Files
cleveragents-core/features/mocks/mock_devcontainer_cli.py
CoreRasurae cf67ba0a86
CI / benchmark-publish (pull_request) Has been skipped
CI / lint (pull_request) Successful in 15s
CI / build (pull_request) Successful in 16s
CI / quality (pull_request) Successful in 18s
CI / security (pull_request) Successful in 35s
CI / typecheck (pull_request) Successful in 37s
CI / unit_tests (pull_request) Successful in 2m27s
CI / docker (pull_request) Successful in 49s
CI / integration_tests (pull_request) Successful in 3m46s
CI / coverage (pull_request) Successful in 4m56s
CI / lint (push) Successful in 12s
CI / build (push) Successful in 14s
CI / quality (push) Successful in 16s
CI / security (push) Successful in 32s
CI / typecheck (push) Successful in 36s
CI / benchmark-regression (push) Has been skipped
CI / unit_tests (push) Successful in 4m7s
CI / integration_tests (push) Successful in 4m41s
CI / docker (push) Successful in 44s
CI / coverage (push) Successful in 4m56s
CI / benchmark-publish (push) Successful in 17m17s
CI / benchmark-regression (pull_request) Successful in 31m25s
feat(devcontainer): add lazy activation and lifecycle management
Implemented lazy container activation for devcontainer-instance resources
with ContainerLifecycleState enum tracking six states (inactive, starting,
active, stopping, stopped, error) with validated transitions. Extended
DevcontainerHandler with devcontainer up CLI integration and JSON output
parsing for container start. Added periodic health checking via
devcontainer exec ping with configurable interval. Added agents resource
stop and agents resource rebuild CLI commands for manual lifecycle
control. Wired session close and plan completion hooks to automatic
container cleanup. Includes lifecycle state persistence in resource
registry with timestamped transitions. Added Behave BDD tests, Robot
integration tests, and ASV activation latency benchmarks.

- Added remoteWorkspaceFolder absolute-path validation
- Aligned spec: handler name, rebuild types, --yes flag on stop/rebuild
- Added registry re-read in stop_container success path for consistency
- Added session_id field to ContainerLifecycleTracker for scoped cleanup
- Scoped stop_all_active_containers to session_id when provided
- Wired _cleanup_devcontainers into fail_apply and fail_execute
- Wired start_health_check into activate_container success path
- Restructured facade session close to always run container cleanup
  even without session service (F4)
- Re-read tracker from registry in activate_container success path
- Added evict_terminal_trackers to cap registry growth
- Updated devcontainer_resources.md: health check auto-start, scoped
  cleanup hooks, known limitations for eviction and sandbox_strategy
- Wired evict_terminal_trackers into stop_all_active_containers so
  terminal-state trackers are actually evicted in production
- Made stop_container idempotent: returns early when container is
  already in a terminal state instead of raising ValueError
- Fixed benchmark health check thread leak in TimeActivationLatency
  by clearing registry after each timing loop
- Added rebuild pass-through (--reset-container flag to devcontainer up)
- Added host_workspace_path field on ContainerLifecycleTracker so
  health probes use the host-side path for devcontainer exec
- Wired lazy activation into DevcontainerHandler.resolve() for
  devcontainer-instance resources in non-running states
- Changed _default_strategy from SNAPSHOT to NONE (container
  itself provides isolation; SandboxFactory raises NotImplementedError
  for snapshot)
- Restricted _STOPPABLE_TYPES to devcontainer-instance only
  (container-instance is not directly stoppable via CLI)

