Files
sub2api/backend/internal/service
Erik 7f1f85cb76 fix(gemini): stop cooling Vertex 429s until PST midnight, honor RetryInfo
Vertex AI reports 429s with a standard google.rpc.RetryInfo detail
(retryDelay like "39s"), but ParseGeminiRateLimitResetTime only knew the
AI Studio quotaResetDelay metadata, so parsing always failed for Vertex
bodies. The fallback then lumped service_account accounts in with
API-key/AI-Studio ones and rate limited them until the next PST
midnight, so a transient per-minute throttle could take a pay-as-you-go
account (and with it the whole group) offline for up to a day.

- Parse google.rpc.RetryInfo retryDelay from 429 bodies, capped at 15
  minutes to guard against absurd upstream values.
- When no reset time can be parsed, cool service_account (Vertex)
  accounts down for 60s instead of until PST midnight: pay-as-you-go
  quotas are short-window RPM/TPM with no daily reset.

Fallback behavior for Code Assist, Google One and API-key accounts is
unchanged, covered by new regression tests.
2026-09-22 11:31:31 +08:00
..
2026-07-08 15:26:54 +08:00
2026-07-04 05:30:50 +08:00
2026-07-04 05:30:50 +08:00
2026-03-13 17:00:16 +08:00
2026-03-13 19:15:27 +08:00
2026-07-01 11:32:22 +08:00
2026-07-28 10:08:39 +08:00