Files
cleveragents-core/robot/helper_apply_pipeline.py
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

216 lines
6.2 KiB
Python

"""Robot Framework helper for apply pipeline smoke tests.
Provides a CLI-style interface for Robot to invoke validation-gated
apply operations. Exit code 0 = success, 1 = failure.
Usage:
python robot/helper_apply_pipeline.py apply-passes
python robot/helper_apply_pipeline.py apply-blocked
python robot/helper_apply_pipeline.py already-applied
python robot/helper_apply_pipeline.py empty-changeset
python robot/helper_apply_pipeline.py model-checks
"""
from __future__ import annotations
import sys
from pathlib import Path
from typing import Any
from unittest.mock import MagicMock
# Ensure the src directory is on the import path.
_SRC = str(Path(__file__).resolve().parents[1] / "src")
if _SRC not in sys.path:
sys.path.insert(0, _SRC)
from cleveragents.application.services.plan_apply_service import ( # noqa: E402
ApplyOutcome,
ApplyResult,
PlanApplyService,
)
from cleveragents.domain.models.core.change import ( # noqa: E402
ChangeEntry,
ChangeOperation,
SpecChangeSet,
)
from cleveragents.domain.models.core.plan import ( # noqa: E402
PlanPhase,
PlanTimestamps,
ProcessingState,
)
_PLAN_ID = "01PLANTEST000000000000001"
def _make_plan(
*,
phase: PlanPhase = PlanPhase.EXECUTE,
state: ProcessingState = ProcessingState.COMPLETE,
changeset_id: str | None = "CS001",
validation_summary: dict[str, Any] | None = None,
is_terminal: bool = False,
) -> MagicMock:
plan = MagicMock()
plan.identity.plan_id = _PLAN_ID
plan.phase = phase
plan.processing_state = state
plan.changeset_id = changeset_id
plan.validation_summary = validation_summary
plan.is_terminal = is_terminal
plan.error_details = None
plan.timestamps = PlanTimestamps()
return plan
def _make_changeset(n: int = 1) -> 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/test-tool",
operation=ChangeOperation.MODIFY,
path=f"src/file_{i}.py",
before_hash=f"b{i}",
after_hash=f"a{i}",
)
)
return cs
def _make_service(
plan: MagicMock, changeset: SpecChangeSet | None = None
) -> PlanApplyService:
lifecycle = MagicMock()
lifecycle.get_plan.return_value = plan
lifecycle.complete_apply.return_value = plan
lifecycle.constrain_apply.return_value = plan
lifecycle.commit_plan = MagicMock()
store = MagicMock()
store.get.return_value = changeset
return PlanApplyService(lifecycle_service=lifecycle, changeset_store=store)
def _cmd_apply_passes() -> int:
"""Apply with all validations passing."""
cs = _make_changeset(3)
plan = _make_plan(
changeset_id=cs.changeset_id,
validation_summary={
"total": 2,
"required_passed": 2,
"required_failed": 0,
},
)
svc = _make_service(plan, cs)
result = svc.apply_with_validation_gate(_PLAN_ID)
assert result.outcome == ApplyOutcome.APPLIED, f"Got {result.outcome}"
assert result.files_changed == 3
assert "applied successfully" in result.message
print("apply-passes-ok")
return 0
def _cmd_apply_blocked() -> int:
"""Apply blocked by validation failure."""
cs = _make_changeset(2)
plan = _make_plan(
changeset_id=cs.changeset_id,
validation_summary={
"total": 3,
"required_passed": 1,
"required_failed": 2,
},
)
svc = _make_service(plan, cs)
result = svc.apply_with_validation_gate(_PLAN_ID)
assert result.outcome == ApplyOutcome.CONSTRAINED, f"Got {result.outcome}"
assert result.validations_failed == 2
assert "Apply refused" in result.message
print("apply-blocked-ok")
return 0
def _cmd_already_applied() -> int:
"""Re-apply on already applied plan."""
cs = _make_changeset(1)
plan = _make_plan(
phase=PlanPhase.APPLY,
state=ProcessingState.APPLIED,
is_terminal=True,
)
svc = _make_service(plan, cs)
result = svc.apply_with_validation_gate(_PLAN_ID)
assert result.outcome == ApplyOutcome.ALREADY_APPLIED, f"Got {result.outcome}"
assert "already been applied" in result.message
print("already-applied-ok")
return 0
def _cmd_empty_changeset() -> int:
"""Apply blocked on empty changeset."""
cs = _make_changeset(0)
plan = _make_plan(changeset_id=cs.changeset_id)
svc = _make_service(plan, cs)
result = svc.apply_with_validation_gate(_PLAN_ID)
assert result.outcome == ApplyOutcome.BLOCKED_EMPTY, f"Got {result.outcome}"
assert "empty ChangeSet" in result.message
print("empty-changeset-ok")
return 0
def _cmd_model_checks() -> int:
"""Verify ApplyOutcome and ApplyResult models."""
# Check all enum values exist
assert ApplyOutcome.APPLIED == "applied"
assert ApplyOutcome.CONSTRAINED == "constrained"
assert ApplyOutcome.ALREADY_APPLIED == "already_applied"
assert ApplyOutcome.BLOCKED_EMPTY == "blocked_empty"
# Check ApplyResult construction
result = ApplyResult(
outcome=ApplyOutcome.APPLIED,
plan_id="TEST",
message="ok",
files_changed=5,
validations_total=3,
validations_passed=3,
validations_failed=0,
)
assert result.outcome == ApplyOutcome.APPLIED
assert result.plan_id == "TEST"
assert result.files_changed == 5
print("model-checks-ok")
return 0
def main() -> int:
if len(sys.argv) < 2:
print(
"Usage: helper_apply_pipeline.py "
"<apply-passes|apply-blocked|already-applied|"
"empty-changeset|model-checks>"
)
return 1
cmd = sys.argv[1]
if cmd == "apply-passes":
return _cmd_apply_passes()
if cmd == "apply-blocked":
return _cmd_apply_blocked()
if cmd == "already-applied":
return _cmd_already_applied()
if cmd == "empty-changeset":
return _cmd_empty_changeset()
if cmd == "model-checks":
return _cmd_model_checks()
print(f"Unknown command: {cmd}")
return 1
if __name__ == "__main__":
sys.exit(main())