{
 "schema": 1,
 "run": {
  "slug": "mzp-eval-2026-10-03",
  "date": "2026-10-03",
  "startedAt": "2026-10-03T01:57:23Z",
  "finishedAt": "2026-10-03T10:10:15Z",
  "target": "https://publisher.maierzone.de",
  "stages": [
   "deterministic",
   "llm"
  ],
  "tasksCommit": "bed2685",
  "baseline": "mzp-eval-2026-10-02",
  "gate": "gruen",
  "counts": {
   "gruen": 15,
   "gelb": 0,
   "rot": 0,
   "UNEXPECTED_PASS": 0,
   "ABGEBROCHEN": 0
  },
  "unexpectedPass": [],
  "note": "ms je Aufruf nicht gemessen (null). Aufraeumen am Anfang: 16 der 17 parallel gesendeten deletePage scheiterten mit HTTP 502 (Instanz ~40 s nicht erreichbar), danach einzeln wiederholt -- im Protokoll als attempt 1/2. LLM-Stufe in zwei Anlaeufen: der erste brach nach 14 Laeufen ab (deletePage-Helfer NO_CALL x3), die fehlenden 76 Laeufe liefen in drei Teilen nach (llm.meta.parts). run-llm.py: Frontmatter-Trennung korrigiert (dia-ascii-architecture verlor sonst seinen verify-Schritt), nicht committet."
 },
 "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,
   "note": "A11Y_IMAGE_ALT WARNING nodes=1; zusaetzlich MISSING_ALT (WARNING, Bundle-Pruefung)"
  },
  {
   "id": "art-analog-tusche",
   "family": "artifact",
   "knownIssue": null,
   "status": "gruen",
   "calls": 3,
   "failedAttempts": {},
   "violations": [],
   "serverQuality": {
    "layoutQuality": null,
    "renderClean": true,
    "visualProof": null
   },
   "silent": {},
   "ms": null,
   "note": "TUSCHE_APPLIED schwell=4, FIGURE_CLEAN frames=2; Schritte 2+3 parallel gesendet (beide lesend)"
  },
  {
   "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": "_data.snapshot.json sources.stats.pages=449; Payload nutzt mz-stat-label/-value (Server schlaegt mz-stat__label/__value vor, WARNING)"
  },
  {
   "id": "art-patch",
   "family": "artifact",
   "knownIssue": null,
   "status": "gruen",
   "calls": 5,
   "failedAttempts": {},
   "violations": [],
   "serverQuality": {
    "layoutQuality": null,
    "renderClean": true,
    "visualProof": null
   },
   "silent": {},
   "ms": null,
   "note": "v1=1, v2=2; diffVersions listet nur index.html"
  },
  {
   "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 02.10."
  },
  {
   "id": "dia-ascii-architecture",
   "family": "diagram",
   "knownIssue": null,
   "status": "gruen",
   "calls": 3,
   "failedAttempts": {},
   "violations": [],
   "serverQuality": {
    "layoutQuality": {
     "connectorOverlaps": 0,
     "edgeLengthCv": 0.62,
     "zoneOverlaps": 0,
     "edgeCrossings": 0,
     "clean": true,
     "nodeOverlaps": 0,
     "bends": 2,
     "hotspotsOmitted": 0,
     "hotspots": 0
    },
    "renderClean": true,
    "visualProof": {
     "elements": 28,
     "invisible": 0,
     "outsideViewBox": 0,
     "overflow": 0
    }
   },
   "silent": {},
   "ms": null,
   "note": "constraints=1, constraintsUnmet=0, layout clean"
  },
  {
   "id": "dia-constraints",
   "family": "diagram",
   "knownIssue": null,
   "status": "gruen",
   "calls": 2,
   "failedAttempts": {},
   "violations": [],
   "serverQuality": {
    "layoutQuality": {
     "connectorOverlaps": 0,
     "edgeLengthCv": 0.26,
     "zoneOverlaps": 0,
     "edgeCrossings": 0,
     "clean": true,
     "nodeOverlaps": 0,
     "bends": 4,
     "hotspotsOmitted": 0,
     "hotspots": 0
    },
    "renderClean": true,
    "visualProof": {
     "elements": 22,
     "invisible": 0,
     "outsideViewBox": 0,
     "overflow": 0
    }
   },
   "silent": {},
   "ms": null,
   "note": "constraints=1, constraintsUnmet=0"
  },
  {
   "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,
   "note": "Quittung: 1 Knoten + 1 Kante added, 0 removed"
  },
  {
   "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": "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,
   "note": "decorations=21"
  },
  {
   "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-2026-09-30",
  "results": [
   {
    "id": "art-a11y-check",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 0,
    "successes": null,
    "calls": {
     "median": 1,
     "min": 0,
     "max": 2
    },
    "failedAttempts": {},
    "tokens": {
     "median": 87063.5
    },
