Merge pull request #30 from codegen-sh/codegen-cg-18917-fix-build

Author: jayhack

.github/workflows/benchmark.yml

@@ -28,10 +28,14 @@ jobs:
       with:
         python-version: '3.12'
 
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+      with:
+        version: "latest"
+
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements.txt
+        uv sync --all-extras
 
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v3
@@ -43,13 +47,13 @@ jobs:
 
     - name: Run benchmarks
       run: |
-        python benchmarks/scripts/auto_publish.py --run-benchmark
+        uv run python benchmarks/scripts/auto_publish.py --run-benchmark
       env:
         DOCKER_HOST: unix:///var/run/docker.sock
 
     - name: Generate summary report
       run: |
-        python benchmarks/scripts/auto_publish.py --generate-summary
+        uv run python benchmarks/scripts/auto_publish.py --generate-summary
 
     - name: Commit and push results
       run: |
@@ -64,7 +68,7 @@ jobs:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
     - name: Upload benchmark artifacts
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       if: always()
       with:
         name: benchmark-results

benchmarks/analysis/comparator.py

@@ -23,7 +23,7 @@ def __init__(self, data_parser: BenchmarkDataParser):
         self.data_parser = data_parser
 
     def compare_providers(
-        self, provider1: str, provider2: str, time_range_days: str | Noneint] = None
+        self, provider1: str, provider2: str, time_range_days: int | None = None
     ) -> ComparisonResult:
         """Compare two providers across all available metrics"""
 
@@ -115,7 +115,7 @@ def compare_providers(
 
     def analyze_time_trends(
         self,
-        provider: str | Nonestr] = None,
+        provider: str | None = None,
         days: int = 30,
         metric: str = "success_rate",
     ) -> TrendAnalysis:
@@ -409,7 +409,7 @@ def _aggregate_provider_metrics_list(
 
     def _extract_metric_value(
         self, provider_metrics: ProviderMetrics, metric: str
-    ) -> str | Nonefloat]:
+    ) -> float | None:
         """Extract a specific metric value from provider metrics"""
         if metric == "success_rate":
             return provider_metrics.overall_success_rate

benchmarks/analysis/config.py

@@ -10,7 +10,7 @@
 class AnalysisConfig:
     """Configuration manager for benchmark analysis settings"""
 
-    def __init__(self, config_path: str | Nonestr | Path] = None):
+    def __init__(self, config_path: str | Path | None = None):
         if config_path is None:
             config_path = Path(__file__).parent.parent / "configs" / "analysis.json"
 
@@ -104,7 +104,7 @@ def set(self, key: str, value: Any) -> None:
         # Set the value
         config[keys[-1]] = value
 
-    def save(self, path: str | Nonestr | Path] = None) -> None:
+    def save(self, path: str | Path | None = None) -> None:
         """Save configuration to file"""
         save_path = Path(path) if path else self.config_path
         save_path.parent.mkdir(parents=True, exist_ok=True)

benchmarks/analysis/data_parser.py

@@ -48,7 +48,7 @@ def load_all_results(self) -> list[BenchmarkResult]:
         results.sort(key=lambda x: x.timestamp)
         return results
 
-    def load_json_result(self, file_path: Path) -> str | NoneBenchmarkResult]:
+    def load_json_result(self, file_path: Path) -> BenchmarkResult | None:
         """Load a benchmark result from a JSON file"""
         try:
             with open(file_path) as f:
@@ -59,7 +59,7 @@ def load_json_result(self, file_path: Path) -> str | NoneBenchmarkResult]:
             print(f"Error loading JSON file {file_path}: {e}")
             return None
 
-    def load_markdown_result(self, file_path: Path) -> str | NoneBenchmarkResult]:
+    def load_markdown_result(self, file_path: Path) -> BenchmarkResult | None:
         """Load a benchmark result from a Markdown file"""
         try:
             with open(file_path) as f:
@@ -279,7 +279,7 @@ def get_results_by_date_range(
             if start_date <= result.timestamp <= end_date
         ]
 
