fix(agent): Enable model fallback for prompt-phase quota/rate limit errors

When a prompt submission fails with quota or rate limit errors, throw
FailoverError instead of the raw promptError. This enables the model
fallback system to try alternative models.

Previously, rate limit errors during the prompt phase (before streaming)
were thrown directly, bypassing fallback. Only response-phase errors
triggered model fallback.

Now checks if fallback models are configured and the error is failover-
eligible. If so, wraps in FailoverError to trigger the fallback chain.

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

@@ -318,6 +318,19 @@ export async function runEmbeddedPiAgent(
               thinkLevel = fallbackThinking;
               continue;
             }
+            // FIX: Throw FailoverError for prompt errors when fallbacks configured
+            // This enables model fallback for quota/rate limit errors during prompt submission
+            const promptFallbackConfigured =
+              (params.config?.agents?.defaults?.model?.fallbacks?.length ?? 0) > 0;
+            if (promptFallbackConfigured && isFailoverErrorMessage(errorText)) {
+              throw new FailoverError(errorText, {
+                reason: promptFailoverReason ?? "unknown",
+                provider,
+                model: modelId,
+                profileId: lastProfileId,
+                status: resolveFailoverStatus(promptFailoverReason ?? "unknown"),
+              });
+            }
             throw promptError;
           }