From 448394a0de2c90ef146804351c7718db4e22ac14 Mon Sep 17 00:00:00 2001
From: Mykyta Bozhenko <1245729+cheeeee@users.noreply.github.com>
Date: Sun, 18 Jan 2026 01:29:48 +0000
Subject: [PATCH] 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 | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/src/agents/pi-embedded-runner/run.ts b/src/agents/pi-embedded-runner/run.ts
index 0e0946428..25f36a712 100644
--- a/src/agents/pi-embedded-runner/run.ts
+++ b/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;
           }