Commit History
-
refactor(debt): resolve all 10 technical debt items from audit
CognxSafeTrack +1: Claude Sonnet 4.6- Redis: singleton pattern (lib/redis.ts) in api + worker, removes 16+ new Redis() calls - Meta token: systemUserTokenIssuedAt field + weekly cron monitor (warn @50d, critical @55d) - Rate limiting: @fastify/rate-limit global 200/min, login 10/min, forgot-password 3/min - Dead code: delete WhatsAppConnectButton.tsx, archive one-off scripts - Silent catches: logger.warn(err) on all backend catch blocks, console.warn on frontend - Meta API types: 5 typed interfaces replace 6 as any casts in organization.ts - Frontend logger: lib/logger.ts wraps Sentry (active when VITE_SENTRY_DSN is set) - Migration: add systemUserTokenIssuedAt + metaBusinessId to Organization schema Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>a966957
-
chore: stabilization, audit fixes and project synchronization
CognxSafeTrack7b0c22b
-
feat: centralize AI logic in @repo /ai-sdk, harmonize worker HTTP clients
CognxSafeTrack +1: Claude Sonnet 4.6Architecture refactoring: - Extract all AI providers (OpenAI, Gemini, ProviderRegistry, ffmpeg, search) from apps/api/src/services/ai/ into new packages/ai-sdk package - API's services/ai/index.ts is now a thin wrapper that injects prisma, redis and organization context into the shared AIService - Worker gains @repo/ai-sdk dependency; ai-pedagogy.ts delegates to aiService.generatePersonalizedLesson instead of duplicating logic - New apiClient (Axios, 30s timeout) and whatsappClient replace bare fetch calls in InboundHandler and MediaHandler for consistent error handling - Prisma seed fixed: Tracks now include organizationId for multi-tenant compliance Build: all 8 packages pass pnpm turbo run build from clean state. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>2849f33 -
feat: implement inbound audio/image transcription, secure media proxy, and client-side bulk contact import
CognxSafeTrack30d60ea
-
feat: implement AI campaign generation logic and frontend integration
CognxSafeTrack9f0410f -
feat: push notifications, CRM analytics, Fastify v5 upgrades, schema updates
CognxSafeTrack +1: Claude Sonnet 4.6- Add web push notification service and admin endpoints - Add CRM analytics component and conversational dashboard - Extend Contacts page with campaign management - Update AI and whatsapp routes (Fastify v5 compat, webhook fixes) - Extend Prisma schema with new models and indexes - Add CRM campaign prompt template Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>b43e552
-
feat: complete final technical debt polishing (structured logs, stripe tests, and automated migrations)
CognxSafeTrack86731f4 -
fix: resolve test import errors and export AIService class
CognxSafeTrack459f379 -
fix: restore logger compatibility and fix major TS errors in services
CognxSafeTrack38df3bf -
feat: implement organization-specific API keys and tenant-aware webhooks (Phase 2)
CognxSafeTrackc37b68c
-
feat: Premium Onboarding with Meta SDK and Technical Debt resolution
CognxSafeTrack6248bf4
-
feat: B2B SaaS Multi-tenant architecture & Tech Debt Resolution
CognxSafeTracke289c5c
-
Chore: Added AI regression test framework and enhanced Mock provider
CognxSafeTrackd95a6d7 -
Refactor: Isolated AI prompts into @repo /prompts package for better maintainability
CognxSafeTrackb8ae83d -
Refactor: Technical Debt Repayment (Clean Dashboard, Strict Typing, Pino Logging, SQL Migration)
CognxSafeTrackde6a95b
-
feat: 4 UX/backend fixes — anti-ghost image, time-travel replay, UX message order, contextual AI remediation
