fix: wave 5b review blockers - suppressed memory key, finalizer merge, zero-image guard

2026-08-10 12:21:41 -05:00
parent 3df359500c
commit b174b531cd
5 changed files with 126 additions and 13 deletions
@@ -0,0 +1,86 @@
+"""Runner-level wave-5b tests: suppression path and zero-image guard."""
+
+import backend.agents.runner as runner_mod
+from backend.agents.base import AgentResult
+from backend.agents.runner import run_agent_pipeline
+
+
+def _finding(sheets):
+    return {
+        "issue_id": "C1", "severity": "critical", "confidence": "high",
+        "source_stage": "constructability", "sheets": sheets,
+        "description": "HSS16x4 on (2) 2x6 STUD PACK is unbuildable",
+        "evidence": [{"sheet": sheets[0], "source_text": "(2) 2x6 STUD PACK"}],
+    }
+
+
+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, finding):
+    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": []},
+    ]))
+    monkeypatch.setattr(runner_mod, "ConflictCriticAgent", _stub_agent([]))
+    monkeypatch.setattr(runner_mod, "CodeAgent", _stub_agent([]))
+    monkeypatch.setattr(runner_mod, "ConstructabilityAgent", _stub_agent([finding]))
+    monkeypatch.setattr(runner_mod, "CompletenessAgent", _stub_agent([]))
+    monkeypatch.setattr(
+        runner_mod, "BrainAgent",
+        lambda usage: type("B", (), {
+            "run": lambda self, findings, sheet_index, jurisdiction:
+                (list(findings), [])})())
+
+
+def test_refuted_finding_is_suppressed_not_crash(monkeypatch, tmp_path):
+    """Regression: memory.replace("suppressed", ...) must not KeyError."""
+    _patch_pipeline(monkeypatch, _finding(["S401"]))
+    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": "callout reads (5)"},
+        ]})
+    pdf = tmp_path / "dummy.pdf"
+    pdf.write_bytes(b"%PDF-1.4\n")
+    report = run_agent_pipeline(str(pdf), out_dir=str(tmp_path),
+                                require_review=False)
+    assert [f["issue_id"] for f in report["suppressed_issues"]] == ["C1"]
+    assert report["suppressed_issues"][0]["verification"]["status"] == "refuted"
+
+
+def test_zero_image_finding_is_not_suppressed(monkeypatch, tmp_path):
+    """A finding whose sheets resolve to no page images must not be judged
+    (and must never be refuted) without pixels."""
+    _patch_pipeline(monkeypatch, _finding(["S999"]))  # no such sheet
+    monkeypatch.setattr(
+        "backend.agents.verifier.call_json",
+        lambda **kwargs: {"verdicts": [
+            {"sheet": "S999", "source_text": "(2) 2x6 STUD PACK",
+             "verdict": "not_found", "actual_text": None, "notes": None},
+        ]})
+    pdf = tmp_path / "dummy.pdf"
+    pdf.write_bytes(b"%PDF-1.4\n")
+    report = run_agent_pipeline(str(pdf), out_dir=str(tmp_path),
+                                require_review=False)
+    assert report["suppressed_issues"] == []
+    validated = report.get("validated_issues") or []
+    assert any(f.get("issue_id") == "C1" for f in validated)