kunthawat/ALwrity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
946 Commits 42 Branches 2 Tags
45231625fd888dcf072094946d3dd9fe1f59cd6e
Commit Graph

8 Commits

Author SHA1 Message Date
ajaysi
348839be36 Fix: Improve podcast analysis LLM prompt and skip bible generation in podcast mode 
- Add pandas to requirements-podcast.txt for usage tracking
- Fix LLM prompt to return plain strings instead of objects for enhanced_ideas
- Add object-to-string normalization for LLM responses that return objects
- Skip bible generation in podcast-only mode (onboarding disabled)
- Skip alerts polling in AlertsBadge when in podcast-only demo mode
 2026-04-06 15:19:23 +05:30
ajaysi
63bb937796 feat: podcast demo mode with ALWRITY_ENABLED_FEATURES support 
- Add ALWRITY_ENABLED_FEATURES env var for feature gating
- Podcast-only mode: skip LLM bootstrap, scheduler, persona services
- Enhance video generation prompt with scene context, analysis, narration
- Add voice cloning support via custom_voice_id in WaveSpeed
- Add text-to-speech for research results (browser speechSynthesis)
- Fix render queue to sync images from script phase
- Add WaveSpeed LLM pricing (gpt-oss-120b)
- Fix podcast bible generation error handling
- Refactor RouterManager for feature-based router loading
 2026-04-03 06:59:59 +05:30
ajaysi
746a5eeeb9 Fix LLM provider selection in podcast handlers 
- Remove hardcoded preferred_provider=huggingface in podcast handlers
- Set preferred_provider=None to respect GPT_PROVIDER env var
- Change default model from Qwen to gpt-oss-120b:cerebras (the model user had access to)
- WaveSpeed will now use gpt-oss-120b model instead of Qwen
 2026-04-01 06:54:37 +05:30
ajaysi
35fd700b22 Propagate LLM errors in podcast handlers to frontend 
- analysis.py: enhance_podcast_idea now re-raises HTTPException (429)
- analysis.py: analyze_podcast_idea already re-raises HTTPException
- research.py: re-raise HTTPException instead of silent fallback
- script.py: re-raise HTTPException instead of generic 500

Ensures 429 errors with usage_info reach frontend for modal display
 2026-03-31 19:32:23 +05:30
ajaysi
92bcd27004 Fix generate_image() call in podcast analysis handler 
Use options dict instead of direct width/height params to match
the generate_image() function signature in main_image_generation.py
 2026-03-31 18:16:19 +05:30
ajaysi
01881bb405 "feat:enhance-podcast-topic-ai" 2026-03-11 19:09:27 +05:30
ajaysi
4828274cbf Release Candidate: Production Release with Multi-Tenant & Onboarding Enhancements 2026-02-28 20:08:00 +05:30
ajaysi
1d745c9bc8 AI podcast project 2025-12-16 16:25:52 +05:30