Files
paperclip/ui/src/lib/issue-reference.ts
T
Devin Foley 8145141c55 Fix external issue URL rewriting in markdown (#4558)
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies.
> - Issue and comment rendering is part of the board UI where humans
supervise and inspect agent work.
> - External Paperclip issue URLs can appear in comments as references
to other runs, review threads, or remote test environments.
> - Those links must preserve their full destination, including origin,
port, and `#comment-...` fragments, or the operator is taken to the
wrong place.
> - The bug here was that absolute `http(s)` issue URLs were being
normalized into internal `/issues/...` routes in the markdown path.
> - This pull request stops rewriting absolute URLs while keeping
internal issue-reference behavior for relative paths and identifiers.
> - The benefit is that authored external links now navigate exactly
where the operator expects, especially for remote test and
comment-deep-link workflows.

## What Changed

- Stopped `ui/src/lib/issue-reference.ts` from treating absolute
`http(s)` URLs as internal issue paths.
- Added defense-in-depth in `ui/src/lib/mention-chips.ts` so absolute
`http(s)` URLs are never reclassified as issue mention chips.
- Updated `ui/src/lib/issue-reference.test.ts` to cover absolute
Paperclip URLs with preserved origin, port, and comment hash.
- Updated `ui/src/components/MarkdownBody.test.tsx` to assert the
reported URL renders as an external link, not an internal `/issues/...`
href.

## Verification

- `pnpm exec vitest run ui/src/lib/issue-reference.test.ts
ui/src/components/MarkdownBody.test.tsx`
- Expected result: `2` files passed, `37` tests passed.
- Manual spot-check from the issue report path: a URL like
`http://remote.example.test:3103/PAPA/issues/PAPA-115#comment-...`
should remain an external link with its full destination preserved.

## Risks

- Low risk. The change narrows when Paperclip rewrites URLs, so the main
risk is if some existing workflow depended on absolute `http(s)`
Paperclip URLs being converted into internal issue links. The added
regression coverage is aimed at preventing that from regressing
silently.

## Model Used

- OpenAI Codex local agent via Paperclip `codex_local`
- Backing model family: GPT-5-based Codex runtime
- Exact backend model ID/version: not exposed by this adapter/runtime
surface
- Context window: not exposed by this adapter/runtime surface
- Capabilities used: tool use, shell command execution, code editing,
git operations, and local test execution

## 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 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
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] I will address all Greptile and reviewer comments before
requesting merge
2026-04-26 17:19:23 -07:00

