@leostera/evalkit 0.0.2 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@leostera/evalkit",
3
- "version": "0.0.2",
3
+ "version": "0.2.0",
4
4
  "description": "Author and run agent evals as code",
5
5
  "type": "module",
6
6
  "license": "MIT",
@@ -12,7 +12,7 @@
12
12
  "workspaces": [
13
13
  "packages/*",
14
14
  "examples/*",
15
- "www"
15
+ "sites/*"
16
16
  ],
17
17
  "publishConfig": {
18
18
  "access": "public",
@@ -43,6 +43,7 @@
43
43
  "scripts": {
44
44
  "build": "bun run --filter './packages/*' build && bun scripts/sync-package.ts",
45
45
  "check": "bun run --filter './packages/*' check && bun run --filter './examples/*' check",
46
+ "lint": "oxlint --react-plugin --jsx-a11y-plugin --deny-warnings packages examples scripts sites/evalkit.leostera.dev/src",
46
47
  "test": "bun test",
47
48
  "pack:check": "bun packages/evalkit/scripts/pack-check.ts",
48
49
  "format": "prettier --write .",
@@ -51,6 +52,7 @@
51
52
  },
52
53
  "devDependencies": {
53
54
  "@types/bun": "latest",
55
+ "oxlint": "1.87.0",
54
56
  "prettier": "latest",
55
57
  "typescript": "latest"
56
58
  }
@@ -1 +0,0 @@
1
- :root{--lightningcss-light:initial;--lightningcss-dark: ;color-scheme:light;--canvas:#fff;--surface:#fff;--surface-subtle:#f5f5f5;--surface-hover:#f8f8f8;--ink:#171717;--muted:#595959;--line:#e5e5e5;--line-strong:#b8b8b8;--accent:#171717;--accent-ink:#171717;--focus:#171717;--sidebar:#171717;--sidebar-ink:#fafafa;--sidebar-muted:#bdbdbd;--sidebar-hover:#2e2e2e;--sidebar-active:#343434;--success-bg:#ededed;--success-ink:#171717;--danger-bg:#fff;--danger-ink:#171717;--pending-bg:#f5f5f5;--pending-ink:#333;color:var(--ink);background:var(--canvas);font-family:Helvetica Neue,-apple-system,BlinkMacSystemFont,Segoe UI,sans-serif;font-size:14px;line-height:1.5}*{box-sizing:border-box}body{margin:0}::selection{color:#fff;background:#171717}button,input{font:inherit}button{cursor:pointer}button:disabled{cursor:not-allowed;opacity:.5}button:focus-visible,a:focus-visible,input:focus-visible,summary:focus-visible{outline:2px solid var(--focus);outline-offset:2px}.dashboard-shell{grid-template-columns:196px minmax(0,1fr);min-height:100vh;transition:grid-template-columns .15s ease-out;display:grid}.dashboard-shell.navigation-collapsed{grid-template-columns:52px minmax(0,1fr)}.dashboard-shell nav[hidden],.dashboard-shell .brand[hidden]{display:none}.dashboard-shell>aside{background:var(--sidebar);color:var(--sidebar-ink);border-right:1px solid var(--sidebar);min-width:0;padding:19px 12px}.nav-top{justify-content:space-between;align-items:center;gap:4px;min-height:38px;margin:0 0 20px;display:flex}.brand{letter-spacing:-.045em;min-height:32px;color:var(--sidebar-ink);align-items:center;margin-left:10px;font-size:17px;font-weight:700;text-decoration:none;display:flex}.dashboard-shell>aside nav{gap:2px;display:grid}.dashboard-shell>aside nav a{min-height:35px;color:var(--sidebar-muted);letter-spacing:0;text-transform:none;border-radius:2px;align-items:center;padding:6px 12px;font-size:13px;font-weight:550;text-decoration:none;display:flex}.dashboard-shell>aside nav a:hover{color:#fff;background:var(--sidebar-hover)}.dashboard-shell>aside nav a.active{background:var(--sidebar-active);color:#fff;font-weight:700}.content{width:100%;min-width:0;padding:22px clamp(18px,2.25vw,38px) 48px}.content>header{border-bottom:1px solid var(--line);align-items:center;gap:14px;min-height:42px;margin-bottom:16px;padding-bottom:14px;display:flex}.navigation-toggle{width:28px;height:30px;color:var(--sidebar-ink);background:0 0;border:1px solid #0000;border-radius:2px;flex:none;padding:0;font-size:24px;line-height:1}.navigation-toggle:hover{background:var(--sidebar-hover)}.navigation-toggle:focus-visible{outline-color:#fff}.navigation-collapsed .nav-top{justify-content:center}.dashboard-shell>aside