Spaces:
Running
Running
File size: 40,643 Bytes
509e21e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 |
"use client"
import { useState, useEffect, useMemo } from "react"
import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card"
import { Button } from "@/components/ui/button"
import { RadioGroup, RadioGroupItem } from "@/components/ui/radio-group"
import { Label } from "@/components/ui/label"
import { Textarea } from "@/components/ui/textarea"
import { Input } from "@/components/ui/input"
import { Badge } from "@/components/ui/badge"
import { Separator } from "@/components/ui/separator"
import type { CategoryScore } from "@/components/ai-evaluation-dashboard"
import { HelpCircle, CheckCircle, Plus, Trash2 } from "lucide-react"
import { Tooltip, TooltipContent, TooltipProvider, TooltipTrigger } from "@/components/ui/tooltip"
import { BENCHMARK_QUESTIONS, PROCESS_QUESTIONS, SOURCE_TYPES, ADDITIONAL_ASPECTS_SECTION, getFieldPlaceholder, getHint } from "@/lib/category-data"
// The detailed per-category and per-question hints, plus recommended placeholders,
// are centralized in `lib/category-data.ts`. This component uses the exported
// helpers `getHint` and `getFieldPlaceholder` and the question lists.
const CustomFieldComponent = ({
questionId,
fieldType,
value,
onChange,
}: {
questionId: string
fieldType: string
value: string
onChange: (value: string) => void
}) => {
const getFieldConfig = (questionId: string, fieldType: string) => {
const configs: Record<string, Record<string, { label: string; placeholder: string; type?: string }>> = {
A2: {
thresholds: { label: "Quantitative Thresholds", placeholder: "e.g., >85% accuracy, <0.1 error rate" },
thresholdSource: {
label: "Threshold Source",
placeholder: "e.g., industry standard, research paper, policy requirement",
},
passFail: { label: "Pass/Fail Determination", placeholder: "e.g., Pass - exceeded 85% threshold" },
},
A3: {
comparativeScores: {
label: "Comparative Scores",
placeholder: "e.g., Our model: 87.2%, GPT-4: 85.1%, Previous version: 82.3%",
},
baselineType: { label: "Baseline Type", placeholder: "e.g., SOTA, previous version, industry standard" },
significance: { label: "Statistical Significance", placeholder: "e.g., p<0.05, 95% CI: [1.2, 3.8]" },
},
A4: {
testTypes: { label: "Test Types", placeholder: "e.g., adversarial attacks, load testing, distribution shift" },
failureRates: { label: "Failure/Degradation Rates", placeholder: "e.g., 15% failure under adversarial inputs" },
robustnessMetrics: {
label: "Robustness Metrics",
placeholder: "e.g., attack success rate, performance drop %",
},
},
A5: {
liveMetrics: { label: "Live Metrics Tracked", placeholder: "e.g., error rates, latency, drift detection" },
samplingCadence: { label: "Sampling Cadence", placeholder: "e.g., every 1000 requests, hourly, daily" },
alertThresholds: { label: "Alert Thresholds", placeholder: "e.g., >5% error rate, >500ms latency" },
},
A6: {
procedure: {
label: "Contamination Check Procedure",
placeholder: "e.g., n-gram overlap analysis, URL deduplication",
},
contaminationRate: {
label: "Contamination Rate",
placeholder: "e.g., <1% overlap detected, 0.3% exact matches",
},
mitigations: { label: "Mitigations Taken", placeholder: "e.g., removed overlapping samples, used holdout set" },
},
A7: {
comparisonSystems: { label: "Comparison Systems", placeholder: "e.g., GPT-4, Claude-3, Gemini Pro" },
evaluationConditions: {
label: "Evaluation Conditions",
placeholder: "e.g., same prompts, temperature=0, identical hardware",
},
relativeMetrics: {
label: "Relative Performance Metrics",
placeholder: "e.g., 15% better accuracy, 2x faster inference",
},
},
B1: {
scope: {
label: "Evaluation Scope",
placeholder: "e.g., measures reasoning capability in mathematical contexts",
},
successFailureDefinitions: {
label: "Success/Failure Definitions",
placeholder: "e.g., success = >80% on grade-level problems",
},
hypotheses: { label: "Hypotheses Being Tested", placeholder: "e.g., model can solve multi-step word problems" },
},
B2: {
replicationPackage: {
label: "Replication Package",