154 lines
4.7 KiB
TypeScript

type MarkdownNode = {
type: string;
value?: string;
url?: string;
children?: MarkdownNode[];
};
const BARE_ISSUE_IDENTIFIER_RE = /^[A-Z][A-Z0-9]+-\d+$/i;
const ISSUE_SCHEME_RE = /^issue:\/\/:?([^?#\s]+)(?:[?#].*)?$/i;
const ISSUE_REFERENCE_TOKEN_RE = /issue:\/\/:?[^\s<>()]+|https?:\/\/[^\s<>()]+|\/(?:[^\s<>()/]+\/)*issues\/[A-Z][A-Z0-9]+-\d+(?=$|[\s<>)\],.;!?:])|\b[A-Z][A-Z0-9]+-\d+\b/gi;
export function parseIssuePathIdFromPath(pathOrUrl: string | null | undefined): string | null {
if (!pathOrUrl) return null;
const pathname = pathOrUrl.trim();
if (!pathname) return null;
if (/^https?:\/\//i.test(pathname)) return null;
const segments = pathname.split("/").filter(Boolean);
const issueIndex = segments.findIndex((segment) => segment === "issues");
if (issueIndex === -1 || issueIndex === segments.length - 1) return null;
const issuePathId = decodeURIComponent(segments[issueIndex + 1] ?? "");
if (!issuePathId || issuePathId.startsWith(":")) return null;
return BARE_ISSUE_IDENTIFIER_RE.test(issuePathId) ? issuePathId.toUpperCase() : issuePathId;
}
export function parseIssueReferenceFromHref(href: string | null | undefined) {
if (!href) return null;
const trimmed = href.trim();
const issueSchemeMatch = trimmed.match(ISSUE_SCHEME_RE);
if (issueSchemeMatch?.[1]) {
const issuePathId = decodeURIComponent(issueSchemeMatch[1]);
return {
issuePathId,
href: `/issues/${encodeURIComponent(issuePathId)}`,
};
}
const pathId = parseIssuePathIdFromPath(href);
if (pathId) {
return {
issuePathId: pathId,
href: `/issues/${encodeURIComponent(pathId)}`,
};
}
if (!BARE_ISSUE_IDENTIFIER_RE.test(trimmed)) return null;
const normalized = trimmed.toUpperCase();
return {
issuePathId: normalized,
href: `/issues/${encodeURIComponent(normalized)}`,
};
}
function splitTrailingPunctuation(token: string) {
let core = token;
let trailing = "";
while (core.length > 0) {
const lastChar = core.at(-1);
if (!lastChar || !/[),.;!?:\]]/.test(lastChar)) break;
if (lastChar === ")") {
const openCount = (core.match(/\(/g) ?? []).length;
const closeCount = (core.match(/\)/g) ?? []).length;
if (closeCount <= openCount) break;
}
if (lastChar === "]") {
const openCount = (core.match(/\[/g) ?? []).length;
const closeCount = (core.match(/\]/g) ?? []).length;
if (closeCount <= openCount) break;
}
trailing = `${lastChar}${trailing}`;
core = core.slice(0, -1);
}
return { core, trailing };
}
function createIssueLinkNode(value: string, href: string, childType: "text" | "inlineCode" = "text"): MarkdownNode {
return {
type: "link",
url: href,
children: [{ type: childType, value }],
};
}
function linkifyIssueReferencesInText(value: string): MarkdownNode[] | null {
const nodes: MarkdownNode[] = [];
let cursor = 0;
let matched = false;
for (const match of value.matchAll(ISSUE_REFERENCE_TOKEN_RE)) {
const raw = match[0];
if (!raw) continue;
const start = match.index ?? 0;
const end = start + raw.length;
const { core, trailing } = splitTrailingPunctuation(raw);
const issueRef = parseIssueReferenceFromHref(core);
if (!issueRef) continue;
matched = true;
if (start > cursor) {
nodes.push({ type: "text", value: value.slice(cursor, start) });
}
nodes.push(createIssueLinkNode(core, issueRef.href));
if (trailing) {
nodes.push({ type: "text", value: trailing });
}
cursor = end;
}
if (!matched) return null;
if (cursor < value.length) {
nodes.push({ type: "text", value: value.slice(cursor) });
}
return nodes;
}
function rewriteMarkdownTree(node: MarkdownNode) {
if (!Array.isArray(node.children) || node.children.length === 0) return;
if (node.type === "link" || node.type === "linkReference" || node.type === "code" || node.type === "definition" || node.type === "html") {
return;
}
const nextChildren: MarkdownNode[] = [];
for (const child of node.children) {
if (child.type === "inlineCode" && typeof child.value === "string") {
const issueRef = parseIssueReferenceFromHref(child.value);
if (issueRef) {
nextChildren.push(createIssueLinkNode(child.value, issueRef.href, "inlineCode"));
continue;
}
}
if (child.type === "text" && typeof child.value === "string") {
const linked = linkifyIssueReferencesInText(child.value);
if (linked) {
nextChildren.push(...linked);
continue;
}
}
rewriteMarkdownTree(child);
nextChildren.push(child);
}
node.children = nextChildren;
}
export function remarkLinkIssueReferences() {
return (tree: MarkdownNode) => {
rewriteMarkdownTree(tree);
};
}