fix: resolve CI linting and type errors

src/promptforge/testing/results.py

@@ -1,33 +1,139 @@
-from dataclasses import dataclass
-from typing import Dict, List, Optional
+"""Test results and formatting."""
+
+from dataclasses import dataclass, field
+from datetime import datetime
+from typing import Any, Dict, List, Optional
+
+from .ab_test import ABTestSummary
+from .metrics import MetricsSummary
 
 
 @dataclass
 class TestResult:
+    """Result of a single test."""
+
+    test_id: str
+    prompt_name: str
+    provider: str
     success: bool
     response: str
-    metrics: "TestMetrics"
-    error: Optional[str] = None
+    metrics: Dict[str, Any] = field(default_factory=dict)
+    validation_results: Dict[str, bool] = field(default_factory=dict)
+    error_message: Optional[str] = None
+    timestamp: datetime = field(default_factory=datetime.utcnow)
 
 
 @dataclass
-class ComparisonResult:
-    prompt_name: str
-    total_runs: int
-    successful_runs: int
-    failed_runs: int
-    avg_latency_ms: float
-    min_latency_ms: float
-    max_latency_ms: float
-    avg_tokens: float
-    avg_cost: float
-    success_rate: float
-    all_metrics: List["TestMetrics"]
+class TestSessionResults:
+    """Collection of test results."""
 
-
-@dataclass
-class TestReport:
     test_id: str
-    timestamp: str
-    results: Dict[str, ComparisonResult]
-    summary: Dict[str, float]
+    name: str
+    results: List[TestResult] = field(default_factory=list)
+    metrics: MetricsSummary = field(default_factory=lambda: MetricsSummary(name=""))
+    ab_comparisons: Dict[str, ABTestSummary] = field(default_factory=dict)
+    start_time: datetime = field(default_factory=datetime.utcnow)
+    end_time: Optional[datetime] = None
+
+    __test__ = False
+
+    @property
+    def duration_seconds(self) -> float:
+        """Get test duration in seconds."""
+        if self.end_time is None:
+            return 0.0
+        return (self.end_time - self.start_time).total_seconds()
+
+    @property
+    def success_count(self) -> int:
+        """Count of successful tests."""
+        return sum(1 for r in self.results if r.success)
+
+    @property
+    def failure_count(self) -> int:
+        """Count of failed tests."""
+        return sum(1 for r in self.results if not r.success)
+
+    @property
+    def pass_rate(self) -> float:
+        """Calculate pass rate."""
+        if not self.results:
+            return 0.0
+        return self.success_count / len(self.results)
+
+
+class ResultFormatter:
+    """Format test results for display."""
+
+    @staticmethod
+    def format_text(results: TestSessionResults) -> str:
+        """Format results as plain text."""
+        lines = [
+            f"Test Results: {results.name}",
+            f"Duration: {results.duration_seconds:.2f}s",
+            f"Passed: {results.success_count}/{len(results.results)} ({results.pass_rate:.1%})",
+            "",
+        ]
+
+        for result in results.results:
+            status = "PASS" if result.success else "FAIL"
+            lines.append(f"[{status}] {result.prompt_name}")
+            if result.error_message:
+                lines.append(f"  Error: {result.error_message}")
+            if result.metrics:
+                metrics_str = ", ".join(f"{k}: {v}" for k, v in result.metrics.items())
+                lines.append(f"  Metrics: {metrics_str}")
+
+        return "\n".join(lines)
+
+    @staticmethod
+    def format_json(results: TestSessionResults) -> str:
+        """Format results as JSON."""
+        import json
+        from datetime import datetime
+
+        def serialize(obj):
+            if isinstance(obj, datetime):
+                return obj.isoformat()
+            raise TypeError(f"Object of type {type(obj)} is not JSON serializable")
+
+        data = {
+            "test_id": results.test_id,
+            "name": results.name,
+            "duration_seconds": results.duration_seconds,
+            "summary": {
+                "total": len(results.results),
+                "passed": results.success_count,
+                "failed": results.failure_count,
+                "pass_rate": results.pass_rate,
+            },
+            "results": [
+                {
+                    "test_id": r.test_id,
+                    "prompt_name": r.prompt_name,
+                    "provider": r.provider,
+                    "success": r.success,
+                    "response": r.response[:500] if r.response else "",
+                    "metrics": r.metrics,
+                    "validation_results": r.validation_results,
+                    "error_message": r.error_message,
+                    "timestamp": r.timestamp.isoformat(),
+                }
+                for r in results.results
+            ],
+        }
+        return json.dumps(data, default=serialize, indent=2)
+
+    @staticmethod
+    def format_ab_comparison(comparisons: Dict[str, ABTestSummary]) -> str:
+        """Format A/B test comparisons."""
+        lines = ["A/B Test Comparison", "=" * 40]
+
+        for name, summary in comparisons.items():
+            lines.append(f"\nPrompt: {name}")
+            lines.append(f"  Runs: {summary.successful_runs}/{summary.total_runs}")
+            lines.append(f"  Avg Latency: {summary.avg_latency_ms:.2f}ms")
+            lines.append(f"  Avg Tokens: {summary.avg_tokens:.0f}")
+            lines.append(f"  Avg Cost: ${summary.avg_cost:.4f}")
+
+        return "\n".join(lines)