:root{color-scheme:light;--paper:#f6f5f1;--surface:#fff;--ink:#172c30;--muted:#697777;--line:#dfe4df;--green:#146a57;--green-soft:#e8f2ec;--amber:#966522;--amber-soft:#fbf4e4;--red:#a64740;--mono:ui-monospace,SFMono-Regular,Consolas,monospace;--sans:Inter,ui-sans-serif,-apple-system,BlinkMacSystemFont,"Segoe UI",sans-serif}
*{box-sizing:border-box}body{margin:0;background:var(--paper);color:var(--ink);font-family:var(--sans);font-size:14px}button,input,select{font:inherit}button{cursor:pointer}button:disabled{opacity:.5;cursor:wait}button:focus-visible,input:focus-visible,select:focus-visible,summary:focus-visible{outline:3px solid #419683;outline-offset:3px}button{color:inherit}pre{white-space:pre-wrap;overflow-wrap:anywhere;font-family:var(--mono);font-size:12px;line-height:1.7}p{line-height:1.65}code{font-family:var(--mono);font-size:.9em;background:#eef0ec;border-radius:4px;padding:2px 4px}small{font-weight:400}select{border:1px solid var(--line);border-radius:6px;background:#fff;padding:8px 24px 8px 9px;min-width:0;color:#415254;font-size:12px}
.topbar{height:74px;padding:0 28px;border-bottom:1px solid var(--line);background:#fff;display:flex;align-items:center;gap:28px}.brand{display:flex;gap:11px;align-items:center;font-weight:750;letter-spacing:1.7px;font-size:15px;white-space:nowrap}.brand-mark{background:var(--ink);color:#f2f2df;width:32px;height:32px;display:grid;place-items:center;border-radius:50%;font-size:23px;font-weight:400;letter-spacing:0}.brand-sub{font-size:14px;font-weight:450;color:var(--muted);letter-spacing:0;margin-left:9px}.dataset-tag{font-family:var(--mono);font-size:10px;letter-spacing:1px;color:var(--muted);border-left:1px solid var(--line);padding-left:24px}.dataset-tag span{display:block;letter-spacing:0;font-family:var(--sans);font-size:12px;margin-top:5px}.recipe-switch{margin-left:auto;display:flex;gap:3px;border:1px solid var(--line);padding:4px;border-radius:8px;background:#f6f7f4}.recipe-switch button{border:0;background:transparent;padding:9px 16px;border-radius:5px;font-weight:600;font-size:12px}.recipe-switch button span{font-family:var(--mono);color:var(--muted);font-weight:400;margin-left:7px}.recipe-switch button.active{background:var(--ink);color:#fff}.recipe-switch button.active span{color:#bacec6}
.run-summary{min-height:123px;display:grid;grid-template-columns:1.4fr 1fr 1fr 1.1fr 1.3fr;padding:22px 28px;border-bottom:1px solid var(--line);gap:22px}.summary-context{display:flex;flex-direction:column;justify-content:center;gap:8px}.eyebrow{font-size:10px;letter-spacing:1.15px;font-weight:700;color:var(--green)}.eyebrow span{color:var(--muted);font-weight:450;letter-spacing:0}.summary-context strong{font-size:16px}.summary-context strong span{font-weight:400;color:var(--muted);font-size:13px}.summary-context>span:last-child{color:var(--muted);font-size:11px}.summary-stat{border-left:1px solid var(--line);padding-left:24px;display:flex;flex-direction:column;gap:6px;justify-content:center}.summary-stat>span:first-child{font-size:11px;color:#4b5e5f}.summary-stat>strong{font-size:28px;letter-spacing:-1px;font-weight:550;font-variant-numeric:tabular-nums}.summary-stat strong small{font-size:16px;margin-left:3px;letter-spacing:0;color:var(--muted)}.summary-stat>span:last-child{font-size:10px;color:var(--muted)}
.workspace{height:calc(100vh - 197px);min-height:420px;display:grid;grid-template-columns:318px minmax(0,1fr)}.sidebar{border-right:1px solid var(--line);background:#fafbf8;display:flex;flex-direction:column;min-height:0}.sidebar-heading{display:flex;align-items:center;justify-content:space-between;padding:22px 20px 12px}.sidebar-heading h1{font-size:14px;margin:0;font-weight:650}.sidebar-heading>span{color:var(--muted);font-size:11px;font-family:var(--mono)}.search-wrap{display:flex;gap:8px;align-items:center;border:1px solid var(--line);border-radius:6px;background:white;margin:0 16px 10px;padding:8px 10px}.search-wrap>span{font-size:21px;line-height:17px;color:var(--muted)}.search-wrap