edtech / apps /api /src /services

Commit History

feat: Time-Travel complet via Redis — effectiveDay override, coupe-circuits SUITE/INSCRIPTION, skip COMPLETED en mode replay
d978795
Running

CognxSafeTrack commited on

feat: 4 UX/backend fixes — anti-ghost image, time-travel replay, UX message order, contextual AI remediation
a4ce760

CognxSafeTrack commited on

fix: re-validate COMPLETED→PENDING for text exercise responses + guard businessProfile.upsert at Day 10+
a66a580

CognxSafeTrack commited on

fix: comprehensive vision hardening (loosen wordcount bypass + 60s timeout)
184eeee

CognxSafeTrack commited on

fix: resolve Module 8 image response failure (Vision GPT-4o + Caption fix)
255918d

CognxSafeTrack commited on

feat: upgrade Vision to GPT-4o with J11 bypass and enhanced logging
5fae74c

CognxSafeTrack commited on

feat: Global Vision Activation and Day 8 Visual Proof Analysis
bad47e7

CognxSafeTrack commited on

fix: Correct Gemini model name and increase OpenAI timeout
f9b06cf

CognxSafeTrack commited on

feat: Implement Non-Blocking Card UX and Prompt Hook Hook
635e9f4

CognxSafeTrack commited on

fix: Unlock Day 7 Button Handlers and Optimize AI Latency
582a75d

CognxSafeTrack commited on

fix: Harden Pipeline with Day 11 Guards and Null Safety
47c20fe

CognxSafeTrack commited on

fix: Resolve Production Crash (Gemini 404, OpenAI Zod, Job Payload mismatch)
9f4922e

CognxSafeTrack commited on

feat: Async-First Webhook Architecture & Idempotency Hardening
74e06ff

CognxSafeTrack commited on

fix(progression): atomic logic inversion and command unlocking
c1cf9c6

CognxSafeTrack commited on

fix(whatsapp): idempotency lock and progression blockers
cfe6413

CognxSafeTrack commited on

feat(ai): team building visual experience and persistence
7b4936e

CognxSafeTrack commited on

chore(qa): final QA adjustments for multimodal and search
6da0dd6

CognxSafeTrack commited on

feat(ai): implement multimodal vision and dynamic data for business context
b073e6a

CognxSafeTrack commited on

feat(ai): coaching refinements - temperature support, memory filter, and flexible guardrails for Day 6/7
e6d84cb

CognxSafeTrack commited on

feat: stabilize AI engine, harden Zod schemas, and implement UX guardrails
77c96f8

CognxSafeTrack commited on

feat: Implement fuzzy matching for commands and input guardrails in whatsapp.ts
2d900bc

CognxSafeTrack commited on

fix: Update Gemini model names and harden transcription body reader
e47c6bd

CognxSafeTrack commited on

fix: Decouple A/V providers in AIService and refactor routes for robustness
739dce1

CognxSafeTrack commited on

feat: Implement Multi-AI Architecture with Google Gemini provider and failover logic
f41372b

CognxSafeTrack commited on

fix(whatsapp): Sprint 42 - Sécurisation routage Deep Dive et immuabilité secteur
22341b3

CognxSafeTrack commited on

fix(ai): Sprint 41 - Détanchéité linguistique Wolof stricte et réinjection boucle Deep Dive
936cad5

CognxSafeTrack commited on

feat(Sprint 40): Boucle interactive Deep Dive & persistences des réponses
ab37938

CognxSafeTrack commited on

feat(ai): refactor coach feedback to 3-pillar format with mandatory browsing (Sprint 39)
74d7942

CognxSafeTrack commited on

chore: execute Sprint 38 technical debt resolution (Type Safety, Zod validation, Vitest, Mock LLM extracted)
d9879cf

CognxSafeTrack commited on

feat: Genspark-Standard upgrade, MLOps audit fixes, and XAMLÉ branding
eac938a

CognxSafeTrack commited on

feat(ai): integrate Whisper STT confidence score for auto-validation
672b517

CognxSafeTrack commited on

fix(core): remove AI jus-de-fruits hallucination, expand onboarding sectors to 8, streamline pedagogy menu and lock REPRISE badge
9ca5873

CognxSafeTrack commited on

fix(ai): implement pedagogical leap fixes, pending_remediation, coherence locks and cache wipes
4967196

CognxSafeTrack commited on

feat(ai): integrate XAMLÉ v2 prompt guidelines including anti-hallucination constraints and strict Wolof normalization
90b1788

CognxSafeTrack commited on

fix(ai): remove hardcoded sector examples from system prompts to prevent AI hallucinations across mismatched domains
75c0b4c

CognxSafeTrack commited on

fix(ai): add imageUrl field to Prisma schema and correctly route language selection inside whatsapp.ts
f0f0df4

CognxSafeTrack commited on

fix(ai): fully wipe BusinessProfile and Response history on INSCRIPTION to prevent AI context leaks
854ab32

CognxSafeTrack commited on

feat(ai): expert coaching system with persistent business context and explicit SUITE progression fix
3c5c1e0

CognxSafeTrack commited on

feat(sprint19-20): production-ready video integration & STT hardening
19d10a4

CognxSafeTrack commited on

chore: final integration audit and logic hardening
567fb57

CognxSafeTrack commited on

fix(syntax): resolve unbalanced braces and scoping in WhatsAppService
aa52c48

CognxSafeTrack commited on

fix(logic): prioritize commands over exercises and strictly lock gateway routing
4a79a6d

CognxSafeTrack commited on

feat(hardening): implement anti-silence, gateway loop protection and deep trace logging
5443165

CognxSafeTrack commited on

Fix Post-STT Blockage: Async chain, Intent detection, and Feedback fallback
31e6d9a

CognxSafeTrack commited on

Audit Final: Fix feedback message construction & Global Hardening
42c5945

CognxSafeTrack commited on

feat(wolof): standardized tracks T1-T5 with glossary v4.0 and implemented adaptive multi-sector architecture
b9727b3

CognxSafeTrack commited on

chore: final logic hardening, AI prompt reinforcement and SUITE command fix
26c5d48

CognxSafeTrack commited on

feat(ai): fully operational v1.0 criteria engine and 5-level curriculum (10 modules)
86d6011

CognxSafeTrack commited on

feat(pedagogy): implementation of dynamic content infrastructure and evaluation criteria
ca816a7

CognxSafeTrack commited on

fix: final hardening audit fixes (normalizeCommand, activityLabel key, Zod schemas)
8927585

CognxSafeTrack commited on