CognxSafeTracka4ce760 -
fix: comprehensive vision hardening (loosen wordcount bypass + 60s timeout)
CognxSafeTrack184eeee -
fix: resolve Module 8 image response failure (Vision GPT-4o + Caption fix)
CognxSafeTrack255918d
-
feat: upgrade Vision to GPT-4o with J11 bypass and enhanced logging
CognxSafeTrack5fae74c -
feat: Global Vision Activation and Day 8 Visual Proof Analysis
CognxSafeTrackbad47e7 -
fix: Correct Gemini model name and increase OpenAI timeout
CognxSafeTrackf9b06cf -
feat: Implement Non-Blocking Card UX and Prompt Hook Hook
CognxSafeTrack635e9f4 -
fix: Unlock Day 7 Button Handlers and Optimize AI Latency
CognxSafeTrack582a75d -
fix: Harden Pipeline with Day 11 Guards and Null Safety
CognxSafeTrack47c20fe -
fix: Resolve Production Crash (Gemini 404, OpenAI Zod, Job Payload mismatch)
CognxSafeTrack9f4922e -
fix(progression): atomic logic inversion and command unlocking
CognxSafeTrackc1cf9c6 -
feat(ai): team building visual experience and persistence
CognxSafeTrack7b4936e
-
chore(qa): final QA adjustments for multimodal and search
CognxSafeTrack6da0dd6 -
feat(ai): implement multimodal vision and dynamic data for business context
CognxSafeTrackb073e6a
-
feat(ai): coaching refinements - temperature support, memory filter, and flexible guardrails for Day 6/7
CognxSafeTracke6d84cb
-
feat: stabilize AI engine, harden Zod schemas, and implement UX guardrails
CognxSafeTrack77c96f8
-
fix: Update Gemini model names and harden transcription body reader
CognxSafeTracke47c6bd
-
fix: Decouple A/V providers in AIService and refactor routes for robustness
CognxSafeTrack739dce1 -
feat: Implement Multi-AI Architecture with Google Gemini provider and failover logic
CognxSafeTrackf41372b
-
fix(whatsapp): Sprint 42 - Sécurisation routage Deep Dive et immuabilité secteur
CognxSafeTrack22341b3 -
fix(ai): Sprint 41 - Détanchéité linguistique Wolof stricte et réinjection boucle Deep Dive
CognxSafeTrack936cad5 -
feat(Sprint 40): Boucle interactive Deep Dive & persistences des réponses
CognxSafeTrackab37938
-
feat(ai): refactor coach feedback to 3-pillar format with mandatory browsing (Sprint 39)
CognxSafeTrack74d7942 -
chore: execute Sprint 38 technical debt resolution (Type Safety, Zod validation, Vitest, Mock LLM extracted)
CognxSafeTrackd9879cf -
feat: Genspark-Standard upgrade, MLOps audit fixes, and XAMLÉ branding
CognxSafeTrackeac938a
-
feat(ai): integrate Whisper STT confidence score for auto-validation
CognxSafeTrack672b517
-
fix(core): remove AI jus-de-fruits hallucination, expand onboarding sectors to 8, streamline pedagogy menu and lock REPRISE badge
CognxSafeTrack9ca5873
-
feat(ai): integrate XAMLÉ v2 prompt guidelines including anti-hallucination constraints and strict Wolof normalization
CognxSafeTrack90b1788 -
fix(ai): remove hardcoded sector examples from system prompts to prevent AI hallucinations across mismatched domains
CognxSafeTrack75c0b4c -
feat(ai): expert coaching system with persistent business context and explicit SUITE progression fix
CognxSafeTrack3c5c1e0
-
feat(wolof): standardized tracks T1-T5 with glossary v4.0 and implemented adaptive multi-sector architecture
CognxSafeTrackb9727b3 -
chore: final logic hardening, AI prompt reinforcement and SUITE command fix
CognxSafeTrack26c5d48
-
feat(ai): fully operational v1.0 criteria engine and 5-level curriculum (10 modules)
CognxSafeTrack86d6011 -
feat(pedagogy): implementation of dynamic content infrastructure and evaluation criteria
CognxSafeTrackca816a7 -
feat: localize AI documents (FR/WO) and fix Zod warnings
CognxSafeTrack7ce77fe