{"schema": 1, "run": {"slug": "mzp-eval-2026-09-30", "date": "2026-09-30", "startedAt": "2026-09-30T09:33:41Z", "finishedAt": "2026-09-30T09:36:41Z", "target": "https://publisher.maierzone.de", "stages": ["deterministic", "llm"], "tasksCommit": "f5a4a06", "baseline": "mzp-eval-2026-09-28", "gate": "gruen", "counts": {"gruen": 12, "gelb": 0, "rot": 0, "UNEXPECTED_PASS": 0, "ABGEBROCHEN": 0}, "unexpectedPass": []}, "deterministic": [{"id": "art-a11y-check", "family": "artifact", "knownIssue": null, "status": "gruen", "calls": 1, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": null}, "silent": {}, "ms": null}, {"id": "art-asset-bundle", "family": "artifact", "knownIssue": null, "status": "gruen", "calls": 3, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": null}, "silent": {}, "ms": null}, {"id": "art-broken", "family": "artifact", "knownIssue": null, "status": "gruen", "calls": 2, "failedAttempts": {"CONSOLE_ERROR": 2, "PAGE_EXCEPTION": 1, "RESOURCE_FAILED": 2, "PAGE_NOT_FOUND": 1}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": false, "visualProof": null}, "silent": {}, "ms": null}, {"id": "art-live-report", "family": "artifact", "knownIssue": null, "status": "gruen", "calls": 3, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": null}, "silent": {}, "ms": null, "note": "Alle drei Schritte bestanden (_data.snapshot.json sources.stats.pages=427); Marker knownIssue: E11 mit f5a4a06 entfernt"}, {"id": "art-patch", "family": "artifact", "knownIssue": null, "status": "gruen", "calls": 5, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": null}, "silent": {}, "ms": null}, {"id": "art-report", "family": "artifact", "knownIssue": null, "status": "gruen", "calls": 3, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": null}, "silent": {}, "ms": null}, {"id": "dia-architecture-auto", "family": "diagram", "knownIssue": null, "status": "gruen", "calls": 3, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": {"connectorOverlaps": 8, "edgeLengthCv": 0.46, "zoneOverlaps": 0, "edgeCrossings": 3, "clean": false, "nodeOverlaps": 0, "bends": 24, "hotspotsOmitted": 0, "hotspots": 11}, "renderClean": true, "visualProof": {"elements": 49, "invisible": 0, "outsideViewBox": 0, "overflow": 0}}, "silent": {}, "ms": null, "note": "3 Kreuzungen (Schwelle 3), 8 Connector-Ueberlappungen, 24 Knicke -- unveraendert gegenueber 28.09.; Marker knownIssue: E3 mit f5a4a06 entfernt -- mehr als 3 Kreuzungen sind ab jetzt rot"}, {"id": "dia-diff", "family": "diagram", "knownIssue": null, "status": "gruen", "calls": 4, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": {"elements": 22, "invisible": 0, "outsideViewBox": 0, "overflow": 0}}, "silent": {}, "ms": null}, {"id": "dia-mermaid-flow", "family": "diagram", "knownIssue": null, "status": "gruen", "calls": 3, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": {"connectorOverlaps": 0, "edgeLengthCv": 1.36, "zoneOverlaps": 0, "edgeCrossings": 2, "clean": false, "nodeOverlaps": 0, "bends": 12, "hotspotsOmitted": 0, "hotspots": 2}, "renderClean": true, "visualProof": {"elements": 44, "invisible": 0, "outsideViewBox": 0, "overflow": 0}}, "silent": {}, "ms": null, "note": "Regressionspruefung fuer MZP-134 (Id-Muster im