placeholder: "e.g., GitHub repo with code, configs, prompts",
},
accessLevel: { label: "Access Level", placeholder: "e.g., public, access-controlled, internal only" },
proxies: { label: "Proxies (if not shareable)", placeholder: "e.g., synthetic examples, anonymized data" },
},
B5: {
reviewers: { label: "Reviewers", placeholder: "e.g., domain experts, affected user groups, ethics board" },
feedbackChanges: {
label: "Changes from Feedback",
placeholder: "e.g., added bias metrics, revised interpretation",
},
disagreements: {
label: "Unresolved Disagreements",
placeholder: "e.g., threshold levels, risk severity ratings",
},
},
B6: {
uncertaintyDisclosure: {
label: "Uncertainty Disclosure",
placeholder: "e.g., error bars, confidence intervals, variance across runs",
},
axesConsistency: { label: "Axes Consistency", placeholder: "e.g., consistent 0-100 scale, no truncated axes" },
sampleSizes: { label: "Sample Sizes", placeholder: "e.g., n=1000 test samples, 5 random seeds" },
selectionCriteria: { label: "Selection Criteria", placeholder: "e.g., all results shown, no cherry-picking" },
},
B8: {
triggers: {
label: "Re-evaluation Triggers",
placeholder: "e.g., model updates, data drift >5%, security incidents",
},
versionedSpecs: { label: "Versioned Eval Specs", placeholder: "e.g., eval spec v2.1, change log maintained" },
auditTrail: { label: "Audit Trail", placeholder: "e.g., all changes logged with timestamps and rationale" },
mitigationProtocols: {
label: "Mitigation Protocols",
placeholder: "e.g., automated rollback, manual review process",
},
retestProcedures: {
label: "Retest Procedures",
placeholder: "e.g., full eval suite after fixes, regression testing",
},
},
}
return configs[questionId]?.[fieldType] || { label: fieldType, placeholder: "" }
}
const config = getFieldConfig(questionId, fieldType)
return (
<div>
<Label className="text-xs font-medium">{config.label}</Label>
<Textarea
placeholder={config.placeholder}
value={value}
onChange={(e) => onChange(e.target.value)}
rows={2}
className="mt-1"
/>
</div>
)
}
// Local types used by this component (kept minimal for readability)
export type Source = {
id: string
url: string
description: string
sourceType: string
benchmarkName?: string
metrics?: string
score?: string
confidenceInterval?: string
version?: string
taskVariants?: string
customFields: Record<string, string>
}
export type DocumentationSource = {
id: string
url: string
description: string
sourceType: string
documentType?: string
title?: string
author?: string
organization?: string
date?: string
customFields: Record<string, string>
}
export type CategoryEvaluationProps = {
category: { id: string; name: string; description: string; type: string; detailedGuidance?: string }
score?: CategoryScore | null
onScoreUpdate: (score: CategoryScore) => void
}
export function CategoryEvaluation({ category, score, onScoreUpdate }: CategoryEvaluationProps) {
const [benchmarkAnswers, setBenchmarkAnswers] = useState<Record<string, string>>({})
const [processAnswers, setProcessAnswers] = useState<Record<string, string>>({})
const [benchmarkSources, setBenchmarkSources] = useState<Record<string, Source[]>>({})
const [processSources, setProcessSources] = useState<Record<string, DocumentationSource[]>>({})
const [additionalAspects, setAdditionalAspects] = useState<string>("")
const [naExplanations, setNaExplanations] = useState<Record<string, string>>({})
useEffect(() => {
if (score) {
// This would be populated from saved data in a real implementation
// For now, we'll calculate based on the scores
}
}, [score])
const addSource = (questionId: string, section: "benchmark" | "process") => {
if (section === "benchmark") {
const newSource: Source = {
id: Date.now().toString(),
url: "",
description: "",
sourceType: "internal",
benchmarkName: "",
metrics: "",
score: "",
confidenceInterval: "",
version: "",
taskVariants: "",
customFields: {},
}
setBenchmarkSources((prev) => ({
...prev,
[questionId]: [...(prev[questionId] || []), newSource],
}))
} else {
const newDocSource: DocumentationSource = {
id: Date.now().toString(),
url: "",
description: "",
