diegosouzapw 0ed7738c7c feat: add LLM evaluation framework with golden set testing ...

Introduce built-in eval system for testing LLM response quality against
golden sets. Includes eval runner with 4 match strategies (exact,
contains, regex, custom), a pre-loaded 10-case golden set, REST API
endpoints for managing and running suites, and a dashboard UI under
Analytics → Evals with real-time progress tracking and pass rate
summaries. Also adds OpenAPI tags for Audio, Moderations, and Rerank.

2026-02-15 18:37:18 -03:00

..

adr

feat: complete all 46 tasks — ADRs, eval framework, compliance, a11y, CLI, Playwright specs (Batch B)

2026-02-14 19:18:02 -03:00

ARCHITECTURE.md

refactor(phase5-6): domain persistence, policy engine, OAuth extraction, proxy decoupling

2026-02-15 08:12:12 -03:00

CODEBASE_DOCUMENTATION.md

feat: v0.2.0 — advanced routing services, cost analytics dashboard, pricing overhaul

2026-02-14 13:50:45 -03:00

openapi.yaml

feat: add LLM evaluation framework with golden set testing

2026-02-15 18:37:18 -03:00

TASKS.md

feat(resilience): rate limit overhaul — exponential backoff, circuit breaker, anti-thundering herd, Resilience UI

2026-02-15 01:42:50 -03:00