Flowchart-Parser auf \\p{L}): Layout-Kennzahlen identisch zur Baseline (2/0/12)"}, {"id": "dia-quadrant-longlabels", "family": "diagram", "knownIssue": null, "status": "gruen", "calls": 2, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": {"elements": 37, "invisible": 0, "outsideViewBox": 0, "overflow": 0}}, "silent": {"textInsideViewBox": {"clean": true, "violations": 0, "samples": []}}, "ms": null}, {"id": "dia-radar-wrapped", "family": "diagram", "knownIssue": null, "status": "gruen", "calls": 3, "failedAttempts": {}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": true, "visualProof": {"elements": 28, "invisible": 0, "outsideViewBox": 0, "overflow": 0}}, "silent": {}, "ms": null}, {"id": "edge-invalid-slug", "family": "edge", "knownIssue": null, "status": "gruen", "calls": 2, "failedAttempts": {"INVALID_SLUG": 1, "PAGE_NOT_FOUND": 1}, "violations": [], "serverQuality": {"layoutQuality": null, "renderClean": null, "visualProof": null}, "silent": {}, "ms": null}], "llm": {"limits": {"maxCalls": 15, "maxSeconds": 300}, "baseline": "mzp-eval-2026-09-28", "results": [{"id": "dia-architecture-auto", "model": "claude-haiku-4-5-20251001", "runs": 3, "measured": 3, "successes": 3, "calls": {"median": 2, "min": 1, "max": 2}, "failedAttempts": {"DIAGRAM_INVALID": 2}, "tokens": {"median": 52943}, "warnings": []}, {"id": "dia-diff", "model": "claude-haiku-4-5-20251001", "runs": 3, "measured": 3, "successes": 3, "calls": {"median": 2, "min": 2, "max": 2}, "failedAttempts": {}, "tokens": {"median": 48977}, "warnings": []}, {"id": "dia-mermaid-flow", "model": "claude-haiku-4-5-20251001", "runs": 3, "measured": 3, "successes": 2, "calls": {"median": 1, "min": 1, "max": 2}, "failedAttempts": {}, "tokens": {"median": 38496}, "warnings": []}, {"id": "dia-quadrant-longlabels", "model": "claude-haiku-4-5-20251001", "runs": 3, "measured": 3, "successes": 3, "calls": {"median": 4, "min": 4, "max": 4}, "failedAttempts": {"DIAGRAM_INVALID": 6}, "tokens": {"median": 121341}, "warnings": []}, {"id": "dia-radar-wrapped", "model": "claude-haiku-4-5-20251001", "runs": 3, "measured": 3, "successes": 3, "calls": {"median": 4, "min": 2, "max": 4}, "failedAttempts": {"DIAGRAM_INVALID": 5}, "tokens": {"median": 95513}, "warnings": []}], "modelWarnings": {}}, "history": [{"slug": "mzp-eval-2026-09-23", "date": "2026-09-23", "gate": "gruen", "counts": {"gruen": 5, "gelb": 1, "rot": 0, "UNEXPECTED_PASS": 4, "ABGEBROCHEN": 0}, "calls": 28, "llm": null}, {"slug": "mzp-eval-2026-09-26", "date": "2026-09-26", "gate": "gruen", "counts": {"gruen": 9, "gelb": 0, "rot": 0, "UNEXPECTED_PASS": 1, "ABGEBROCHEN": 0}, "calls": 30, "llm": null}, {"slug": "mzp-eval-2026-09-28", "date": "2026-09-28", "gate": "gruen", "counts": {"gruen": 10, "gelb": 0, "rot": 0, "UNEXPECTED_PASS": 2, "ABGEBROCHEN": 0}, "calls": 34, "llm": {"claude-haiku-4-5-20251001": {"successes": 13, "runs": 15, "medianCalls": 2}, "claude-sonnet-5": {"successes": 15, "runs": 15, "medianCalls": 2}}}, {"slug": "mzp-eval-2026-09-30", "date": "2026-09-30", "gate": "gruen", "counts": {"gruen": 12, "gelb": 0, "rot": 0, "UNEXPECTED_PASS": 0, "ABGEBROCHEN": 0}, "calls": 34, "llm": {"claude-haiku-4-5-20251001": {"successes": 14, "runs": 15, "medianCalls": 2}}}]}