feat: weighted criteria in AI ranking, z-score normalization, threshold advancement, CSV export

- Add criteriaWeights to EvaluationConfig for per-criterion weight assignment (0-10)
- Rewrite ai-ranking service: fetch eval form criteria, compute per-criterion averages,
  z-score normalize juror scores to correct grading bias, send weighted criteria to AI
- Update AI prompts with criteria_definitions and per-project criteria_scores
- compositeScore uses weighted criteria when configured, falls back to globalScore
- Add collapsible ranking config section to dashboard (criteria text + weight sliders)
- Move rankingCriteria textarea from eval config tab to ranking dashboard
- Store criteriaWeights in ranking snapshot parsedRulesJson for audit
- Enhance projectScores CSV export with per-criterion averages, category, country
- Add Export CSV button to ranking dashboard header
- Add threshold-based advancement mode (decimal score threshold, e.g. 6.5)
  alongside existing top-N mode in advance dialog

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/components/admin/rounds/config/evaluation-config.tsx

@@ -4,7 +4,6 @@ import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/com
 import { Input } from '@/components/ui/input'
 import { Label } from '@/components/ui/label'
 import { Switch } from '@/components/ui/switch'
-import { Textarea } from '@/components/ui/textarea'
 import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select'
 
 type EvaluationConfigProps = {
@@ -225,7 +224,7 @@ export function EvaluationConfig({ config, onChange }: EvaluationConfigProps) {
             <div className="flex items-center justify-between">
               <div>
                 <Label htmlFor="autoRankEnabled">AI Ranking</Label>
-                <p className="text-xs text-muted-foreground">Rank projects using AI when all evaluations are complete</p>
+                <p className="text-xs text-muted-foreground">Rank projects using AI when all evaluations are complete. Configure ranking criteria and weights in the Ranking tab.</p>
               </div>
               <Switch
                 id="autoRankEnabled"
@@ -233,21 +232,6 @@ export function EvaluationConfig({ config, onChange }: EvaluationConfigProps) {
                 onCheckedChange={(v) => update('autoRankEnabled', v)}
               />
             </div>
-
-            <div className="space-y-2">
-              <Label htmlFor="rankingCriteria">Ranking Criteria</Label>
-              <p className="text-xs text-muted-foreground">
-                Natural-language criteria the AI uses to rank projects. E.g. &quot;Prioritize innovation and ocean impact. Weight jury scores 60%, feasibility 40%.&quot;
-              </p>
-              <Textarea
-                id="rankingCriteria"
-                rows={4}
-                placeholder="Describe how projects should be ranked..."
-                value={(config.rankingCriteria as string) ?? ''}
-                onChange={(e) => update('rankingCriteria', e.target.value)}
-                className="resize-y"
-              />
-            </div>
           </div>
         </CardContent>
       </Card>