retrieval: remove the cross-encoder reranker (ablation showed no earned keep) (#100)

eval: built-in rerank ablation, judge on paid hy3, answer-latency measurement (#94)

enrichment: paid hy3, batch 50, and per-batch checkpoint push (#93)

QuOTE questions in the enrichment pipeline + one-click eval default (#88)

Eval knobs as workflow inputs: rerank on/off and k (#86)

Answer-quality eval (LLM-judge) + hy3-led OpenRouter default (#81)

Consolidate the Actions list: 9 workflows -> 5, one Eval button

Remove superseded manual workflows from the Actions list

Revert the embedder to bge-small: the bge-base A/B showed no gain

Swap the embedder: bge-small (384d) -> bge-base (768d)

openai-compat: fall back across a chain of free models on rate-limit

Eval workflow: default to grounded=true (the real M2 test)

M2 wiring: grounded answers with validated citations + grounded eval mode

Workflows: read secrets by their actual repo names (GOOGLE_API, NEON)

Eval workflow: model as input (free slugs rotate); fail fast on 404 model-gone

Eval workflow: read the OpenRouter key from the 'OPENROUTER' repo secret

Add manual Eval workflow: run v0 eval on Actions runners, commit results back