ISSUES CLOSED: #514
2026-03-10 12:17:51 +00:00

210 lines
6.6 KiB
Python

"""Mock subprocess runner for devcontainer CLI commands.
Provides configurable mock responses for ``devcontainer up``,
``devcontainer exec``, and ``docker stop`` commands used in
lifecycle BDD tests.
All mocks reside in ``features/mocks/`` per project convention.
"""
from __future__ import annotations
import json
from dataclasses import dataclass, field
@dataclass
class MockProcessResult:
"""Mimics ``subprocess.CompletedProcess`` for test assertions."""
returncode: int = 0
stdout: str = ""
stderr: str = ""
args: list[str] = field(default_factory=list)
class MockDevcontainerRunner:
"""Configurable mock for subprocess.run calls.
Records all invocations and returns pre-configured results
based on the command being run.
Usage::
runner = MockDevcontainerRunner()
runner.set_up_result(container_id="abcdef012345", workspace="/ws")
# pass runner as ``run_command=runner`` in handler calls
Attributes:
calls: List of all recorded (args, kwargs) invocations.
up_result: Result returned for ``devcontainer up`` commands.
exec_result: Result returned for ``devcontainer exec`` commands.
stop_result: Result returned for ``docker stop`` commands.
"""
def __init__(self) -> None:
self.calls: list[tuple[list[str], dict[str, object]]] = []
self.up_result: MockProcessResult = MockProcessResult()
self.exec_result: MockProcessResult = MockProcessResult()
self.stop_result: MockProcessResult = MockProcessResult()
#: TEST-4 fix: expected subprocess kwargs that production code must pass.
#: If production code sets ``check=True`` (causing CalledProcessError on
#: non-zero rc) or omits ``capture_output``/``text``, this mock will
#: flag the mismatch.
_EXPECTED_KWARGS = frozenset({"capture_output", "text", "timeout", "check"})
def __call__(
self,
args: list[str],
**kwargs: object,
) -> MockProcessResult:
"""Handle a subprocess.run invocation.
Args:
args: Command-line arguments.
**kwargs: Additional subprocess kwargs — validated against
expected production kwargs (TEST-4 fix).
Returns:
Mock result based on the command.
Raises:
AssertionError: If required kwargs are missing or ``check``
is set to ``True`` (which would raise
``CalledProcessError`` in production).
"""
self.calls.append((list(args), dict(kwargs)))
# TEST-4 fix: validate subprocess kwargs.
missing = self._EXPECTED_KWARGS - set(kwargs)
if missing:
raise AssertionError(
f"MockDevcontainerRunner: missing expected subprocess kwargs "
f"{missing} in call {args}"
)
if kwargs.get("check") is True:
raise AssertionError(
f"MockDevcontainerRunner: check=True would raise "
f"CalledProcessError in production for {args}"
)
if len(args) >= 2 and args[0] == "devcontainer" and args[1] == "up":
return self.up_result
if len(args) >= 2 and args[0] == "devcontainer" and args[1] == "exec":
return self.exec_result
if len(args) >= 2 and args[0] == "docker" and args[1] == "stop":
return self.stop_result
return MockProcessResult(returncode=0)
def set_up_result(
self,
*,
container_id: str = "aabbccddee0011223344",
workspace: str = "/workspaces/project",
returncode: int = 0,
stderr: str = "",
) -> None:
"""Configure the result for ``devcontainer up``.
Args:
container_id: Container ID in the JSON output.
workspace: Workspace path in the JSON output.
returncode: Exit code.
stderr: Stderr text.
"""
output = json.dumps(
{
"outcome": "success" if returncode == 0 else "error",
"containerId": container_id,
"remoteWorkspaceFolder": workspace,
}
)
self.up_result = MockProcessResult(
returncode=returncode,
stdout=output,
stderr=stderr,
)
def set_up_no_container_id(self) -> None:
"""Configure ``devcontainer up`` to succeed without a containerId."""
output = json.dumps({"outcome": "success"})
self.up_result = MockProcessResult(
returncode=0,
stdout=output,
stderr="",
)
def set_up_failure(self, stderr: str = "container build failed") -> None:
"""Configure ``devcontainer up`` to fail.
Args:
stderr: Error message.
"""
self.up_result = MockProcessResult(
returncode=1,
stdout="",
stderr=stderr,
)
def set_exec_result(self, *, returncode: int = 0, stdout: str = "ping") -> None:
"""Configure the result for ``devcontainer exec``.
Args:
returncode: Exit code.
stdout: Stdout text.
"""
self.exec_result = MockProcessResult(
returncode=returncode,
stdout=stdout,
)
def set_exec_failure(self) -> None:
"""Configure ``devcontainer exec`` to fail."""
self.exec_result = MockProcessResult(
returncode=1,
stdout="",
stderr="container not responding",
)
def set_stop_result(self, *, returncode: int = 0) -> None:
"""Configure the result for ``docker stop``.
Args:
returncode: Exit code.
"""
self.stop_result = MockProcessResult(returncode=returncode)
@property
def call_count(self) -> int:
"""Total number of invocations."""
return len(self.calls)
@property
def up_calls(self) -> list[tuple[list[str], dict[str, object]]]:
"""Calls to ``devcontainer up``."""
return [
(a, k)
for a, k in self.calls
if len(a) >= 2 and a[0] == "devcontainer" and a[1] == "up"
]
@property
def exec_calls(self) -> list[tuple[list[str], dict[str, object]]]:
"""Calls to ``devcontainer exec``."""
return [
(a, k)
for a, k in self.calls
if len(a) >= 2 and a[0] == "devcontainer" and a[1] == "exec"
]
@property
def stop_calls(self) -> list[tuple[list[str], dict[str, object]]]:
"""Calls to ``docker stop``."""
return [
(a, k)
for a, k in self.calls
if len(a) >= 2 and a[0] == "docker" and a[1] == "stop"
]