docs: address Copilot review round 5 on #2203

The truncation guard read only the first physical line of the scalar, so
a multiline plain scalar slipped past it:

    description: Covers boards
      #28 and #11

YAML parses that as `Covers boards`, and the first-line-only comparison
saw `Covers boards` on both sides and reported no loss — passing the
exact silent truncation the guard exists to reject.

It now walks the whole plain scalar: the value line plus every indented
continuation, whitespace-collapsed to match YAML's folding of newlines to
spaces. Quoted and block scalars are still skipped, since neither loses
text to a comment.

Two regression cases: the multiline truncation, and a multiline scalar
with no `#`, which must stay clean — the fix cannot be "reject anything
multiline".

No skill description or eval case changed, so skills:eval is unchanged
from round 4's 63/63. local:gate passes, 34/34. 390/390 script tests.

Signed-off-by: cliffhall <cliff@futurescale.com>
This commit is contained in:
cliffhall 2026-09-01 11:31:22 -04:00
commit ec2ef5656d
2 changed files with 66 additions and 10 deletions

View file

@ -156,27 +156,50 @@ export function parseSkill(dirName, text) {
// non-empty string. `board-ops` shipped for a while with its two board numbers
// and the option-deletion hazard cut off this way. Compare the raw scalar
// against what YAML actually kept and make any loss an error.
//
// The comparison has to span the WHOLE plain scalar, not its first physical
// line. A plain scalar continues onto more-indented lines, so
//
// description: Covers boards
// #28 and #11
//
// parses to `Covers boards` — and a first-line-only check compares that
// against `Covers boards` and sees no loss, passing the exact truncation this
// guard exists to reject (Copilot).
const lines = frontmatter.split("\n");
for (const [field, parsed] of [
["description", description],
["when_to_use", whenToUse],
]) {
if (typeof parsed !== "string") continue;
const raw = new RegExp("^" + field + ":[ \\t]*(.*)$", "m").exec(
frontmatter,
)?.[1];
if (raw === undefined) continue;
const trimmed = raw.trim();
const start = lines.findIndex((l) =>
new RegExp("^" + field + ":([ \\t]|$)").test(l),
);
if (start === -1) continue;
const head = lines[start].slice(field.length + 1).trim();
// Only an unquoted scalar can lose text to a comment; a quoted one is safe,
// and a block scalar (`|`/`>`) puts nothing on this line to compare.
if (/^["'|>]/.test(trimmed)) continue;
if (trimmed.length > parsed.trim().length) {
// and a block scalar (`|`/`>`) is read literally rather than comment-stripped.
if (/^["'|>]/.test(head)) continue;
// Continuation lines are indented and are not the next `key:` of the map.
const parts = [head];
for (let i = start + 1; i < lines.length; i++) {
const l = lines[i];
if (!/^[ \t]/.test(l) || l.trim() === "") break;
parts.push(l.trim());
}
// YAML folds a plain scalar's newlines to single spaces, so compare on
// whitespace-collapsed text rather than on the raw characters.
const collapse = (s) => s.replace(/\s+/g, " ").trim();
const rawText = collapse(parts.join(" "));
const keptText = collapse(parsed);
if (rawText.length > keptText.length) {
errors.push(
"`" +
field +
"` is truncated by an unquoted `#` — YAML kept " +
parsed.trim().length +
keptText.length +
" of " +
trimmed.length +
rawText.length +
" characters; quote the value",
);
}

View file

@ -471,3 +471,36 @@ test("the truncation guard covers `when_to_use`, not just `description`", () =>
assert.deepEqual(ok.errors, []);
assert.equal(ok.whenToUse, "Use when filing against board #28 or board #11.");
});
test("the truncation guard spans a multiline plain scalar", () => {
// A plain scalar continues onto more-indented lines, so a first-line-only
// comparison sees `Covers boards` on both sides and reports no loss — passing
// the exact truncation this guard exists to reject.
const multiline = [
"---",
"name: alpha",
"description: Covers boards",
" #28 and #11 and the hazard.",
"disable-model-invocation: false",
"---",
"body",
].join("\n");
const parsed = parseSkill("alpha", multiline);
assert.equal(parsed.description, "Covers boards");
assert.match(parsed.errors.join(" "), /`description` is truncated/);
// A multiline plain scalar with no `#` folds to one line and must stay clean,
// so the fix cannot be "reject anything multiline".
const folded = [
"---",
"name: alpha",
"description: Covers boards",
" and the option-deletion hazard.",
"disable-model-invocation: false",
"---",
"body",
].join("\n");
const ok = parseSkill("alpha", folded);
assert.deepEqual(ok.errors, []);
assert.equal(ok.description, "Covers boards and the option-deletion hazard.");
});