Companion: rules-based, context-aware writing advice

Replace the kitten's random generic tips with a deterministic, LLM-free
prose checker that reads the actual document and surfaces one gentle,
bilingual note at a time — quoting a slice of her own sentence so the
advice is clearly about *this* draft.

Rules (all conservative, tuned for a Mandarin-native ESL writer):
run-ons, comma splices, unclear antecedents, Oxford comma, a/an,
uncountable plurals, capitalize languages/days/months, subject-verb
agreement, plural-after-number, double determiner, "there is" + plural,
its/it's, than/then, comma-after-transition, doubled words, lowercase
"i", sentence capitals, and spacing around punctuation.

Each rule is paired with false-positive guards (e.g. "a university",
"After dinner, I went home and read", existing Oxford lists) and pinned
by a 45-case Vitest suite (npm test).

Also: bubbles now linger proportional to how much there is to read
(zh+en) and pause-on-hover, so denser advice no longer vanishes mid-read.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd

web/package.json

@@ -6,7 +6,9 @@
   "scripts": {
     "dev": "vite",
     "build": "tsc && vite build",
-    "preview": "vite preview"
+    "preview": "vite preview",
+    "test": "vitest run",
+    "test:watch": "vitest"
   },
   "dependencies": {
     "@tiptap/extension-character-count": "^2.11.5",
@@ -29,6 +31,7 @@
     "dictionary-en": "^4.0.0",
     "tailwindcss": "^4.0.0",
     "typescript": "^5.7.3",
-    "vite": "^6.1.0"
+    "vite": "^6.1.0",
+    "vitest": "^4.1.9"
   }
 }