fix(aiui): content cards carried the PREVIOUS item's description

Operator-reported via a Bitcoin-films transcript: "Banking on Bitcoin" was
captioned with *The Rise and Rise of Bitcoin*'s description, "Cryptopia" with
*The Bitcoin Standard*'s, and the section header "Documentaries:" bled into the
first card of each group. Read as the model talking nonsense; the model's prose
was correct throughout and only the pairing was wrong.

Several patterns anchor with `(?:^|\n)` so they fire only at a line start.
That makes m.index point at the NEWLINE — one character before the line the
match is really on — so extractDescriptionForTag's window, which walks back
from `matchIndex - 1`, landed on the PREVIOUS line. The description became
"previous line + this item's own text".

Normalised inside the helper rather than at each of its nine call sites, so a
pattern that gains a `(?:^|\n)` anchor later cannot silently reintroduce it.

Fault-injected to prove the tests are not vacuous: with the fix removed, two
fail with exactly the reported strings — 'Documentaries: – Early documentary
fo…' and 'The Rise and Rise of Bitcoin – Early …'. 26/26 with it restored.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

aiui/packages/app/src/composables/__tests__/contentExtraction.test.ts

@@ -123,3 +123,44 @@ And a book:
     expect(titles.length).toBeGreaterThan(0)
   })
 })
+
+describe('description pairing (operator-reported: cards carried the WRONG description)', () => {
+  // Verbatim shape of the Bitcoin-films answer that produced mis-paired cards.
+  // The model's prose was correct; the parser paired each title with the
+  // PREVIOUS line because `(?:^|\n)`-anchored patterns report m.index at the
+  // newline, shifting the line window back by one line.
+  const TRANSCRIPT = [
+    'Here are some films about Bitcoin:',
+    '',
+    'Documentaries:',
+    '',
+    '- The Rise and Rise of Bitcoin (2014) – Early documentary following Bitcoin\'s emergence and community.',
+    '- Banking on Bitcoin (2016) – Explores Bitcoin\'s origins and its potential to disrupt finance.',
+    '- Cryptopia (2020) – Examines both the promise and pitfalls of crypto.',
+  ].join('\n')
+
+  it('does not caption a title with the previous item\'s description', () => {
+    const series = extractAllTVSeries(TRANSCRIPT, 'recommend me some bitcoin series')
+    const banking = series.find(s => /Banking on Bitcoin/i.test(s.title))
+    if (banking?.synopsis) {
+      expect(banking.synopsis).not.toMatch(/Early documentary/i)
+      expect(banking.synopsis).toMatch(/Explores Bitcoin/i)
+    }
+  })
+
+  it('does not bleed a section header into the first card of a group', () => {
+    const series = extractAllTVSeries(TRANSCRIPT, 'recommend me some bitcoin series')
+    for (const s of series) {
+      expect(s.synopsis ?? '').not.toMatch(/Documentaries:/i)
+    }
+  })
+
+  it('keeps each item paired with its OWN description', () => {
+    const series = extractAllTVSeries(TRANSCRIPT, 'recommend me some bitcoin series')
+    const rise = series.find(s => /Rise and Rise/i.test(s.title))
+    if (rise?.synopsis) {
+      expect(rise.synopsis).toMatch(/Early documentary/i)
+      expect(rise.synopsis).not.toMatch(/Explores Bitcoin/i)
+    }
+  })
+})

aiui/packages/app/src/composables/contentExtraction.ts

@@ -70,6 +70,24 @@ function extractFirstImageFromText(text: string): string | undefined {
 }
 
 function extractDescriptionForTag(text: string, matchIndex: number, matchLength: number): string {
+  // Several patterns anchor with `(?:^|\n)` so they only fire at a line start.
+  // That makes `m.index` point at the NEWLINE, one character before the line
+  // the match is actually on — and the line window below then walks back from
+  // `matchIndex - 1` and lands on the PREVIOUS line. The description became
+  // "previous line + this item's own text".
+  //
+  // Operator-visible result: "Banking on Bitcoin" captioned with *The Rise and
+  // Rise of Bitcoin*'s description, and the section header "Documentaries:"
+  // bleeding into the first card of each group. The model's prose was correct
+  // throughout; only this pairing was wrong.
+  //
+  // Normalised here rather than at each of the nine call sites, so a pattern
+  // that gains a `(?:^|\n)` anchor later cannot silently reintroduce it.
+  while (matchLength > 0 && (text[matchIndex] === '\n' || text[matchIndex] === '\r')) {
+    matchIndex += 1
+    matchLength -= 1
+  }
+
   const prevNewline = text.lastIndexOf('\n', matchIndex - 1)
   const lineStart = prevNewline === -1 ? 0 : prevNewline + 1
   const nextNewline = text.indexOf('\n', matchIndex + matchLength)