fix(agents): handle overloaded failover separately (#38301)

* fix(agents): skip auth-profile failure on overload

* fix(agents): note overload auth-profile fallback fix

* fix(agents): classify overloaded failures separately

* fix(agents): back off before overload failover

* fix(agents): tighten overload probe and backoff state

* fix(agents): persist overloaded cooldown across runs

* fix(agents): tighten overloaded status handling

* test(agents): add overload regression coverage

* fix(agents): restore runner imports after rebase

* test(agents): add overload fallback integration coverage

* fix(agents): harden overloaded failover abort handling

* test(agents): tighten overload classifier coverage

* test(agents): cover all-overloaded fallback exhaustion

* fix(cron): retry overloaded fallback summaries

* fix(cron): treat HTTP 529 as overloaded retry

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

@@ -311,7 +311,7 @@ export async function runAgentTurnWithFallback(params: {
             model,
             runId,
             authProfile,
-            allowRateLimitCooldownProbe: runOptions?.allowRateLimitCooldownProbe,
+            allowTransientCooldownProbe: runOptions?.allowTransientCooldownProbe,
           });
           return (async () => {
             const result = await runEmbeddedPiAgent({

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

@@ -487,7 +487,7 @@ export async function runMemoryFlushIfNeeded(params: {
           model,
           runId: flushRunId,
           authProfile,
-          allowRateLimitCooldownProbe: runOptions?.allowRateLimitCooldownProbe,
+          allowTransientCooldownProbe: runOptions?.allowTransientCooldownProbe,
         });
         const result = await runEmbeddedPiAgent({
           ...embeddedContext,

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

@@ -166,7 +166,7 @@ export function buildEmbeddedRunBaseParams(params: {
   model: string;
   runId: string;
   authProfile: ReturnType<typeof resolveProviderScopedAuthProfile>;
-  allowRateLimitCooldownProbe?: boolean;
+  allowTransientCooldownProbe?: boolean;
 }) {
   return {
     sessionFile: params.run.sessionFile,
@@ -187,7 +187,7 @@ export function buildEmbeddedRunBaseParams(params: {
     bashElevated: params.run.bashElevated,
     timeoutMs: params.run.timeoutMs,
     runId: params.runId,
-    allowRateLimitCooldownProbe: params.allowRateLimitCooldownProbe,
+    allowTransientCooldownProbe: params.allowTransientCooldownProbe,
   };
 }
 

src/auto-reply/reply/agent-runner.runreplyagent.e2e.test.ts

@@ -1054,6 +1054,11 @@ describe("runReplyAgent typing (heartbeat)", () => {
         reportedReason: "rate_limit",
         expectedReason: "rate limit",
       },
+      {
+        existingReason: undefined,
+        reportedReason: "overloaded",
+        expectedReason: "overloaded",
+      },
       {
         existingReason: "rate limit",
         reportedReason: "timeout",

src/auto-reply/reply/followup-runner.ts

@@ -208,7 +208,7 @@ export function createFollowupRunner(params: {
               bashElevated: queued.run.bashElevated,
               timeoutMs: queued.run.timeoutMs,
               runId,
-              allowRateLimitCooldownProbe: runOptions?.allowRateLimitCooldownProbe,
+              allowTransientCooldownProbe: runOptions?.allowTransientCooldownProbe,
               blockReplyBreak: queued.run.blockReplyBreak,
               bootstrapPromptWarningSignaturesSeen,
               bootstrapPromptWarningSignature: