Ajax Davis
|
ea742c9386
|
feat: add scenarios system for collection testing
Implements the complete scenarios feature for TPMJS:
API endpoints:
- GET/POST /api/scenarios - list/create scenarios
- GET/PATCH/DELETE /api/scenarios/:id - scenario CRUD
- POST /api/scenarios/:id/run - execute scenario
- GET /api/scenarios/:id/runs - run history
- POST /api/scenarios/check-similarity - vector similarity check
- GET /api/scenarios/featured - featured scenarios
- POST /api/collections/:id/scenarios/generate - AI scenario generation
- GET /api/collections/:id/scenarios - list collection scenarios
Services:
- generate-prompt.ts - AI prompt generation using GPT-4o-mini
- similarity.ts - vector embedding and cosine similarity
- evaluate.ts - LLM-based success evaluation
- execute.ts - scenario execution orchestration
CLI commands:
- tpm scenario list [collection] - list scenarios
- tpm scenario run <collection> - run all scenarios
- tpm scenario test <id> - run single scenario
- tpm scenario generate <collection> - generate scenarios
- tpm scenario info <id> - scenario details
Database:
- Scenario, ScenarioEmbedding, ScenarioRun, ScenarioQuota models
- Streak-based quality scoring
- Daily quota management
Migration script included for converting existing useCases.
|
2026-01-18 09:31:31 +10:00 |
|