sourceType: "internal",
documentType: "",
title: "",
author: "",
organization: "",
date: "",
customFields: {},
}
setProcessSources((prev) => ({
...prev,
[questionId]: [...(prev[questionId] || []), newDocSource],
}))
}
}
const removeSource = (questionId: string, sourceId: string, section: "benchmark" | "process") => {
if (section === "benchmark") {
setBenchmarkSources((prev) => ({
...prev,
[questionId]: (prev[questionId] || []).filter((s) => s.id !== sourceId),
}))
} else {
setProcessSources((prev) => ({
...prev,
[questionId]: (prev[questionId] || []).filter((s) => s.id !== sourceId),
}))
}
}
const updateSource = (
questionId: string,
sourceId: string,
field: string,
value: string,
section: "benchmark" | "process",
) => {
if (section === "benchmark") {
setBenchmarkSources((prev) => ({
...prev,
[questionId]: (prev[questionId] || []).map((source) =>
source.id === sourceId ? { ...source, [field]: value } : source,
),
}))
} else {
setProcessSources((prev) => ({
...prev,
[questionId]: (prev[questionId] || []).map((source) =>
source.id === sourceId ? { ...source, [field]: value } : source,
),
}))
}
}
const updateSourceCustomField = (
questionId: string,
sourceId: string,
fieldType: string,
value: string,
section: "benchmark" | "process",
) => {
if (section === "benchmark") {
setBenchmarkSources((prev) => ({
...prev,
[questionId]: (prev[questionId] || []).map((source) =>
source.id === sourceId
? {
...source,
customFields: {
...source.customFields,
[fieldType]: value,
},
}
: source,
),
}))
} else {
setProcessSources((prev) => ({
...prev,
[questionId]: (prev[questionId] || []).map((source) =>
source.id === sourceId
? {
...source,
customFields: {
...source.customFields,
[fieldType]: value,
},
}
: source,
),
}))
}
}
const currentScore = useMemo(() => {
// Calculate counts
const totalBenchmarkQuestions = BENCHMARK_QUESTIONS.length
const totalProcessQuestions = PROCESS_QUESTIONS.length
const totalQuestions = totalBenchmarkQuestions + totalProcessQuestions
const benchmarkYesCount = Object.values(benchmarkAnswers).filter((answer) => answer === "yes").length
const processYesCount = Object.values(processAnswers).filter((answer) => answer === "yes").length
const benchmarkNaCount = Object.values(benchmarkAnswers).filter((answer) => answer === "na").length
const processNaCount = Object.values(processAnswers).filter((answer) => answer === "na").length
const naCount = benchmarkNaCount + processNaCount
const totalYes = benchmarkYesCount + processYesCount
// Denominator = total questions in the category minus NA answers
const totalApplicable = Math.max(0, totalQuestions - naCount)
const scorePercentage = totalApplicable > 0 ? totalYes / totalApplicable : 0
let status: CategoryScore["status"]
if (scorePercentage >= 0.8) status = "strong"
else if (scorePercentage >= 0.6) status = "adequate"
else if (scorePercentage >= 0.4) status = "weak"
else status = "insufficient"
const result = {
benchmarkScore: benchmarkYesCount,
processScore: processYesCount,
totalScore: totalYes,
status,
totalQuestions,
totalApplicable,
naCount,
}
return result
}, [benchmarkAnswers, processAnswers])
const handleAnswerChange = (questionId: string, value: string, section: "benchmark" | "process") => {
if (section === "benchmark") {
setBenchmarkAnswers((prev) => ({ ...prev, [questionId]: value }))
if (value !== "yes") {
setBenchmarkSources((prev) => ({ ...prev, [questionId]: [] }))
}
if (value !== "na") {
setNaExplanations((prev) => {
const newExplanations = { ...prev }
delete newExplanations[questionId]
return newExplanations
})
}
} else {
setProcessAnswers((prev) => ({ ...prev, [questionId]: value }))
if (value !== "yes") {
setProcessSources((prev) => ({ ...prev, [questionId]: [] }))
}
if (value !== "na") {
setNaExplanations((prev) => {
const newExplanations = { ...prev }
delete newExplanations[questionId]
return newExplanations
})
}
}
}
const handleNaExplanationChange = (questionId: string, explanation: string) => {
setNaExplanations((prev) => ({ ...prev, [questionId]: explanation }))
}
const handleSave = () => {
const allAnswers = { ...benchmarkAnswers, ...processAnswers }
