Spaces:

safetrack
/

edtech

Paused

App Files Files Community

edtech / apps /api /src

Commit History

Mar 6

12:49
feat(ai): integrate Whisper STT confidence score for auto-validation

CognxSafeTrack

672b517
12:32
feat(admin): add viewing full chat history in user list

CognxSafeTrack

3b473c3

Mar 2

21:57
fix(e2e): type correction in user creation mock

CognxSafeTrack

5681aa5
21:55
test(e2e): add api journey tests for sprint 22 and 23 validations

CognxSafeTrack

4012011
21:02
feat(admin): human-in-the-loop dashboard base, add PENDING_REVIEW logic and audio overdrive worker

CognxSafeTrack

41fe9a9
20:36
fix(core): remove AI jus-de-fruits hallucination, expand onboarding sectors to 8, streamline pedagogy menu and lock REPRISE badge

CognxSafeTrack

9ca5873

Mar 1

18:02
fix(ai): implement pedagogical leap fixes, pending_remediation, coherence locks and cache wipes

CognxSafeTrack

4967196
17:01
feat(ai): integrate XAMLÉ v2 prompt guidelines including anti-hallucination constraints and strict Wolof normalization

CognxSafeTrack

90b1788
05:48
fix(ai): remove hardcoded sector examples from system prompts to prevent AI hallucinations across mismatched domains

CognxSafeTrack

75c0b4c
05:28
fix(ai): update validation schemas and types to properly handle null context parameters for new users

CognxSafeTrack

9102815
05:10
fix(ai): add imageUrl field to Prisma schema and correctly route language selection inside whatsapp.ts

CognxSafeTrack

f0f0df4
04:23
fix(ai): fully wipe BusinessProfile and Response history on INSCRIPTION to prevent AI context leaks

CognxSafeTrack

854ab32
02:04
feat(ai): expert coaching system with persistent business context and explicit SUITE progression fix

CognxSafeTrack

3c5c1e0

Feb 28

23:10
feat(media): complete T4-T5 unique images — all T1-T5 tracks now have full image coverage⁠

CognxSafeTrack

3e52c7d
18:53
fix(build): remove unused url variable in upload-t2t4-images.ts (TS6133)

CognxSafeTrack

489821f
17:17
chore: add complete-t4t5-images.ts script for remaining image generation

CognxSafeTrack

8925074
16:57
feat(media): inject imageUrls for T2-T5 (17 unique + fallback for T4-T5 remainder)⁠

CognxSafeTrack

ab7ffa3
16:33
feat(sprint19-20): production-ready video integration & STT hardening⁠

CognxSafeTrack

19d10a4

Feb 27

16:52
chore: final integration audit and logic hardening

CognxSafeTrack

567fb57
15:54
fix(stt): resolve post-transcription silence and harden gateway detection

CognxSafeTrack

70901bb
15:24
fix(syntax): resolve unbalanced braces and scoping in WhatsAppService

CognxSafeTrack

aa52c48
15:21
fix(logic): prioritize commands over exercises and strictly lock gateway routing

CognxSafeTrack

4a79a6d
15:08
feat(hardening): implement anti-silence, gateway loop protection and deep trace logging

CognxSafeTrack

5443165
14:40
Fix gateway forwarding authorization: use Bearer token instead of x-admin-key

CognxSafeTrack

9d2d3b2
13:18
Fix Post-STT Blockage: Async chain, Intent detection, and Feedback fallback

CognxSafeTrack

31e6d9a
00:10
Audit Final: Fix feedback message construction & Global Hardening

CognxSafeTrack

42c5945

Feb 26

14:28
feat(wolof): standardized tracks T1-T5 with glossary v4.0 and implemented adaptive multi-sector architecture

CognxSafeTrack

b9727b3
11:01
chore: final logic hardening, AI prompt reinforcement and SUITE command fix

CognxSafeTrack

26c5d48

Feb 25

15:52
feat(ai): fully operational v1.0 criteria engine and 5-level curriculum (10 modules)

CognxSafeTrack

86d6011
13:54
fix(deployment): resolve ESM module not found by decoupling seed from database index

CognxSafeTrack

f04a1e3
13:50
feat(pedagogy): implementation of dynamic content infrastructure and evaluation criteria

CognxSafeTrack

ca816a7
10:54
fix: final hardening audit fixes (normalizeCommand, activityLabel key, Zod schemas)

