admin/gbrain
1
0
Fork 0
mirror of https://github.com/garrytan/gbrain.git synced 2026-07-27 22:15:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(tutorial): drop dead --remote flag from company-brain search examples

Browse Source 
With unknown op flags now a hard error (this PR), the tutorial's
`gbrain search ... --remote` invocations would fail: no code path ever
read a --remote flag — thin-client installs route shared ops through the
remote MCP server automatically. Update the three examples to the
flagless form and explain the automatic routing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-07-22 11:10:47 -07:00
co-authored by Claude Fable 5
parent 04a2a1f7bf
commit 55290e9088
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/tutorials/company-brain.md
+5 -3
View File
@@ -223,14 +223,16 @@ export GBRAIN_REMOTE_CLIENT_ID=<Alice's client_id>
export GBRAIN_REMOTE_CLIENT_SECRET=<Alice's client_secret>
export GBRAIN_REMOTE_MCP_URL=https://brain.acme-co.com/mcp
gbrain search "performance review" --remote
gbrain search "performance review"
```
(On a thin-client install every shared op routes through the remote MCP server automatically — no flag needed. The env vars select whose credentials the call uses.)
Alice should see results only from `customers` and `shared`. The performance-review notes live in `internal`, which she's not scoped to read. She shouldn't see them.
```bash
# Terminal 2, as Bob (export his credentials similarly)
gbrain search "performance review" --remote
gbrain search "performance review"
```
Bob should see the performance-review notes from `internal`, plus anything related from `shared`. He shouldn't see anything that lives only in `customers`.
@@ -514,7 +516,7 @@ The first sync embeds every page, which takes time. Check `gbrain sources status
### "I see a page I shouldn't see"
This shouldn't happen, but if you suspect it, run `gbrain search <query> --remote --json` as the constrained client and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
This shouldn't happen, but if you suspect it, run `gbrain search <query> --json` as the constrained client (thin-client install, with the client's `GBRAIN_REMOTE_*` env exported) and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
### "The synthesized answer is wrong"