Upgrade test functionality to maximize usefulness for AI agents

[Copilot]

This PR transforms the iOS MCP Code Quality Server into a powerful tool that enables AI agents like Copilot to iteratively help developers fix failing iOS tests with minimal human intervention. The implementation provides rich context, structured data, and actionable guidance optimized for AI parsing and decision-making.

Key Enhancements

🤖 AI-Optimized Response Structure

• Machine-readable metadata: Added _meta.structured containing all data AI agents need for automated processing
• Priority-based workflow: Clear hierarchy (build errors → critical → high → medium → low) guides AI agents on fix order
• Actionable suggestions: Each failure includes specific, contextual recommendations tailored to the error type

📊 Enhanced Test Failure Analysis

• Advanced categorization: Automatic classification into assertion, crash, timeout, build, setup, teardown failures
• Severity assessment: Critical, high, medium, low priority levels based on failure impact
• Rich failure context: Duration, platform info, attachments, and comprehensive error details

📝 Source Code Context Integration

• Automatic code extraction: Parses Swift test files to include relevant source code snippets
• Method-level context: Extracts complete test methods with line number highlighting
• Import analysis: Captures dependency information for better AI understanding

// Example of extracted context
→  25: XCTAssertTrue(result.success, "Invalid user should not be able to log in")
   26: XCTAssertNil(result.token, "Failed login should not return a token")

🎯 User-Friendly Output

• Visual indicators: Rich emoji-based formatting (🧪🔴🟠🟡📄📍💡) for instant recognition
• Hierarchical display: Priority-grouped failures with expandable source context
• Clear next steps: Specific guidance for both AI agents and human developers

✅ Comprehensive Testing

• 79 total tests (28 new) covering all enhanced functionality
• End-to-end integration tests validating complete AI agent workflows
• Edge case handling for malformed Swift code, missing files, and complex scenarios

AI Agent Benefits

This implementation enables AI agents to:

1. Parse structured failure data from standardized metadata format
2. Prioritize fixes efficiently using severity and category classifications
3. Access source context including test code, imports, and method details
4. Follow specific suggestions tailored to each failure type (assertion logic, network issues, etc.)
5. Track progress iteratively through comprehensive result metadata
6. Provide meaningful user feedback using rich, formatted output

Example Enhanced Output

Before:

Test failures:
- TestCase.testFeature: Assertion failed

After:

🧪 Test Failures Detected

🔴 CRITICAL Priority (1 failure)

1. **TestCase.testFeature**
   📄 File: /path/to/TestCase.swift
   📍 Line: 42
   💬 Error: XCTAssertTrue failed: Expected success but got failure
   🏷️ Category: assertion
   💡 Suggestions:
      • Review the assertion logic and expected vs actual values
      • Check if the test data setup is correct
   📝 Test Code:
   ```swift
   → 42: XCTAssertTrue(result.success, "Should succeed")

## Backward Compatibility

All existing functionality remains unchanged. The enhancements are additive and don't affect current MCP server behavior or API contracts.

Fixes #10.

<!-- START COPILOT CODING AGENT TIPS -->
---

✨ Let Copilot coding agent [set things up for you](https://github.com/a-25/ios-mcp-code-quality-server/issues/new?title=✨+Set+up+Copilot+instructions&body=Configure%20instructions%20for%20this%20repository%20as%20documented%20in%20%5BBest%20practices%20for%20Copilot%20coding%20agent%20in%20your%20repository%5D%28https://gh.io/copilot-coding-agent-tips%29%2E%0A%0A%3COnboard%20this%20repo%3E&assignees=copilot) — coding agent works faster and does higher quality work when set up for your repo.

[Copilot]

Pull Request Overview

This PR transforms the iOS MCP Code Quality Server into a powerful AI-optimized tool that enables agents like Copilot to iteratively fix failing iOS tests with minimal human intervention. The implementation provides structured metadata, enhanced failure analysis, and source code context integration for better AI decision-making.

Key changes include:

• AI-optimized structured response format with machine-readable metadata
• Enhanced test failure categorization with severity levels and actionable suggestions
• Source code context extraction from Swift test files with line-level highlighting

Reviewed Changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
src/core/testRunner.ts	Adds test failure categorization, severity assessment, suggestion generation, and source context integration
src/core/taskOrchestrator.ts	Introduces TaskErrorType enum for consistent error handling across the application
src/core/sourceCodeContext.ts	New module for extracting Swift source code context with import analysis and test method parsing
src/core/formatTestResultResponse.ts	Comprehensive overhaul to provide AI-friendly structured responses with rich formatting and metadata
src/tests/testRunner.test.ts	Updated tests to handle new structured response format and error type enums
src/tests/sourceCodeContext.test.ts	New test suite covering source code extraction functionality with edge case handling
src/tests/orchestrateTask.test.ts	Updated to use new TaskErrorType enum instead of local test error types
src/tests/lintFix.test.ts	Updated error handling to use TaskErrorType enum with proper type checking
src/tests/e2eAiIntegration.test.ts	New comprehensive end-to-end tests validating complete AI agent integration workflows
src/tests/aiEnhancements.test.ts	New test suite focused on AI enhancement features including structured responses and categorization

Comments suppressed due to low confidence (1)

src/core/testRunner.ts:1

• [nitpick] The multi-line ternary operator chain for priority assignment is difficult to read and maintain. Consider extracting this logic into a separate function like 'determinePriority(buildErrors, priorities, testFailures)' for better readability.

import { TestFixOptions } from "./taskOptions.js";

[Copilot]

[nitpick] The function name 'categorizeFailure' is ambiguous since it returns both category and severity. Consider renaming to 'analyzeFailure' or 'categorizeAndAssessSeverity' to better reflect its dual purpose.

Suggested change

	// Helper function to categorize test failures
	function categorizeFailure(failure: TestFailure): { category: TestFailureCategory; severity: TestFailureSeverity } {
	// Helper function to analyze test failures (categorize and assess severity)
	function analyzeFailure(failure: TestFailure): { category: TestFailureCategory; severity: TestFailureSeverity } {

[Copilot]

Same logical operator precedence issue as in the previous method. The condition should be clarified with proper parentheses to ensure the intended logic.

Suggested change

	if ((trimmed.includes('func test') || (trimmed.includes('func ') && trimmed.includes('test'))) &&
	!inMethod) {
	if ((trimmed.includes('func test') || (trimmed.includes('func ') && trimmed.includes('test'))) && !inMethod) {