Files
cleveragents-core/benchmarks/devcontainer_lifecycle_bench.py
T
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

220 lines
6.6 KiB
Python

"""ASV benchmarks for devcontainer lifecycle activation latency.
Measures the performance of:
- ContainerLifecycleState transition validation
- Lifecycle tracker construction and transition
- Lazy activation with mock runner (no real subprocess)
- JSON output parsing from devcontainer up
- Lifecycle registry operations (get/set/list)
Based on issue #514: Devcontainer lifecycle management.
"""
from __future__ import annotations
import json
import sys
from pathlib import Path
try:
from cleveragents.domain.models.core.container_lifecycle import (
ContainerLifecycleState,
ContainerLifecycleTracker,
transition_state,
validate_transition,
)
from cleveragents.resource.handlers.devcontainer import (
_parse_devcontainer_up_output,
activate_container,
clear_lifecycle_registry,
get_lifecycle_tracker,
list_active_containers,
set_lifecycle_tracker,
)
except ModuleNotFoundError:
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
from cleveragents.domain.models.core.container_lifecycle import (
ContainerLifecycleState,
ContainerLifecycleTracker,
transition_state,
validate_transition,
)
from cleveragents.resource.handlers.devcontainer import (
_parse_devcontainer_up_output,
activate_container,
clear_lifecycle_registry,
get_lifecycle_tracker,
list_active_containers,
set_lifecycle_tracker,
)
class _MockResult:
"""Minimal mock result for benchmark subprocess calls."""
def __init__(self) -> None:
self.returncode = 0
self.stdout = json.dumps(
{
"outcome": "success",
# F3 fix: use valid 20-char hex ID to pass S1 validation
"containerId": "aabbccddee0011223344",
"remoteWorkspaceFolder": "/ws",
}
)
self.stderr = ""
def _mock_runner(args: list[str], **kwargs: object) -> _MockResult:
"""Zero-overhead mock subprocess runner."""
return _MockResult()
class TimeTransitionValidation:
"""Benchmark validate_transition throughput."""
timeout = 10
def time_valid_transition(self) -> None:
"""Time valid transition check (1000 iterations)."""
for _ in range(1000):
validate_transition(
ContainerLifecycleState.DETECTED,
ContainerLifecycleState.BUILDING,
)
def time_invalid_transition(self) -> None:
"""Time invalid transition check (1000 iterations)."""
for _ in range(1000):
validate_transition(
ContainerLifecycleState.DETECTED,
ContainerLifecycleState.RUNNING,
)
class TimeTrackerConstruction:
"""Benchmark lifecycle tracker creation."""
timeout = 10
def time_tracker_construction(self) -> None:
"""Time ContainerLifecycleTracker instantiation."""
for i in range(1000):
ContainerLifecycleTracker(
resource_id=f"01BENCH{i:020d}",
)
class TimeTransitionState:
"""Benchmark state transition with history recording."""
timeout = 30
def time_single_transition(self) -> None:
"""Time a single state transition."""
for _ in range(1000):
tracker = ContainerLifecycleTracker(
resource_id="01BENCHTRACKER0000000001",
)
transition_state(
tracker,
ContainerLifecycleState.BUILDING,
reason="benchmark",
)
class TimeActivationLatency:
"""Benchmark lazy activation with mock runner."""
timeout = 30
params: list[int] = [1, 10, 50]
param_names: list[str] = ["num_activations"]
def setup(self, num_activations: int) -> None:
"""Clear registry before each timing iteration (R17 fix).
Without this, trackers from prior iterations accumulate in
``_lifecycle_registry`` and subsequent activate calls fail
with invalid-transition errors (``running`` → ``building``).
"""
clear_lifecycle_registry()
def time_activation(self, num_activations: int) -> None:
"""Time container activation with mock runner.
R8-F6 fix: clear the registry after the loop to stop health
check threads spawned by each activation (F3 auto-start).
Without this, ``num_activations`` daemon threads accumulate
during the timing call.
"""
for i in range(num_activations):
activate_container(
f"01BENCHACTIVATE{i:011d}",
"/workspace",
run_command=_mock_runner,
)
clear_lifecycle_registry()
def teardown(self, num_activations: int) -> None:
"""Clear registry after each timing iteration (safety net)."""
clear_lifecycle_registry()
class TimeJsonParsing:
"""Benchmark devcontainer up JSON output parsing."""
timeout = 10
def setup(self) -> None:
"""Create sample JSON output."""
self.valid_json = json.dumps(
{
"outcome": "success",
"containerId": "aabbccddee0011223344",
"remoteWorkspaceFolder": "/workspaces/project",
}
)
self.invalid_json = "not valid json {{"
def time_parse_valid_json(self) -> None:
"""Time parsing valid JSON output."""
for _ in range(1000):
_parse_devcontainer_up_output(self.valid_json)
def time_parse_invalid_json(self) -> None:
"""Time parsing invalid JSON output."""
for _ in range(1000):
_parse_devcontainer_up_output(self.invalid_json)
class TimeRegistryOperations:
"""Benchmark lifecycle registry get/set/list operations."""
timeout = 30
def setup(self) -> None:
"""Pre-populate registry with trackers."""
clear_lifecycle_registry()
for i in range(100):
tracker = ContainerLifecycleTracker(
resource_id=f"01BENCHREG{i:016d}",
current_state=ContainerLifecycleState.RUNNING
if i % 2 == 0
else ContainerLifecycleState.DETECTED,
)
set_lifecycle_tracker(tracker)
def teardown(self) -> None:
"""Clear registry."""
clear_lifecycle_registry()
def time_get_tracker(self) -> None:
"""Time registry lookup."""
for i in range(1000):
get_lifecycle_tracker(f"01BENCHREG{(i % 100):016d}")
def time_list_active(self) -> None:
"""Time listing active containers."""
for _ in range(100):
list_active_containers()