-    def get_latest_result(self) -> str | NoneBenchmarkResult]:
+    def get_latest_result(self) -> BenchmarkResult | None:
         """Get the most recent benchmark result"""
         all_results = self.load_all_results()
         return all_results[-1] if all_results else None

benchmarks/analysis/models.py

@@ -34,8 +34,8 @@ class ProviderMetrics:
     avg_execution_time: float
     total_scenarios: int
     scenarios: dict[str, ScenarioMetrics] = field(default_factory=dict)
-    benchmark_timestamp: str | Nonedatetime] = None
-    benchmark_duration: str | Nonefloat] = None
+    benchmark_timestamp: datetime | None = None
+    benchmark_duration: float | None = None
     status: str = "unknown"
 
 
@@ -48,17 +48,17 @@ class BenchmarkResult:
     providers_tested: list[str]
     test_scenarios: int
     provider_results: dict[str, ProviderMetrics] = field(default_factory=dict)
-    file_path: str | NonePath] = None
-    raw_data: str | Nonedict[str, Any]] = None
+    file_path: Path | None = None
+    raw_data: dict[str, Any] | None = None
 
 
 @dataclass
 class ComparisonResult:
     """Result of comparing benchmark data"""
 
     comparison_type: str  # "provider", "time_series", "regression"
-    baseline: str | str, datetime]  # Provider name or timestamp
-    target: str | str, datetime]
+    baseline: str | datetime  # Provider name or timestamp
+    target: str | datetime
     metrics_compared: list[str]
     improvements: dict[str, float] = field(default_factory=dict)
     regressions: dict[str, float] = field(default_factory=dict)
@@ -71,7 +71,7 @@ class TrendAnalysis:
     """Time-series trend analysis result"""
 
     metric_name: str
-    provider: str | Nonestr]
+    provider: str | None
     time_period: str
     trend_direction: str  # "improving", "declining", "stable"
     trend_strength: float  # 0-1 scale

benchmarks/analysis/reporter.py

@@ -21,7 +21,7 @@ def __init__(self, output_dir: str | Path = "benchmarks/reports"):
     def generate_comparison_report(
         self,
         comparison_result: ComparisonResult,
-        output_path: str | NonePath] = None,
+        output_path: str | Path | None = None,
         format: str = "markdown",
     ) -> Path:
         """Generate a detailed comparison report"""
@@ -44,7 +44,7 @@ def generate_comprehensive_report(
         self,
         results: list[BenchmarkResult],
         format: str = "html",
-        output_path: str | NonePath] = None,
+        output_path: str | Path | None = None,
         include_charts: bool = True,
     ) -> Path:
         """Generate a comprehensive benchmark analysis report"""

benchmarks/analysis/visualizer.py

@@ -39,7 +39,7 @@ def create_provider_comparison_chart(
         self,
         comparison_result: ComparisonResult,
         chart_type: str = "bar",
-        save_path: str | NonePath] = None,
+        save_path: str | Path | None = None,
     ) -> Path:
         """Create a chart comparing two providers"""
 
@@ -70,7 +70,7 @@ def create_provider_comparison_chart(
         return save_path
 
     def create_trend_chart(
-        self, trend_analysis: TrendAnalysis, save_path: str | NonePath] = None
+        self, trend_analysis: TrendAnalysis, save_path: str | Path | None = None
     ) -> Path:
         """Create a trend analysis chart"""
 
@@ -175,7 +175,7 @@ def create_trend_chart(
         return save_path
 
     def create_performance_dashboard(
-        self, results: list[BenchmarkResult], save_path: str | NonePath] = None
+        self, results: list[BenchmarkResult], save_path: str | Path | None = None
     ) -> Path:
         """Create a comprehensive performance dashboard"""
 
@@ -226,8 +226,8 @@ def create_performance_dashboard(
         return save_path
 
     def create_interactive_dashboard(
-        self, results: list[BenchmarkResult], save_path: str | NonePath] = None
-    ) -> str | NonePath]:
+        self, results: list[BenchmarkResult], save_path: str | Path | None = None
+    ) -> str | Path | None:
         """Create an interactive HTML dashboard using Plotly"""
 
         if not PLOTLY_AVAILABLE:
@@ -671,7 +671,7 @@ def _plot_scenario_success_rates(self, results: list[BenchmarkResult], ax):
             )
 
     def export_chart_data(
-        self, results: list[BenchmarkResult], save_path: str | NonePath] = None
+        self, results: list[BenchmarkResult], save_path: str | Path | None = None
     ) -> Path:
         """Export chart data as JSON for external visualization tools"""