Files
cleveragents-core/benchmarks/resource_cli_tree_bench.py
T
CoreRasurae 80f1664a0d
CI / benchmark-publish (pull_request) Has been skipped
CI / build (pull_request) Successful in 23s
CI / lint (pull_request) Successful in 3m20s
CI / typecheck (pull_request) Successful in 3m54s
CI / security (pull_request) Successful in 4m13s
CI / quality (pull_request) Successful in 4m17s
CI / integration_tests (pull_request) Successful in 9m21s
CI / unit_tests (pull_request) Successful in 9m42s
CI / docker (pull_request) Successful in 14s
CI / e2e_tests (pull_request) Successful in 12m1s
CI / coverage (pull_request) Successful in 11m41s
CI / status-check (pull_request) Successful in 1s
CI / build (push) Successful in 26s
CI / lint (push) Successful in 3m19s
CI / quality (push) Successful in 3m41s
CI / typecheck (push) Successful in 3m56s
CI / benchmark-regression (push) Has been skipped
CI / security (push) Successful in 4m2s
CI / integration_tests (push) Successful in 9m3s
CI / unit_tests (push) Successful in 9m24s
CI / docker (push) Successful in 1m9s
CI / e2e_tests (push) Successful in 13m51s
CI / coverage (push) Successful in 11m25s
CI / status-check (push) Successful in 1s
CI / benchmark-publish (push) Failing after 24m52s
CI / benchmark-regression (pull_request) Failing after 37m6s
test(integration): workflow example 7 — CI/CD integration, automated PR review and fix (ci profile)
Implemented Robot Framework integration test suite validating the CI/CD
workflow (Specification Example 7). Tests cover ci-profile configuration
(automation-profile, format, log level), idempotent resource and project
registration with duplicate-detection assertions, three validation tools
(ci-lint, ci-typecheck, ci-tests) registration and resource attachment
via ToolRegistryService, action creation with typed arguments and
invariants per spec Step 2, plan lifecycle with phase-by-phase completion
through all phases (strategize, execute, apply) until terminal applied
state, and JSON output structure verification including plan_id, phase,
state, action, projects, and arguments fields.

Post-review fixes applied (round 1):
- H1: Fix truncated invariant #2 text to match spec line 39051
- H2: Fix definition_of_done to match spec's 5-bullet-point format
- M1: Register all 3 spec validations (ci-lint, ci-typecheck, ci-tests)
- M3: Add branch property to resource registration per spec Step 3
- M4: Replace phantom resource_id with real registered resource
- M5: Add projects and arguments field assertions to JSON output test
- M7: Replace 'polling-based' with 'phase-by-phase' in docs/comments
- L1: Use timezone-aware datetime (timezone.utc)
- L2: Use tempfile for resource path instead of hardcoded /tmp
- L3: Clarify json_output() docstring to reflect as_cli_dict() scope
- L4: Tighten attachment count assertion from >= 1 to == 1 (now == 3)

Post-review fixes applied (round 2):
- M2: Use Setup Test Environment With Database Isolation for pabot safety
- L1: Replace remaining hardcoded /tmp paths with tempfile (validation_attach,
  resource_idempotent duplicate registration)
- L2: Fix stale 'Polling-based' comment missed in round 1
- L5: Align action description with spec line 39027
- M1/L3/L6: Document automation_profile propagation gap in use_action()
  with TODO for when production code wires the field onto Plan
- L4: Add comment explaining local actor name deviation from spec

Includes CHANGELOG update describing the integration test scope.

