Vadym Samoilenko a0d73b3b63 Phase 4: Generation Pipeline — brand enforcement, enhanced LLM calls, ARQ job queue ...

- Step 14: Brand enforcement service (font/color/logo replacement, WCAG contrast check, LLM prompt context)
- Step 15: Enhanced outline & slide content generation with brand context, content summary, "no hallucination" instructions
- Step 15b: LLM auto-fallback retry logic across providers (FALLBACK_LLM_PROVIDERS env)
- Step 16: Redis/ARQ job queue — worker entry point, presentation & master deck workers, job status/SSE endpoints, graceful fallback to BackgroundTasks when Redis unavailable

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-26 16:15:25 +00:00

0 lines

Python

Raw Permalink Blame History