cleanup: remove the translation module — the guard is English-only now (#105)

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

Make the deploy usable: strip/redact API keys + gate non-English + faster QuOTE (#91)

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

Reranker as the precision stage + fold glossing into Build Index (#85)

Contextual Retrieval: LLM glosses for api reference pages

Add the v1 eval dataset: 100 valid + 100 invalid + 20 agentic

Ground the eval in EXTERNAL docs truth, not our own index

Add an index-manifest dump to ground the eval set in verified sources

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

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

Guard: replace the injection classifier with embedding-space membership

Add input guard: prompt-injection + topicality check on the user's question

Codebase quality pass: kill silent-truncation hacks, fix latent bugs, cover them (#46)

Fix smoke test harness: gradio_client token kwarg and empty question (#42)

OpenRouter free-tier resilience + GEMINI alias + live HF Space smoke test (#41)

M3: three tools + manual agent loop (planner-driven, budgeted)

Add non-English query translation (via OpenRouter) before retrieval

Fix polluted anchors/titles, purge stale chunks, add channel debug to search

Add search CLI + Search workflow: retrieval acceptance testing from the Actions UI

Switch embeddings to a local CPU model (bge-small): free tier APIs can't index the corpus

Build Index: fail fast on missing secrets, stream progress unbuffered

M2 indexing: Neon schema, resumable Gemini embedding, one-command build script

Make Gemini the default generation provider (free tier)

Add M0 smoke script: Neon write/read, one LLM call, one Gemini embedding

Scaffold repo structure per M0 (pyproject, ruff, pytest, pre-commit)