    "warnings": []
   },
   {
    "id": "art-a11y-check",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 0,
    "successes": null,
    "calls": {
     "median": 0,
     "min": 0,
     "max": 0
    },
    "failedAttempts": {},
    "tokens": {
     "median": 46641
    },
    "warnings": []
   },
   {
    "id": "art-analog-tusche",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 1,
    "calls": {
     "median": 4,
     "min": 4,
     "max": 5
    },
    "failedAttempts": {},
    "tokens": {
     "median": 229438
    },
    "warnings": []
   },
   {
    "id": "art-analog-tusche",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 0,
    "calls": {
     "median": 4,
     "min": 3,
     "max": 5
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 5,
     "UNSTRUCTURED": 1
    },
    "tokens": {
     "median": 131329
    },
    "warnings": []
   },
   {
    "id": "art-asset-bundle",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 2,
    "successes": 2,
    "calls": {
     "median": 1,
     "min": 0,
     "max": 2
    },
    "failedAttempts": {},
    "tokens": {
     "median": 83923
    },
    "warnings": []
   },
   {
    "id": "art-asset-bundle",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 1,
    "successes": 1,
    "calls": {
     "median": 1,
     "min": 1,
     "max": 1
    },
    "failedAttempts": {},
    "tokens": {
     "median": 43547
    },
    "warnings": []
   },
   {
    "id": "art-broken",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 0,
    "successes": 0,
    "calls": {
     "median": 0,
     "min": 0,
     "max": 0
    },
    "failedAttempts": {},
    "tokens": null,
    "warnings": []
   },
   {
    "id": "art-broken",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 1,
    "calls": {
     "median": 0,
     "min": 0,
     "max": 1
    },
    "failedAttempts": {},
    "tokens": {
     "median": 33384
    },
    "warnings": []
   },
   {
    "id": "art-live-report",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 2,
    "calls": {
     "median": 4,
     "min": 1,
     "max": 6
    },
    "failedAttempts": {},
    "tokens": {
     "median": 83014
    },
    "warnings": []
   },
   {
    "id": "art-live-report",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 0,
    "calls": {
     "median": 1,
     "min": 1,
     "max": 3
    },
    "failedAttempts": {},
    "tokens": {
     "median": 61382
    },
    "warnings": []
   },
   {
    "id": "art-patch",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 1,
    "successes": 0,
    "calls": {
     "median": 0,
     "min": 0,
     "max": 0
    },
    "failedAttempts": {},
    "tokens": {
     "median": 30480
    },
    "warnings": []
   },
   {
    "id": "art-patch",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 0,
    "calls": {
     "median": 0,
     "min": 0,
     "max": 0
    },
    "failedAttempts": {},
    "tokens": {
     "median": 23762
    },
    "warnings": []
   },
   {
    "id": "art-report",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 2,
     "min": 2,
     "max": 2
    },
    "failedAttempts": {},
    "tokens": {
     "median": 55264
    },
    "warnings": []
   },
   {
    "id": "art-report",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 1,
     "min": 1,
     "max": 1
    },
    "failedAttempts": {},
    "tokens": {
     "median": 36614
    },
    "warnings": []
   },
   {
    "id": "dia-architecture-auto",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 2,
    "successes": 2,
    "calls": {
     "median": 2,
     "min": 0,
     "max": 2
    },
    "failedAttempts": {},
    "tokens": {
     "median": 47182
    },
    "warnings": []
   },
   {
    "id": "dia-architecture-auto",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 2,
    "calls": {
     "median": 5,
     "min": 3,
     "max": 6
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 6
    },
    "tokens": {
     "median": 147264
    },
    "warnings": [
     "CALLS_UP"
    ]
   },
   {
    "id": "dia-ascii-architecture",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 0,
    "calls": {
     "median": 5,
     "min": 1,
     "max": 10
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 8,