input{min-width:0;width:100%;border:0;background:transparent;font-size:11px;outline:none;padding:2px 0}.filters{display:grid;grid-template-columns:1fr 1fr;gap:7px;margin:0 16px 14px}.filters select{font-size:10px;padding:7px 16px 7px 7px}.task-list{overflow-y:auto;min-height:0;flex:1;border-top:1px solid var(--line)}.task-row{width:100%;text-align:left;border:0;border-bottom:1px solid #e6e9e3;border-left:3px solid transparent;background:transparent;padding:14px 17px;display:flex;flex-direction:column;gap:7px}.task-row:hover{background:#eef2ec}.task-row.selected{background:#eaf2ec;border-left-color:var(--green)}.task-row-top{display:flex;align-items:center;gap:7px}.bench-label{text-transform:uppercase;font-family:var(--mono);font-size:9px;letter-spacing:.65px;color:var(--muted)}.outcome-dot{width:6px;height:6px;display:inline-block;border-radius:50%;margin-left:auto}.outcome-dot.passed{background:var(--green)}.outcome-dot.failed{background:var(--red)}.outcome-dot.partial{background:var(--amber)}.task-row>strong{font-weight:560;font-size:12px;line-height:1.5;display:-webkit-box;-webkit-line-clamp:2;-webkit-box-orient:vertical;overflow:hidden}.task-repository{color:var(--muted);font-size:10px;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;max-width:270px}.task-row-bottom{display:flex;justify-content:space-between;gap:5px;font-size:9px;color:var(--muted);margin-top:1px}.task-row-bottom b{font-weight:500}.positive{color:var(--green)}.negative{color:var(--red)}.star-icon{color:var(--amber);font-size:11px}.sidebar-footer{border-top:1px solid var(--line);padding:12px 15px;font-size:10px;color:var(--muted);text-align:center}.empty-list{padding:30px 20px;color:var(--muted);font-size:12px;line-height:2}
.detail{overflow-y:auto;padding:30px 36px 32px;scroll-behavior:smooth;background:#fff}.detail-heading{display:flex;align-items:flex-start;justify-content:space-between;gap:20px}.detail-heading h2{font-weight:570;font-size:25px;letter-spacing:-.55px;line-height:1.35;max-width:800px;margin:10px 0}.detail-heading .task-id{font-family:var(--mono);font-size:9px;color:#7b8583;max-width:740px;overflow-wrap:anywhere}.detail-actions{display:flex;gap:6px;flex-shrink:0}.button{border:1px solid var(--line);border-radius:6px;background:white;padding:9px 12px;font-size:11px;white-space:nowrap}.button:hover{background:#f1f5f0}.button.primary{background:var(--green);border-color:var(--green);color:white}.button.primary:hover{background:#0b5445}.icon-button{font-size:17px;line-height:14px;padding:9px 10px}.bookmarked{color:var(--amber);background:var(--amber-soft)}.task-metrics{display:grid;grid-template-columns:1.1fr 1fr 1fr 1fr;margin:25px 0 20px;border:1px solid var(--line);border-radius:8px;background:#fbfcf9}.task-metrics>div{padding:16px 18px;display:flex;flex-direction:column;gap:8px;border-left:1px solid var(--line)}.task-metrics>div:first-child{border-left:0}.task-metrics>div>span:first-child{font-size:10px;color:var(--muted)}.task-metrics>div>strong{font-size:19px;font-weight:550;letter-spacing:-.4px}.task-metrics>div>strong small{font-size:11px;color:var(--muted);letter-spacing:0}.task-metrics>div>span:last-child{font-size:10px;color:var(--muted)}.badge{display:inline-flex;align-self:flex-start;gap:5px;font-size:10px;border-radius:4px;padding:4px 6px}.task-metrics>div>span.badge.passed{color:var(--green);background:var(--green-soft)}.task-metrics>div>span.badge.failed{color:var(--red);background:#f7ece9}.task-metrics>div>span.badge.partial{color:var(--amber);background:var(--amber-soft)}.decision-evidence{border-left:3px solid #69a38a;padding:4px 16px;margin:20px 0 23px}.decision-evidence p{font-size:12px;color:#405655;max-width:1000px;margin:8px 0 1px}.detail-toolbar{display:flex;justify-content:space-between;gap:15px;align-items:center;border-bottom:1px solid var(--line);margin-top:25px}.tabs{display:flex;gap:22px}.tabs button{background:transparent;border:0;border-bottom:2px solid transparent;color:var(--muted);font-size:11px;padding:13px 0}.tabs button.active{color:var(--ink);border-bottom-color:var(--green);font-weight:650}.trace-options{display:flex;align-items:center;gap:12px;font-size:10px;color:var(--muted)}.trace-options label{display:flex;align-items:center;gap:5px;white-space:nowrap}.trace-options input{accent-color:var(--green);width:12px;height:12px}.trace-options select{font-size:10px;padding:5px 17px 5px 7px}