ISSUES CLOSED: #771
2026-03-26 21:42:37 +00:00

175 lines
5.4 KiB
Python

"""ASV benchmarks for Resource CLI tree/inspect command overhead.
Measures the performance of:
- Tree rendering for a resource with no children
- Tree rendering for a resource with multiple children
- Inspect command rendering
- Link-child / unlink-child command throughput
"""
from __future__ import annotations
import importlib
import sys
from datetime import UTC, 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.resource import app as resource_app # noqa: E402
from cleveragents.domain.models.core.resource import ( # noqa: E402
PhysVirt,
Resource,
ResourceCapabilities,
)
_runner = CliRunner()
def _mock_resource(
resource_id: str = "01HBENCH0000000000RES0RCE0",
name: str = "local/bench-res",
type_name: str = "git-checkout",
) -> Resource:
return Resource(
resource_id=resource_id,
name=name,
resource_type_name=type_name,
classification=PhysVirt.PHYSICAL,
description="Benchmark resource",
properties={"path": "/tmp/bench"},
location="/tmp/bench",
content_hash=None,
sandbox_strategy=None,
capabilities=ResourceCapabilities(),
created_at=datetime.now(tz=UTC),
updated_at=datetime.now(tz=UTC),
)
def _mock_tree_node(
resource: Resource,
children: list[dict[str, object]] | None = None,
) -> dict[str, object]:
return {
"resource": resource,
"children": children or [],
}
class ResourceTreeSuite:
"""Benchmark resource tree command throughput."""
def setup(self) -> None:
"""Set up mock service."""
root = _mock_resource()
child1 = _mock_resource(
"01HBENCH0000000000CHJKD001", "local/child-1", "fs-directory"
)
child2 = _mock_resource(
"01HBENCH0000000000CHJKD002", "local/child-2", "fs-directory"
)
tree = [
_mock_tree_node(
root,
[
_mock_tree_node(child1),
_mock_tree_node(child2),
],
)
]
self._mock_service = MagicMock()
self._mock_service.get_resource_tree.return_value = tree
self._mock_service.show_resource.return_value = root
self._patcher = patch(
"cleveragents.cli.commands.resource._get_registry_service",
return_value=self._mock_service,
)
self._patcher.start()
def teardown(self) -> None:
self._patcher.stop()
def time_tree_default(self) -> None:
"""Benchmark tree with default settings."""
_runner.invoke(resource_app, ["tree", "local/bench-res"])
def time_tree_json(self) -> None:
"""Benchmark tree with JSON output."""
_runner.invoke(resource_app, ["tree", "local/bench-res", "--format", "json"])
def time_tree_depth(self) -> None:
"""Benchmark tree with depth limit."""
_runner.invoke(resource_app, ["tree", "local/bench-res", "--depth", "1"])
class ResourceInspectSuite:
"""Benchmark resource inspect command throughput."""
def setup(self) -> None:
"""Set up mock service."""
res = _mock_resource()
tree = [_mock_tree_node(res)]
self._mock_service = MagicMock()
self._mock_service.show_resource.return_value = res
self._mock_service.get_resource_tree.return_value = tree
self._patcher = patch(
"cleveragents.cli.commands.resource._get_registry_service",
return_value=self._mock_service,
)
self._patcher.start()
def teardown(self) -> None:
self._patcher.stop()
def time_inspect_default(self) -> None:
"""Benchmark inspect with default settings."""
_runner.invoke(resource_app, ["inspect", "local/bench-res"])
def time_inspect_json(self) -> None:
"""Benchmark inspect with JSON output."""
_runner.invoke(resource_app, ["inspect", "local/bench-res", "--format", "json"])
def time_inspect_with_tree(self) -> None:
"""Benchmark inspect with --tree flag."""
_runner.invoke(resource_app, ["inspect", "local/bench-res", "--tree"])
class ResourceLinkSuite:
"""Benchmark resource link-child/unlink-child command throughput."""
def setup(self) -> None:
"""Set up mock service."""
self._mock_service = MagicMock()
self._mock_service.link_child.return_value = None
self._mock_service.unlink_child.return_value = None
self._patcher = patch(
"cleveragents.cli.commands.resource._get_registry_service",
return_value=self._mock_service,
)
self._patcher.start()
def teardown(self) -> None:
self._patcher.stop()
def time_link_child(self) -> None:
"""Benchmark link-child command."""
_runner.invoke(resource_app, ["link-child", "local/parent", "local/child"])
def time_unlink_child(self) -> None:
"""Benchmark unlink-child command."""
_runner.invoke(
resource_app, ["unlink-child", "--yes", "local/parent", "local/child"]
)