fix: parse YAML block scalar skill descriptions (#5046)

## Thinking Path

> - Paperclip is the open source control plane teams use to manage AI
agents for work.
> - Company skills are imported from `SKILL.md` files and rely on YAML
frontmatter to describe what each skill does.
> - Multi-line descriptions commonly use YAML block scalars (`>` and
`|`), but the broken parser path behind #4989 reduced those descriptions
to a literal `>` or `|`.
> - The earliest contributor fix for that bug was PR #5046, so this
branch keeps that PR as the canonical merge target instead of replacing
it.
> - Follow-up work from #5071 and #8258 was then transplanted onto this
earlier branch so the final PR preserves contributor credit while still
shipping the strongest complete fix.
> - The resulting change fixes block-scalar parsing in the shared
frontmatter path, aligns server company-skill imports with that shared
parser, and prevents already-stale stored markers from rendering as junk
in the UI.

## Linked Issues or Issue Description

- Fixes #4989
- Refs #2863
- Refs #788
- Related superseded PRs: #5071, #8258

## What Changed

- Kept the original PR #5046 server-side company-skill fix and
regression coverage as the base branch history.
- Added the missing YAML chomping and indicator hardening explored
further in #5071.
- Moved frontmatter parsing to the shared parser path so
`packages/shared`, `packages/skills-catalog`, and server company-skill
imports stay aligned.
- Added UI summary sanitization and fallback handling so stale stored
`>` / `|` values no longer render as visible junk in company-skill
cards.
- Added regression coverage for shared frontmatter parsing,
skills-catalog parsing, company-skill imports, and stale-summary
fallback behavior.

## Verification

- Passed locally: `pnpm exec vitest run
packages/shared/src/frontmatter.test.ts
packages/skills-catalog/src/frontmatter.test.ts
server/src/__tests__/company-skills.test.ts
ui/src/lib/company-skill-summary.test.ts`
- Passed locally: `pnpm --filter @paperclipai/shared typecheck`
- Passed locally: `pnpm --filter @paperclipai/skills-catalog typecheck`
- Not fully runnable in this worktree: `pnpm --filter
@paperclipai/server typecheck` currently fails in `packages/plugins/sdk`
before reaching server code because local workspace `node_modules` type
deps are missing (`TS2688` for `node` / `react`).
- GitHub Actions / PR checks are rerunning on PR #5046 head
`005290b7557725abf748d00f36dd24ea0d919aba`.

