Commit Graph

5 Commits

Author SHA1 Message Date
80a7bedddc fix: ranking shows all reviewed projects, fix override badge sync issue
All checks were successful
Build and Push Docker Image / build (push) Successful in 10m17s
- AI ranking now includes ALL projects (never filters/excludes any)
- Updated system prompt: filter criteria inform priority, not exclusion
- Dynamic maxTokens scaling for large project pools (80 tokens/project)
- Fallback: projects AI omits are appended sorted by composite score
- Override badge uses snapshotOrder state (synced with localOrder in same
  useEffect) instead of rankingMap.originalIndex to prevent stale-render
  mismatch where all items incorrectly showed as overridden

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 14:10:48 +01:00
2df9c54de2 fix: backfill binaryDecision, fix boolean criterion lookup, add assign buttons
All checks were successful
Build and Push Docker Image / build (push) Successful in 10m9s
- Backfilled 166 evaluations' binaryDecision from criterionScoresJson on production DB
- Fixed roundEvaluationScores and ai-ranking to look in EvaluationForm.criteriaJson
  instead of round.configJson for the boolean "Move to the Next Stage?" criterion
- Added advanceMode (count/threshold) toggle to round config Advancement Targets
- Added "Assign to Jurors" button on Unassigned Projects section and Projects tab bulk bar

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 12:48:08 +01:00
19b58e4434 feat: weighted criteria in AI ranking, z-score normalization, threshold advancement, CSV export
All checks were successful
Build and Push Docker Image / build (push) Successful in 9m16s
- 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>
2026-03-02 11:24:14 +01:00
c6ebd169dd feat: admin evaluation editing, ranking improvements, status transition fix
All checks were successful
Build and Push Docker Image / build (push) Successful in 9m26s
- Add adminEditEvaluation mutation and getJurorEvaluations query
- Create shared EvaluationEditSheet component with inline feedback editing
- Add Evaluations tab to member detail page (grouped by round)
- Make jury group member names clickable (link to member detail)
- Replace inline EvaluationDetailSheet on project page with shared component
- Fix project status transition validation (skip when status unchanged)
- Fix frontend to not send status when unchanged on project edit
- Ranking dashboard improvements and boolean decision converter fixes
- Backfill script updates for binary decisions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 10:46:52 +01:00
aa383f53f8 feat(01-02): create ai-ranking.ts service with criteria parsing and ranking
- Add parseRankingCriteria() — parses natural-language criteria via OpenAI JSON mode
- Add executeAIRanking() — anonymizes projects (P001…), calls OpenAI, de-anonymizes results
- Add quickRank() — one-shot helper that parses + ranks both categories in parallel
- Add fetchAndRankCategory() — fetches eligible projects from Prisma and calls executeAIRanking
- compositeScore: 50% normalised avgGlobalScore + 50% passRate + tiny tiebreak bonus
- Projects with zero SUBMITTED evaluations are excluded (not ranked last)
- All project IDs anonymized before OpenAI — no PII in prompts
- Follows ai-filtering.ts pattern: getOpenAI, logAIUsage with action RANKING, classifyAIError
2026-02-27 00:48:09 +01:00