Builds the §24 product on top of the LangGraph runtime from §22:
Phase A (Sources / RAG)
- encoach.course.plan.source model (file | url | text)
- SourceIndexer extracts PDF (pypdf), DOCX (python-docx), HTML, plain
text and embeds chunks via the existing pgvector pipeline scoped to
plan_id, so resources.search only returns the plan's own corpus
- Endpoints: list/create/upload/reindex/delete + plan-scoped retrieval
Phase B (Deliverables)
- services.deliverables.compute_deliverables walks the plan, derives
{planned, generated, ready} per week from material + media state
- GET /api/ai/course-plan/<id>/deliverables drives the new wizard
preview step and the live progress strip on the detail page
Phase C (Multi-modal media)
- encoach.course.plan.media model + MediaService:
audio: AWS Polly (default) or ElevenLabs
image: OpenAI DALL-E 3, capped per plan via system parameter
video: local ffmpeg subprocess (image + audio -> MP4 1280x720)
- Three new agent tools (media.synthesize_audio / generate_image /
compose_video), wired into course_week_materials and a new
course_media_director agent
- Endpoints per material + week-level batch generator
Phase D (Assignments)
- encoach.course.plan.assignment supports mode='batch' (op.batch) or
mode='students' (res.users), with due_date + message + state
- REST endpoints to list / create / delete assignments
Phase E (Student view)
- /api/student/course-plans + /api/student/course-plans/<id>
enforce visibility via assignment.expand_user_ids()
- New /student/course-plans list + read-only drilldown rendering
audio/image/video tiles from /web/content/<attachment_id>
Cross-cutting
- encoach.ai.tool.category: + media (so the new tools register)
- encoach.embedding gains a plan_id filter for plan-scoped RAG
- Wizard adds Sources + Multimedia steps; AdminCoursePlanDetail
rewritten with DeliverablesStrip + SourcesCard + AssignmentsCard +
per-material MediaDrawer
- ~280 new EN + AR i18n keys (full RTL coverage)
- smoke_course_plan.py exercises every phase via odoo-bin shell;
last run: PASS A/B/D/E + DALL-E 3 image (753 KB), Polly audio
fails cleanly when AWS creds aren't configured (expected)
Documentation: §24 added to docs/PROJECT_SUMMARY.md with phase-by-phase
artefact list, endpoints, smoke test, ops notes, and gotchas.
Made-with: Cursor
Frontend
- i18n: install tailwindcss-rtl, Cairo font, RTL-aware direction in index.css.
- Language toggle: localize aria-label / menu label, persist choice, update
document dir synchronously.
- Sidebar: add `side` prop so the drawer pins to the right in RTL; wire up
AdminLmsLayout, RoleLayout (student/teacher) and AppSidebar to pass
side = i18n.dir() === 'rtl' ? 'right' : 'left'.
- AdminLmsLayout: convert every nav item from hard-coded title to titleKey,
translate group labels (incl. the collapsible Training), breadcrumbs,
user menu (Profile / Settings / Logout), help button and toggle aria
labels; replace physical mr-/right- utilities with logical me-/end-.
- AI components (AiTipBanner, AiInsightsPanel, AiAlertBanner, AiSearchBar,
AiAssistantDrawer): apply dir="auto" at the container level, localize
titles, loading / error / empty states.
- Dashboards (admin / student / teacher): wrap numeric values in <bdi>,
localize dates via ar-EG, fix flex direction for KPI and assignment cards.
- UI primitives (breadcrumb, calendar, carousel, dropdown-menu, menubar,
context-menu, pagination, sidebar): flip chevrons in RTL via a scoped
CSS rule, swap pl-/pr-/ml-/mr- for ps-/pe-/ms-/me-.
- Add logical-direction helpers and bidirectional isolation classes.
Locales
- Expand en.ts and ar.ts with full `nav`, `sidebarGroup`, `breadcrumb`,
`userMenu`, `chrome`, `ai`, and dashboard key sets; keep key parity.
API client
- `api-client.ts` reads the active language from localStorage/i18n and sends
`Accept-Language` on every request so the backend can localize AI output.
Backend (encoach_ai)
- openai_service: add _LANGUAGE_NAMES, normalize_language, language-aware
system prompt injection for every OpenAI call.
- coach_service + controllers (coach_controller, ai_controller): thread
the requested language from headers / user locale down to OpenAIService.
- ai_feedback: fix latent registry error by pointing course_id at op.course
instead of the non-existent encoach.course.
Other
- .gitignore: ignore runtime odoo logs and local caches.
Made-with: Cursor