a:focus-visible{outline-color:#fff}h1{letter-spacing:-.035em;margin:0;font-size:23px;font-weight:650;line-height:1.25}h2{letter-spacing:-.02em;margin:0 0 10px;font-size:17px;font-weight:650}h3{font-size:13px}p{line-height:1.55}.mono{font-variant-numeric:tabular-nums;font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:12px}.eyebrow{color:var(--muted)}.cards{grid-template-columns:repeat(auto-fit,minmax(230px,1fr));gap:12px;display:grid}.card,.empty,.table-wrap{background:var(--surface);border:1px solid var(--line);border-radius:2px}.card{padding:14px}.card button,.trial-overview>button{border:1px solid var(--accent);background:var(--accent);color:#fff;border-radius:2px;padding:7px 11px;font-weight:600}.card button:hover,.trial-overview>button:hover{background:var(--accent-ink)}.empty{color:var(--muted);text-align:center;padding:28px}.runs-layout{grid-template-columns:208px minmax(0,1fr);align-items:start;gap:14px;display:grid}.runs-filter-panel{border:1px solid var(--line);background:var(--surface);border-radius:2px;max-height:calc(100vh - 140px);overflow-y:auto}.runs-filter-panel>summary{cursor:pointer;border-bottom:1px solid var(--line);padding:11px 13px;font-size:12px;font-weight:650}.runs-filter-fields{gap:13px;padding:12px 13px 14px;display:grid}.runs-filter-fields fieldset{border:0;border-top:1px solid var(--line);min-width:0;margin:0;padding:9px 0 0}.runs-filter-fields legend{color:var(--ink);padding-right:5px;font-size:11px;font-weight:650}.runs-choice{cursor:pointer;overflow-wrap:anywhere;align-items:baseline;gap:7px;padding:4px 0;font-size:12px;display:flex}.runs-choice input{accent-color:var(--accent);flex:none}.runs-choice span{min-width:0}.runs-choice small{margin-left:auto}.runs-date{gap:5px;font-size:11px;font-weight:600;display:grid}.runs-date input{border:1px solid var(--line-strong);background:var(--surface);width:100%;min-width:0;color:var(--ink);border-radius:2px;padding:5px 7px}.clear-filters{border:1px solid var(--line-strong);background:var(--surface);color:var(--ink);border-radius:2px;padding:6px 9px}.clear-filters:hover:not(:disabled){border-color:var(--accent)}.table-wrap{max-width:100%;overflow-x:auto}table{border-collapse:separate;border-spacing:0;width:100%}th,td{border-bottom:1px solid var(--line);text-align:left;white-space:nowrap;font-variant-numeric:tabular-nums;padding:8px 11px}tr:last-child>td{border-bottom:0}th{color:var(--muted);background:var(--surface-subtle);letter-spacing:.035em;text-transform:uppercase;font-size:11px;font-weight:680}td{font-size:13px}.nested{background:var(--surface)}.matrix-filter{color:var(--muted);flex-wrap:wrap;align-items:center;gap:9px;padding:10px 12px;font-size:11px;font-weight:620;display:flex}.matrix-filter input{border:1px solid var(--line-strong);background:var(--surface);min-width:0;color:var(--ink);outline-color:var(--focus);border-radius:2px;flex:200px;padding:6px 9px;font-size:12px}.matrix-filter input::placeholder{color:var(--muted);opacity:.86}.matrix-filter span{color:var(--muted);font-variant-numeric:tabular-nums;font-weight:500}.matrix-pages{border-top:1px solid var(--line);justify-content:flex-end;align-items:center;gap:9px;padding:9px 12px;display:flex}.matrix-pages span{color:var(--muted);font-variant-numeric:tabular-nums;margin-right:auto;font-size:11px}.matrix-pages button,.data-table button:not(.table-sort):not(.table-link){border:1px solid var(--line-strong);color:var(--ink);background:var(--surface);border-radius:2px;padding:5px 9px;font-size:11px;font-weight:600}.matrix-pages button:hover:not(:disabled),.data-table button:not(.table-sort):not(.table-link):hover:not(:disabled){border-color:var(--accent);color:var(--accent-ink)}.table-sort{color:inherit;font:inherit;letter-spacing:inherit;text-transform:inherit;background:0 0;border:0;padding:0}.table-sort:hover,th[aria-sort] .table-sort{color:var(--accent-ink)}.data-table th,.data-table