Signals judge one subject, with a sentence of your own, not any one word (#259)

Jev was asked "Is this item about any of these: ai, development, programming?", so any one broad
word was enough and the Signal's name, which says what is meant, was never sent. AI Development
held 54 items: Sega pulling a game remaster (0.90), a Surface Laptop review (0.95), a C++ tutorial
(0.99). It is now asked about one subject, called by the Signal's name, described by its words
and, when those are not enough, its owner's sentence. Scored against TypeSafe over those 54 with
"AI tools for writing software: coding agents, AI dev tools, vibe coding, AI in code review.":
5 stay, Linux kernel AI code review highest at 0.94; the remaster 0.06, the C++ tutorial 0.02.

signals.description is new, and its first start deletes every verdict, which answered the old
question, so everything in the window is asked again. Any change to a Signal's name, words or
sentence drops its verdicts, since each is part of the question. The queue query names the
Signal's sentence apart from the item's description, which share a row; the test caught the
item's winning.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/ui/fixtures/serve.js

@@ -21,7 +21,7 @@ http.createServer((req, res) => {
       const title = String(state).toLowerCase();
       const answers = {};
       for (const [id, q] of Object.entries(questions)) {
-        const words = q.instructions.replace(/^.*: /, '').replace(/\?$/, '').split(', ');
+        const words = /described by these words: ([^.]*)\./.exec(q.instructions)[1].split(', ');
         answers[id] = { noul: words.some(w => title.includes(w.toLowerCase())) ? 0.9 : 0.1 };
       }
       res.writeHead(200, { 'content-type': 'application/json' }).end(JSON.stringify({ answers }));