refactor(memory-ingest): reunite preparePages with its docblock; pin disambiguateSlugs wiring

The #2724 disambiguateSlugs block was inserted between preparePages'
docblock and the function, orphaning the secret-scanning policy doc onto
the wrong symbol. Reordered. A call-site pin now asserts the prepare→stage
flow actually invokes disambiguateSlugs, so a refactor can't drop the call
while every unit test stays green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-09-01 16:08:05 +00:00
co-authored by Claude Fable 5
parent 8079803f2a
commit 781cc13779
2 changed files with 59 additions and 22 deletions
+22 -22
View File
@@ -1303,28 +1303,6 @@ async function probeMode(args: CliArgs): Promise<ProbeReport> {
};
}
/**
* Prepare phase: walk sources, apply incremental + optional-secret-scan filters,
* parse transcripts/artifacts into PageRecord, render bodies with
* frontmatter. Returns the PreparedPage[] to stage + counts of files
* filtered at each gate.
*
* Secret scanning policy (post 2026-05-10 perf review):
*
* The actual cross-machine exfiltration boundary is `gstack-brain-sync`,
* which runs a regex-based secret scanner on the staged diff before
* `git commit` (see bin/gstack-brain-sync:78-110: AWS keys, GitHub
* tokens, OpenAI keys, PEM blocks, JWTs, bearer-token-in-JSON). That's
* the right place — it gates content leaving the machine.
*
* memory-ingest, by contrast, moves data from one local file to a
* local PGLite database. Scanning every source file at ingest time
* doesn't change exposure (the secret already lives in plaintext
* where the user keeps their transcripts and artifacts) but costs
* ~470s on cold runs. We removed the per-file gitleaks gate as
* redundant defense-in-depth and made it opt-in via `--scan-secrets`
* for users who want belt-and-suspenders.
*/
/**
* Disambiguate colliding page slugs before staging (#2724).
*
@@ -1362,6 +1340,28 @@ export function disambiguateSlugs(pages: PreparedPage[]): void {
}
}
/**
* Prepare phase: walk sources, apply incremental + optional-secret-scan filters,
* parse transcripts/artifacts into PageRecord, render bodies with
* frontmatter. Returns the PreparedPage[] to stage + counts of files
* filtered at each gate.
*
* Secret scanning policy (post 2026-05-10 perf review):
*
* The actual cross-machine exfiltration boundary is `gstack-brain-sync`,
* which runs a regex-based secret scanner on the staged diff before
* `git commit` (see bin/gstack-brain-sync:78-110: AWS keys, GitHub
* tokens, OpenAI keys, PEM blocks, JWTs, bearer-token-in-JSON). That's
* the right place — it gates content leaving the machine.
*
* memory-ingest, by contrast, moves data from one local file to a
* local PGLite database. Scanning every source file at ingest time
* doesn't change exposure (the secret already lives in plaintext
* where the user keeps their transcripts and artifacts) but costs
* ~470s on cold runs. We removed the per-file gitleaks gate as
* redundant defense-in-depth and made it opt-in via `--scan-secrets`
* for users who want belt-and-suspenders.
*/
function preparePages(
args: CliArgs,
ctx: WalkContext,
@@ -9,6 +9,8 @@
* ("accounted for N-1 of N staged ... Refusing to advance state").
*/
import { describe, it, expect } from "bun:test";
import { readFileSync } from "fs";
import { join } from "path";
import { disambiguateSlugs } from "../bin/gstack-memory-ingest";
const mk = (slug: string, source_path: string) => ({
@@ -62,4 +64,39 @@ describe("regression: disambiguateSlugs resolves colliding staged slugs", () =>
disambiguateSlugs(pages);
expect(pages.map((p) => p.slug)).toEqual(before);
});
it("call-site wiring: the prepare/stage flow actually invokes disambiguateSlugs (source pin)", () => {
// The unit tests above prove the function works; nothing else proves the
// flow CALLS it — a refactor could drop the invocation and every test
// would stay green while #2724 regresses. Anchor narrowly: extract the
// preparePages function body (and, as an accepted alternate home, the
// main-flow stretch between the preparePages call and writeStaged) and
// require a disambiguateSlugs( invocation inside — cosmetic changes
// (argument rename, comment edits) don't trip this; moving the call out
// of the prepare→stage flow entirely does.
const src = readFileSync(
join(import.meta.dir, "..", "bin", "gstack-memory-ingest.ts"),
"utf-8",
);
// preparePages body: from its declaration to the next top-level function.
const defStart = src.indexOf("function preparePages(");
expect(defStart).toBeGreaterThan(-1);
const afterDef = src.slice(defStart + "function preparePages(".length);
const endRel = afterDef.search(/\n(?:export )?(?:async )?function /);
const prepareBody = endRel === -1 ? afterDef : afterDef.slice(0, endRel);
// Alternate home: the stage flow between the preparePages call site and
// the writeStaged call that consumes its output.
const callSite = src.indexOf("= preparePages(");
const stageSite = callSite === -1 ? -1 : src.indexOf("writeStaged(", callSite);
const stageFlow =
callSite !== -1 && stageSite !== -1 ? src.slice(callSite, stageSite) : "";
const invokes = (text: string) =>
// An invocation, not the `function disambiguateSlugs(` definition.
/(?<!function )\bdisambiguateSlugs\(/.test(text);
expect(invokes(prepareBody) || invokes(stageFlow)).toBe(true);
});
});