woogi
d37ac8c1c7
- ENABLE_CODE_REVIEW flag (default off): skips code/ADA/jurisdiction review path in both pipelines; nothing deleted, one env flag to restore. - Per-sheet Drawing Integrity QA wave (agent + classic, default on): dangling refs, on-sheet contradictions, dimension sanity, missing sheet essentials, tag hygiene. New DrawingIntegrityAgent + classic stage. - Broadened conflict critic: intra-sheet + same-discipline contradictions, not just cross-discipline. - Wave 6.5 Brain-directed clarification (bounded hub-and-spoke): Brain names uncertain findings, verify_evidence requests route through the wave-5b verifier; refuted findings suppressed. One planning call + capped verifies, single iteration. Shared _build_verify_scopes across 5b and 6.5. - Config knobs, .env.example, frontend copy, tests (182 passing).
103 lines
4.3 KiB
Python
103 lines
4.3 KiB
Python
"""Flag-gating tests: ENABLE_CODE_REVIEW off skips code, drawing_integrity runs.
|
|
|
|
Runner-level smoke tests using stubbed agents (same pattern as
|
|
test_wave5b_suppression). Verifies the code/ADA wave is skipped when
|
|
ENABLE_CODE_REVIEW is false and the Drawing Integrity wave feeds findings
|
|
into the report by_stage counters.
|
|
"""
|
|
|
|
import backend.agents.runner as runner_mod
|
|
from backend import config
|
|
from backend.agents.base import AgentResult
|
|
from backend.agents.runner import run_agent_pipeline
|
|
|
|
|
|
def _stub_agent(artifacts):
|
|
return lambda usage: type("S", (), {
|
|
"name": "stub",
|
|
"run": lambda self, scope: AgentResult(
|
|
scope_id=scope.scope_id, artifacts=list(artifacts)),
|
|
})()
|
|
|
|
|
|
def _integrity_finding():
|
|
return {
|
|
"issue_id": "DI-1", "severity": "high", "confidence": "high",
|
|
"source_stage": "drawing_integrity", "sheets": ["A101"],
|
|
"category": "dangling_reference",
|
|
"description": "Detail callout 5/A101 has no detail 5 on this sheet",
|
|
"evidence": [{"sheet": "A101", "source_text": "5/A101"}],
|
|
}
|
|
|
|
|
|
def _patch(monkeypatch, code_should_raise):
|
|
monkeypatch.setattr(
|
|
runner_mod, "convert_pdf_to_images",
|
|
lambda path: [{"page_number": 1, "base64": "QUJD"}])
|
|
# Sheet has 3+ assertions so the integrity wave does NOT skip it.
|
|
monkeypatch.setattr(runner_mod, "SheetExtractorAgent", _stub_agent([
|
|
{"sheet_number": "A101", "page_number": 1, "level": "1",
|
|
"discipline": "A", "assertions": [
|
|
{"text": "5/A101", "object_type": "detail_marker"},
|
|
{"text": "ROOM 101", "object_type": "room"},
|
|
{"text": "DOOR 101A", "object_type": "door"},
|
|
]},
|
|
]))
|
|
monkeypatch.setattr(runner_mod, "SheetIndexAgent", _stub_agent([{}]))
|
|
monkeypatch.setattr(runner_mod, "JurisdictionAgent", _stub_agent([{}]))
|
|
monkeypatch.setattr(runner_mod, "LinkerAgent", _stub_agent([]))
|
|
monkeypatch.setattr(runner_mod, "ConflictCriticAgent", _stub_agent([]))
|
|
|
|
def code_boom(usage):
|
|
if code_should_raise:
|
|
raise AssertionError("CodeAgent must not run when gated off")
|
|
return _stub_agent([])(usage)
|
|
monkeypatch.setattr(runner_mod, "CodeAgent", code_boom)
|
|
|
|
monkeypatch.setattr(runner_mod, "DrawingIntegrityAgent",
|
|
_stub_agent([_integrity_finding()]))
|
|
monkeypatch.setattr(runner_mod, "ConstructabilityAgent", _stub_agent([]))
|
|
monkeypatch.setattr(runner_mod, "CompletenessAgent", _stub_agent([]))
|
|
monkeypatch.setattr(
|
|
runner_mod, "BrainAgent",
|
|
lambda usage: type("B", (), {
|
|
"run": lambda self, findings, si, ju: (list(findings), []),
|
|
"plan_clarifications": lambda self, prioritized: []})())
|
|
# Stub the wave-5b verifier so the high-severity integrity finding is
|
|
# confirmed (never a live network call).
|
|
monkeypatch.setattr(
|
|
"backend.agents.verifier.call_json",
|
|
lambda **kwargs: {"verdicts": [
|
|
{"sheet": "A101", "source_text": "5/A101",
|
|
"verdict": "confirmed", "actual_text": None, "notes": None},
|
|
]})
|
|
|
|
|
|
def test_code_gated_off_integrity_on(monkeypatch, tmp_path):
|
|
monkeypatch.setattr(config, "ENABLE_CODE_REVIEW", False)
|
|
monkeypatch.setattr(config, "ENABLE_DRAWING_INTEGRITY", True)
|
|
_patch(monkeypatch, code_should_raise=True)
|
|
pdf = tmp_path / "d.pdf"
|
|
pdf.write_bytes(b"%PDF-1.4\n")
|
|
report = run_agent_pipeline(str(pdf), out_dir=str(tmp_path),
|
|
require_review=False)
|
|
by_stage = report["summary"]["by_stage"]
|
|
assert by_stage["code"] == 0
|
|
assert by_stage["drawing_integrity"] == 1
|
|
# The integrity finding survived into the validated set.
|
|
assert any(f.get("issue_id") == "DI-1"
|
|
for f in report.get("validated_issues") or [])
|
|
|
|
|
|
def test_code_enabled_runs(monkeypatch, tmp_path):
|
|
monkeypatch.setattr(config, "ENABLE_CODE_REVIEW", True)
|
|
monkeypatch.setattr(config, "ENABLE_DRAWING_INTEGRITY", True)
|
|
_patch(monkeypatch, code_should_raise=False)
|
|
# build_code_scopes runs on the real sheet; CodeAgent is stubbed to []
|
|
pdf = tmp_path / "d.pdf"
|
|
pdf.write_bytes(b"%PDF-1.4\n")
|
|
report = run_agent_pipeline(str(pdf), out_dir=str(tmp_path),
|
|
require_review=False)
|
|
# No crash; integrity still reported.
|
|
assert report["summary"]["by_stage"]["drawing_integrity"] == 1
|