forked from HAL9000/cleveragents-core
hurui200320
1878998b7a
Rename the TDD tag system from tdd_bug/tdd_bug_<N> to tdd_issue/tdd_issue_<N> across the entire codebase. The tdd_expected_fail tag is unchanged. The TDD expected-failure workflow is not limited to bug fixes — it applies equally to any issue type (features, tasks, refactors). The _bug suffix was misleading and narrowed the perceived scope. The new _issue suffix accurately reflects that the TDD tagging system applies to any Forgejo issue. Changes span 92 files: - features/environment.py: validate_tdd_tags(), should_invert_result(), and apply_tdd_inversion() updated — regex, variables, error messages - robot/tdd_expected_fail_listener.py: _validate_tdd_tags(), _should_invert_result(), start_test(), end_test() updated consistently - 33 Behave .feature files: all @tdd_bug/@tdd_bug_<N> tags renamed - 29 Robot .robot files: all tdd_bug/tdd_bug_<N> tags renamed - 3 Robot fixture files renamed (tdd_bug_alone, tdd_missing_tdd_bug, tdd_expected_fail_missing_bug_n) with content and references updated - Tag validation tests and helpers updated (function names, command dispatch keys, output strings, fixture references) - CONTRIBUTING.md: section renamed from 'TDD Bug Test Tags' to 'TDD Issue Test Tags', all tag references and examples updated - noxfile.py: comment references updated - Step definition files, mock helpers, and benchmark files: docstring references updated ISSUES CLOSED: #965
55 lines
1.8 KiB
Python
55 lines
1.8 KiB
Python
"""ASV benchmarks for TDD Issue #554 — session list CLI throughput.
|
|
|
|
Measures the performance of the session list CLI command path to establish
|
|
a baseline before and after the DI bug fix. Uses a mocked service so the
|
|
benchmark isolates CLI/rendering overhead from database I/O.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import MagicMock
|
|
|
|
from benchmarks._session_bench_common import mock_session, runner
|
|
from cleveragents.cli.commands import session as session_mod
|
|
from cleveragents.cli.commands.session import app as session_app
|
|
|
|
|
|
class TDDSessionListDISuite:
|
|
"""Benchmark session list command throughput (TDD issue #554 baseline)."""
|
|
|
|
def setup(self) -> None:
|
|
self._svc = MagicMock()
|
|
# Use deterministic, unique session IDs for reproducible benchmarks.
|
|
self._svc.list.return_value = [
|
|
mock_session(
|
|
session_id=f"01HXYZ{i:020d}",
|
|
actor_name=f"openai/gpt-{i}",
|
|
)
|
|
for i in range(50)
|
|
]
|
|
session_mod._service = self._svc
|
|
|
|
def teardown(self) -> None:
|
|
session_mod._service = None
|
|
|
|
def time_list_rich(self) -> None:
|
|
"""Benchmark listing sessions with default rich format."""
|
|
runner.invoke(session_app, ["list"])
|
|
|
|
def time_list_json(self) -> None:
|
|
"""Benchmark listing sessions with JSON format."""
|
|
runner.invoke(session_app, ["list", "--format", "json"])
|
|
|
|
def time_list_empty(self) -> None:
|
|
"""Benchmark listing with no sessions."""
|
|
self._svc.list.return_value = []
|
|
runner.invoke(session_app, ["list"])
|
|
# Restore for next benchmark (deterministic IDs).
|
|
self._svc.list.return_value = [
|
|
mock_session(
|
|
session_id=f"01HXYZ{i:020d}",
|
|
actor_name=f"openai/gpt-{i}",
|
|
)
|
|
for i in range(50)
|
|
]
|