Oliver/ppt-tool
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
43 commits 2 branches 0 tags 21 MiB
Commit graph

6 commits

Author SHA1 Message Date
Vadym Samoilenko
73d8aa8c7a Increase ARQ job timeout to 90 minutes 
Master deck parsing with 20+ layouts requires ~44 LLM calls.
At 60s per call with gemini-3.1-pro = 44-60 minutes total.
Previous 30 min timeout caused failures at layout 19/22.

Co-Authored-By: Claude Sonnet 4.5 (1M context) <noreply@anthropic.com>
 2026-02-27 21:48:51 +00:00
Vadym Samoilenko
69a8829750 Phase 3: Bug fixes, feature enhancements, and polish 
P0 Critical: presentation isolation (client scoping), storage super_admin fix,
template selection in worker, IMAGE_PROVIDERS list fix.

P1 High: template layout management UI (delete/filter/bulk), slide-based parsing
mode, LLM model listing & connection test, settings persistence to DB (Fernet
encryption), logout button.

P2 Polish: storage improvements (master deck files, per-client breakdown, bulk
delete, hard purge, client selector), image generation error visibility
(__image_error__ badge), hamster wheel loading animation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-27 12:58:52 +00:00
Vadym Samoilenko
d3d1667a79 Phase 2: Admin panel, analytics, storage, template pipeline, multi-provider LLM 
- Fix admin sidebar: remove duplicate Teams, add Storage nav item
- Analytics: client-scoped queries, super_admin sees all (including NULL client_id)
- Storage management: list/download/delete presentations with file metadata
- Settings page with brand config router
- AI usage tracking: new AIUsageModel, ai_usage_service, analytics endpoint
- Master deck → template bridge: _register_as_template creates TemplateModel
  + PresentationLayoutCodeModel so parsed layouts appear in template picker
- Multi-provider LLM vision in parser: Anthropic/Google/OpenAI with asyncio.to_thread
- Fix PPTX upload 400: accept by .pptx extension (browser sends octet-stream)
- Fix reparse FK violation: presentation_id=None for parse_master_deck jobs
- Worker job_timeout increased to 1800s for LLM-heavy master deck parsing
- PYTHONUNBUFFERED=1 in docker-compose worker for real-time log output
- Auth: clientId in /me response, dev-login cookie improvements
- Frontend: auth slice clientId, master-deck thumbnails, storage page

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 23:39:34 +00:00
Vadym Samoilenko
bdf6e4b4d0 Fix Docker build, test suite, and runtime issues for local deployment 
- Fix UV index strategy: mark PyTorch CPU index as explicit with name
- Add --index-strategy unsafe-best-match to Dockerfile uv pip install
- Fix redis version constraint (>=5.0,<6) for ARQ compatibility
- Fix Anthropic model name (claude-sonnet-4-5-20250929)
- Fix IMAGE_PROVIDER enum value (gemini_flash, not google)
- Resolve middlewares.py vs middlewares/ package conflict
- Fix worker import paths (models.sql.presentation, models.sql.slide, utils split)
- Fix seed script FK resolution by importing all related models
- Fix test suite: async fixture scoping, greenlet dep, regex patterns, fixture params
- Fix frontend TypeScript error (Boolean cast for layout.react_code)
- Regenerate package-lock.json with i18n packages
- Add initial Alembic migration (autogenerated from all models)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 17:56:30 +00:00
Vadym Samoilenko
c97841f6d1 Phase 6: Export & Polish — brand export, client dashboard, retention, analytics 
- Brand-enforced export pipeline (PPTX/PDF with auto brand fonts/colors/logo)
- Client library dashboard with two-level navigation (client grid → detail tabs)
- Data retention service with ARQ cron jobs (daily cleanup + weekly purge)
- Brand-adaptive UI theme via CSS custom properties (dynamic per client)
- Analytics dashboard with overview, usage, quality, and performance metrics

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 16:41:58 +00:00
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