td{vertical-align:middle}.data-table>thead th:first-child,.data-table>tbody>tr>td.identity-cell{z-index:1;background:var(--surface);min-width:105px;max-width:260px;box-shadow:1px 0 0 var(--line);position:sticky;left:0}.data-table>thead th:first-child{z-index:2;background:var(--surface-subtle)}.data-table>tbody>tr:hover>td.identity-cell{background:var(--surface-hover)}.identity-cell small{color:var(--muted);text-overflow:ellipsis;max-width:210px;overflow:hidden}.table-link,.data-table button.table-link{color:var(--accent-ink);font:inherit;text-align:left;background:0 0;border:0;padding:0;font-weight:600;text-decoration:none}.table-link:hover{text-underline-offset:3px;text-decoration:underline}tr{cursor:default}tbody tr:hover{background:var(--surface-hover)}small{color:var(--muted);font-size:11px;display:block}.status{text-transform:capitalize;border:1px solid #0000;border-radius:2px;padding:2px 6px;font-size:11px;font-weight:650;line-height:1.3;display:inline-block}.status.running{background:var(--pending-bg);border-color:var(--line-strong);color:var(--pending-ink)}.status.passed{background:var(--success-bg);color:var(--success-ink)}.status.failed{background:var(--danger-bg);border-color:var(--ink);color:var(--danger-ink)}.status.errored{background:var(--ink);color:#fff}.error{color:var(--ink);background:var(--surface-subtle);border:1px solid var(--line-strong);border-radius:2px;padding:10px 12px}.trial-inspector{grid-template-columns:minmax(250px,325px) minmax(0,1fr);align-items:start;gap:16px;display:grid}.trial-overview{background:var(--surface);border:1px solid var(--line);border-radius:2px;width:auto;padding:14px}.trial-overview h2,.trial-overview h3{border-bottom:1px solid var(--line);padding-bottom:7px;font-size:12px;font-weight:650}.metadata-list{grid-template-columns:90px minmax(0,1fr);margin:12px 0;display:grid}.metadata-list dt,.metadata-list dd{border-bottom:1px solid var(--line);overflow-wrap:anywhere;margin:0;padding:6px 0;font-size:12px}.metadata-list dt{color:var(--muted)}.metadata-list dd{font-variant-numeric:tabular-nums;font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace}.compact-table{font-size:11px}.compact-table th,.compact-table td{white-space:normal;padding:6px 7px}.timeline{gap:10px;min-width:0;display:grid}.timeline-heading{border-bottom:1px solid var(--line);justify-content:space-between;align-items:baseline;padding:0 0 7px;display:flex}.timeline-heading h2{margin:0;font-size:14px}.timeline .card{border-left:1px solid var(--line)}.timeline h2{margin:2px 0 5px;font-size:12px}.event-fields{border-collapse:collapse;width:100%;font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:11px}.event-fields td{white-space:normal;vertical-align:top;border:0;padding:3px 5px}.event-fields td:first-child{color:var(--muted);width:120px}.trial-summary{border:1px solid var(--line);background:var(--surface);border-radius:2px;grid-template-columns:repeat(4,minmax(0,1fr));margin:6px 0 12px;display:grid}.trial-summary div{border-right:1px solid var(--line);gap:2px;padding:9px 12px;display:grid}.trial-summary div:last-child{border-right:0}.trial-summary strong{color:var(--muted);font-size:10px;font-weight:650}.raw-details{border:1px solid var(--line);background:var(--surface);border-radius:4px;margin-bottom:10px;padding:9px}.raw-details summary{cursor:pointer;font-size:11px;font-weight:600}pre{border:1px solid var(--line);white-space:pre-wrap;overflow-wrap:anywhere;background:#f7f7f7;border-radius:4px;max-height:320px;margin:8px 0 0;padding:10px;font:11px/1.55 ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;overflow:auto}.trial-panel{border:0;border-left:1px solid var(--line-strong);background:var(--surface);width:min(780px,100vw - 80px);max-width:none;height:100dvh;max-height:none;color:var(--ink);flex-direction:column;margin:0;padding:0;position:fixed;inset:0 0 0 