feat: refocus on drawings — code/ADA gated off, drawing-integrity wave, Brain-directed clarification
Docker Release / build-and-push (push) Successful in 1m8s
Docker Release / release (push) Skipped

- 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).
This commit is contained in:
2026-08-20 15:10:32 -05:00
parent bae608a505
commit d37ac8c1c7
22 changed files with 1917 additions and 63 deletions
+198
View File
@@ -0,0 +1,198 @@
"""Wave 6.5 Brain-directed clarification: planning unit + runner integration."""
import backend.agents.brain as brain_mod
import backend.agents.runner as runner_mod
from backend import config
from backend.agents.base import AgentResult
from backend.agents.base import AgentUsage
from backend.agents.brain import BrainAgent
from backend.agents.runner import run_agent_pipeline
# --- plan_clarifications unit tests ---------------------------------------
def _finding(issue_id, **kw):
base = {"issue_id": issue_id, "severity": "medium", "confidence": "low",
"source_stage": "conflict", "description": "d",
"evidence": [{"sheet": "A1", "source_text": "x"}]}
base.update(kw)
return base
def test_plan_caps_and_filters_unknown_ids(monkeypatch):
monkeypatch.setattr(config, "BRAIN_CLARIFY_MAX_REQUESTS", 2)
monkeypatch.setattr(brain_mod, "call_json", lambda **k: {"requests": [
{"issue_id": "A", "request_type": "verify_evidence", "reason": "thin"},
{"issue_id": "GHOST", "request_type": "verify_evidence", "reason": "x"},
{"issue_id": "B", "request_type": "verify_evidence", "reason": "amb"},
{"issue_id": "C", "request_type": "verify_evidence", "reason": "over cap"},
]})
prioritized = [_finding("A"), _finding("B"), _finding("C")]
reqs = BrainAgent(AgentUsage()).plan_clarifications(prioritized)
ids = [r["issue_id"] for r in reqs]
assert ids == ["A", "B"] # GHOST filtered, capped at 2
def test_plan_skips_already_verified(monkeypatch):
monkeypatch.setattr(config, "BRAIN_CLARIFY_MAX_REQUESTS", 8)
captured = {}
def fake(**kwargs):
captured["user_text"] = kwargs["user_text"]
return {"requests": [
{"issue_id": "A", "request_type": "verify_evidence", "reason": "y"},
]}
monkeypatch.setattr(brain_mod, "call_json", fake)
prioritized = [
_finding("A"),
_finding("V", verification={"status": "confirmed", "verdicts": []}),
]
reqs = BrainAgent(AgentUsage()).plan_clarifications(prioritized)
assert [r["issue_id"] for r in reqs] == ["A"]
# The already-verified finding must not even be offered to the model.
assert '"V"' not in captured["user_text"]
def test_plan_empty_on_call_failure(monkeypatch):
monkeypatch.setattr(config, "BRAIN_CLARIFY_MAX_REQUESTS", 8)
def boom(**k):
raise RuntimeError("brain down")
monkeypatch.setattr(brain_mod, "call_json", boom)
assert BrainAgent(AgentUsage()).plan_clarifications([_finding("A")]) == []
def test_plan_no_requests_returns_empty(monkeypatch):
monkeypatch.setattr(config, "BRAIN_CLARIFY_MAX_REQUESTS", 8)
monkeypatch.setattr(brain_mod, "call_json", lambda **k: {"requests": []})
assert BrainAgent(AgentUsage()).plan_clarifications([_finding("A")]) == []
# --- runner-level integration ---------------------------------------------
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 _patch_pipeline(monkeypatch, brain_finding, plan_requests):
monkeypatch.setattr(
runner_mod, "convert_pdf_to_images",
lambda path: [{"page_number": 1, "base64": "QUJD"}])
monkeypatch.setattr(runner_mod, "SheetExtractorAgent", _stub_agent([
{"sheet_number": "S401", "page_number": 1, "level": "roof",
"discipline": "S", "assertions": [
{"text": "(2) 2x6 STUD PACK", "object_type": "framing"},
{"text": "HSS16X4 beam", "object_type": "framing"},
]},
]))
monkeypatch.setattr(runner_mod, "SheetIndexAgent", _stub_agent([{}]))
monkeypatch.setattr(runner_mod, "JurisdictionAgent", _stub_agent([{}]))
monkeypatch.setattr(runner_mod, "LinkerAgent", _stub_agent([
{"key": "c1", "location": "roof beam pocket", "assertions": []},
]))