const missingExplanations = Object.entries(allAnswers)
.filter(([_, answer]) => answer === "na")
.filter(([questionId, _]) => !naExplanations[questionId]?.trim())
.map(([questionId, _]) => questionId)
if (missingExplanations.length > 0) {
alert(
`Please provide explanations for why the following questions are not applicable: ${missingExplanations.join(", ")}`,
)
return
}
console.log("[v0] Saving category evaluation")
console.log("[v0] Calling onScoreUpdate with:", currentScore)
onScoreUpdate(currentScore)
}
const isComplete =
Object.keys(benchmarkAnswers).length + Object.keys(processAnswers).length === BENCHMARK_QUESTIONS.length + PROCESS_QUESTIONS.length
return (
<TooltipProvider>
<div className="space-y-6">
<Card>
<CardHeader>
<div className="flex items-center justify-between">
<div className="flex-1">
<CardTitle className="font-heading flex items-center gap-2">
{category.name}
<Badge variant={category.type === "capability" ? "secondary" : "destructive"}>{category.type}</Badge>
</CardTitle>
<CardDescription className="mt-2">{category.description}</CardDescription>
</div>
{isComplete && (
<div className="text-right">
<div className="flex items-center gap-2 mb-1">
<CheckCircle className="h-5 w-5 text-green-600" />
<span className="font-medium">Score: {currentScore.totalScore}/{currentScore.totalApplicable || currentScore.totalQuestions}</span>
</div>
<Badge
variant={
currentScore.status === "strong"
? "default"
: currentScore.status === "adequate"
? "secondary"
: currentScore.status === "weak"
? "outline"
: "destructive"
}
>
{currentScore.status.charAt(0).toUpperCase() + currentScore.status.slice(1)}
</Badge>
</div>
)}
</div>
</CardHeader>
<CardContent>
<div className="space-y-4">
<div className="bg-muted/30 p-4 rounded-lg">
<h4 className="font-medium mb-2">Source Types</h4>
<div className="grid gap-2 text-sm">
{Object.entries(SOURCE_TYPES).map(([key, type]) => (
<div key={key}>
<span className="font-medium">{type.label}:</span> {type.description}
</div>
))}
</div>
</div>
<div className="bg-muted/30 p-4 rounded-lg">
<h4 className="font-medium mb-2">Evaluation Guidance</h4>
<p className="text-sm mb-2 font-medium">
Note: The benchmarks and evaluations listed below are suggested examples, not exhaustive requirements.
You may use other relevant benchmarks and evaluation methods appropriate for your system.
</p>
<div className="text-sm whitespace-pre-line">{category.detailedGuidance}</div>
</div>
</div>
</CardContent>
</Card>
<Card>
<CardHeader>
<CardTitle className="text-lg">Part A: Benchmark & Testing Evaluation</CardTitle>
<CardDescription>
Quantitative assessment through standardized tests and measurements ({currentScore.benchmarkScore}/6)
</CardDescription>
</CardHeader>
<CardContent className="space-y-6">
{BENCHMARK_QUESTIONS.map((question) => (
<div key={question.id} className="space-y-3">
<div className="flex items-start gap-2">
<Label className="text-sm font-medium flex-1">
{question.id}. {question.text}
</Label>
<Tooltip>
<TooltipTrigger>
<HelpCircle className="h-4 w-4 text-muted-foreground" />
</TooltipTrigger>
<TooltipContent className="max-w-sm">
<p>{question.tooltip}</p>
</TooltipContent>
</Tooltip>
</div>
<RadioGroup
value={benchmarkAnswers[question.id] || ""}
onValueChange={(value) => handleAnswerChange(question.id, value, "benchmark")}
>
<div className="flex items-center space-x-2">
<RadioGroupItem value="yes" id={`${question.id}-yes`} />
<Label htmlFor={`${question.id}-yes`}>Yes</Label>
</div>
<div className="flex items-center space-x-2">
<RadioGroupItem value="no" id={`${question.id}-no`} />
<Label htmlFor={`${question.id}-no`}>No</Label>
</div>
<div className="flex items-center space-x-2">
<RadioGroupItem value="na" id={`${question.id}-na`} />
<Label htmlFor={`${question.id}-na`}>Not Applicable</Label>
</div>
</RadioGroup>
{benchmarkAnswers[question.id] === "na" && (
<div className="ml-4 p-4 bg-yellow-50 dark:bg-yellow-900/20 border border-yellow-200 dark:border-yellow-800 rounded-lg">
<Label className="text-sm font-medium text-yellow-800 dark:text-yellow-200">
Explanation Required: Why is this question not applicable?
