chore(conductor): Checkpoint Phase 2: Manifest and Tooling for test curation track

conductor/tracks/test_curation_20260225/plan.md

@@ -9,10 +9,12 @@ This plan outlines the process for categorizing, organizing, and curating the ex
 - [x] Task: Conductor - User Manual Verification 'Phase 1: Research and Inventory' (Protocol in workflow.md) be689ad
 
 ## Phase 2: Manifest and Tooling
-- [ ] Task: Design and create `tests.toml` manifest file
+- [x] Task: T3-P2-1-STUB: Design tests.toml manifest schema (Completed by PM)
-- [ ] Task: Implement a test runner wrapper or `pytest` configuration to respect the manifest and categories
+- [x] Task: T3-P2-1-IMPL: Populate tests.toml with full inventory
-- [ ] Task: Verify that Conductor/MMA tests can be explicitly excluded from default runs
+- [x] Task: T3-P2-2-STUB: Stub run_tests.py category-aware interface
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: Manifest and Tooling' (Protocol in workflow.md)
+- [x] Task: T3-P2-2-IMPL: Implement run_tests.py filtering logic (Verified)
+- [x] Task: Verify that Conductor/MMA tests can be explicitly excluded from default runs (Verified)
+- [x] Task: Conductor - User Manual Verification 'Phase 2: Manifest and Tooling' (Protocol in workflow.md)
 
 ## Phase 3: Curation and Consolidation
 - [ ] Task: Fix all identified non-redundant failing tests

run_tests.py

@@ -1,5 +1,123 @@
-import pytest
+import argparse
 import sys
+import tomllib
+import pytest
+from typing import Dict, List, Any
+
+def load_manifest(path: str) -> Dict[str, Any]:
+    """
+    Loads a manifest file (expected to be in TOML format) from the given path.
+
+    Args:
+        path: The path to the TOML manifest file.
+
+    Returns:
+        A dictionary representing the loaded manifest.
+
+    Raises:
+        FileNotFoundError: If the manifest file does not exist.
+        tomllib.TOMLDecodeError: If the manifest file is not valid TOML.
+    """
+    try:
+        with open(path, 'rb') as f:
+            return tomllib.load(f)
+    except FileNotFoundError:
+        print(f"Error: Manifest file not found at {path}", file=sys.stderr)
+        raise
+    except tomllib.TOMLDecodeError:
+        print(f"Error: Could not decode TOML from {path}", file=sys.stderr)
+        raise
+
+def get_test_files(manifest: Dict[str, Any], category: str) -> List[str]:
+    """
+    Determines the list of test files based on the manifest and a specified category.
+
+    Args:
+        manifest: The loaded manifest dictionary.
+        category: The category of tests to retrieve.
+
+    Returns:
+        A list of file paths corresponding to the tests in the given category.
+        Returns an empty list if the category is not found or has no tests.
+    """
+    print(f"DEBUG: Looking for category '{category}' in manifest.", file=sys.stderr)
+    files = manifest.get("categories", {}).get(category, {}).get("files", [])
+    print(f"DEBUG: Found test files for category '{category}': {files}", file=sys.stderr)
+    return files
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Run tests with optional manifest and category filtering, passing additional pytest arguments.",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""\
+Example usage:
+  python run_tests.py --manifest tests.toml --category unit -- --verbose --cov=my_module
+  python run_tests.py --manifest tests.toml --category integration
+  python run_tests.py --manifest tests.toml --category core
+  python run_tests.py --manifest tests.toml # Runs tests from default_categories
+  python run_tests.py -- --capture=no # Runs all tests with pytest args
+"""
+    )
+    parser.add_argument(
+        "--manifest",
+        type=str,
+        help="Path to the TOML manifest file containing test configurations."
+    )
+    parser.add_argument(
+        "--category",
+        type=str,
+        help="Category of tests to run (e.g., 'unit', 'integration')."
+    )
+
+    args, remaining_pytest_args = parser.parse_known_args(sys.argv[1:])
+
+    selected_test_files = []
+    manifest_data = None
+
+    if args.manifest:
+        try:
+            manifest_data = load_manifest(args.manifest)
+        except (FileNotFoundError, tomllib.TOMLDecodeError):
+            # Error message already printed by load_manifest
+            sys.exit(1)
+
+        if args.category:
+            # Case 1: --manifest and --category provided
+            files = get_test_files(manifest_data, args.category)
+            selected_test_files.extend(files)
+        else:
+            # Case 2: --manifest provided, but no --category
+            # Load default categories from manifest['execution']['default_categories']
+            default_categories = manifest_data.get("execution", {}).get("default_categories", [])
+            if not default_categories:
+                print(f"Error: --manifest provided without --category, and no 'default_categories' found in manifest '{args.manifest}'.", file=sys.stderr)
+                parser.print_help(sys.stderr)
+                sys.exit(1)
+
+            print(f"DEBUG: Using default categories from manifest '{args.manifest}': {default_categories}", file=sys.stderr)
+            for cat in default_categories:
+                files = get_test_files(manifest_data, cat)
+                selected_test_files.extend(files)
+    elif args.category:
+        # Case 3: --category provided without --manifest
+        print("Error: --category requires --manifest to be specified.", file=sys.stderr)
+        parser.print_help(sys.stderr)
+        sys.exit(1)
+
+    # Combine selected test files with any remaining pytest arguments
+    # If --manifest was not provided, selected_test_files will be empty.
+    # If no tests were selected from manifest/category, selected_test_files will be empty.
+    pytest_command_args = selected_test_files + remaining_pytest_args
+
+    # Filter out empty strings that might appear if remaining_pytest_args had them
+    final_pytest_args = [arg for arg in pytest_command_args if arg]
+
+    # If no specific tests were selected and no manifest was provided,
+    # and no other pytest args were given, pytest.main([]) runs default discovery.
+    # This handles cases where user only passes pytest args like `python run_tests.py -- --cov=app`
+    # or when manifest/category selection results in an empty list and no other args are passed.
+    print(f"Running pytest with arguments: {final_pytest_args}", file=sys.stderr)
+    sys.exit(pytest.main(final_pytest_args))
 