CognxSafeTrack

8927585
10:30
fix: improve STT suspect detection regex

CognxSafeTrack

647a8ba
10:14
feat: localize AI documents (FR/WO) and fix Zod warnings

CognxSafeTrack

7ce77fe
02:04
fix: resolve ESM module not found error in database package

CognxSafeTrack

84be762
01:23
feat: implement adaptive pedagogy, visuals, and remediation (WOW Phase 1)

CognxSafeTrack

6c294cb
00:53
feat: implement WOW Sprint 1 (BusinessProfile, Structured Feedback, STT Hardening, Progress Bar)

CognxSafeTrack

65aabf4

Feb 24

23:00
feat: audit and hardening of audio pipeline, AI localization, and WhatsApp UX improvements

CognxSafeTrack

9eff59c
21:19
fix: port alignment, cascade delete, and audio pipeline hardening

CognxSafeTrack

0de1348
13:27
feat: complete audio pipeline hardening and audit requirements

CognxSafeTrack

538f814
00:31
build: force deep rebuild v4 with improved logging

CognxSafeTrack

3ec3d38

Feb 23

23:51
debug: add detailed logging for transcription connection error

CognxSafeTrack

1fe7477
23:16
fix(audio): Ensure /tmp/audio exists and fix nixpacks syntax

CognxSafeTrack

24260b4
20:10
feat(audio): Enforce strict AI_API_BASE_URL and add FFmpeg MP3 STT conversion

CognxSafeTrack

29ead2c
14:15
feat(audio): Complete robust outbound/inbound pipeline and async AI generation

CognxSafeTrack

818c5f2
13:34
fix: Prevent HF webhook from pushing empty Whatsapp access token to Railway worker

CognxSafeTrack

a5db32b
13:00
fix: Split Webhook into Gateway (HuggingFace) and Processor (Railway), fix missing https:// in API_URL

CognxSafeTrack

df0edd7
03:02
fix(whatsapp): resolve duplicate CONTINUE action match and remote 120s blocking delay on feedback

CognxSafeTrack

0e83f45
02:55
feat: implement STT inbound audio, TTS fallback, and Interactive Lists

CognxSafeTrack

abc4e24
02:13
fix(deploy): make Stripe keys optional at initialization

CognxSafeTrack

e290651

Commit History

Mar 6

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

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

Mar 2

fix(e2e): type correction in user creation mock

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

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

Mar 1

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

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

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

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

Feb 28

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

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

chore: add complete-t4t5-images.ts script for remaining image generation

feat(media): inject imageUrls for T2-T5 (17 unique + fallback for T4-T5 remainder)⁠

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

Feb 27

chore: final integration audit and logic hardening

fix(stt): resolve post-transcription silence and harden gateway detection

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

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

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

Fix gateway forwarding authorization: use Bearer token instead of x-admin-key

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

Audit Final: Fix feedback message construction & Global Hardening

Feb 26

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

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

Feb 25

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

fix(deployment): resolve ESM module not found by decoupling seed from database index

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

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

fix: improve STT suspect detection regex

feat: localize AI documents (FR/WO) and fix Zod warnings

fix: resolve ESM module not found error in database package

feat: implement adaptive pedagogy, visuals, and remediation (WOW Phase 1)

feat: implement WOW Sprint 1 (BusinessProfile, Structured Feedback, STT Hardening, Progress Bar)

Feb 24

feat: audit and hardening of audio pipeline, AI localization, and WhatsApp UX improvements

fix: port alignment, cascade delete, and audio pipeline hardening

feat: complete audio pipeline hardening and audit requirements

build: force deep rebuild v4 with improved logging

Feb 23

debug: add detailed logging for transcription connection error

fix(audio): Ensure /tmp/audio exists and fix nixpacks syntax

feat(audio): Enforce strict AI_API_BASE_URL and add FFmpeg MP3 STT conversion

feat(audio): Complete robust outbound/inbound pipeline and async AI generation

fix: Prevent HF webhook from pushing empty Whatsapp access token to Railway worker

fix: Split Webhook into Gateway (HuggingFace) and Processor (Railway), fix missing https:// in API_URL

fix(whatsapp): resolve duplicate CONTINUE action match and remote 120s blocking delay on feedback

feat: implement STT inbound audio, TTS fallback, and Interactive Lists

fix(deploy): make Stripe keys optional at initialization