Study/README.md
Elijah 85d5c9186d
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 1m0s
Fifth revision: share-link AI safety, sturdier generation, cleaner UI
- Malformed model JSON is sent back for repair, then retried; a failed job
  starts over once before it fails. Visitors can dismiss failed sets.
- Generated sets get a short distinct name and description; flashcards are
  atomic and have no hints; standard study shows known/learning counts.
- Share links: "In progress" list, finished sets join the normal lists with a
  "New" tag, plain progress steps, newest exam first.
- Share-link AI expires after a week, can be limited to the US or Arizona
  (DB-IP Lite or Cloudflare headers) and is locked by abuse protection
  (migration 8).
- The assistant never answers from general knowledge; MCP and web search
  tools load without a manual test.
- Plain-text copy, no question count in exam mode, filler text removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-16 09:17:50 -07:00

105 lines
5.6 KiB
Markdown

# Study Desk V2
A personal study platform for nursing school: classes and folders, quizzes, FSRS flashcards,
notes, private documents, and AI-assisted content creation. One administrator; friends study
through revocable public links without accounts.
## Run locally
Requires Node.js 24 or newer and npm. The development VM currently uses Node 26.
```powershell
npm.cmd ci
npm.cmd run dev
```
Open the Vite address printed in the terminal (normally http://localhost:5173).
The API listens on port 3726. For the production build locally:
```powershell
npm.cmd run build
npm.cmd start
```
Open http://localhost:3726. On a fresh install, enter the setup code from the server log or
`data/setup-code.txt`, then choose your administrator password. Alternatively set
`ADMIN_PASSWORD` for first startup. An optional `.env` file is loaded by the server; see
[.env.example](.env.example). Existing environment variables take precedence.
**This checkout already has an ignored `.env` pointing at `.data/` from development.**
Do not delete it or run reset/seed commands against content you want to keep. The demo seeder
is an opt-in development tool, never part of startup.
## What is implemented
- Classes divided into exams (or units, modules…), each with its own documents, quizzes and
flashcards; generating for an exam uses only its material.
- Search, edit/duplicate/move/delete actions; Markdown and embedded images.
- Multiple-choice, select-all and numeric (type-the-answer calculation) questions; a start
screen that hides answers, practice feedback, optional exam time limits, shuffle, partial
credit, saved sessions, missed-question review, 7-point letter grades and history.
- Flashcard editing, browse/self-assessment sessions, FSRS scheduling, persistent reviews,
undo, keyboard shortcuts and streak effects.
- Public quiz/deck/class/folder/note/document links. Collection (class and folder) shares
include current and future quizzes, decks, notes and processed documents. Each link can
allow "Explain this" and a chat about the shared material, separately (off by default).
- Flashcards in Standard mode (know it / still learning, optionally repeating missed cards
until known) or spaced repetition.
- JSON import previews, validation, templates, content exports and a V1 SQLite import path.
- PDF/DOCX/PPTX/TXT/Markdown/image uploads; text extraction, OCR via a configured vision model,
chunking and SQLite FTS retrieval with source references. The original is shown next to the
extracted text (Word and PowerPoint as a generated preview).
- OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter and OpenAI-compatible (Ollama, LM Studio…)
provider connections,
manual/discovered models, task routing with reasoning effort from Off to Max, encrypted keys
and usage estimates that price cached input separately.
- Semantic search with cloud embeddings or a built-in model that runs on the server.
- AI generation with editable drafts and editable instructions/presets; generation and
assistant answers keep running on the server when you leave the page. The assistant
searches materials, reads notes, creates drafts, finds weak topics, proposes confirmed
content changes, accepts tagged or dragged-in materials, can switch models per chat and can
show its reasoning. It runs Python in a sandbox, and generated quizzes are checked with it.
- Built-in web search (Parallel; no account needed, optional sign-in for higher limits).
- Share links for classes and exams can let visitors generate their own quizzes and flashcards
(daily limits per link), and quizzes can include med math on request.
- AI on share links turns itself off after a week, can be limited to the US or Arizona, and is
locked automatically when a link looks leaked or abused.
- Interactive charts, practice questions and other blocks inline in assistant replies, and
clarifying questions before the assistant generates.
- MCP servers (Streamable HTTP, with OAuth sign-in) as extra assistant tools, each with your own instructions and
switches for chat, explanations, generation and the quiz check.
- Responsive light/dark interface and an installable app shell. Offline studying is limited:
private data is not cached; most operations need a server connection.
## Deploy, back up, migrate
See [deployment and restore](docs/DEPLOYMENT.md), [V1 migration](docs/MIGRATION.md), and
[AI providers and account integration](docs/AI.md).
The image runs a single Node process with SQLite and local file storage. No database or queue
container is required. The container runs as UID/GID 1000 and persists everything under `/data`.
```sh
docker compose up -d --build
```
Default V2 host port: **3727**, deliberately separate from the old application. Use a separate
data folder. Docker Desktop image build and disposable-container runtime checks now pass;
Unraid-specific permissions and reverse-proxy checks remain. No production deployment has
been performed.
## Verification and resuming work
```powershell
npm.cmd run check
```
Tests create isolated temporary databases. AI integration tests use a local mock server and
need loopback networking. They do not spend provider credits. Real provider credentials,
account-specific model access, Linux container behavior and Unraid proxy configuration must
be checked in their target environments.
[PROGRESS.md](PROGRESS.md) records completed work, remaining verification, decisions and the
resume procedure. V1 remains on `main` and in Git history; V2 work is on the `v2` branch.
Pushing `v2` to Forgejo runs CI and publishes the `study:v2` image (never `:latest`); see
[deployment](docs/DEPLOYMENT.md). Nothing deploys automatically.