auto;overflow:hidden;box-shadow:-12px 0 36px #00000014}.trial-panel[open]{display:flex}.trial-panel::backdrop{-webkit-backdrop-filter:blur(1px);backdrop-filter:blur(1px);background:#ffffff52}.trial-panel-header{border-bottom:1px solid var(--line);flex:none;justify-content:space-between;align-items:flex-start;gap:16px;padding:22px 28px 18px;display:flex}.trial-panel-heading{min-width:0}.trial-panel-heading h2{letter-spacing:-.035em;margin:12px 0 2px;font-size:24px}.trial-panel-heading>p{color:var(--muted);overflow-wrap:anywhere;margin:0}.trial-breadcrumbs{color:var(--muted);flex-wrap:wrap;align-items:center;gap:5px 8px;font-size:12px;display:flex}.trial-breadcrumbs a,.trial-breadcrumbs button{color:var(--muted);font:inherit;background:0 0;border:0;padding:0;text-decoration:none}.trial-breadcrumbs a:hover,.trial-breadcrumbs button:hover{color:var(--ink);text-decoration:underline}.trial-breadcrumbs [aria-current=page]{color:var(--ink);font-weight:650}.trial-panel-close{border:1px solid var(--line);background:var(--surface);width:36px;height:36px;color:var(--ink);flex:none;font-size:24px;line-height:1}.trial-panel-close:hover{background:var(--surface-subtle)}.trial-panel-body{overscroll-behavior:contain;flex:1;padding:22px 28px 40px;overflow:auto}.trial-panel .trial-inspector{flex-direction:column;align-items:stretch;gap:26px;display:flex}.trial-panel .metadata-list{grid-template-columns:136px minmax(0,1fr)}.trial-panel .trial-overview{border:0;padding:0}.trial-panel .trial-overview>p:first-child,.trial-panel .workspace-inspector>p:first-child{display:none}.trial-panel .trial-overview h2{font-size:15px}.trial-panel .trial-overview>button{background:var(--surface);border-color:var(--line-strong);color:var(--ink);margin:2px 0 18px;padding:7px 10px;font-size:12px}.trial-panel .trial-overview>button:hover{background:var(--surface-subtle)}.trial-panel .timeline{border-top:1px solid var(--line);padding-top:20px}.trial-panel .workspace-inspector table{display:block;overflow-x:auto}.trial-panel .trial-overview .compact-table{max-width:100%;display:block;overflow-x:auto}@media (width<=980px){.runs-layout{grid-template-columns:minmax(0,1fr)}.runs-filter-panel{max-height:320px}}@media (width<=740px){.dashboard-shell,.dashboard-shell.navigation-collapsed{grid-template-rows:auto minmax(0,1fr);grid-template-columns:minmax(0,1fr)}.dashboard-shell>aside{border-right:0;border-bottom:1px solid var(--sidebar);padding:6px 14px}.nav-top,.navigation-collapsed .nav-top{justify-content:flex-start;min-height:38px;margin:0}.nav-top .brand{order:1;margin-left:8px}.dashboard-shell>aside nav{flex-wrap:wrap;gap:4px;margin:3px 0 7px;display:flex}.dashboard-shell>aside nav a{min-height:34px;padding:6px 10px}.content{padding:18px 14px 36px}.content>header{margin-bottom:14px;padding-bottom:12px}.trial-inspector{grid-template-columns:minmax(0,1fr)}}@media (width<=600px){.trial-panel{border-left:0;width:100vw}.trial-panel-header{padding:18px 18px 14px}.trial-panel-body{padding:18px 18px 36px}}@media (prefers-reduced-motion:reduce){.dashboard-shell{transition:none}}@media (width<=520px){.matrix-filter{grid-template-columns:minmax(0,1fr) auto;display:grid}.matrix-filter input{grid-area:2/1/auto/-1;width:100%}.matrix-filter span{grid-area:1/2}.trial-summary{grid-template-columns:repeat(2,minmax(0,1fr))}.trial-summary div:nth-child(2){border-right:0}.trial-summary div:nth-child(-n+2){border-bottom:1px solid var(--line)}.runs-filter-panel{max-height:min(55vh,300px)}}@media (pointer:coarse){.dashboard-shell>aside nav a,.navigation-toggle,.table-link,.data-table button:not(.table-sort),.table-sort,.matrix-pages button,.runs-choice,.clear-filters,.runs-filter-panel>summary{align-items:center;min-height:44px;display:inline-flex}.runs-choice,.runs-filter-panel>summary{display:flex}.matrix-filter input,.runs-date input{min-height:44px;font-size:16px}}