bavitutor 0.1.4 → 0.2.0

package/README.md

@@ -37,8 +37,15 @@ vp install
 vp run dev
 ```
 
-Open <http://localhost:5180>. The API runs on port 4100 and the web dev server
-proxies `/api` to it. Data lives in `apps/server/data/bavitutor.db` (SQLite).
+Open <https://bavitutor.localhost>. Both dev servers run through
+[portless](https://github.com/vercel-labs/portless), which gives them free
+ports behind named URLs, so they never clash with another checkout: the API is
+<https://api.bavitutor.localhost> and the web dev server proxies `/api` to it.
+In a git worktree the branch name is prepended
+(`https://<branch>.bavitutor.localhost`); both URLs are printed on start. The
+first run creates a local certificate authority, trusts it and starts the proxy
+on port 443; if that times out, run it again. Data lives in
+`apps/server/data/bavitutor.db` (SQLite).
 
 ### Use it
 
@@ -132,6 +139,11 @@ The three `BAVI_MODEL_*` variables are only starting points: **Settings → AI m
    answer counts. Concepts that keep slipping get flagged with remediation;
    a backlog switches to triaged catch-up spread over a week; after a long
    absence a 5-minute check-in replaces the pile. "Just 5" keeps it short.
+   Every concept is also split into a few **ideas**, each with its own FSRS
+   card: a flashcard round closes each lesson, and due ideas come back as
+   flashcards written fresh each time from how they were asked before. You
+   recall the answer first, tap "Show choices", then pick the right statement
+   out of four near-identical ones; recall time and the pick set the rating.
 6. **Your day.** Home plans reviews first, then as many new lessons as fit
    your daily time and a two-week review-load forecast. Settings cover daily
    time, retention, new-concept cap, visuals, a daily reminder, and the
@@ -141,6 +153,19 @@ The three `BAVI_MODEL_*` variables are only starting points: **Settings → AI m
    review forecast. Lessons resume after a reload, and a break is suggested
    after about 25 minutes.
 
+### Learning from your own sources
+
+Instead of (or as well as) describing a goal, add your own documents on the
+landing page: several `.txt` or `.md` files at once, dropped files, or pasted
+text. Choose **Only my sources** to make them the whole truth, or **Also search
+the web** to let research fill gaps (added concepts are marked "Added"). An
+agent reads each document in parts and splits it into lessons in the author's
+order. Each lesson holds 4 to 12 ideas, written close to the author's words,
+each with a verbatim quote checked against the text. Lessons are taught from
+the source: each chunk says **From your source** or **Added by BaviTutor**, with
+the original words one tap away. The notes page lists every idea with its
+quote, so you can re-read the book idea by idea.
+
 The design rests on the research in [`docs/research`](docs/research):
 learning science (≈235 references, with engine rules), adaptive placement,
 source curation and graph building, 3Blue1Brown-style visualization, and an