## Risks

- Medium-low risk: the fix now touches shared parser code, server
company-skill imports, and UI fallback display rather than only the
server import path.
- The parser is still intentionally narrower than a full YAML
implementation; this change focuses on block-scalar correctness and the
stale-description rendering path relevant to #4989 / #2863.
- This branch intentionally supersedes narrower overlapping work from
#5071 and duplicate work from #8258 once the survivor PR is green.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex / GPT-5-based coding agent with local shell and
code-editing tools enabled.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Devin Foley <devin@paperclip.ing>
This commit is contained in:
MrBob
2026-06-18 16:01:11 -03:00
committed by GitHub
parent 5320a44088
commit 5f16efb3d0
13 changed files with 496 additions and 316 deletions
@@ -0,0 +1,34 @@
import { describe, expect, it } from "vitest";
import { parseFrontmatterMarkdown } from "./frontmatter.js";
describe("skills catalog frontmatter parsing", () => {
it("supports YAML block scalars used by SKILL.md descriptions", () => {
const parsed = parseFrontmatterMarkdown([
"---",
"name: Catalog Skill",
"description: >",
" First line",
" second line",
"---",
"",
"Body",
].join("\n"));
expect(parsed.frontmatter.description).toBe("First line second line\n");
});
it("supports block-scalar chomping variants", () => {
const parsed = parseFrontmatterMarkdown([
"---",
"name: Catalog Skill",
"description: >-",
" First line",
" second line",
"---",
"",
"Body",
].join("\n"));
expect(parsed.frontmatter.description).toBe("First line second line");
});
});
+8 -153
View File
@@ -1,154 +1,9 @@
export interface MarkdownDoc {
frontmatter: Record<string, unknown>;
body: string;
hasFrontmatter: boolean;
}
export {
asBoolean,
asString,
asStringArray,
parseFrontmatterMarkdown,
type MarkdownDoc,
} from "@paperclipai/shared";
export function isPlainRecord(value: unknown): value is Record<string, unknown> {
return typeof value === "object" && value !== null && !Array.isArray(value);
}
export function asString(value: unknown): string | null {
if (typeof value !== "string") return null;
const trimmed = value.trim();
return trimmed.length > 0 ? trimmed : null;
}
export function asBoolean(value: unknown): boolean | null {
return typeof value === "boolean" ? value : null;
}
export function asStringArray(value: unknown): string[] | null {
if (value === undefined) return [];
if (!Array.isArray(value)) return null;
const out: string[] = [];
for (const item of value) {
const text = asString(item);
if (!text) return null;
out.push(text);
}
return out;
}
export function parseFrontmatterMarkdown(raw: string): MarkdownDoc {
const normalized = raw.replace(/\r\n/g, "\n");
if (!normalized.startsWith("---\n")) {
return { frontmatter: {}, body: normalized.trim(), hasFrontmatter: false };
}
const closing = normalized.indexOf("\n---\n", 4);
if (closing < 0) {
return { frontmatter: {}, body: normalized.trim(), hasFrontmatter: false };
}
const frontmatterRaw = normalized.slice(4, closing).trim();
const body = normalized.slice(closing + 5).trim();
return {
frontmatter: parseYamlFrontmatter(frontmatterRaw),
body,
hasFrontmatter: true,
};
}
function parseYamlFrontmatter(raw: string): Record<string, unknown> {
const prepared = prepareYamlLines(raw);
if (prepared.length === 0) return {};
const parsed = parseYamlBlock(prepared, 0, prepared[0]!.indent);
return isPlainRecord(parsed.value) ? parsed.value : {};
}
function prepareYamlLines(raw: string) {
return raw
.split("\n")
.map((line) => ({
indent: line.match(/^ */)?.[0].length ?? 0,
content: line.trim(),
}))
.filter((line) => line.content.length > 0 && !line.content.startsWith("#"));
}
function parseYamlBlock(
lines: Array<{ indent: number; content: string }>,
startIndex: number,
indentLevel: number,
): { value: unknown; nextIndex: number } {
let index = startIndex;
if (index >= lines.length || lines[index]!.indent < indentLevel) {
return { value: {}, nextIndex: index };
}
const isArray = lines[index]!.indent === indentLevel && lines[index]!.content.startsWith("-");
if (isArray) {
const values: unknown[] = [];
while (index < lines.length) {
const line = lines[index]!;
if (line.indent < indentLevel) break;
if (line.indent !== indentLevel || !line.content.startsWith("-")) break;
const remainder = line.content.slice(1).trim();
index += 1;
if (!remainder) {
const nested = parseYamlBlock(lines, index, indentLevel + 2);
values.push(nested.value);
index = nested.nextIndex;
continue;
}
values.push(parseYamlScalar(remainder));
}
return { value: values, nextIndex: index };
}
const record: Record<string, unknown> = {};
while (index < lines.length) {
const line = lines[index]!;
if (line.indent < indentLevel) break;
if (line.indent !== indentLevel) {
index += 1;
continue;
}
const separatorIndex = line.content.indexOf(":");
if (separatorIndex <= 0) {
index += 1;
continue;
}
const key = line.content.slice(0, separatorIndex).trim();
const remainder = line.content.slice(separatorIndex + 1).trim();
index += 1;
if (!remainder) {
const nested = parseYamlBlock(lines, index, indentLevel + 2);
record[key] = nested.value;
index = nested.nextIndex;
continue;
}
record[key] = parseYamlScalar(remainder);
}
return { value: record, nextIndex: index };
}
function parseYamlScalar(rawValue: string): unknown {
const trimmed = rawValue.trim();
if (trimmed === "") return "";
if (trimmed === "null" || trimmed === "~") return null;
if (trimmed === "true") return true;
if (trimmed === "false") return false;
if (trimmed === "[]") return [];
if (trimmed === "{}") return {};
if (/^-?\d+(\.\d+)?$/.test(trimmed)) return Number(trimmed);
if (
trimmed.startsWith("\"") ||
trimmed.startsWith("[") ||
trimmed.startsWith("{")
) {
try {
return JSON.parse(trimmed);
} catch {
return trimmed;
}
}
return trimmed;
}
export { isFrontmatterPlainRecord as isPlainRecord } from "@paperclipai/shared";