fix(reply): classify billing cooldown summaries (#66363)

Merged via squash.

Prepared head SHA: 8cfc42a7ac
Co-authored-by: Rohan5commit <181558744+Rohan5commit@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf

CHANGELOG.md

@@ -28,6 +28,7 @@ Docs: https://docs.openclaw.ai
 - Feishu/webhook: harden the webhook transport and card-action replay guards to fail closed on missing `encryptKey` and blank callback tokens — refuse to start the webhook transport without an `encryptKey`, reject unsigned requests when no key is present instead of accepting them, and drop blank card-action tokens before the dedupe claim and dispatcher. Defense-in-depth over the already-closed monitor-account layer. (#66707) Thanks @eleqtrizit.
 - Agents/workspace files: route `agents.files.get`, `agents.files.set`, and workspace listing through the shared `fs-safe` helpers (`openFileWithinRoot`/`readFileWithinRoot`/`writeFileWithinRoot`), reject symlink aliases for allowlisted agent files, and have `fs-safe` resolve opened-file real paths from the file descriptor before falling back to path-based `realpath` so a symlink swap between `open` and `realpath` can no longer redirect the validated path off the intended inode. (#66636) Thanks @eleqtrizit.
 - Gateway/MCP loopback: switch the `/mcp` bearer comparison from plain `!==` to constant-time `safeEqualSecret` (matching the convention every other auth surface in the codebase uses), and reject non-loopback browser-origin requests via `checkBrowserOrigin` before the auth gate runs. Loopback origins (`127.0.0.1:*`, `localhost:*`, same-origin) still go through, including the `localhost`↔`127.0.0.1` host mismatch that browsers flag as `Sec-Fetch-Site: cross-site`. (#66665) Thanks @eleqtrizit.
+- Auto-reply/billing: classify pure billing cooldown fallback summaries from structured fallback reasons so users see billing guidance instead of the generic failure reply. (#66363) Thanks @Rohan5commit.
 
 ## 2026.4.14
 

src/auto-reply/reply/agent-runner-execution.test.ts

@@ -912,6 +912,64 @@ describe("runAgentTurnWithFallback", () => {
     }
   });
 
+  it("surfaces billing guidance for pure billing cooldown fallback exhaustion", async () => {
+    state.runWithModelFallbackMock.mockRejectedValueOnce(
+      Object.assign(
+        new Error(
+          "All models failed (2): anthropic/claude-opus-4-6: Provider anthropic has billing issue (skipping all models) (billing) | anthropic/claude-sonnet-4-6: Provider anthropic has billing issue (skipping all models) (billing)",
+        ),
+        {
+          name: "FallbackSummaryError",
+          attempts: [
+            {
+              provider: "anthropic",
+              model: "claude-opus-4-6",
+              error: "Provider anthropic has billing issue (skipping all models)",
+              reason: "billing",
+            },
+            {
+              provider: "anthropic",
+              model: "claude-sonnet-4-6",
+              error: "Provider anthropic has billing issue (skipping all models)",
+              reason: "billing",
+            },
+          ],
+          soonestCooldownExpiry: Date.now() + 60_000,
+        },
+      ),
+    );
+
+    const runAgentTurnWithFallback = await getRunAgentTurnWithFallback();
+    const result = await runAgentTurnWithFallback({
+      commandBody: "hello",
+      followupRun: createFollowupRun(),
+      sessionCtx: {
+        Provider: "whatsapp",
+        MessageSid: "msg",
+      } as unknown as TemplateContext,
+      opts: {},
+      typingSignals: createMockTypingSignaler(),
+      blockReplyPipeline: null,
+      blockStreamingEnabled: false,
+      resolvedBlockStreamingBreak: "message_end",
+      applyReplyToMode: (payload) => payload,
+      shouldEmitToolResult: () => true,
+      shouldEmitToolOutput: () => false,
+      pendingToolTasks: new Set(),
+      resetSessionAfterCompactionFailure: async () => false,
+      resetSessionAfterRoleOrderingConflict: async () => false,
+      isHeartbeat: false,
+      sessionKey: "main",
+      getActiveSessionEntry: () => undefined,
+      resolvedVerboseLevel: "off",
+    });
+
+    expect(result.kind).toBe("final");
+    if (result.kind === "final") {
+      expect(result.payload.text).toBe("billing");
+    }
+  });
+
   it("surfaces gateway restart text when fallback exhaustion wraps a drain error", async () => {
     const { replyOperation, failMock } = createMockReplyOperation();
     state.runWithModelFallbackMock.mockRejectedValueOnce(

src/auto-reply/reply/agent-runner-execution.ts

@@ -311,6 +311,14 @@ function isPureTransientRateLimitSummary(err: unknown): boolean {
   );
 }
 
+function isPureBillingSummary(err: unknown): boolean {
+  return (
+    isFallbackSummaryError(err) &&
+    err.attempts.length > 0 &&
+    err.attempts.every((attempt) => attempt.reason === "billing")
+  );
+}
+
 function isToolResultTurnMismatchError(message: string): boolean {
   const lower = normalizeLowercaseStringOrEmpty(message);
   return (
@@ -1320,7 +1328,9 @@ export async function runAgentTurnWithFallback(params: {
         continue;
       }
       const message = formatErrorMessage(err);
-      const isBilling = isBillingErrorMessage(message);
+      const isBilling = isFallbackSummaryError(err)
+        ? isPureBillingSummary(err)
+        : isBillingErrorMessage(message);
       const isContextOverflow = !isBilling && isLikelyContextOverflowError(message);
       const isCompactionFailure = !isBilling && isCompactionFailureError(message);
       const isSessionCorruption = /function call turn comes immediately after/i.test(message);