Spaces:

safetrack
/

edtech

Paused

App Files Files Community

edtech / apps /api /src

Commit History

Apr 7

15:34
Refactor: Isolated AI prompts into @repo /prompts package for better maintainability

CognxSafeTrack

b8ae83d
15:24
Fix: Add Garbage Collector (GC) for media and temp files

CognxSafeTrack

f4e46e8
14:27
Fix: Add Cascade Delete for UserBadge and TeamMember during INSCRIPTION reset

CognxSafeTrack

2e888dc
14:08
Refactor: Technical Debt Repayment (Clean Dashboard, Strict Typing, Pino Logging, SQL Migration)

CognxSafeTrack

de6a95b
12:34
fix(time-travel): allow deep dive based on historical day response⁠

CognxSafeTrack

1fd81cb
11:46
feat(arch): evolve Franglof STT, Admin Audio, Admin MSG, UX TimeTravel

CognxSafeTrack

16c2960

Mar 30

15:30
feat: Fix Time-Travel Replay & Deep Dive logic via Redis Context Override

CognxSafeTrack

0785ad1

Mar 27

21:02
feat: Time-Travel complet via Redis — effectiveDay override, coupe-circuits SUITE/INSCRIPTION, skip COMPLETED en mode replay

CognxSafeTrack

d978795
20:22
feat: 4 UX/backend fixes — anti-ghost image, time-travel replay, UX message order, contextual AI remediation

CognxSafeTrack

a4ce760
17:50
fix: re-validate COMPLETED→PENDING for text exercise responses + guard businessProfile.upsert at Day 10+

CognxSafeTrack

a66a580
17:13
fix: restore image forwarding and result propagation in internal routes

CognxSafeTrack

0ee3f5e
15:03
fix: comprehensive vision hardening (loosen wordcount bypass + 60s timeout)

CognxSafeTrack

184eeee
14:41
fix: resolve Module 8 image response failure (Vision GPT-4o + Caption fix)

CognxSafeTrack

255918d
12:16
fix: restore missing loops and fix syntax in whatsapp route

CognxSafeTrack

c4487e4

Mar 24

17:57
fix(scripts): move reset script to apps/api to fix IDE error

CognxSafeTrack

d92dbd4
17:54
fix: restore whatsapp routes and add diagnostic logs

CognxSafeTrack

b0907ad
17:19
feat: upgrade Vision to GPT-4o with J11 bypass and enhanced logging

CognxSafeTrack

5fae74c
16:55
fix: restore image interception and vision pipeline with [IMAGE-FLOW] logs

CognxSafeTrack

78e4fe8
16:15
feat: Global Vision Activation and Day 8 Visual Proof Analysis

CognxSafeTrack

bad47e7
15:09
fix: Correct Gemini model name and increase OpenAI timeout

CognxSafeTrack

f9b06cf
14:17
feat: Implement Non-Blocking Card UX and Prompt Hook Hook

CognxSafeTrack

635e9f4
14:05
fix: Unlock Day 7 Button Handlers and Optimize AI Latency

CognxSafeTrack

582a75d
13:22
fix: Harden Pipeline with Day 11 Guards and Null Safety

CognxSafeTrack

47c20fe
13:01
fix: Resolve Production Crash (Gemini 404, OpenAI Zod, Job Payload mismatch)

CognxSafeTrack

9f4922e
12:22
feat: Async-First Webhook Architecture & Idempotency Hardening

CognxSafeTrack

74e06ff
12:02
fix(progression): atomic logic inversion and command unlocking

CognxSafeTrack

c1cf9c6
11:16
fix(whatsapp): idempotency lock and progression blockers

CognxSafeTrack

cfe6413
10:49
feat(ai): team building visual experience and persistence

CognxSafeTrack

7b4936e

Mar 23

15:13
chore(qa): final QA adjustments for multimodal and search

CognxSafeTrack

6da0dd6
12:15
feat(ai): implement multimodal vision and dynamic data for business context

CognxSafeTrack

b073e6a

Mar 16

22:57
feat(ai): coaching refinements - temperature support, memory filter, and flexible guardrails for Day 6/7