# A filler conflict finding so memory["findings"] is non-empty and wave 6
# actually invokes Brain.run (which our stub replaces with brain_finding).
monkeypatch.setattr(runner_mod, "ConflictCriticAgent", _stub_agent([
{"issue_id": "FILLER", "severity": "low", "confidence": "low",
"source_stage": "conflict", "sheets": [], "description": "filler",
"evidence": []},
]))
monkeypatch.setattr(runner_mod, "CodeAgent", _stub_agent([]))
monkeypatch.setattr(runner_mod, "ConstructabilityAgent", _stub_agent([]))
monkeypatch.setattr(runner_mod, "CompletenessAgent", _stub_agent([]))
monkeypatch.setattr(runner_mod, "DrawingIntegrityAgent", _stub_agent([]))
# Brain.run returns our finding; plan_clarifications returns the requests.
monkeypatch.setattr(
runner_mod, "BrainAgent",
lambda usage: type("B", (), {
"run": lambda self, findings, si, ju: ([dict(brain_finding)], []),
"plan_clarifications": lambda self, prioritized: list(plan_requests),
})())
def test_brain_clarify_refutes_and_suppresses(monkeypatch, tmp_path):
"""Brain flags a MEDIUM finding wave-5b's severity gate skipped; the
clarification verifier refutes it, so it moves to suppressed_issues."""
monkeypatch.setattr(config, "ENABLE_BRAIN_CLARIFY", True)
finding = {
"issue_id": "M1", "severity": "medium", "confidence": "low",
"source_stage": "conflict", "sheets": ["S401"],
"description": "beam bears on (2) 2x6 stud pack",
"evidence": [{"sheet": "S401", "source_text": "(2) 2x6 STUD PACK"}],
}
_patch_pipeline(monkeypatch, finding, [
{"issue_id": "M1", "request_type": "verify_evidence", "reason": "misread?"},
])
# The clarification verifier returns a 'corrected' verdict -> refuted.
monkeypatch.setattr(
"backend.agents.verifier.call_json",
lambda **kwargs: {"verdicts": [
{"sheet": "S401", "source_text": "(2) 2x6 STUD PACK",
"verdict": "corrected", "actual_text": "(5) 2x6 STUD PACK",
"notes": "reads (5)"},
]})
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)
validated = report.get("validated_issues") or []
assert all(f.get("issue_id") != "M1" for f in validated) # dropped
assert [f["issue_id"] for f in report["suppressed_issues"]] == ["M1"]
assert report["suppressed_issues"][0]["verification"]["status"] == "refuted"
def test_brain_clarify_confirms_keeps_finding(monkeypatch, tmp_path):
monkeypatch.setattr(config, "ENABLE_BRAIN_CLARIFY", True)
finding = {
"issue_id": "M2", "severity": "medium", "confidence": "low",
"source_stage": "conflict", "sheets": ["S401"],
"description": "beam bears on (5) 2x6 stud pack",
"evidence": [{"sheet": "S401", "source_text": "(5) 2x6 STUD PACK"}],
}
_patch_pipeline(monkeypatch, finding, [
{"issue_id": "M2", "request_type": "verify_evidence", "reason": "check"},
])
monkeypatch.setattr(
"backend.agents.verifier.call_json",
lambda **kwargs: {"verdicts": [
{"sheet": "S401", "source_text": "(5) 2x6 STUD PACK",
"verdict": "confirmed", "actual_text": None, "notes": None},
]})
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)
validated = report.get("validated_issues") or []
kept = [f for f in validated if f.get("issue_id") == "M2"]
assert len(kept) == 1
assert kept[0]["verification"]["status"] == "confirmed"
assert report["suppressed_issues"] == []
def test_brain_clarify_disabled_is_noop(monkeypatch, tmp_path):
monkeypatch.setattr(config, "ENABLE_BRAIN_CLARIFY", False)
finding = {
"issue_id": "M3", "severity": "medium", "confidence": "low",
"source_stage": "conflict", "sheets": ["S401"],
"description": "d", "evidence": [{"sheet": "S401", "source_text": "t"}],
}
# plan_clarifications should never be consulted; give it a bomb to prove it.
def _bomb(self, prioritized):
raise AssertionError("plan_clarifications must not run when disabled")
_patch_pipeline(monkeypatch, finding, [])
monkeypatch.setattr(
runner_mod, "BrainAgent",
lambda usage: type("B", (), {
"run": lambda self, findings, si, ju: ([dict(finding)], []),
"plan_clarifications": _bomb})())
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)
validated = report.get("validated_issues") or []
assert any(f.get("issue_id") == "M3" for f in validated)