     "ASCII_EDGE_DANGLING": 4,
     "ASCII_BOX_OVERLAP": 2
    },
    "tokens": {
     "median": 170377
    },
    "warnings": []
   },
   {
    "id": "dia-ascii-architecture",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 2,
    "calls": {
     "median": 9,
     "min": 5,
     "max": 9
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 10,
     "ASCII_EDGE_DANGLING": 12,
     "INVALID_NODE_TYPE": 4
    },
    "tokens": {
     "median": 243340
    },
    "warnings": []
   },
   {
    "id": "dia-constraints",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 0,
    "successes": null,
    "calls": {
     "median": 3,
     "min": 2,
     "max": 3
    },
    "failedAttempts": {},
    "tokens": {
     "median": 58733
    },
    "warnings": []
   },
   {
    "id": "dia-constraints",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 0,
    "successes": null,
    "calls": {
     "median": 1,
     "min": 1,
     "max": 2
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 1
    },
    "tokens": {
     "median": 57187
    },
    "warnings": []
   },
   {
    "id": "dia-diff",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 2,
     "min": 2,
     "max": 2
    },
    "failedAttempts": {},
    "tokens": {
     "median": 45690
    },
    "warnings": []
   },
   {
    "id": "dia-diff",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 2,
     "min": 2,
     "max": 3
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 1
    },
    "tokens": {
     "median": 49727
    },
    "warnings": []
   },
   {
    "id": "dia-mermaid-flow",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 2,
     "min": 2,
     "max": 3
    },
    "failedAttempts": {},
    "tokens": {
     "median": 50116
    },
    "warnings": []
   },
   {
    "id": "dia-mermaid-flow",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 1,
     "min": 1,
     "max": 1
    },
    "failedAttempts": {},
    "tokens": {
     "median": 36774
    },
    "warnings": []
   },
   {
    "id": "dia-quadrant-longlabels",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 3,
     "min": 2,
     "max": 3
    },
    "failedAttempts": {},
    "tokens": {
     "median": 63524
    },
    "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": 5
    },
    "tokens": {
     "median": 108708
    },
    "warnings": []
   },
   {
    "id": "dia-radar-wrapped",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 3,
     "min": 2,
     "max": 3
    },
    "failedAttempts": {},
    "tokens": {
     "median": 56829
    },
    "warnings": []
   },
   {
    "id": "dia-radar-wrapped",
    "model": "claude-haiku-4-5-20251001",
    "runs": 3,
    "measured": 3,
    "successes": 3,
    "calls": {
     "median": 4,
     "min": 3,
     "max": 4
    },
    "failedAttempts": {
     "DIAGRAM_INVALID": 6
    },
    "tokens": {
     "median": 92748
    },
    "warnings": []
   },
   {
    "id": "edge-invalid-slug",
    "model": "claude-sonnet-5",
    "runs": 3,
    "measured": 2,
    "successes": 0,
    "calls": {
     "median": 2,
     "min": 0,
     "max": 2
    },
    "failedAttempts": {
     "UNSTRUCTURED": 2
    },
    "tokens": {
     "median": 41801
    },
    "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
    }
   }
  },
  {
   "slug": "mzp-eval-2026-10-01",
   "date": "2026-10-01",
   "gate": "gruen",
   "counts": {
    "gruen": 13,
    "gelb": 0,
    "rot": 0,
    "UNEXPECTED_PASS": 0,
    "ABGEBROCHEN": 0
   },
   "calls": 36,
   "llm": null
  },
  {
   "slug": "mzp-eval-2026-10-02",
   "date": "2026-10-02",
   "gate": "gruen",
   "counts": {
    "gruen": 15,
    "gelb": 0,
    "rot": 0,
    "UNEXPECTED_PASS": 0,
    "ABGEBROCHEN": 0
   },
   "calls": 42,
   "llm": null
  },
  {
   "slug": "mzp-eval-2026-10-03",
   "date": "2026-10-03",
   "gate": "gruen",
   "counts": {
    "gruen": 15,
    "gelb": 0,
    "rot": 0,
    "UNEXPECTED_PASS": 0,
    "ABGEBROCHEN": 0
   },
   "calls": 42,
   "llm": {
    "claude-haiku-4-5-20251001": {
     "successes": 21,
     "runs": 34,
     "medianCalls": 1
    },
    "claude-sonnet-5": {
     "successes": 22,
     "runs": 31,
     "medianCalls": 2
    }
   }
  }
 ]
}