feat(agents): skip cooldowned providers during failover

When all auth profiles for a provider are in cooldown, the failover
mechanism now skips that provider immediately rather than attempting
and waiting for the cooldown error. This prevents long delays when
multiple OAuth providers fail in sequence.

src/agents/model-fallback.ts

@@ -14,6 +14,9 @@ import {
   resolveModelRefFromString,
 } from "./model-selection.js";
 import type { FailoverReason } from "./pi-embedded-helpers.js";
+import { loadAuthProfileStore, isProfileInCooldown } from "./auth-profiles/usage.js";
+import { resolveAuthProfileOrder } from "./auth-profiles/order.js";
+import { getAgentAuthStoreDir } from "./agent-dirs.js";
 
 type ModelCandidate = {
   provider: string;
@@ -211,11 +214,34 @@ export async function runWithModelFallback<T>(params: {
     model: params.model,
     fallbacksOverride: params.fallbacksOverride,
   });
+
+  const authStore = params.cfg
+    ? loadAuthProfileStore(getAgentAuthStoreDir(params.cfg, "main"))
+    : null;
+
   const attempts: FallbackAttempt[] = [];
   let lastError: unknown;
 
   for (let i = 0; i < candidates.length; i += 1) {
     const candidate = candidates[i] as ModelCandidate;
+
+    // Skip candidates that are in cooldown
+    if (authStore) {
+      const profileIds = resolveAuthProfileOrder(authStore, candidate.provider);
+      const isAnyProfileAvailable = profileIds.some((id) => !isProfileInCooldown(authStore, id));
+
+      if (profileIds.length > 0 && !isAnyProfileAvailable) {
+        // All profiles for this provider are in cooldown; skip without attempting
+        attempts.push({
+          provider: candidate.provider,
+          model: candidate.model,
+          error: `Provider ${candidate.provider} is in cooldown (all profiles unavailable)`,
+          reason: "auth", // Best effort classification
+        });
+        continue;
+      }
+    }
+
     try {
       const result = await params.run(candidate.provider, candidate.model);
       return {