</Label>
<Textarea
placeholder="Please explain why this question/category is not applicable to your system. This explanation will be included in the evaluation documentation."
value={naExplanations[question.id] || ""}
onChange={(e) => handleNaExplanationChange(question.id, e.target.value)}
rows={3}
className="mt-2 border-yellow-300 dark:border-yellow-700"
required
/>
</div>
)}
{benchmarkAnswers[question.id] === "yes" && (
<div className="space-y-4 ml-4 p-4 bg-muted/30 rounded-lg">
<div className="flex items-center justify-between">
<Label className="text-sm font-medium">Sources & Evidence</Label>
<Button
type="button"
variant="outline"
size="sm"
onClick={() => addSource(question.id, "benchmark")}
className="flex items-center gap-1"
>
<Plus className="h-3 w-3" />
Add Source
</Button>
</div>
{(benchmarkSources[question.id] || []).map((source, index) => (
<div key={source.id} className="space-y-3 p-3 border rounded-lg bg-background">
<div className="flex items-center justify-between">
<span className="text-sm font-medium">Source {index + 1}</span>
<Button
type="button"
variant="ghost"
size="sm"
onClick={() => removeSource(question.id, source.id, "benchmark")}
>
<Trash2 className="h-3 w-3" />
</Button>
</div>
<div className="grid gap-3">
{/* no structured hint here; description has contextual hints */}
<div>
<Label className="text-xs">Benchmark/Dataset Name</Label>
<Input
placeholder={getFieldPlaceholder(category.id, question.id, "benchmarkName")}
value={source.benchmarkName || ""}
onChange={(e) =>
updateSource(question.id, source.id, "benchmarkName", e.target.value, "benchmark")
}
/>
</div>
<div className="grid grid-cols-2 gap-3">
<div>
<Label className="text-xs">Version</Label>
<Input
placeholder="e.g., v1.2, 2024-01"
value={source.version || ""}
onChange={(e) =>
updateSource(question.id, source.id, "version", e.target.value, "benchmark")
}
/>
</div>
<div>
<Label className="text-xs">Task Variants</Label>
<Input
placeholder="e.g., multiple choice, generation"
value={source.taskVariants || ""}
onChange={(e) =>
updateSource(question.id, source.id, "taskVariants", e.target.value, "benchmark")
}
/>
</div>
</div>
<div>
<Label className="text-xs">Metrics</Label>
<Input
placeholder={getFieldPlaceholder(category.id, question.id, "metrics")}
value={source.metrics || ""}
onChange={(e) =>
updateSource(question.id, source.id, "metrics", e.target.value, "benchmark")
}
/>
</div>
<div>
<Label className="text-xs">URL</Label>
<Input
placeholder="https://..."
value={source.url}
onChange={(e) => updateSource(question.id, source.id, "url", e.target.value, "benchmark")}
/>
</div>
<div>
<Label className="text-xs">Description</Label>
<Textarea
placeholder="Describe the benchmark, test, or evaluation method..."
