fix(ai): disable hidden provider 429 retries (#4991)

This commit is contained in:
Armin Ronacher
2026-05-26 23:41:58 +02:00
committed by GitHub
parent 96f0edd02b
commit 8fb1e877cd
10 changed files with 161 additions and 31 deletions

View File

@@ -101,11 +101,13 @@ Set `PI_SKIP_VERSION_CHECK=1` to disable the Pi version update check. Use `--off
| `retry.maxRetries` | number | `3` | Maximum agent-level retry attempts |
| `retry.baseDelayMs` | number | `2000` | Base delay for agent-level exponential backoff (2s, 4s, 8s) |
| `retry.provider.timeoutMs` | number | SDK default | Provider/SDK request timeout in milliseconds |
| `retry.provider.maxRetries` | number | SDK default | Provider/SDK retry attempts |
| `retry.provider.maxRetries` | number | `0` | Provider/SDK retry attempts |
| `retry.provider.maxRetryDelayMs` | number | `60000` | Max server-requested delay before failing (60s) |
When a provider requests a retry delay longer than `retry.provider.maxRetryDelayMs` (e.g., Google's "quota will reset after 5h"), the request fails immediately with an informative error instead of waiting silently. Set to `0` to disable the cap.
Keep `retry.provider.maxRetries` at `0` unless provider-level retries are explicitly needed. Setting it above `0` can make SDK/provider retries handle out-of-usage-limit errors before Pi sees them, which may block the agent until the provider quota resets in some circumstances.
```json
{
"retry": {