feat: stabilize AI engine, harden Zod schemas, and implement UX guardrails

feat: Implement fuzzy matching for commands and input guardrails in whatsapp.ts

fix: Correct audio handler brace structure - FR users now get confirmation and feedback after voice message

fix: Update Gemini model names and harden transcription body reader

trigger: Railway redeploy for Multi-AI Architecture

fix: Decouple A/V providers in AIService and refactor routes for robustness

feat: Implement Multi-AI Architecture with Google Gemini provider and failover logic

fix(whatsapp): Sprint 42 - Sécurisation routage Deep Dive et immuabilité secteur

fix(ai): Sprint 41 - Détanchéité linguistique Wolof stricte et réinjection boucle Deep Dive

feat(Sprint 40): Boucle interactive Deep Dive & persistences des réponses

feat(ai): refactor coach feedback to 3-pillar format with mandatory browsing (Sprint 39)

chore: execute Sprint 38 technical debt resolution (Type Safety, Zod validation, Vitest, Mock LLM extracted)

feat: Genspark-Standard upgrade, MLOps audit fixes, and XAMLÉ branding

feat(ai): add bank-level pitch deck and business plan generator script

test(e2e): add full journey simulation script that generates final AI pitch deck

fix(qa): resolve missing image anomalies and secure pedagogy worker TTS audio flow

feat(admin): build Ground Truth Training Lab to calculate WER and capture dictionary improvements

chore(api): add fast-levenshtein for Whisper WER calibration benchmark

chore: test API distribution

feat(api): add whisper confidence calibration script and endpoint

feat(admin): display Whisper STT confidence score in moderation live feed

fix(api): remove redundant /admin prefix in admin routes to fix dashboard 404

chore(web): update branding to Xamlé Studio

fix(admin): remove unused React and Play imports breaking the netlify build

feat(ai): integrate Whisper STT confidence score for auto-validation

feat(admin): add viewing full chat history in user list

feat(admin): integrate LiveFeed moderation component into the dashboard

chore(infra): remove global netlify.toml & add web spa redirects

fix(admin): resolve SPA 404 routing errors and broken favicon

fix(e2e): type correction in user creation mock

test(e2e): add api journey tests for sprint 22 and 23 validations

chore(pedagogy): add badge guard debug logs for remediation visibility

feat(admin): human-in-the-loop dashboard base, add PENDING_REVIEW logic and audio overdrive worker

fix(core): remove AI jus-de-fruits hallucination, expand onboarding sectors to 8, streamline pedagogy menu and lock REPRISE badge

fix(ai): implement pedagogical leap fixes, pending_remediation, coherence locks and cache wipes

fix(ai): remove double day incrementation on success and queue remediation correctly

feat(ai): integrate XAMLÉ v2 prompt guidelines including anti-hallucination constraints and strict Wolof normalization

fix(ai): remove hardcoded sector examples from system prompts to prevent AI hallucinations across mismatched domains

chore: explicit rebuild request for railway deployment sync

fix(ai): update validation schemas and types to properly handle null context parameters for new users

fix(ai): add imageUrl field to Prisma schema and correctly route language selection inside whatsapp.ts

fix(ai): fully wipe BusinessProfile and Response history on INSCRIPTION to prevent AI context leaks

chore: force rebuild on Railway and HF via Dockerfile cache invalidation

chore: remove tsbuildinfo from git tracking

feat(ai): expert coaching system with persistent business context and explicit SUITE progression fix

feat(media): complete T4-T5 unique images — all T1-T5 tracks now have full image coverage

fix(docker): set SKIP_DB_PUSH=true default to prevent HF Space dropping schema columns

chore(docker): bump REBUILD_DATE to v6 to force Railway redeploy after build fix

chore: ignore *.tsbuildinfo files (TS build cache)

fix(build): remove unused url variable in upload-t2t4-images.ts (TS6133)