value={source.description}
onChange={(e) =>
updateSource(question.id, source.id, "description", e.target.value, "benchmark")
}
rows={2}
/>
<p className="text-xs text-muted-foreground mt-1">
{getHint(category.id, question.id, "benchmark")}
</p>
</div>
<div className="grid grid-cols-2 gap-3">
<div>
<Label className="text-xs">Source Type</Label>
<RadioGroup
value={source.sourceType}
onValueChange={(value) =>
updateSource(question.id, source.id, "sourceType", value, "benchmark")
}
>
{Object.entries(SOURCE_TYPES).map(([key, type]) => (
<div key={key} className="flex items-center space-x-2">
<RadioGroupItem value={key} id={`${source.id}-${key}`} />
<Label htmlFor={`${source.id}-${key}`} className="text-xs">
{type.label}
</Label>
</div>
))}
</RadioGroup>
</div>
<div>
<Label className="text-xs">Score (if applicable)</Label>
<Input
placeholder="e.g., 85%, 0.92, Pass"
value={source.score || ""}
onChange={(e) =>
updateSource(question.id, source.id, "score", e.target.value, "benchmark")
}
/>
<Label className="text-xs mt-2">Confidence Interval (optional)</Label>
<Input
placeholder="e.g., 95% CI [90,94]"
value={(source as any).confidenceInterval || ""}
onChange={(e) =>
updateSource(question.id, source.id, "confidenceInterval", e.target.value, "benchmark")
}
/>
</div>
</div>
</div>
</div>
))}
{(benchmarkSources[question.id] || []).length === 0 && (
<div className="text-center py-4 text-muted-foreground text-sm">
Click "Add Source" to document benchmarks and evidence
</div>
)}
</div>
)}
<Separator />
</div>
))}
</CardContent>
</Card>
<Card>
<CardHeader>
<CardTitle className="text-lg">Part B: Documentation & Process Evaluation</CardTitle>
<CardDescription>
Governance, transparency, and risk management processes ({currentScore.processScore}/5)
</CardDescription>
</CardHeader>
<CardContent className="space-y-6">
{PROCESS_QUESTIONS.map((question) => (
<div key={question.id} className="space-y-3">
<div className="flex items-start gap-2">
<Label className="text-sm font-medium flex-1">
{question.id}. {question.text}
</Label>
<Tooltip>
<TooltipTrigger>
<HelpCircle className="h-4 w-4 text-muted-foreground" />
</TooltipTrigger>
<TooltipContent className="max-w-sm">
<p>{question.tooltip}</p>
</TooltipContent>
</Tooltip>
</div>
<RadioGroup
value={processAnswers[question.id] || ""}
onValueChange={(value) => handleAnswerChange(question.id, value, "process")}
>
<div className="flex items-center space-x-2">
<RadioGroupItem value="yes" id={`${question.id}-yes`} />
<Label htmlFor={`${question.id}-yes`}>Yes</Label>
</div>
<div className="flex items-center space-x-2">
<RadioGroupItem value="no" id={`${question.id}-no`} />
<Label htmlFor={`${question.id}-no`}>No</Label>
</div>
<div className="flex items-center space-x-2">
<RadioGroupItem value="na" id={`${question.id}-na`} />
<Label htmlFor={`${question.id}-na`}>Not Applicable</Label>
</div>
</RadioGroup>
{processAnswers[question.id] === "na" && (
<div className="ml-4 p-4 bg-yellow-50 dark:bg-yellow-900/20 border border-yellow-200 dark:border-yellow-800 rounded-lg">
<Label className="text-sm font-medium text-yellow-800 dark:text-yellow-200">
Explanation Required: Why is this question not applicable?
</Label>
<Textarea
placeholder="Please explain why this question/category is not applicable to your system. This explanation will be included in the evaluation documentation."
value={naExplanations[question.id] || ""}
onChange={(e) => handleNaExplanationChange(question.id, e.target.value)}
rows={3}
className="mt-2 border-yellow-300 dark:border-yellow-700"
required
/>
</div>
)}
{processAnswers[question.id] === "yes" && (
<div className="space-y-4 ml-4 p-4 bg-muted/30 rounded-lg">
<div className="flex items-center justify-between">
<Label className="text-sm font-medium">Documentation & Evidence</Label>
<Button
type="button"
variant="outline"
size="sm"
onClick={() => addSource(question.id, "process")}
className="flex items-center gap-1"
>
<Plus className="h-3 w-3" />
Add Documentation
</Button>
</div>
{(processSources[question.id] || []).map((source, index) => (
<div key={source.id} className="space-y-3 p-3 border rounded-lg bg-background">
<div className="flex items-center justify-between">
<span className="text-sm font-medium">Document {index + 1}</span>
<Button
type="button"
variant="ghost"
size="sm"
onClick={() => removeSource(question.id, source.id, "process")}
>
<Trash2 className="h-3 w-3" />
</Button>
</div>
<div className="grid gap-3">
{/* no structured hint here; description has contextual hints */}
<div>
<Label className="text-xs">URL</Label>
<Input
placeholder="https://..."