CognxSafeTrack

e6d84cb

Mar 13

00:33
feat: stabilize AI engine, harden Zod schemas, and implement UX guardrails

CognxSafeTrack

77c96f8

Mar 12

21:28
feat: Implement fuzzy matching for commands and input guardrails in whatsapp.ts

CognxSafeTrack

2d900bc
13:43
fix: Update Gemini model names and harden transcription body reader

CognxSafeTrack

e47c6bd

Mar 10

16:26
fix: Decouple A/V providers in AIService and refactor routes for robustness

CognxSafeTrack

739dce1
16:14
feat: Implement Multi-AI Architecture with Google Gemini provider and failover logic

CognxSafeTrack

f41372b

Mar 8

04:02
fix(whatsapp): Sprint 42 - Sécurisation routage Deep Dive et immuabilité secteur

CognxSafeTrack

22341b3
02:24
fix(ai): Sprint 41 - Détanchéité linguistique Wolof stricte et réinjection boucle Deep Dive

CognxSafeTrack

936cad5
01:34
feat(Sprint 40): Boucle interactive Deep Dive & persistences des réponses

CognxSafeTrack

ab37938

Mar 7

23:01
feat(ai): refactor coach feedback to 3-pillar format with mandatory browsing (Sprint 39)

CognxSafeTrack

74d7942
22:20
chore: execute Sprint 38 technical debt resolution (Type Safety, Zod validation, Vitest, Mock LLM extracted)

CognxSafeTrack

d9879cf
18:39
feat: Genspark-Standard upgrade, MLOps audit fixes, and XAMLÉ branding

CognxSafeTrack

eac938a
03:03
feat(ai): add bank-level pitch deck and business plan generator script

CognxSafeTrack

4d733e8
02:42
test(e2e): add full journey simulation script that generates final AI pitch deck

CognxSafeTrack

89117b5
02:35
fix(qa): resolve missing image anomalies and secure pedagogy worker TTS audio flow

CognxSafeTrack

082d3db
01:25
feat(admin): build Ground Truth Training Lab to calculate WER and capture dictionary improvements

CognxSafeTrack

83c2a9a
01:15
chore(api): add fast-levenshtein for Whisper WER calibration benchmark

CognxSafeTrack

b6de1ea
01:06
chore: test API distribution

CognxSafeTrack

181ff6e
00:45
feat(api): add whisper confidence calibration script and endpoint

CognxSafeTrack

ef0913c
00:32
fix(api): remove redundant /admin prefix in admin routes to fix dashboard 404

CognxSafeTrack

cfa14f7

Commit History

Apr 7

Refactor: Isolated AI prompts into @repo /prompts package for better maintainability

Fix: Add Garbage Collector (GC) for media and temp files

Fix: Add Cascade Delete for UserBadge and TeamMember during INSCRIPTION reset

Refactor: Technical Debt Repayment (Clean Dashboard, Strict Typing, Pino Logging, SQL Migration)

fix(time-travel): allow deep dive based on historical day response⁠

feat(arch): evolve Franglof STT, Admin Audio, Admin MSG, UX TimeTravel

Mar 30

feat: Fix Time-Travel Replay & Deep Dive logic via Redis Context Override

Mar 27

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

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

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

fix: restore image forwarding and result propagation in internal routes

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

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

fix: restore missing loops and fix syntax in whatsapp route

Mar 24

fix(scripts): move reset script to apps/api to fix IDE error

fix: restore whatsapp routes and add diagnostic logs

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

fix: restore image interception and vision pipeline with [IMAGE-FLOW] logs

feat: Global Vision Activation and Day 8 Visual Proof Analysis

fix: Correct Gemini model name and increase OpenAI timeout

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

fix: Unlock Day 7 Button Handlers and Optimize AI Latency

fix: Harden Pipeline with Day 11 Guards and Null Safety

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

feat: Async-First Webhook Architecture & Idempotency Hardening

fix(progression): atomic logic inversion and command unlocking

fix(whatsapp): idempotency lock and progression blockers

feat(ai): team building visual experience and persistence

Mar 23

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

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

Mar 16

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

Mar 13

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

Mar 12

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

fix: Update Gemini model names and harden transcription body reader

Mar 10

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

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

Mar 8

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

Mar 7

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

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