.reasoning-note{background:#f1f5f3;border:1px solid #e0e9e3;border-radius:7px;display:flex;gap:11px;padding:14px 16px;margin:22px 0;color:#4b6460}.reasoning-note strong{font-size:11px;font-weight:600}.reasoning-note p{font-size:11px;margin:4px 0 0;max-width:1000px}.note-icon{border:1px solid #85a49b;border-radius:50%;width:16px;height:16px;display:grid;place-items:center;flex-shrink:0;font-family:Georgia,serif;font-size:11px;font-style:italic;margin-top:1px}.timeline-heading{display:flex;align-items:center;justify-content:space-between;margin:25px 0 20px}.timeline-heading .eyebrow{font-size:9px;color:var(--muted)}.text-button{border:0;background:transparent;color:var(--green);font-size:11px;padding:3px 0;text-decoration:underline;text-underline-offset:3px}.timeline{padding-left:3px}.timeline-item{position:relative;padding:0 0 18px 35px}.timeline-item:not(:last-child):before{content:"";position:absolute;left:11px;top:22px;bottom:-1px;width:1px;background:var(--line)}.timeline-marker{position:absolute;left:0;top:4px;border:1px solid var(--line);width:24px;height:24px;background:white;border-radius:50%;display:grid;place-items:center;font-size:12px;color:var(--muted)}.reasoning .timeline-marker{color:var(--green);border-color:#cadfd1}.preview .timeline-marker{color:var(--amber);border-color:#ead5ac}.submission .timeline-marker{color:white;background:var(--green);border-color:var(--green)}.error .timeline-marker{color:var(--red);border-color:#e3bdb8}.step-label{display:block;font-size:9px;letter-spacing:.9px;color:var(--muted);font-weight:650}.step-label>span{font-weight:400;letter-spacing:0;margin-left:9px;color:#94a09b}.reasoning-card{padding:7px 15px 10px}.reasoning-card .step-label{color:var(--green)}.reasoning-card p{font-size:13px;margin:7px 0 0;line-height:1.65;white-space:pre-wrap;color:#3c5753}.message-card{padding:12px 16px;background:#fafbf8;border-radius:6px}.message-card p{font-size:12px;margin:7px 0 0;white-space:pre-wrap;color:#52605f}.tool-detail{border:1px solid var(--line);border-radius:7px;overflow:hidden;background:#fff}.tool-detail summary{list-style:none;display:flex;justify-content:space-between;gap:18px;padding:15px 18px;cursor:pointer;position:relative}.tool-detail summary:after{content:"+";font-family:var(--mono);color:var(--muted);align-self:center;margin-left:3px}.tool-detail[open] summary:after{content:"−"}.tool-detail summary:hover{background:#fafbf8}.tool-detail summary>span:first-child{min-width:0;flex:1}.tool-detail summary strong{font-size:12px;font-family:var(--mono);font-weight:550;display:block;margin-top:6px}.tool-summary{font-size:10px;color:var(--muted);display:block;margin-top:6px;overflow-wrap:anywhere}.tool-time{font-family:var(--mono);font-size:10px;color:#637875;white-space:nowrap;padding-top:5px;text-align:right}.tool-time small{font-size:9px;display:block;color:#8d9893;margin-top:5px}.preview .tool-detail{border-color:#e7d8bd}.preview .step-label{color:var(--amber)}.submission .tool-detail{border-color:#aec9b8}.submission .step-label{color:var(--green)}.error .tool-detail{border-color:#dfbbb6}.error .step-label{color:var(--red)}.tool-body{border-top:1px solid var(--line);padding:16px 18px}.subheading{text-transform:uppercase;font-size:9px;letter-spacing:1px;color:var(--muted);margin-bottom:9px}.tool-body pre{background:#f7f8f4;border:1px solid #e8eae2;border-radius:5px;margin:0 0 20px;padding:12px 14px;font-size:11px;max-height:540px;overflow:auto}.tool-body pre:last-child{margin-bottom:0}.preview-meta{display:flex;justify-content:space-between;font-size:10px;color:var(--amber);padding:10px 