📝 docs(readme): lead with AI features + add quire-definition tagline (#75)

Pull the AI story up front instead of burying it under privacy. New
'AI, on your terms' section leads with book scan + grounded insights,
framing everything as opt-in and routed through a self-hosted endpoint.
Add a definitional tagline that ties the etymology of 'quire' (a
gathering of leaves bound into a book) to what Quire unifies: library,
reading state, and insights.

Author: vitofico

README.md

@@ -5,7 +5,13 @@
 <h1 align="center">Quire</h1>
 
 <p align="center">
-  <em>Self-hosted EPUB reader for calibre-web. No telemetry, no cloud, your data.</em>
+  <strong>quire</strong> <em>&nbsp;/ˈkwaɪər/ &nbsp;n.&nbsp; — a gathering of folded leaves, bound into a book.</em>
+</p>
+
+<p align="center">
+  <em>A privacy-first Android EPUB reader for calibre-web — gathering your library,<br>
+  your reading state, and opt-in, self-hosted AI into one bound whole.<br>
+  No telemetry, no cloud, your data.</em>
 </p>
 
 <p align="center">
@@ -27,9 +33,14 @@
 A self-hosted reading stack for people who already run [calibre-web]:
 
 - **Quire** — native Android EPUB reader (Kotlin / Compose / Readium).
-- **Quire Server** — small FastAPI service that stores reading progress
-  (and later bookmarks) in Postgres. The Python package is `quire_server`
-  and the container image is `ghcr.io/vitofico/quire-server`.
+- **Quire Server** — small FastAPI service that stores reading state and
+  your per-user library mirror in Postgres, and orchestrates the optional
+  AI features. The Python package is `quire_server` and the container image
+  is `ghcr.io/vitofico/quire-server`.
+- **Optional, private AI** — book insights, catalog previews, a reader
+  profile, recommendations, and barcode book-scanning — all routed through
+  an OpenAI-compatible endpoint *you* control. Off by default, opt-in per
+  user. [Jump to AI ↓](#ai-on-your-terms)
 
 calibre-web stays the source of truth for books. Quire Server is the
 source of truth for reading state. Quire reconciles both on the device.
@@ -45,6 +56,77 @@ source of truth for reading state. Quire reconciles both on the device.
                                          [Postgres]
 ```
 
+## AI, on your terms
+
+Most reading apps that got "smart" did it by shipping your library to
+someone else's cloud. Quire does the opposite: the intelligence runs
+against an endpoint **you** point it at, it is **off by default**, and
+every user **opts in** individually. The admin configures any
+OpenAI-compatible endpoint — Ollama, llama.cpp, vLLM, OpenAI,
+OpenRouter, … — and if AI isn't enabled and opted into, Quire makes no
+AI calls at all.
+
+What that unlocks:
+
+### 📷 Scan a book before you buy it
+
+Point your phone at a physical book's barcode (or type the ISBN) and
+Quire tells you, on the spot, whether it belongs on your shelf:
+
+- **Reader-affinity score** — a deterministic 0–100 match score with a
+  band (very low → very high) and plain-language reasons, computed from
+  the authors, series, and subjects already in your library. **No LLM,
+  no AI network call** — instant, private, and works as a snap judgment
+  in a bookshop.
+- **Already-owned detection** — tells you if it's in your library and
+  where you left off (unread / in progress / finished / abandoned).
+- **Cover + one-tap deep dive** — pulls the cover from OpenLibrary and,
+  if you want more, loads the full AI insight card on demand.
+
+### 📖 Insights that actually say something
+
+Per-book insight cards generated by the LLM and **grounded with real
+citations** from Wikipedia and OpenLibrary — not hallucinated blurbs:
+
+- intro · author context · series placement
+- themes & **craft notes** (how the book is *made*, not just what it's about)
+- **comparative anchors** ("if you liked…")
+- a distinctive take · discussion prompts · content advisory · cited sources
+
+Insights show up **on catalog tiles before you download** (tap the info
+icon), so you can size up a book before it ever touches your device.
+Download it and the cached insight is promoted onto the owned book
+instantly. Cards are cached per book and shared across every opted-in
+reader on your instance, so you pay for each generation once.
+
+### 🎚️ In your voice, in your language
+
+Set the tone — neutral, enthusiastic, scholarly, or casual — and the
+language: 100+ options, or **`auto`** to follow the book's own language.
+Don't like a card? Regenerate it with feedback.
+
+### 🧭 A reader profile that recommends
+
+From the books you've finished, Quire builds an AI-written narrative of
+your taste (refresh on demand) that powers three flavors of suggestions:
+
+- **In-library** — unfinished books you *already own* that fit your taste.
+- **Discovery** — more from authors you've finished, fetched from OpenLibrary.
+- **AI-suggested** — books you don't own yet, worth hunting down.
+
+Plus **Library Stats** (finished / in-progress / abandoned counts, top
+authors, top themes) and an **abandoned-book** status that quietly drops
+DNFs out of your library view until you ask for them.
+
+### 🔧 Built for self-hosters
+
+Per-user daily budgets and quotas, an AI **health endpoint**, and deploy
+modes for **sync-only**, **AI-only**, or **full-stack** operation. Bring
+your own model; cap your own spend.
+
+> All of the above is opt-in and routed through your endpoint. For setup,
+> env vars, and deploy modes see [`server/README.md`](server/README.md).
+
 ## Why this exists
 
 The starting point was an OPDS catalog (calibre-web) and a simple need:
@@ -81,40 +163,6 @@ Apache-2.0, calibre-web-only, **no telemetry, ever.**
 - Credentials are stored in Android Keystore (hardware-backed where the
   device supports it).
 
-## AI features (optional)
-
-Quire optionally calls AI for book insights and library analysis. AI is
-**off by default**. The Quire Server admin enables it server-side by
-configuring an OpenAI-compatible endpoint (Ollama, llama.cpp, vLLM,
-OpenAI, OpenRouter, …); each user then opts in from Quire's settings.
-
-When enabled, Quire Server sends the EPUB metadata (title, author,
-publisher, description, subjects) of books a user opens to the
-configured AI endpoint, plus deterministic queries to Wikipedia and
-OpenLibrary to ground the generated insights with citations. The
-generated insight is cached server-side per book and reused across all
-of that user's devices and other opted-in users on the same instance.
-
-Surfaces in the app today:
-
-- **Book-detail cards** — summary, author, series, themes, craft notes,
-  comparative anchors, discussion prompts, content advisory, sources.
-- **Catalog detail screen** — previews the same insight cards before
-  download via an `info` icon on each catalog tile. Once the EPUB is
-  downloaded the cached catalog insight is promoted onto the canonical
-  identity so the book-detail screen shows it immediately.
-- **Library Stats** — totals, finished / in-progress / abandoned counts,
-  top authors, top themes, backed by `GET /library/v1/stats`.
-- **Library Insights** — a per-user reader profile (narrative, in-library
-  recommendations, OpenLibrary discovery recommendations, AI-suggested
-  reads), refreshed on demand from the screen. Backed by
-  `GET /ai/v1/profile` + `POST /ai/v1/profile/refresh`. A "Delete
-  profile" action in Settings wipes the cached row.
-- **Abandoned book UX** — books you've marked abandoned drop out of
-  Library by default; a "Show abandoned" toggle reveals them.
-
-For configuration details see [`server/README.md`](server/README.md).
-
 ## Install
 
 Install Quire from [F-Droid] or grab the latest APK from [Releases],