fix: recognize Venice 402 billing errors for model fallback (#43205)

Merged via squash.

Prepared head SHA: 1f6b10b9d934235e71f279f888292139c4a85aa6
Co-authored-by: Squabble9 <194720422+Squabble9@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf

CHANGELOG.md

@@ -108,6 +108,7 @@ Docs: https://docs.openclaw.ai
 - Agents/cooldowns: default cooldown windows with no recorded failure history to `unknown` instead of `rate_limit`, avoiding false API rate-limit warnings while preserving cooldown recovery probes. (#42911) Thanks @VibhorGautam.
 - Discord/config typing: expose channel-level `autoThread` on the canonical guild-channel config type so strict config loading matches the existing Discord schema and runtime behavior. (#35608) Thanks @ingyukoh.
 - Agents/error rendering: ignore stale assistant `errorMessage` fields on successful turns so background/tool-side failures no longer prepend synthetic billing errors over valid replies. (#40616) Thanks @ingyukoh.
+- Agents/fallback: recognize Venice `402 Insufficient USD or Diem balance` billing errors so configured model fallbacks trigger instead of surfacing the raw provider error. (#43205) Thanks @Squabble9.
 
 ## 2026.3.8
 

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

@@ -106,6 +106,9 @@ describe("isBillingErrorMessage", () => {
       "Payment Required",
       "HTTP 402 Payment Required",
       "plans & billing",
+      // Venice returns "Insufficient USD or Diem balance" which has extra words
+      // between "insufficient" and "balance"
+      "Insufficient USD or Diem balance to complete request. Visit https://venice.ai/settings/api to add credits.",
     ];
     for (const sample of samples) {
       expect(isBillingErrorMessage(sample)).toBe(true);
@@ -149,6 +152,11 @@ describe("isBillingErrorMessage", () => {
     expect(longResponse.length).toBeGreaterThan(512);
     expect(isBillingErrorMessage(longResponse)).toBe(false);
   });
+  it("does not false-positive on short non-billing text that mentions insufficient and balance", () => {
+    const sample = "The evidence is insufficient to reconcile the final balance after compaction.";
+    expect(isBillingErrorMessage(sample)).toBe(false);
+    expect(classifyFailoverReason(sample)).toBeNull();
+  });
   it("still matches explicit 402 markers in long payloads", () => {
     const longStructuredError =
       '{"error":{"code":402,"message":"payment required","details":"' + "x".repeat(700) + '"}}';
@@ -650,6 +658,12 @@ describe("classifyFailoverReason", () => {
     expect(classifyFailoverReason(TOGETHER_ENGINE_OVERLOADED_MESSAGE)).toBe("overloaded");
     expect(classifyFailoverReason(GROQ_TOO_MANY_REQUESTS_MESSAGE)).toBe("rate_limit");
     expect(classifyFailoverReason(GROQ_SERVICE_UNAVAILABLE_MESSAGE)).toBe("overloaded");
+    // Venice 402 billing error with extra words between "insufficient" and "balance"
+    expect(
+      classifyFailoverReason(
+        "Insufficient USD or Diem balance to complete request. Visit https://venice.ai/settings/api to add credits.",
+      ),
+    ).toBe("billing");
   });
 
   it("classifies internal and compatibility error messages", () => {

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

@@ -52,6 +52,7 @@ const ERROR_PATTERNS = {
     "credit balance",
     "plans & billing",
     "insufficient balance",
+    "insufficient usd or diem balance",
   ],
   authPermanent: [
     /api[_ ]?key[_ ]?(?:revoked|invalid|deactivated|deleted)/i,