fix(agents): classify Anthropic extra-usage billing (#61608) (thanks @neeravmakwana)

CHANGELOG.md

@@ -74,6 +74,7 @@ Docs: https://docs.openclaw.ai
 - Telegram/reasoning: only create a Telegram reasoning preview lane when the session is explicitly `reasoning:stream`, so hidden `<think>` traces from streamed replies stop surfacing as chat previews on normal sessions. Thanks @vincentkoc.
 - Telegram/native command menu: trim long menu descriptions before dropping commands so sub-100 command sets can still fit Telegram's payload budget and keep more `/` entries visible. (#61129) Thanks @neeravmakwana.
 - Telegram/startup: bound `deleteWebhook`, `getMe`, and `setWebhook` startup requests while keeping the longer `getUpdates` poll timeout, so wedged Telegram control-plane calls stop hanging startup indefinitely. (#61601) Thanks @neeravmakwana.
+- Agents/failover: classify Anthropic "extra usage" exhaustion as billing so same-turn model fallback still triggers when Claude blocks long-context requests on usage limits. (#61608) Thanks @neeravmakwana.
 - Discord: keep REST, webhook, and monitor traffic on the configured proxy, preserve component-only media sends, honor `@everyone` and `@here` mention gates, keep ACK reactions on the active account, and split voice connect/playback timeouts so auto-join is more reliable. (#57465, #60361, #60345) Thanks @geekhuashan.
 - Discord/reply tags: strip leaked `[[reply_to_current]]` control tags from preview text and honor explicit reply-tag threading during final delivery, so Discord replies stay attached to the triggering message instead of printing reply metadata into chat.
 - Discord/replies: replace the unshipped `replyToOnlyWhenBatched` flag with `replyToMode: "batched"` so native reply references only attach on debounced multi-message turns while explicit reply tags still work.

src/agents/pi-embedded-helpers.isbillingerrormessage.test.ts

@@ -127,6 +127,8 @@ describe("isBillingErrorMessage", () => {
         "Insufficient USD or Diem balance to complete request. Visit https://venice.ai/settings/api to add credits.",
         "This model requires more credits to use",
         "This endpoint require more credits",
+        "You're out of extra usage. Add more at claude.ai/settings/usage and keep going.",
+        "Extra usage is required for long context requests.",
       ],
       expected: true,
     },
@@ -215,6 +217,20 @@ describe("isBillingErrorMessage", () => {
     expect(isBillingErrorMessage(sample)).toBe(true);
     expect(classifyFailoverReason(sample)).toBe("billing");
   });
+
+  it("classifies Anthropic extra-usage exhaustion variants as billing", () => {
+    const samples = [
+      "You're out of extra usage. Add more at claude.ai/settings/usage and keep going.",
+      "Extra usage is required for long context requests.",
+      '{"type":"error","error":{"type":"invalid_request_error","message":"You\'re out of extra usage. Add more at claude.ai/settings/usage and keep going."}}',
+      '{"type":"error","error":{"type":"invalid_request_error","message":"Extra usage is required for long context requests."}}',
+    ];
+
+    for (const sample of samples) {
+      expect(isBillingErrorMessage(sample)).toBe(true);
+      expect(classifyFailoverReason(sample, { provider: "anthropic" })).toBe("billing");
+    }
+  });
 });
 
 describe("isCloudCodeAssistFormatError", () => {

src/agents/pi-embedded-helpers/failover-matches.ts

@@ -120,6 +120,8 @@ const ERROR_PATTERNS = {
     "insufficient balance",
     "insufficient usd or diem balance",
     /requires?\s+more\s+credits/i,
+    /out of extra usage/i,
+    /extra usage is required(?: for long context requests)?/i,
   ],
   authPermanent: HIGH_CONFIDENCE_AUTH_PERMANENT_PATTERNS,
   auth: [...AMBIGUOUS_AUTH_ERROR_PATTERNS, ...COMMON_AUTH_ERROR_PATTERNS],