{"schema":1,"run":{"slug":"mzp-eval-2026-09-28","date":"2026-09-28","startedAt":"2026-09-28T04:41:53Z","finishedAt":"2026-09-28T04:52:00Z","target":"https://publisher.maierzone.de","stages":["deterministic","llm"],"tasksCommit":"c371a24","baseline":"mzp-eval-2026-09-26","gate":"gruen","counts":{"gruen":10,"gelb":0,"rot":0,"UNEXPECTED_PASS":2,"ABGEBROCHEN":0},"unexpectedPass":["art-live-report","dia-architecture-auto"]},"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":"E11","status":"UNEXPECTED_PASS","calls":3,"failedAttempts":{},"violations":[],"serverQuality":{"layoutQuality":null,"renderClean":true,"visualProof":null},"silent":{},"ms":null,"note":"E11 live: alle drei Schritte bestanden (_data.snapshot.json sources.stats.pages=421) -- Marker knownIssue: E11 entfernen"},{"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":"E3","status":"UNEXPECTED_PASS","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":"E3 live: 3 Kreuzungen (Schwelle 3), 8 Connector-Ueberlappungen und 24 Knicke (26.09.: 8/26) -- der Nudger (MZP-129) faechert hier nichts auf, weil jede Auffaecherung eine Kreuzung kostete"},{"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":"Connector-Ueberlappungen 1 -> 0 gegenueber 26.09. (MZP-129 Nudger)"},{"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,"note":"Sichtpruefung: Seriennamen stehen jetzt als Legende im SVG -- Notiz vom 26.09. erledigt"},{"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":null,"results":[{"id":"dia-architecture-auto","model":"claude-haiku-4-5-20251001","runs":3,"measured":3,"successes":2,"calls":{"median":2,"min":2,"max":3},"failedAttempts":{"DIAGRAM_INVALID":4},"tokens":{"median":51675},"warnings":[]},{"id":"dia-architecture-auto","model":"claude-sonnet-5","runs":3,"measured":3,"successes":3,"calls":{"median":2,"min":1,"max":2},"failedAttempts":{},"tokens":{"median":69083},"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":48878},"warnings":[]},{"id":"dia-diff","model":"claude-sonnet-5","runs":3,"measured":3,"successes":3,"calls":{"median":2,"min":2,"max":2},"failedAttempts":{},"tokens":{"median":81481},"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":{"DIAGRAM_INVALID":1},"tokens":{"median":37504},"warnings":[]},{"id":"dia-mermaid-flow","model":"claude-sonnet-5","runs":3,"measured":3,"successes":3,"calls":{"median":2,"min":2,"max":4},"failedAttempts":{},"tokens":{"median":74093},"warnings":[]},{"id":"dia-quadrant-longlabels","model":"claude-haiku-4-5-20251001","runs":3,"measured":3,"successes":3,"calls":{"median":3,"min":2,"max":6},"failedAttempts":{"DIAGRAM_INVALID":2},"tokens":{"median":199409},"warnings":[]},{"id":"dia-quadrant-longlabels","model":"claude-sonnet-5","runs":3,"measured":3,"successes":3,"calls":{"median":3,"min":3,"max":3},"failedAttempts":{},"tokens":{"median":112782},"warnings":[]},{"id":"dia-radar-wrapped","model":"claude-haiku-4-5-20251001","runs":3,"measured":3,"successes":3,"calls":{"median":3,"min":3,"max":5},"failedAttempts":{"DIAGRAM_INVALID":4},"tokens":{"median":83952},"warnings":[]},{"id":"dia-radar-wrapped","model":"claude-sonnet-5","runs":3,"measured":3,"successes":3,"calls":{"median":2,"min":2,"max":3},"failedAttempts":{},"tokens":{"median":83471},"warnings":[]}],"modelWarnings":{},"source":{"file":"llm-B.json","runner":"run-llm.py","startedAt":"2026-09-28T03:35:55+00:00","complete":true,"reconstructed":"29 Laeufe aus Rohstroemen + Log (Abbruch 06:20 beim Aufraeumen); Messgroessen via StreamAnalyzer, Urteil aus dem Log","ticket":"MZP-127 (Variante B, validateDiagram-Beschreibung gekuerzt)"}},"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}}}]}