12px;background:var(--amber-soft);border-radius:5px 5px 0 0}.tool-body .solver-answer{background:#fffdf8;border-color:#eee4d2;max-height:650px}.table-scroll{overflow-x:auto}table{border-collapse:collapse;width:100%;font-size:11px;margin:0 0 15px}th{text-align:left;font-weight:550;color:var(--muted);font-size:10px;background:#f7f8f5;padding:11px 12px;border-bottom:1px solid var(--line)}td{padding:11px 12px;border-bottom:1px solid #e9ece6;line-height:1.5;font-variant-numeric:tabular-nums}.reference-links{display:flex;flex-wrap:wrap;gap:6px;margin:14px 0}.reference-button{font-size:10px;background:#edf3ed;border:1px solid #d9e4d9;border-radius:4px;padding:6px 8px;color:var(--green)}.accounting-note{font-size:10px;line-height:1.65;color:var(--muted);margin-top:26px;border-top:1px solid var(--line);padding-top:15px}.comparison-header{display:flex;justify-content:space-between;align-items:center;margin:26px 0 18px;gap:20px}h3{font-size:18px;font-weight:550;letter-spacing:-.3px;margin:8px 0 0}.baseline-label{font-size:10px;color:var(--muted);display:flex;flex-direction:column;gap:7px}.baseline-label select{max-width:340px}.comparison-delta{display:flex;gap:32px;padding:19px;background:#edf3ed;border-radius:7px;margin-bottom:22px}.comparison-delta span{font-size:10px;color:var(--muted)}.comparison-delta strong{display:block;margin-top:6px;font-size:18px;color:var(--ink);font-weight:550}.compare-table th:nth-child(2){color:var(--green)}.compare-table td:nth-child(2){font-weight:600}.compare-table tr:nth-last-child(-n+2){background:#f7f9f5}.token-card{border:1px solid var(--line);border-radius:7px;padding:20px;margin-top:24px}.token-card h3{font-size:13px;margin:0 0 17px}.token-card>div{display:flex;gap:50px}.token-card span{font-size:10px;color:var(--muted)}.token-card strong{display:block;margin-top:7px;font-size:18px;color:var(--ink);font-weight:500;font-family:var(--mono)}.token-card p{font-size:10px;color:var(--muted);margin:20px 0 0}.prompt-section{margin-top:26px}.prompt-section pre,.recipe-prompt pre{padding:20px;background:#f7f8f4;border:1px solid var(--line);border-radius:6px;font-size:12px;line-height:1.8}.recipe-prompt summary{cursor:pointer;padding:14px 0;font-size:12px;font-weight:550}.empty-state,.loading,.error-state{padding:50px 24px;color:var(--muted);font-size:13px}.error-state{color:var(--red)}dialog{max-width:900px;width:90vw;border:1px solid var(--line);border-radius:10px;padding:28px;color:var(--ink);box-shadow:0 20px 70px #172c3026}dialog::backdrop{background:#172c3066}dialog h2{font-size:22px;line-height:1.5;font-weight:550}dialog pre{background:#f5f7f2;padding:18px;border-radius:6px;max-height:50vh;overflow-y:auto}dialog p{font-size:11px;color:var(--muted)}.reference-scores{display:flex;gap:15px;margin:20px 0;flex-wrap:wrap}.reference-scores span{font-size:11px;color:var(--muted);background:var(--green-soft);padding:12px;border-radius:5px}.reference-scores strong{display:block;margin-top:6px;color:var(--ink)}#toast{position:fixed;bottom:24px;left:50%;transform:translateX(-50%) translateY(15px);opacity:0;pointer-events:none;background:var(--ink);color:white;border-radius:6px;padding:12px 20px;font-size:12px;transition:.2s;z-index:100}#toast.visible{opacity:1;transform:translateX(-50%) translateY(0)}
@media(min-width:1600px){.workspace{grid-template-columns:350px minmax(0,1fr)}.detail{padding-left:50px;padding-right:50px}.task-row{padding-left:22px;padding-right:22px}.task-repository{max-width:300px}}
@media(max-width:1150px){.dataset-tag{display:none}.detail{padding:24px}.detail-heading{flex-direction:column;gap:14px}.detail-heading h2{font-size:23px}.task-metrics>div{padding:14px 12px}.task-metrics>div>strong{font-size:17px}.tabs{gap:16px}.trace-options{gap:6px}.tabs button{font-size:10px}.run-summary{gap:12px;padding-left:20px;padding-right:20px}.summary-stat{padding-left:16px}.summary-stat>span:last-child{line-height:1.5}.summary-context strong span{display:block;margin-top:4px}.comparison-header{align-items:flex-start;flex-direction:column}.baseline-label select{max-width:100%}}