value={source.url}
onChange={(e) => updateSource(question.id, source.id, "url", e.target.value, "process")}
/>
</div>
<div>
<Label className="text-xs">Description</Label>
<Textarea
placeholder="Describe the documentation, policy, or process..."
value={source.description}
onChange={(e) =>
updateSource(question.id, source.id, "description", e.target.value, "process")
}
rows={2}
/>
<p className="text-xs text-muted-foreground mt-1">
{getHint(category.id, question.id, "process")}
</p>
</div>
<div className="grid grid-cols-2 gap-3">
<div>
<Label className="text-xs">Source Type</Label>
<RadioGroup
value={source.sourceType}
onValueChange={(value) =>
updateSource(question.id, source.id, "sourceType", value, "process")
}
>
{Object.entries(SOURCE_TYPES).map(([key, type]) => (
<div key={key} className="flex items-center space-x-2">
<RadioGroupItem value={key} id={`${source.id}-${key}`} />
<Label htmlFor={`${source.id}-${key}`} className="text-xs">
{type.label}
</Label>
</div>
))}
</RadioGroup>
</div>
<div>
<Label className="text-xs">Document Type</Label>
<Input
placeholder="e.g., Policy, Procedure, Report"
value={source.documentType || ""}
onChange={(e) =>
updateSource(question.id, source.id, "documentType", e.target.value, "process")
}
/>
</div>
</div>
<div className="grid grid-cols-2 gap-3 mt-2">
<div>
<Label className="text-xs">Title</Label>
<Input
placeholder="Document title"
value={(source as any).title || ""}
onChange={(e) => updateSource(question.id, source.id, "title", e.target.value, "process")}
/>
</div>
<div>
<Label className="text-xs">Author</Label>
<Input
placeholder="Author or owner"
value={(source as any).author || ""}
onChange={(e) => updateSource(question.id, source.id, "author", e.target.value, "process")}
/>
</div>
</div>
<div className="grid grid-cols-2 gap-3 mt-2">
<div>
<Label className="text-xs">Organization</Label>
<Input
placeholder="Owning org"
value={(source as any).organization || ""}
onChange={(e) => updateSource(question.id, source.id, "organization", e.target.value, "process")}
/>
</div>
<div>
<Label className="text-xs">Date</Label>
<Input
placeholder="YYYY-MM-DD"
value={(source as any).date || ""}
onChange={(e) => updateSource(question.id, source.id, "date", e.target.value, "process")}
/>
</div>
</div>
</div>
</div>
))}
{(processSources[question.id] || []).length === 0 && (
<div className="text-center py-4 text-muted-foreground text-sm">
Click "Add Documentation" to document policies and processes
</div>
)}
</div>
)}
<Separator />
</div>
))}
</CardContent>
</Card>
<Card>
<CardHeader>
<CardTitle className="text-lg">Part C: Additional Evaluation Aspects</CardTitle>
<CardDescription>{ADDITIONAL_ASPECTS_SECTION.description}</CardDescription>
</CardHeader>
<CardContent>
<div className="space-y-3">
<Label className="text-sm font-medium">
Additional evaluation aspects, methods, or considerations for this category:
</Label>
<Textarea
placeholder="Document any other evaluation approaches, considerations, or aspects that may not have been captured by the structured questions above. This could include novel evaluation methods, domain-specific considerations, or unique aspects of your system's evaluation..."
value={additionalAspects}
onChange={(e) => setAdditionalAspects(e.target.value)}
rows={6}
className="min-h-[120px]"
/>
<p className="text-xs text-muted-foreground">
This section is for documentation purposes and will not affect the numerical score but will be included
in the final evaluation report.
</p>
</div>
</CardContent>
</Card>
<div className="flex justify-center">
<Button onClick={handleSave} disabled={!isComplete} size="lg" className="w-full max-w-md">
{score ? "Update" : "Save"} Category Evaluation
</Button>
</div>
</div>
</TooltipProvider>
)
}
|