Arm the shared cooldown for rate limits tunneled through HTTP 200

Azure is the only zero-data-retention route for the gpt-5.6 family, so its capacity 429s arrive frequently and OpenRouter forwards them inside an HTTP 200 envelope. Those bypassed the rate controller entirely: a paced run kept sending a request every three seconds into a throttled endpoint, failing row by row. An in-envelope 429 now records the same escalating cooldown as a transport 429, so later acquisitions fail fast until the deadline passes.
2026-09-13 11:43:49 +02:00
parent 1b09edc692
commit 4d8a187079
3 changed files with 69 additions and 23 deletions
@@ -365,6 +365,12 @@ func (c *Client) complete(ctx context.Context, gate *ratelimit.Controller, r com
 			Code int `json:"code"`
 		}
 		_ = json.Unmarshal(envelope.Error, &detail)
+		if detail.Code == http.StatusTooManyRequests {
+			// An upstream rate limit tunneled through HTTP 200 must arm the
+			// same cooldown as a transport 429: later Acquire calls fail fast
+			// instead of pacing more requests into a throttled endpoint.
+			return "", gate.ReportLimit()
+		}
 		if detail.Code != 0 {
 			return "", fmt.Errorf("AI provider reported an error (code %d)", detail.Code)
 		}