@media(max-width:850px){.topbar{padding:0 16px;height:auto;min-height:70px;flex-wrap:wrap;gap:12px;padding-top:12px;padding-bottom:12px}.brand-sub{font-size:12px}.recipe-switch button{padding:8px 10px}.recipe-switch button span{margin-left:4px}.run-summary{grid-template-columns:repeat(4,1fr);padding:16px;min-height:110px}.summary-context{display:none}.summary-stat:first-of-type{border-left:0}.summary-stat{padding-left:12px}.summary-stat>strong{font-size:23px}.workspace{height:calc(100vh - 180px);grid-template-columns:245px minmax(0,1fr)}.sidebar-heading{padding-left:15px}.filters{grid-template-columns:1fr}.detail{padding:20px 16px}.task-metrics{grid-template-columns:1fr 1fr}.task-metrics>div:nth-child(3){border-left:0;border-top:1px solid var(--line)}.task-metrics>div:nth-child(4){border-top:1px solid var(--line)}.detail-toolbar{flex-wrap:wrap;gap:4px;padding-bottom:9px}.trace-options{margin-left:auto}.task-row{padding-left:12px;padding-right:12px}.task-row-bottom{flex-direction:column}.comparison-delta{gap:18px}.comparison-delta strong{font-size:15px}.token-card>div{gap:20px}.tool-detail summary{padding:13px 12px}.tool-time{font-size:9px}}
@media(max-width:600px){.topbar{justify-content:center}.recipe-switch{margin-left:0}.brand{font-size:13px}.brand-sub{font-size:12px}.run-summary{grid-template-columns:1fr 1fr;gap:15px}.summary-stat{border:0;padding:0 8px}.summary-stat>strong{font-size:23px}.workspace{height:auto;display:flex;flex-direction:column}.sidebar{border-right:0;border-bottom:1px solid var(--line)}.sidebar-heading{padding-top:15px}.filters{grid-template-columns:1fr 1fr}.task-list{max-height:240px}.sidebar-footer{display:none}.detail{overflow:visible;padding:22px 15px}.detail-heading h2{font-size:22px}.detail-heading .task-id{font-size:8px}.detail-actions{width:100%}.detail-actions .primary{margin-left:auto}.timeline-item{padding-left:28px}.tool-detail summary{gap:6px}.tool-summary{font-size:9px}.reasoning-card{padding-right:0;padding-left:8px}.tool-body{padding:13px 10px}.trace-options{margin-left:0}.tabs{gap:17px}.comparison-delta{flex-wrap:wrap;gap:20px}.token-card>div{gap:16px}.token-card strong{font-size:15px}.task-row-bottom{flex-direction:row}.summary-stat>span:last-child{font-size:9px}.reasoning-note{padding:12px}.task-repository{max-width:85vw}}
@media(prefers-reduced-motion:reduce){*{scroll-behavior:auto!important;transition:none!important}}
.ground-truth{border:1px solid var(--line);border-radius:8px;padding:16px 18px;margin:20px 0;background:#fff}.ground-truth-heading{display:flex;justify-content:space-between;align-items:center;gap:12px}.ground-truth-heading h3{font-size:13px;margin:0;letter-spacing:0}.ground-truth-heading>span{font-family:var(--mono);font-size:9px;color:var(--muted);white-space:nowrap}.ground-truth-models{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:10px;margin-top:14px}.ground-truth-model{padding:12px;border:1px solid var(--line);border-radius:6px;display:flex;flex-direction:column;gap:9px}.ground-truth-model>div{display:flex;align-items:center;justify-content:space-between;gap:6px;flex-wrap:wrap}.ground-truth-model strong{font-size:12px;font-weight:600}.selected-label{font-size:9px;color:var(--green);background:var(--green-soft);padding:3px 5px;border-radius:4px}.ground-truth-verdict{font-size:12px;font-weight:550}.ground-truth-model.passed .ground-truth-verdict{color:var(--green)}.ground-truth-model.failed .ground-truth-verdict{color:var(--red)}.ground-truth-model.partial .ground-truth-verdict{color:var(--amber)}.ground-truth-score,.ground-truth>p{font-size:10px;color:var(--muted)}.ground-truth>p{margin:12px 0 0;line-height:1.6}@media(max-width:600px){.ground-truth{padding:14px 12px}.ground-truth-heading{align-items:flex-start;flex-direction:column;gap:7px}.ground-truth-models{gap:6px}.ground-truth-model{padding:10px 7px}.ground-truth-model strong,.ground-truth-verdict{font-size:11px}.ground-truth-score,.selected-label{font-size:9px}}
