app+llm: stream the answer prose for perceived speed

app: move freshness self-heal fully to the background — kill the never-ending spinner

UI: send-on-Enter + live reasoning trace; docs: answer-cache decision (#106)

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

app: live bare spinner under the answer during the freshness check (#103)

freshness: stale-while-revalidate — self-heal cited pages, correct the live answer on drift (#101)

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

app: animate the thinking indicator so the answer wait never looks frozen (#99)

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

Concise answers + immediate thinking indicator (Ultralytics-style UX) (#90)

Route questions: grounded first, loop for multi-source shapes (#89)

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

Guard: replace the injection classifier with embedding-space membership

App backpressure and cleanups

Merge input guard branch (injection + topicality checks)

Serve questions concurrently instead of one-at-a-time (#49)

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

Add a license link under answer citations (#47)

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

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

M5: Gradio web app + HF Spaces deploy + live-hydrate fallback