Files
cleveragents-core/benchmarks/skill_cli_bench.py
T
freemo 051ee7c290
CI / benchmark-publish (pull_request) Has been skipped
CI / lint (pull_request) Successful in 21s
CI / quality (pull_request) Successful in 31s
CI / typecheck (pull_request) Successful in 47s
CI / security (pull_request) Successful in 52s
CI / build (pull_request) Successful in 56s
CI / e2e_tests (pull_request) Successful in 5m1s
CI / integration_tests (pull_request) Successful in 5m30s
CI / unit_tests (pull_request) Successful in 5m42s
CI / docker (pull_request) Successful in 58s
CI / coverage (pull_request) Successful in 7m35s
CI / build (push) Successful in 21s
CI / docker (push) Has been skipped
CI / benchmark-regression (pull_request) Failing after 49m24s
CI / lint (push) Successful in 22s
CI / quality (push) Successful in 39s
CI / security (push) Successful in 48s
CI / typecheck (push) Successful in 1m26s
CI / benchmark-regression (push) Has been skipped
CI / e2e_tests (push) Successful in 5m53s
CI / coverage (push) Successful in 9m4s
CI / benchmark-publish (push) Successful in 19m10s
CI / integration_tests (push) Failing after 19m18s
CI / unit_tests (push) Failing after 19m20s
test(coverage): add Behave BDD tests to improve coverage across 52 source files
Added 52 new .feature files and corresponding _steps.py files targeting
previously uncovered code paths in the following areas:

- TUI layer: app, commands, persona (state/schema/registry), widgets,
  input (shell_exec, reference_parser)
- Application services: plan lifecycle/service/executor, session,
  project, repo indexing, correction, checkpoint, actor, llm_actors,
  strategy coordinator, resource file watcher, service retry wiring
- CLI commands: session, resource, repl, plan, db, automation_profile
- Domain models: retry_policy, resource_type, cost_budget,
  docker_compose_analyzer, detail_level, _sql_string_aware,
  _postgresql_helpers
- Core: circuit_breaker, retry_service_patterns
- Infrastructure: repositories, transaction_sandbox, strategy_registry,
  plugins/loader, container
- Config: settings
- Agents: plan_generation, context_analysis, auto_debug
- A2A: facade

All new tests follow the Behave/Gherkin BDD standard. Resolved step
definition collisions with unique prefixes. Fixed Alembic fileConfig
logger disabling issue (disable_existing_loggers=False).

ISSUES CLOSED: #1068
2026-03-20 21:22:10 +00:00

192 lines
5.6 KiB
Python

"""ASV benchmarks for Skill CLI command throughput.
Measures the performance of:
- Config-only add (YAML load + validate + Skill registration)
- List command rendering
- Show command rendering
- Tools command (resolver flattening)
"""
from __future__ import annotations
import importlib
import os
import sys
import tempfile
from datetime import datetime
from pathlib import Path
# 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.application.services.skill_service import SkillService # noqa: E402
from cleveragents.cli.commands.skill import ( # noqa: E402
_reset_skill_service,
)
from cleveragents.cli.commands.skill import ( # noqa: E402
app as skill_app,
)
from cleveragents.domain.models.core.skill import Skill # noqa: E402
_VALID_YAML = """\
name: local/bench-skill
description: "Benchmark skill"
tools:
- name: builtin/read_file
- name: builtin/write_file
- name: builtin/list_directory
"""
_runner = CliRunner()
def _fresh_service() -> SkillService:
"""Create and install a fresh service for benchmarking."""
svc = SkillService()
_reset_skill_service(svc)
return svc
class SkillCLIAddSuite:
"""Benchmark skill add --config throughput."""
def setup(self) -> None:
"""Write a temporary YAML file and set up fresh service."""
fd, self._path = tempfile.mkstemp(suffix=".yaml")
with os.fdopen(fd, "w") as fh:
fh.write(_VALID_YAML)
def teardown(self) -> None:
"""Clean up."""
Path(self._path).unlink(missing_ok=True)
def time_add_from_config(self) -> None:
"""Benchmark add --config end-to-end."""
_fresh_service()
_runner.invoke(skill_app, ["add", "--config", self._path])
class SkillCLIListSuite:
"""Benchmark skill list throughput."""
def setup(self) -> None:
"""Set up service with skills."""
svc = _fresh_service()
for i in range(50):
name = f"local/skill-{i}"
skill = Skill(
name=name,
description=f"Benchmark skill {i}",
tool_refs=["builtin/read_file", "builtin/write_file"],
)
svc._skills[name] = skill
svc._created_at[name] = datetime.now()
svc._updated_at[name] = datetime.now()
def teardown(self) -> None:
_fresh_service()
def time_list_all(self) -> None:
"""Benchmark listing all skills."""
_runner.invoke(skill_app, ["list"])
def time_list_with_namespace(self) -> None:
"""Benchmark listing with namespace filter."""
_runner.invoke(skill_app, ["list", "--namespace", "local"])
class SkillCLIShowSuite:
"""Benchmark skill show throughput."""
def setup(self) -> None:
svc = _fresh_service()
skill = Skill(
name="local/bench-show",
description="Benchmark skill for show",
tool_refs=[
"builtin/read_file",
"builtin/write_file",
"builtin/list_directory",
],
)
svc._skills["local/bench-show"] = skill
svc._created_at["local/bench-show"] = datetime.now()
svc._updated_at["local/bench-show"] = datetime.now()
def teardown(self) -> None:
_fresh_service()
def time_show(self) -> None:
"""Benchmark showing a skill."""
_runner.invoke(skill_app, ["show", "local/bench-show"])
class SkillCLIToolsSuite:
"""Benchmark skill tools (resolver) throughput."""
def setup(self) -> None:
svc = _fresh_service()
skill = Skill(
name="local/bench-tools",
description="Benchmark skill for tools resolution",
tool_refs=[
"builtin/read_file",
"builtin/write_file",
"builtin/list_directory",
"builtin/search_files",
"builtin/delete_file",
],
)
svc._skills["local/bench-tools"] = skill
svc._created_at["local/bench-tools"] = datetime.now()
svc._updated_at["local/bench-tools"] = datetime.now()
def teardown(self) -> None:
_fresh_service()
def time_tools(self) -> None:
"""Benchmark resolving tools for a skill."""
_runner.invoke(skill_app, ["tools", "local/bench-tools"])
class SkillCLIRefreshSuite:
"""Benchmark skill refresh command throughput."""
def setup(self) -> None:
"""Set up service with multiple skills."""
svc = _fresh_service()
for i in range(20):
name = f"local/refresh-skill-{i}"
skill = Skill(
name=name,
description=f"Refresh benchmark skill {i}",
tool_refs=[
"builtin/read_file",
"builtin/write_file",
"builtin/list_directory",
],
)
svc._skills[name] = skill
svc._created_at[name] = datetime.now()
svc._updated_at[name] = datetime.now()
def teardown(self) -> None:
_fresh_service()
def time_refresh_single(self) -> None:
"""Benchmark refreshing a single skill."""
_runner.invoke(skill_app, ["refresh", "local/refresh-skill-0"])
def time_refresh_all(self) -> None:
"""Benchmark refreshing all skills."""
_runner.invoke(skill_app, ["refresh", "--all"])