fix(agents): honor explicit rate-limit cooldown probes in fallback runs

src/agents/pi-embedded-runner/run.ts

@@ -633,15 +633,39 @@ export async function runEmbeddedPiAgent(
       };
 
       try {
+        const autoProfileCandidates = profileCandidates.filter(
+          (candidate): candidate is string =>
+            typeof candidate === "string" && candidate.length > 0 && candidate !== lockedProfileId,
+        );
+        const allAutoProfilesInCooldown =
+          autoProfileCandidates.length > 0 &&
+          autoProfileCandidates.every((candidate) => isProfileInCooldown(authStore, candidate));
+        const unavailableReason = allAutoProfilesInCooldown
+          ? (resolveProfilesUnavailableReason({
+              store: authStore,
+              profileIds: autoProfileCandidates,
+            }) ?? "rate_limit")
+          : null;
+        const allowRateLimitCooldownProbe =
+          params.allowRateLimitCooldownProbe === true &&
+          allAutoProfilesInCooldown &&
+          unavailableReason === "rate_limit";
+        let didRateLimitCooldownProbe = false;
+
         while (profileIndex < profileCandidates.length) {
           const candidate = profileCandidates[profileIndex];
-          if (
-            candidate &&
-            candidate !== lockedProfileId &&
-            isProfileInCooldown(authStore, candidate)
-          ) {
-            profileIndex += 1;
-            continue;
+          const inCooldown =
+            candidate && candidate !== lockedProfileId && isProfileInCooldown(authStore, candidate);
+          if (inCooldown) {
+            if (allowRateLimitCooldownProbe && !didRateLimitCooldownProbe) {
+              didRateLimitCooldownProbe = true;
+              log.warn(
+                `probing cooldowned auth profile for ${provider}/${modelId} due to rate_limit unavailability`,
+              );
+            } else {
+              profileIndex += 1;
+              continue;
+            }
           }
           await applyApiKeyInfo(profileCandidates[profileIndex]);
           break;

src/agents/pi-embedded-runner/run/params.ts

@@ -113,4 +113,12 @@ export type RunEmbeddedPiAgentParams = {
   streamParams?: AgentStreamParams;
   ownerNumbers?: string[];
   enforceFinalTag?: boolean;
+  /**
+   * Allow a single run attempt even when all auth profiles are in cooldown,
+   * but only for inferred `rate_limit` cooldowns.
+   *
+   * This is used by model fallback when trying sibling models on providers
+   * where rate limits are often model-scoped.
+   */
+  allowRateLimitCooldownProbe?: boolean;
 };