 if __name__ == "__main__":
-    sys.exit(pytest.main(sys.argv[1:]))
+    main()

tests.toml

@@ -0,0 +1,73 @@
+# Test Manifest for manual_slop
+
+[categories.core]
+description = "Manual Slop Core and GUI tests"
+files = [
+    "tests/test_ai_context_history.py",
+    "tests/test_api_events.py",
+    "tests/test_gui_diagnostics.py",
+    "tests/test_gui_events.py",
+    "tests/test_gui_performance_requirements.py",
+    "tests/test_gui_stress_performance.py",
+    "tests/test_gui_updates.py",
+    "tests/test_gui2_events.py",
+    "tests/test_gui2_layout.py",
+    "tests/test_gui2_mcp.py",
+    "tests/test_gui2_parity.py",
+    "tests/test_gui2_performance.py",
+    "tests/test_headless_api.py",
+    "tests/test_headless_dependencies.py",
+    "tests/test_headless_startup.py",
+    "tests/test_history_blacklist.py",
+    "tests/test_history_bleed.py",
+    "tests/test_history_migration.py",
+    "tests/test_history_persistence.py",
+    "tests/test_history_truncation.py",
+    "tests/test_performance_monitor.py",
+    "tests/test_token_usage.py",
+    "tests/test_layout_reorganization.py"
+]
+
+[categories.conductor]
+description = "Conductor and MMA internal tests (Blacklisted from default core runs)"
+files = [
+    "tests/test_mma_exec.py",
+    "tests/test_mma_skeleton.py",
+    "tests/test_conductor_api_hook_integration.py",
+    "tests/conductor/test_infrastructure.py",
+    "tests/test_gemini_cli_adapter.py",
+    "tests/test_gemini_cli_integration.py",
+    "tests/test_ai_client_cli.py",
+    "tests/test_cli_tool_bridge.py",
+    "tests/test_gemini_metrics.py"
+]
+
+[categories.integrations]
+description = "MCP and other external integration tests"
+files = [
+    "tests/test_api_hook_client.py",
+    "tests/test_api_hook_extensions.py",
+    "tests/test_hooks.py",
+    "tests/test_sync_hooks.py",
+    "tests/test_mcp_perf_tool.py"
+]
+
+[categories.simulations]
+description = "AI and Workflow simulation tests"
+files = [
+    "tests/test_sim_ai_settings.py",
+    "tests/test_sim_base.py",
+    "tests/test_sim_context.py",
+    "tests/test_sim_execution.py",
+    "tests/test_sim_tools.py",
+    "tests/test_workflow_sim.py",
+    "tests/test_extended_sims.py",
+    "tests/test_user_agent.py",
+    "tests/test_live_workflow.py",
+    "tests/test_agent_capabilities.py",
+    "tests/test_agent_tools_wiring.py"
+]
+
+[execution]
+default_categories = ["core", "integrations", "simulations"]
+blacklist_categories = ["conductor"]