Update README.md

feat(frontend): detect HF Space cold start and auto-retry once awake

fix(docs): restore README title/emoji and fix broken demo links

Merge branch 'main' of github.com:GonzaloAsencio/JUGDE

docs: sync eval numbers with 40-question set and latest stratified run

Fix formatting of live app and resource links

Update README.md

Update README.md

Update README.md

docs(env): sync backend .env.example with actual production config

fix(observability): pin langfuse to v2.x

fix(eval): remove erroneous await on synchronous answer_question

Merge pull request #39 from GonzaloAsencio/feat/ui-ux-polish

feat(chat): cross-fade the suggestion chips as the input fills and empties

feat(mentions): enlarge card thumbnails, brand scrollbar, skeleton + prefetch previews

feat(chat): surface request failures as a system notice, not a judge reply

feat(rules): structure run-on clauses, add loading skeleton, fix anchor offset

feat(nav): redesign mobile menu as a full-screen overlay

feat(chat): render Reasoning/Answer as section eyebrows

feat(theme-toggle): rotate and accent the icon on hover

Merge pull request #38 from GonzaloAsencio/fix/gemini-429-retry

fix(generation): retry Gemini 429s to match openai-compat path

Merge pull request #37 from GonzaloAsencio/fix/empty-answer-guard

fix(pipeline): guard empty Answer section with retry and fallback

Merge pull request #36 from GonzaloAsencio/docs/readme-tfm

docs(readme): add TFM sections — live demo, features, project structure

Merge pull request #34 from GonzaloAsencio/feat/corpus-version-reresolve

Merge pull request #35 from GonzaloAsencio/refactor/answer-question-srp

refactor(pipeline): split answer_question into focused helpers

feat(api): re-resolve corpus_version on demand when empty at startup

refactor(db): extract resolve_corpus_version, share with startup

Merge pull request #32: PR2–PR6 hardening chain into main

Merge pull request #23 from GonzaloAsencio/fix/concurrency-threadpool

docs(future-work): record deferred hardening from the risk audit

refactor(pipeline): pass corpus_version explicitly, stop mutating settings

fix(pipeline): whole-word match for exact-card confidence

perf(card-detect): cache compiled patterns per vocabulary

perf(retrieval): add trigram index on lower(section)

fix(api): log exception type, not message, for infra errors

feat(ratelimit): allow shared Redis storage for counters

feat(config): require proxy_shared_secret in production

fix(generation): handle empty Gemini response gracefully

fix(api): return 503 with Retry-After on pool exhaustion

feat(config): make DB pool size configurable

fix(db): use ThreadedConnectionPool and discard broken connections

fix(generation): cap LLM retry backoff and add jitter

refactor(api): run /query as sync handler in the threadpool

refactor(pipeline): make answer_question synchronous

refactor(cache): make get_cached/set_cached synchronous

feat(confidence): match exacto de carta = alta confianza