Files
cleveragents-core/benchmarks/checkpoint_rollback_bench.py
freemo 583e6b7ea2
CI / benchmark-publish (pull_request) Has been skipped
CI / lint (pull_request) Successful in 14s
CI / build (pull_request) Successful in 16s
CI / quality (pull_request) Successful in 17s
CI / security (pull_request) Successful in 36s
CI / typecheck (pull_request) Successful in 54s
CI / unit_tests (pull_request) Successful in 2m39s
CI / integration_tests (pull_request) Successful in 3m10s
CI / docker (pull_request) Successful in 40s
CI / coverage (pull_request) Successful in 5m0s
CI / lint (push) Successful in 14s
CI / build (push) Successful in 15s
CI / quality (push) Successful in 16s
CI / security (push) Successful in 34s
CI / typecheck (push) Successful in 35s
CI / benchmark-regression (push) Has been skipped
CI / unit_tests (push) Successful in 2m23s
CI / docker (push) Successful in 38s
CI / integration_tests (push) Successful in 3m8s
CI / coverage (push) Successful in 5m10s
CI / benchmark-publish (push) Successful in 16m26s
CI / benchmark-regression (pull_request) Successful in 30m12s
feat(correcting-plans): implement Predictive Error Prevention (Layer 4) with Error Pattern Database
Implement spec-mandated Layer 4 Predictive Error Prevention system:

- ErrorPattern domain model with pattern text, historical failures,
  preventive checks, frequency tracking, and keyword-based matching.
- ErrorPatternRepository with in-memory CRUD + context-matching query.
- ErrorPatternService with record_failure(), match_patterns(), and
  get_statistics() methods.
- Wire into plan execution via plan_lifecycle_service pre-execution hook.
- Add error pattern statistics to CLI diagnostics output.

Behave BDD: 11 scenarios covering recording, matching, formatting, stats.
Robot Framework: 3 integration smoke tests.
ASV benchmarks: pattern matching performance.

ISSUES CLOSED: #571
2026-03-08 21:53:21 -04:00

131 lines
4.3 KiB
Python

"""Airspeed Velocity benchmarks for checkpoint and rollback operations.
Measures checkpoint creation, listing, rollback, pruning, and metadata
overhead across varying checkpoint counts.
"""
from __future__ import annotations
from typing import ClassVar
from cleveragents.application.services.checkpoint_service import CheckpointService
from cleveragents.domain.models.core.checkpoint import CheckpointRetentionPolicy
_PLAN_ID = "01ARZ3NDEKTSV4RRFFQ69G5FAV"
# ---------------------------------------------------------------------------
# Checkpoint creation benchmarks
# ---------------------------------------------------------------------------
class CheckpointCreateSuite:
"""Benchmark checkpoint creation at varying counts."""
def setup(self) -> None:
"""Prepare a fresh service instance."""
self.svc = CheckpointService()
def time_create_single(self) -> None:
"""Time creating a single checkpoint."""
self.svc.create_checkpoint(_PLAN_ID, "commit-abc")
def time_create_ten(self) -> None:
"""Time creating 10 checkpoints."""
svc = CheckpointService()
for i in range(10):
svc.create_checkpoint(_PLAN_ID, f"commit-{i}")
def time_create_hundred(self) -> None:
"""Time creating 100 checkpoints."""
svc = CheckpointService()
for i in range(100):
svc.create_checkpoint(_PLAN_ID, f"commit-{i}")
# ---------------------------------------------------------------------------
# Checkpoint listing benchmarks
# ---------------------------------------------------------------------------
class CheckpointListSuite:
"""Benchmark listing checkpoints at varying plan sizes."""
params: ClassVar[list[int]] = [10, 50, 100]
param_names: ClassVar[list[str]] = ["checkpoint_count"]
def setup(self, checkpoint_count: int) -> None:
"""Populate service with checkpoints."""
self.svc = CheckpointService()
for i in range(checkpoint_count):
self.svc.create_checkpoint(_PLAN_ID, f"commit-{i}")
def time_list(self, checkpoint_count: int) -> None:
"""Time listing all checkpoints for a plan."""
self.svc.list_checkpoints(_PLAN_ID)
# ---------------------------------------------------------------------------
# Rollback benchmarks
# ---------------------------------------------------------------------------
class RollbackSuite:
"""Benchmark rollback operations."""
def setup(self) -> None:
"""Prepare a service with sandbox and checkpoints."""
self.svc = CheckpointService()
self.svc.register_sandbox(_PLAN_ID, "sandbox-path")
self.cp = self.svc.create_checkpoint(_PLAN_ID, "commit-abc")
def time_rollback(self) -> None:
"""Time a single rollback operation."""
self.svc.rollback_to_checkpoint(_PLAN_ID, self.cp.checkpoint_id)
# ---------------------------------------------------------------------------
# Prune benchmarks
# ---------------------------------------------------------------------------
class PruneSuite:
"""Benchmark checkpoint pruning at varying counts."""
params: ClassVar[list[int]] = [20, 50, 100]
param_names: ClassVar[list[str]] = ["checkpoint_count"]
def setup(self, checkpoint_count: int) -> None:
"""Populate service with checkpoints."""
self.svc = CheckpointService()
for i in range(checkpoint_count):
self.svc.create_checkpoint(_PLAN_ID, f"commit-{i}")
def time_prune_to_five(self, checkpoint_count: int) -> None:
"""Time pruning down to 5 checkpoints."""
policy = CheckpointRetentionPolicy(max_checkpoints=5, auto_prune=True)
self.svc.prune_checkpoints(_PLAN_ID, policy)
# ---------------------------------------------------------------------------
# Metadata benchmarks
# ---------------------------------------------------------------------------
class MetadataSuite:
"""Benchmark checkpoint creation with metadata."""
def setup(self) -> None:
"""Prepare service."""
self.svc = CheckpointService()
def time_create_with_metadata(self) -> None:
"""Time creating a checkpoint with full metadata."""
self.svc.create_checkpoint(
_PLAN_ID,
"commit-xyz",
reason="pre-execution snapshot",
source_tool="lint-check",
phase="execute",
)