fix(story-mode): a quoted report marks what it skips, a run that never loaded says so (review round 11)

From the fact-checker's last items:
- A helper's report quoted in a notice joined its first sentence to one
  from paragraphs later with nothing between: where text was left out,
  the balloon now says "…" (found in the report itself, so two
  sentences that follow each other are never marked).
- "The first run fails on purpose, as you asked" for a run that never
  loaded a test (a collection error) now reads "At first the tests don't
  even load, as you asked; the second run passes.", as a test panel
  already says it.
- A list intro without a count ("What failed and how I fixed it:") brings
  its items while they fit in 360 characters, not 260.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

test/fixtures/story-corpus/question-tests-first-push.expected.json

@@ -54,7 +54,7 @@
       {
         "kind": "loop",
         "ok": true,
-        "story": "The first run fails on purpose, as you asked; the second passes.",
+        "story": "At first the tests don't even load, as you asked; the second run passes.",
         "unaskedSave": false,
         "director": "2 checks · 4 edits · +150 · last: ok · after 1 second opinion",
         "balloon": "All 19 test cases pass (13 test functions), and ruff check and ruff format both come back clean.",

test/fixtures/story-corpus/text-plan-dry-run-helper.expected.json

@@ -142,7 +142,7 @@
         "story": "A background job reports back.",
         "unaskedSave": false,
         "director": "Prompt · 6 words · task",
-        "balloon": "\"Write README for csvstat\" reports: I wrote README.md and committed it on its own on feat/csvstat. The README has every section you asked for and no badges.",
+        "balloon": "\"Write README for csvstat\" reports: I wrote README.md and committed it on its own on feat/csvstat. … The README has every section you asked for and no badges.",
         "tests": null,
         "roundsOk": null,
         "printed": null,

test/story-mode.test.ts

@@ -9,6 +9,7 @@ import {
   buildStoryPage,
   buildStoryTurns,
   classifyBashCommand,
+  closingText,
   createStoryReducer,
   exactDuration,
   firstSentence,
@@ -1103,6 +1104,29 @@ describe('buildStoryPage', () => {
     expect(performance.now() - start).toBeLessThan(1500);
   });
 
+  it('a quoted report marks only the text it skips with "…"', () => {
+    const report = [
+      'I wrote README.md and committed it.',
+      'It covers usage and the exit codes.',
+      'It reads the file and prints the counts for each column, one line per column. '.repeat(3),
+      'One known issue: big numbers are shown rounded.',
+    ].join('\n\n');
+    // The second sentence follows the first: no mark. The issue is three paragraphs on: marked.
+    expect(
+      closingText(
+        report,
+        ['It covers usage and the exit codes.', 'One known issue: big numbers are shown rounded.'],
+        ' … '
+      )
+    ).toBe(
+      'I wrote README.md and committed it. It covers usage and the exit codes. … One known issue: big numbers are shown rounded.'
+    );
+    // Claude's own closing words are never marked.
+    expect(closingText(report, ['One known issue: big numbers are shown rounded.'])).toBe(
+      'I wrote README.md and committed it. One known issue: big numbers are shown rounded.'
+    );
+  });
+
   it('a short ending keeps the sentence that leaves something open', () => {
     const page = pageOf([
       prompt('run them'),