Files
cleveragents-core/benchmarks/apply_pipeline_bench.py
T
brent.edwards eb46f0ff54
CI / push-validation (push) Successful in 40s
CI / helm (push) Successful in 44s
CI / build (push) Successful in 1m14s
CI / lint (push) Successful in 1m18s
CI / quality (push) Successful in 1m36s
CI / e2e_tests (push) Successful in 1m19s
CI / typecheck (push) Successful in 2m22s
CI / security (push) Successful in 2m23s
CI / benchmark-regression (push) Failing after 41s
CI / integration_tests (push) Successful in 4m46s
CI / unit_tests (push) Failing after 20m13s
CI / benchmark-publish (push) Failing after 28m28s
CI / coverage (push) Has been cancelled
CI / docker (push) Has been cancelled
CI / status-check (push) Has been cancelled
fix(plan): add tier hydration and improve architecture review output (#10938)
## Summary

This PR fixes issue #10878 where architecture reviews were truncated because the regex pattern for parsing file output would stop at the first ``` encountered in the Markdown report.

## Changes

- Change file delimiters from ``` to >>>>>>>/<<<<<<< to avoid Markdown conflicts
- Add tier hydration before strategize phase in plan_executor.py
- Increase max_tokens to 16384 in llm_actors.py for longer outputs
- Increase context_max_tokens_hot from 16000 to 32000 in settings.py
- Fix get_hot_view → get_hot_fragments in strategy_actor.py and plan_executor.py
- Add opencode to skip directories in context_tier_hydrator.py
- Change sandbox output location to plan-output/ directory in plan.py
- Add get_context_summary stub method to acms_service.py

## Testing

Run architecture review action and verify the output report is complete with all sections.

Reviewed-on: #10938
2026-05-19 12:43:34 +00:00

170 lines
4.7 KiB
Python

"""ASV benchmarks for the validation-gated apply pipeline.
Measures the performance of:
- ApplyResult model construction
- Validation count extraction
- apply_with_validation_gate() with mock lifecycle
"""
from __future__ import annotations
import sys
from pathlib import Path
from typing import Any
from unittest.mock import MagicMock
try:
from cleveragents.application.services.plan_apply_service import (
ApplyOutcome,
ApplyResult,
PlanApplyService,
)
from cleveragents.domain.models.core.change import (
ChangeEntry,
ChangeOperation,
SpecChangeSet,
)
from cleveragents.domain.models.core.plan import (
PlanPhase,
PlanTimestamps,
ProcessingState,
)
except ModuleNotFoundError:
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
from cleveragents.application.services.plan_apply_service import (
ApplyOutcome,
ApplyResult,
PlanApplyService,
)
from cleveragents.domain.models.core.change import (
ChangeEntry,
ChangeOperation,
SpecChangeSet,
)
from cleveragents.domain.models.core.plan import (
PlanPhase,
PlanTimestamps,
ProcessingState,
)
_PLAN_ID = "01BENCHPLAN0000000000001"
def _make_plan(
*,
changeset_id: str = "CS001",
validation_summary: dict[str, Any] | None = None,
) -> MagicMock:
plan = MagicMock()
plan.identity.plan_id = _PLAN_ID
plan.phase = PlanPhase.EXECUTE
plan.processing_state = ProcessingState.COMPLETE
plan.changeset_id = changeset_id
plan.validation_summary = validation_summary
plan.is_terminal = False
plan.error_details = None
plan.timestamps = PlanTimestamps()
return plan
def _make_changeset(n: int = 10) -> SpecChangeSet:
cs = SpecChangeSet(plan_id=_PLAN_ID)
for i in range(n):
cs.add_change(
ChangeEntry(
plan_id=_PLAN_ID,
resource_id="RES001",
tool_name="builtin/bench-tool",
operation=ChangeOperation.MODIFY,
path=f"src/mod_{i:04d}.py",
before_hash=f"b{i}",
after_hash=f"a{i}",
)
)
return cs
def _make_service(plan: MagicMock, changeset: SpecChangeSet) -> PlanApplyService:
lifecycle = MagicMock()
lifecycle.get_plan.return_value = plan
lifecycle.complete_apply.return_value = plan
lifecycle.commit_plan = MagicMock()
store = MagicMock()
store.get.return_value = changeset
return PlanApplyService(lifecycle_service=lifecycle, changeset_store=store)
class ApplyResultSuite:
"""Benchmark ApplyResult model construction."""
def time_result_construction_applied(self) -> None:
ApplyResult(
outcome=ApplyOutcome.APPLIED,
plan_id=_PLAN_ID,
message="applied ok",
files_changed=10,
validations_total=5,
validations_passed=5,
validations_failed=0,
)
def time_result_construction_constrained(self) -> None:
ApplyResult(
outcome=ApplyOutcome.CONSTRAINED,
plan_id=_PLAN_ID,
message="blocked",
validations_total=5,
validations_passed=3,
validations_failed=2,
)
class ApplyValidationCountSuite:
"""Benchmark validation count extraction."""
def setup(self) -> None:
self.summary: dict[str, Any] = {
"total": 100,
"required_passed": 80,
"required_failed": 20,
}
self.empty_summary: dict[str, Any] | None = None
def time_extract_counts(self) -> None:
PlanApplyService._extract_validation_counts(self.summary)
def time_extract_counts_none(self) -> None:
PlanApplyService._extract_validation_counts(self.empty_summary)
class ApplyGateSuite:
"""Benchmark the full apply_with_validation_gate flow."""
def setup(self) -> None:
cs = _make_changeset(20)
self.plan_pass = _make_plan(
changeset_id=cs.changeset_id,
validation_summary={
"total": 5,
"required_passed": 5,
"required_failed": 0,
},
)
self.plan_fail = _make_plan(
changeset_id=cs.changeset_id,
validation_summary={
"total": 5,
"required_passed": 3,
"required_failed": 2,
},
)
self.svc_pass = _make_service(self.plan_pass, cs)
self.svc_fail = _make_service(self.plan_fail, cs)
def time_apply_gate_pass(self) -> None:
self.svc_pass.apply_with_validation_gate(_PLAN_ID)
def time_apply_gate_fail(self) -> None:
self.svc_fail.apply_with_validation_gate(_PLAN_ID)