[PATCH 13/23] rteval MCP: Add integration tests and remove hardcoded examples

Replace hardcoded example scripts with a proper integration test that
validates MCP server tools through the actual MCP interface.

Removed files (had hardcoded paths to deleted test data):
- test_server.py: Basic sanity check, too minimal
- test_comparison.py: Redundant with compare_results tool
- test_logs.py: Redundant with list_logs/read_log tools
- test_tools.py: Replaced by test_mcp_integration.py

Added file:
- tests/test_mcp_integration.py: End-to-end integration test
  - Tests 8 MCP tools through the MCP interface
  - Dynamically finds available rteval result directories
  - No hardcoded paths - works with any rteval data
  - Works from rteval/, rteval/mcp-server/, or rteval/mcp-server/tests/
  - Discovered bugs in filter_results, find_best_worst, compare_to_baseline

Test coverage:
- list_tools, list_results, parse_result, list_logs
- get_percentiles, extract_histogram (new histogram features)
- filter_results, find_best_worst (query/filter tools)

All tests pass after server.py glob pattern fixes.

Assisted-by: Claude:claude-sonnet-4-5
Signed-off-by: John Kacur <[email protected]>
---
 mcp-server/tests/test_mcp_integration.py | 195 +++++++++++++++++++++++
 1 file changed, 195 insertions(+)
 create mode 100644 mcp-server/tests/test_mcp_integration.py

diff --git a/mcp-server/tests/test_mcp_integration.py b/mcp-server/tests/test_mcp_integration.py
new file mode 100644
index 000000000000..30f7700786fa
--- /dev/null
+++ b/mcp-server/tests/test_mcp_integration.py
@@ -0,0 +1,195 @@
+#!/usr/bin/env python3
+"""Integration tests for rteval MCP server.
+
+Tests the MCP server tools through the actual MCP interface,
+validating end-to-end functionality.
+"""
+
+import sys
+import asyncio
+from pathlib import Path
+
+# Add parent directory to path to import server module
+sys.path.insert(0, str(Path(__file__).parent.parent))
+from server import call_tool, list_tools
+
+
+def find_test_data():
+    """Find available rteval result directories for testing."""
+    # From tests/ -> mcp-server/ -> rteval/
+    rteval_dir = Path(__file__).parent.parent.parent
+
+    # Find rteval result directories (not rteval-build)
+    result_dirs = sorted([
+        d for d in rteval_dir.glob("rteval-*/")
+        if d.is_dir() and d.name != "rteval-build" and (d / "summary.xml").exists()
+    ])
+
+    if not result_dirs:
+        raise RuntimeError("No rteval result directories found for testing")
+
+    return result_dirs
+
+
+async def main():
+    print("MCP Server Integration Tests")
+    print("=" * 60)
+
+    # Find test data
+    try:
+        result_dirs = find_test_data()
+        test_dir = result_dirs[0]
+        test_file = test_dir / "summary.xml"
+        rteval_parent = test_dir.parent
+
+        print(f"\nUsing test data: {test_dir.name}")
+        print(f"Total result directories available: {len(result_dirs)}")
+        print()
+    except RuntimeError as e:
+        print(f"✗ {e}")
+        sys.exit(1)
+
+    # Test 1: List available tools
+    print("1. Testing list_tools()...")
+    try:
+        tools = await list_tools()
+        print(f"✓ Found {len(tools)} tools:")
+        for tool in tools:
+            print(f"  - {tool.name}: {tool.description[:60]}...")
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 2: List results
+    print("\n2. Testing list_results...")
+    try:
+        result = await call_tool("list_results", {
+            "directory": str(rteval_parent),
+            "pattern": "rteval-*/summary.xml"
+        })
+        output = result[0].text
+        if "Found" in output and "file" in output:
+            lines = output.split('\n')[:5]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 3: Parse a result
+    print("\n3. Testing parse_result...")
+    try:
+        result = await call_tool("parse_result", {
+            "file_path": str(test_file)
+        })
+        output = result[0].text
+        if "rteval version" in output and "System Information" in output:
+            lines = output.split('\n')[:10]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 4: List logs
+    print("\n4. Testing list_logs...")
+    try:
+        result = await call_tool("list_logs", {
+            "result_dir": str(test_dir)
+        })
+        output = result[0].text
+        if "Log files" in output or "logs" in output.lower():
+            lines = output.split('\n')[:8]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 5: Get percentiles (new histogram feature)
+    print("\n5. Testing get_percentiles...")
+    try:
+        result = await call_tool("get_percentiles", {
+            "file_path": str(test_file),
+            "percentiles": [50, 95, 99, 99.9]
+        })
+        output = result[0].text
+        if "Percentiles" in output and "P50" in output:
+            lines = output.split('\n')[:12]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 6: Extract histogram (new feature)
+    print("\n6. Testing extract_histogram...")
+    try:
+        result = await call_tool("extract_histogram", {
+            "file_path": str(test_file),
+            "include_per_cpu": False  # Keep output brief
+        })
+        output = result[0].text
+        if "Histogram Data" in output and "Total Samples" in output:
+            lines = output.split('\n')[:12]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 7: Filter results (query tools)
+    print("\n7. Testing filter_results...")
+    try:
+        result = await call_tool("filter_results", {
+            "directory": str(rteval_parent),
+            "is_rt": False
+        })
+        output = result[0].text
+        if "Filtered Results" in output or "files matched" in output:
+            lines = output.split('\n')[:8]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    # Test 8: Find best/worst
+    print("\n8. Testing find_best_worst...")
+    try:
+        result = await call_tool("find_best_worst", {
+            "directory": str(rteval_parent),
+            "metric": "maximum",
+            "count": 3
+        })
+        output = result[0].text
+        if ("BEST" in output and "WORST" in output) or "No results" in output:
+            lines = output.split('\n')[:10]
+            print("✓ " + '\n  '.join(lines))
+        else:
+            print(f"✗ Unexpected output: {output[:200]}")
+            sys.exit(1)
+    except Exception as e:
+        print(f"✗ Failed: {e}")
+        sys.exit(1)
+
+    print("\n" + "=" * 60)
+    print("✓ All MCP server integration tests passed!")
+    print(f"\nTested with: {test_dir.name}")
+    print(f"Total tools tested: 8")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
-- 
2.55.0