Merge PR #1330: gbrain-valid source ids

bin/gstack-gbrain-sync.ts

@@ -33,6 +33,7 @@ import { existsSync, statSync, mkdirSync, writeFileSync, readFileSync, unlinkSyn
 import { join, dirname } from "path";
 import { execSync, execFileSync, spawnSync } from "child_process";
 import { homedir } from "os";
+import { createHash } from "crypto";
 
 import { detectEngineTier, withErrorContext, canonicalizeRemote } from "../lib/gstack-memory-helpers";
 import { sourcePageCount } from "../lib/gbrain-sources";
@@ -158,20 +159,43 @@ function originUrl(): string | null {
 }
 
 /**
- * Derive a stable source id for the cwd code corpus. Pattern: `gstack-code-<slug>`,
- * where <slug> comes from canonicalizeRemote() then `/` → `-` (e.g.,
- * `github.com/garrytan/gstack` → `gstack-code-github-com-garrytan-gstack`).
+ * Derive a stable source id for the cwd code corpus. Pattern: `gstack-code-<slug>`.
  *
- * Falls back to `gstack-code-<basename(repo)>` when there is no origin (local repo).
+ * gbrain enforces source ids to be 1-32 lowercase alnum chars with optional interior
+ * hyphens. We use the last two segments of the canonical remote (org/repo) and skip
+ * the host — `github.com` etc. is the same for nearly every user and just eats budget.
+ * If the resulting id still exceeds 32 chars, we keep the tail (most distinctive end)
+ * and append a 6-char hash of the full slug for collision resistance.
+ *
+ * Falls back to the repo basename when there is no origin (local repo).
  */
 function deriveCodeSourceId(repoPath: string): string {
   const remote = canonicalizeRemote(originUrl());
   if (remote) {
-    return `gstack-code-${remote.replace(/[\/\s]+/g, "-").replace(/-+/g, "-")}`;
+    const segs = remote.split("/").filter(Boolean);
+    const slugSource = segs.slice(-2).join("-");
+    return constrainSourceId("gstack-code", slugSource);
   }
-  // Fallback for repos without a remote.
   const base = repoPath.split("/").pop() || "repo";
-  return `gstack-code-${base.toLowerCase().replace(/[^a-z0-9-]+/g, "-").replace(/-+/g, "-")}`;
+  return constrainSourceId("gstack-code", base);
+}
+
+/**
+ * Build a gbrain-valid source id (1-32 lowercase alnum + interior hyphens). Sanitizes
+ * `raw`, prefixes with `prefix`, and falls back to a hashed-tail form when total length
+ * would exceed 32 chars.
+ */
+function constrainSourceId(prefix: string, raw: string): string {
+  const MAX = 32;
+  const slug = raw.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-+|-+$/g, "");
+  const full = `${prefix}-${slug}`;
+  if (full.length <= MAX) return full;
+  const hash = createHash("sha1").update(slug).digest("hex").slice(0, 6);
+  // Total budget: prefix + "-" + tail + "-" + hash
+  const tailBudget = MAX - prefix.length - 2 - hash.length;
+  if (tailBudget < 1) return `${prefix}-${hash}`;
+  const tail = slug.slice(-tailBudget).replace(/^-+|-+$/g, "");
+  return tail ? `${prefix}-${tail}-${hash}` : `${prefix}-${hash}`;
 }
 
 function gbrainAvailable(): boolean {

test/gstack-gbrain-sync.test.ts

@@ -108,6 +108,47 @@ describe("gstack-gbrain-sync CLI", () => {
     rmSync(home, { recursive: true, force: true });
   });
 
+  it("derived source ids are gbrain-valid (≤32 chars, alnum + interior hyphens, no dots) for any remote", () => {
+    // gbrain enforces source ids to be 1-32 lowercase alnum chars with optional interior
+    // hyphens. Pre-fix, the slug came from canonicalizeRemote() with only `/` and
+    // whitespace stripped — leaving dots from hostnames (`github.com`) and no length cap.
+    // For `github.com/<org>/<repo>`, the id was `gstack-code-github.com-<org>-<repo>`,
+    // which fails validation on both counts. This test exercises the derivation against
+    // controlled remotes by spawning the CLI in a temp git repo.
+    const cases = [
+      "https://github.com/radubach/platform.git",      // dot in hostname, total > 32 with old slug
+      "git@github.com:garrytan/gstack.git",            // SCP-style remote
+      "https://gitlab.example.com/team/proj.git",      // multi-dot host, non-github
+      "https://github.com/some-very-long-org-name/some-very-long-repo-name.git", // forces hash-truncate
+    ];
+    const VALID_ID = /^[a-z0-9](?:[a-z0-9-]{0,30}[a-z0-9])?$/;
+    for (const remote of cases) {
+      const home = makeTestHome();
+      const gstackHome = join(home, ".gstack");
+      mkdirSync(gstackHome, { recursive: true });
+      const repo = mkdtempSync(join(tmpdir(), "gstack-source-id-repo-"));
+      spawnSync("git", ["init", "--quiet", "-b", "main"], { cwd: repo });
+      spawnSync("git", ["remote", "add", "origin", remote], { cwd: repo });
+
+      const r = spawnSync("bun", [SCRIPT, "--dry-run", "--code-only", "--quiet"], {
+        encoding: "utf-8",
+        timeout: 60000,
+        cwd: repo,
+        env: { ...process.env, HOME: home, GSTACK_HOME: gstackHome },
+      });
+      expect(r.status).toBe(0);
+      const m = (r.stdout || "").match(/gbrain sources add (\S+)/);
+      expect(m).not.toBeNull();
+      const id = m![1];
+      expect(id.length).toBeLessThanOrEqual(32);
+      expect(id).toMatch(VALID_ID);
+      expect(id.startsWith("gstack-code-")).toBe(true);
+
+      rmSync(repo, { recursive: true, force: true });
+      rmSync(home, { recursive: true, force: true });
+    }
+  });
+
   it("dry-run does NOT acquire the lock file (lock is for write paths only)", () => {
     const home = makeTestHome();
     const gstackHome = join(home, ".gstack");