs + traces + code
+- **Gemini 1.5 Pro** shines with huge-context sweeps, synthetic test execution, and analyzing failures that span logs + traces + code
 
 The "escalation" model treats LLMs like heterogeneous microservices - route to the one that's most capable for each sub-task.
 
 ## Features
 
-- **Gemini 2.5 Pro Preview**: Uses Google's latest Gemini 2.5 Pro Preview (05-06) model with enhanced reasoning capabilities
+- **Gemini 1.5 Pro**: Uses Google's Gemini 1.5 Pro (002) model with 2M token context window
 - **Execution Flow Tracing**: Understands data flow and state transformations, not just function calls
 - **Cross-System Impact Analysis**: Models how changes propagate across service boundaries
 - **Performance Modeling**: Identifies N+1 patterns, memory leaks, and algorithmic bottlenecks
 - **Hypothesis Testing**: Tests theories about code behavior with evidence-based validation
-- **Long Context Support**: Leverages Gemini 2.5's improved context handling for analyzing large codebases
+- **Long Context Support**: Leverages Gemini 1.5 Pro's massive 2M token context for analyzing large codebases
 
 ## Prerequisites
 
@@ -85,7 +85,7 @@ Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/
    - Running iterative hypothesis testing with code execution
    - Correlating failures across many microservices
 3. **Server prepares comprehensive context** including code, logs, and traces
-4. **Gemini analyzes with its 1M-token context** and visible "thinking" traces
+4. **Gemini analyzes with its 2M-token context** and visible "thinking" traces
 5. **Results returned to Claude Code** for implementation of fixes
 
 ## Available Tools
@@ -223,7 +223,7 @@ npm run typecheck
 ```
 ┌─────────────────┐     ┌──────────────────┐     ┌─────────────────┐
 │  Claude Code    │────▶│  MCP Server      │────▶│  Gemini API    │
-│  (Fast, Local, │     │  (Router &       │     │  (1M Context,   │
+│  (Fast, Local, │     │  (Router &       │     │  (2M Context,   │
 │   CLI-Native)  │◀────│   Orchestrator)  │◀────│   Code Exec)    │
 └─────────────────┘     └──────────────────┘     └─────────────────┘
                                │