mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-12 16:08:59 +02:00
Ryan AyersandClaude Opus 4.8
96ac9bbfef
Two independent bugs made transcript pages silently fail to reach the brain.
1. Frontmatter fence gluing. buildTranscriptPage() built the closing "---"
with no trailing newline, and session bodies always start with "## ", so
the rendered page ended "...---## User". gbrain's frontmatter matcher
(/^---\r?\n([\s\S]*?)\r?\n---(\r?\n|$)/ in src/core/markdown.ts) requires
the closing "---" to end its own line, so it skipped the glued fence,
latched onto the next standalone "---" in the transcript body, parsed the
prose between as YAML, and dropped the page with "Invalid YAML frontmatter".
Transcripts with no later "---" fell back to body-only, silently losing
their frontmatter. Fix: emit the fence on its own line with a blank
separator, matching renderPageBody()'s artifact branch.
2. Slug collisions. Two source files can map to one path-derived slug (a
session resumed under the same id on one day, or two ids sharing a 12-char
prefix). writeStaged() names each file "${slug}.md", so the second
overwrote the first; gbrain collected N-1 of N staged files and the
reconciliation guard failed the whole batch every run. Fix:
disambiguateSlugs() keeps the first occurrence and gives each later collider
a stable "-<sha8(source_path)>" suffix (deterministic, and slug + page_slug
move together so writeStaged, the failure mapping, and state recording agree).
Exports buildTranscriptPage, renderPageBody, and disambiguateSlugs for tests.
Adds regression tests for both failures.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wave-amended: contributor's local-workaround docblock note removed; issue refs retargeted #2653 (closed by its author) -> #2724 (the live 887-staged-to-0-ingested report)
66 lines
2.9 KiB
TypeScript
66 lines
2.9 KiB
TypeScript
/**
|
|
* Regression: transcript frontmatter fence must terminate its own line.
|
|
*
|
|
* buildTranscriptPage() emitted a closing `---` with no trailing newline, and
|
|
* session bodies always start with "## ", so the rendered page ended
|
|
* `...---## User`. gbrain's frontmatter matcher
|
|
* (`/^---\r?\n([\s\S]*?)\r?\n---(\r?\n|$)/`, src/core/markdown.ts) requires the
|
|
* closing `---` to end its own line, so it skipped the glued fence, latched onto
|
|
* the next standalone `---` in the transcript body, parsed the prose between as
|
|
* YAML, and dropped the whole page with "Invalid YAML frontmatter". Transcripts
|
|
* with no later `---` fell back to body-only (frontmatter silently lost).
|
|
*/
|
|
import { describe, it, expect } from "bun:test";
|
|
import { mkdtempSync, writeFileSync, rmSync } from "fs";
|
|
import { tmpdir } from "os";
|
|
import { join } from "path";
|
|
import {
|
|
parseTranscriptJsonl,
|
|
buildTranscriptPage,
|
|
renderPageBody,
|
|
} from "../bin/gstack-memory-ingest";
|
|
|
|
// The exact fence matcher gbrain uses (src/core/markdown.ts). Kept here so the
|
|
// test fails if the rendered fence ever regresses.
|
|
const GBRAIN_FENCE_RE = /^---\r?\n([\s\S]*?)\r?\n---(\r?\n|$)/;
|
|
|
|
describe("regression: transcript frontmatter fence terminates its own line", () => {
|
|
it("keeps a body-embedded `---` out of the frontmatter block", () => {
|
|
const dir = mkdtempSync(join(tmpdir(), "gstack-fence-"));
|
|
const file = join(dir, "sess.jsonl");
|
|
// User content carries a markdown horizontal rule (`---`) followed by a
|
|
// colon-bearing line — exactly what the old glued fence swept into YAML.
|
|
const content =
|
|
`{"type":"user","message":{"role":"user","content":"before rule\\n\\n---\\n\\nnot: valid: yaml: here"},` +
|
|
`"timestamp":"2026-05-01T00:00:00Z","cwd":"${dir}"}\n` +
|
|
`{"type":"assistant","message":{"role":"assistant","content":"ok"},"timestamp":"2026-05-01T00:00:01Z"}\n`;
|
|
writeFileSync(file, content, "utf-8");
|
|
|
|
const session = parseTranscriptJsonl(file);
|
|
expect(session).not.toBeNull();
|
|
const page = buildTranscriptPage(file, session!);
|
|
const staged = renderPageBody(page);
|
|
|
|
// The fence is never glued onto the body.
|
|
expect(staged).not.toContain("---##");
|
|
|
|
// gbrain's matcher closes the frontmatter at the real fence, not at the
|
|
// horizontal rule deep in the transcript body.
|
|
const m = staged.match(GBRAIN_FENCE_RE);
|
|
expect(m).not.toBeNull();
|
|
const frontmatter = m![1];
|
|
expect(frontmatter).toContain("session_id:");
|
|
expect(frontmatter).toContain("title:");
|
|
// The body (headings, the HR, the colon-trap line) must NOT bleed into YAML.
|
|
expect(frontmatter).not.toContain("## User");
|
|
expect(frontmatter).not.toContain("not: valid: yaml: here");
|
|
|
|
// And the parsed body (after the fence's trailing blank line) is the
|
|
// session content, not YAML-absorbed prose.
|
|
const body = staged.slice(m![0].length);
|
|
expect(body.trimStart().startsWith("## User")).toBe(true);
|
|
|
|
rmSync(dir, { recursive: true, force: true });
|
|
});
|
|
});
|