Repository navigation
Commit 9a05d84
Teach the production config guard about the second callback
The deploy failed at `production:config:check` with "live config vars
drifted", and it was right to. The guard holds an exact expected `vars` map
for both production configs, and the Google callback was added to the
wrangler files without being added here. Nothing in `npm run build` runs
this check, so it stayed invisible until the deploy.
The URL is expected relative to `expected.origin` rather than written out,
because the only thing that can plausibly be wrong about it is the live and
dark-launch origins getting crossed — and a literal string would compare
equal in exactly that case. It is also added to the mode-difference
normalizer for the same reason the GitHub one is there: the two production
configs are required to be identical apart from the surface that genuinely
differs by mode, and an origin-derived callback is part of that surface.
Both lines are temporary in the same way the GitHub path is: when the
existing accounts have finished attaching Google, the GitHub entries come
out of the wrangler files and out of this guard together.
Local proof: `node scripts/orbit-frontend-production-verify.mjs` exits 0 —
the same job that failed in run 31389895331 — with 80 config assertions
passing.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>1 parent 0878c21 commit 9a05d84
1 file changed
Lines changed: 7 additions & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
205 | 205 | | |
206 | 206 | | |
207 | 207 | | |
| 208 | + | |
| 209 | + | |
| 210 | + | |
| 211 | + | |
| 212 | + | |
208 | 213 | | |
| 214 | + | |
209 | 215 | | |
210 | 216 | | |
211 | 217 | | |
| |||
227 | 233 | | |
228 | 234 | | |
229 | 235 | | |
| 236 | + | |
230 | 237 | | |
231 | 238 | | |
232 | 239 | | |
| |||
0 commit comments