fix(memory-ingest): pass --include-gitignored to gbrain import

gstack-artifacts-init writes an ignore-everything .gitignore (a bare `*`,
headed "Do not edit") at the root of ~/.gstack. The memory ingest stages
pages into ~/.gstack/.staging-ingest-<pid>-<ts>/, which is inside that
repo, and gbrain's markdown collector honours .gitignore. The collector
therefore matches every staged file against `*` and collects zero.

The failure is silent. gbrain import exits 0 having imported nothing while
the ingest prints `written: N` from the STAGED count rather than the
imported count, so a run that indexes nothing looks identical to a healthy
one and the memory corpus quietly stops growing.

Reproduction, using git's own ignore machinery (no gbrain needed):

  git init .
  mkdir -p .staging-ingest-12345/learnings
  echo x > .staging-ingest-12345/learnings/page.md
  printf '*\n' > .gitignore
  git ls-files --others --exclude-standard   # -> empty

Passing --include-gitignored makes the import independent of whatever
.gitignore sits above the staging directory. Adding a negation to the
generated .gitignore is the alternative, but that file is gstack-owned and
marked "Do not edit", so any regeneration silently reintroduces the bug.

Adds a regression pin in the shape of memory-ingest-no-put_page.test.ts,
plus a behavioural test for the collision itself. Both source pins fail
against the unpatched file.
This commit is contained in:
Gawie van Blerk 2026-08-13 20:34:34 +02:00 committed by Garry Tan
parent 1d41ee3ab3
commit b1ee32ad86
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
2 changed files with 93 additions and 1 deletions

View File

@ -1417,7 +1417,20 @@ function runGbrainImport(
// inside Next.js / Prisma / Rails projects with their own
// .env.local (codex review #7 — defense in depth on top of the
// parent gstack-gbrain-sync seeding the bun grandchild's env).
const child = spawnGbrainAsync(["import", stagingDir, "--no-embed", "--json"]);
// --include-gitignored is load-bearing, not a convenience. Pages are
// staged into ~/.gstack/.staging-ingest-<pid>-<ts>/, and ~/.gstack is a
// git repo whose .gitignore is `*`. `gbrain import` honours .gitignore,
// so without this flag it collects files=0 and imports NOTHING, while
// still reporting `written: N` from the staged count. Silent data loss
// on every run. A working run logs `import.collect_files done ... files=N`
// with N > 0 and takes minutes, not seconds.
const child = spawnGbrainAsync([
"import",
stagingDir,
"--no-embed",
"--include-gitignored",
"--json",
]);
_activeImportChild = child;
let stdout = "";
let stderr = "";

View File

@ -0,0 +1,79 @@
/**
* Regression pin: `gstack-memory-ingest` must pass `--include-gitignored` to
* `gbrain import`.
*
* gstack-artifacts-init writes an ignore-everything `.gitignore` (a bare `*`,
* headed "Do not edit") at the root of `~/.gstack`. The memory ingest stages
* pages into `~/.gstack/.staging-ingest-<pid>-<ts>/`, which is INSIDE that
* repo, and gbrain's markdown collector honours .gitignore. So the collector
* walks the staging dir, matches every file against `*`, and collects zero.
*
* The failure is silent: `gbrain import` exits 0 having imported nothing,
* while the ingest still prints `written: N` from the STAGED count rather
* than the imported count. A run that indexes nothing is indistinguishable
* from a healthy one, and the memory corpus quietly stops growing.
*
* Two tests here:
* 1. Source pin (same shape as memory-ingest-no-put_page.test.ts): the flag
* is present in active code, so removing it trips the build.
* 2. Behavioural proof of the underlying collision, using git's own ignore
* machinery. No gbrain and no network required.
*/
import { describe, it, expect } from "bun:test";
import { execFileSync } from "child_process";
import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from "fs";
import { tmpdir } from "os";
import { join } from "path";
import { readFileSync } from "fs";
const SOURCE_PATH = join(import.meta.dir, "..", "bin", "gstack-memory-ingest.ts");
/** Strip comments so the pin only inspects executable code. */
function stripComments(src: string): string {
const noBlock = src.replace(/\/\*[\s\S]*?\*\//g, "");
return noBlock.replace(/\/\/[^\n]*/g, "");
}
describe("gstack-memory-ingest: gbrain import must not be filtered by .gitignore", () => {
it("passes --include-gitignored in active code", () => {
const stripped = stripComments(readFileSync(SOURCE_PATH, "utf-8"));
expect(stripped).toContain("--include-gitignored");
});
it("keeps the flag on the same import invocation as the staging dir", () => {
const stripped = stripComments(readFileSync(SOURCE_PATH, "utf-8"));
// Match the spawn call's argument array and assert both the subcommand
// and the flag live in it, so the flag can't drift onto another call.
const call = stripped.match(/spawnGbrainAsync\(\s*\[[^\]]*"import"[^\]]*\]/s);
expect(call).not.toBeNull();
expect(call![0]).toContain("--include-gitignored");
});
it("demonstrates the collision: an ignore-everything root hides staged pages", () => {
const dir = mkdtempSync(join(tmpdir(), "gstack-ingest-gitignore-"));
try {
const git = (...args: string[]) =>
execFileSync("git", args, { cwd: dir, encoding: "utf-8" });
git("init", "-q", ".");
const staging = join(dir, ".staging-ingest-12345-1700000000000", "learnings");
mkdirSync(staging, { recursive: true });
writeFileSync(join(staging, "page.md"), "# a staged page\n", "utf-8");
// Exactly what gstack-artifacts-init writes at the root of ~/.gstack.
writeFileSync(join(dir, ".gitignore"), "*\n", "utf-8");
// `git ls-files --others --exclude-standard` is the same view a
// gitignore-honouring collector takes: untracked and not ignored.
const collectable = git("ls-files", "--others", "--exclude-standard")
.split("\n")
.filter(Boolean);
// The staged page is invisible. This is the silent data loss.
expect(collectable).toHaveLength(0);
} finally {
rmSync(dir, { recursive: true, force: true });
}
});
});