fix(failover): allow model fallback on harness transport timeout

lsr911 · lsr911 · commit c8e70fc81250 · 2026-06-21T22:57:11.000+08:00
When a harness-owned transport provider (Ollama, etc.) times out, resolveRunFailoverDecision immediately surfaced the error without attempting the configured fallback chain. This is inconsistent with the behavior for auth and billing failures, which both trigger fallback_model when fallbacks are configured. Fix: check fallbackConfigured before surfacing timeout errors from harness-owned transports, matching the existing flow for other failure modes. Closes #95574
diff --git a/src/agents/embedded-agent-runner/run/failover-policy.ts b/src/agents/embedded-agent-runner/run/failover-policy.ts
@@ -178,7 +178,16 @@ export function resolveRunFailoverDecision(params: RunFailoverDecisionParams): R
         reason: params.failoverReason,
       };
     }
+    // Timeouts from harness-owned transports (Ollama, etc.) should still
+    // attempt the configured fallback chain before surfacing the error,
+    // consistent with the behavior for auth and billing failures.
     if (params.harnessOwnsTransport && params.failoverReason === "timeout") {
+      if (params.fallbackConfigured) {
+        return {
+          action: "fallback_model",
+          reason: "timeout",
+        };
+      }
       return {
         action: "surface_error",
         reason: params.failoverReason,
