diff --git a/src/resources/extensions/sf/error-classifier.ts b/src/resources/extensions/sf/error-classifier.ts
index bfbadde35..ee0ddf3ab 100644
--- a/src/resources/extensions/sf/error-classifier.ts
+++ b/src/resources/extensions/sf/error-classifier.ts
@@ -51,7 +51,8 @@ const PERMANENT_RE =
 	/auth|unauthorized|forbidden|invalid.*key|invalid.*api|billing|quota exceeded|account/i;
 // Include provider-specific quota-window phrasing like "hit your limit", "usage limit", "quota reached"
 const RATE_LIMIT_RE =
-	/rate.?limit|too many requests|429|hit your limit|usage limit|quota (?:reached|hit)|limit.*resets?/i;
+	/rate.?limit|too many requests|429|hit your limit|usage limit|quota (?:reached|hit|will reset)|limit.*resets?|exhausted (?:your|the) (?:quota|capacity|usage)/i;
+const RESET_QUOTA_DELAY_RE = /reset(?:s)?(?:\s+(?:in|after))?\s+(\d+)s/i;
 // Unsupported-model: provider rejected the model for the current account/plan (#4513).
 // Checked before `permanent` because PERMANENT_RE also matches /account/i.
 const UNSUPPORTED_MODEL_MODEL_RE = /\b(?:model|deployment)\b/i;
@@ -118,7 +119,12 @@ export function classifyError(
 		if (retryAfterMs != null && retryAfterMs > 0) {
 			return { kind: "rate-limit", retryAfterMs };
 		}
-		const resetMatch = errorMsg.match(RESET_DELAY_RE);
+		// Try the existing "reset in Ns" first, then the broader
+		// "reset(s)? (in|after) Ns" form that catches "Your quota will reset
+		// after 51s" — common across providers (Anthropic capacity exhaustion,
+		// OpenAI usage caps, etc.).
+		const resetMatch =
+			errorMsg.match(RESET_DELAY_RE) ?? errorMsg.match(RESET_QUOTA_DELAY_RE);
 		const delayMs = resetMatch ? Number(resetMatch[1]) * 1000 : 60_000;
 		return { kind: "rate-limit", retryAfterMs: delayMs };
 	}