changelog: note the 90-day window for stuck staged pages (#3539)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

changelog.d/gsta209-loopback-gbrain-local.md

@@ -2,7 +2,7 @@
 
 ### Fixed
 - **One locality rule** (`lib/gbrain-mcp-locality.ts`). An http, url or sse entry is local when its URL is http(s) on `localhost`, `127.0.0.0/8` or `::1`, and this machine's gbrain config names an engine with no `remote_mcp` marker. A URL with userinfo or `${` is never local. Every other entry is classified as before.
-- **`gstack-memory-ingest`** imports through gbrain in that case. Pages an earlier run left `staged` / `remote-http` count as new and are imported on the next local run.
+- **`gstack-memory-ingest`** imports through gbrain in that case. Pages an earlier run left `staged` / `remote-http` count as new and are imported on the next local run. Pages older than the 90-day window need one `gstack-memory-ingest --bulk --all-history` run.
 - **`gstack-gbrain-detect`** reports `local-stdio` for it in all three tiers, and `gbrain-local-status` and the `gstack-skill-start` banner use the same rule. A remote `(SSE)` line in `claude mcp list` no longer reads as local. With several gbrain servers, the exact `gbrain:` entry wins, as in the other tiers.
 
 ### Docs