cleveragents-core/benchmarks/plan_cli_bench.py

"""ASV benchmarks for Plan CLI command throughput.

Measures the performance of:
- Plan use with multiple projects and flags
- Lifecycle-list with various filters
- Plan status rendering
- Plan cancel with reason
"""

from __future__ import annotations

import importlib
import sys
from datetime import datetime
from pathlib import Path
from unittest.mock import MagicMock, patch

# Ensure the local *source* tree is importable even when ASV has an
# older build of the package installed.
_SRC = str(Path(__file__).resolve().parents[1] / "src")
if _SRC not in sys.path:
    sys.path.insert(0, _SRC)

import cleveragents  # noqa: E402

importlib.reload(cleveragents)

from typer.testing import CliRunner  # noqa: E402

from cleveragents.cli.commands.plan import app as plan_app  # noqa: E402
from cleveragents.domain.models.core.action import Action, ActionState  # noqa: E402
from cleveragents.domain.models.core.plan import (  # noqa: E402
    AutomationProfileProvenance,
    AutomationProfileRef,
    NamespacedName,
    Plan,
    PlanIdentity,
    PlanPhase,
    PlanTimestamps,
    ProcessingState,
    ProjectLink,
)

_runner = CliRunner()
_PLAN_ULID = "01KHDE6WWS2171PWW3GJEBXZ8S"


def _mock_action(name: str = "local/bench-action") -> Action:
    return Action(
        namespaced_name=NamespacedName.parse(name),
        description="Benchmark action",
        long_description=None,
        definition_of_done="Benchmarks pass",
        strategy_actor="openai/gpt-4",
        execution_actor="openai/gpt-4",
        reusable=True,
        read_only=False,
        state=ActionState.AVAILABLE,
        created_by=None,
        created_at=datetime.now(),
        updated_at=datetime.now(),
    )


def _mock_plan(
    name: str = "local/bench-plan",
    project_links: list[ProjectLink] | None = None,
) -> Plan:
    now = datetime.now()
    return Plan(
        identity=PlanIdentity(plan_id=_PLAN_ULID),
        namespaced_name=NamespacedName.parse(name),
        description="Benchmark plan",
        definition_of_done="Benchmarks pass",
        action_name="local/bench-action",
        phase=PlanPhase.STRATEGIZE,
        processing_state=ProcessingState.QUEUED,
        project_links=project_links or [],
        arguments={"target_coverage": 80},
        arguments_order=["target_coverage"],
        automation_profile=AutomationProfileRef(
            profile_name="trusted",
            provenance=AutomationProfileProvenance.PLAN,
        ),
        strategy_actor="openai/gpt-4",
        execution_actor="openai/gpt-4",
        estimation_actor="openai/gpt-4",
        invariant_actor="openai/gpt-4",
        reusable=True,
        read_only=False,
        created_by=None,
        timestamps=PlanTimestamps(created_at=now, updated_at=now),
    )


class PlanCLIUseSuite:
    """Benchmark plan use command throughput."""

    def setup(self) -> None:
        """Set up mock service."""
        self._mock_service = MagicMock()
        self._mock_service.get_action_by_name.return_value = _mock_action()
        self._mock_service.use_action.return_value = _mock_plan(
            project_links=[
                ProjectLink(project_name="proj-a"),
                ProjectLink(project_name="proj-b"),
            ]
        )
        self._patcher = patch(
            "cleveragents.cli.commands.plan._get_lifecycle_service",
            return_value=self._mock_service,
        )
        self._patcher.start()

    def teardown(self) -> None:
        self._patcher.stop()

    def time_use_with_projects(self) -> None:
        """Benchmark plan use with multiple projects."""
        _runner.invoke(
            plan_app,
            ["use", "local/bench-action", "proj-a", "proj-b", "--arg", "coverage=80"],
        )

    def time_use_with_all_flags(self) -> None:
        """Benchmark plan use with all flags."""
        _runner.invoke(
            plan_app,
            [
                "use",
                "local/bench-action",
                "proj-a",
                "--automation-profile",
                "trusted",
                "--invariant",
                "No warnings",
                "--strategy-actor",
                "openai/gpt-4",
                "--execution-actor",
                "openai/gpt-4",
                "--arg",
                "coverage=80",
            ],
        )


class PlanCLIListSuite:
    """Benchmark plan list throughput."""

    def setup(self) -> None:
        self._mock_service = MagicMock()
        self._mock_service.list_plans.return_value = [
            _mock_plan(f"local/plan-{i}") for i in range(50)
        ]
        self._patcher = patch(
            "cleveragents.cli.commands.plan._get_lifecycle_service",
            return_value=self._mock_service,
        )
        self._patcher.start()

    def teardown(self) -> None:
        self._patcher.stop()

    def time_list_all(self) -> None:
        """Benchmark listing all plans."""
        _runner.invoke(plan_app, ["list"])

    def time_list_with_phase(self) -> None:
        """Benchmark listing with phase filter."""
        _runner.invoke(plan_app, ["list", "--phase", "strategize"])

    def time_list_with_state(self) -> None:
        """Benchmark listing with state filter."""
        _runner.invoke(plan_app, ["list", "--state", "queued"])


class PlanCLIStatusSuite:
    """Benchmark plan status rendering."""

    def setup(self) -> None:
        self._mock_service = MagicMock()
        self._mock_service.get_plan.return_value = _mock_plan(
            project_links=[ProjectLink(project_name="proj-a", alias="api")]
        )
        self._patcher = patch(
            "cleveragents.cli.commands.plan._get_lifecycle_service",
            return_value=self._mock_service,
        )
        self._patcher.start()

    def teardown(self) -> None:
        self._patcher.stop()

    def time_status(self) -> None:
        """Benchmark rendering plan status."""
        _runner.invoke(plan_app, ["status", _PLAN_ULID])