From ff8920299c10e5e58fc84326bf2c973b42ab4de1 Mon Sep 17 00:00:00 2001
From: herbalizer404 <8180647+herbalizer404@users.noreply.github.com>
Date: Thu, 25 Jun 2026 12:50:25 -0700
Subject: [PATCH] fix(auxiliary): treat 403 subscription and
 session-usage-limit errors as payment errors for fallback

Ollama Cloud (and similar) return 403 with bodies like "this model requires
a subscription, upgrade for access" or "you have reached your session usage
limit, upgrade for higher limits". These are capacity/billing conditions
semantically identical to credit exhaustion, but _is_payment_error() did not
recognize them (403 missing from the status set; keywords missing), so the
configured fallback_chain was never tried and compression failed outright.

Adds 403 to the status set and the subscription/session-usage keywords.

Salvaged from #49076 by @herbalizer404.
---
 agent/auxiliary_client.py            |  4 +++-
 tests/agent/test_auxiliary_client.py | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index 0afb0add20b..18a6f9bfa73 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -2470,7 +2470,7 @@ def _is_payment_error(exc: Exception) -> bool:
     # but sometimes wrap them in 429 or other codes.
     # Daily quota exhaustion from Bedrock, Vertex AI, and similar providers
     # uses different language but is semantically identical to credit exhaustion.
-    if status in {402, 404, 429, None}:
+    if status in {402, 403, 404, 429, None}:
         if any(kw in err_lower for kw in (
             "credits", "insufficient funds",
             "can only afford", "billing",
@@ -2479,6 +2479,8 @@ def _is_payment_error(exc: Exception) -> bool:
             "balance_depleted", "no usable credits",
             "model_not_supported_on_free_tier",
             "not available on the free tier",
+            "requires a subscription", "upgrade for access",
+            "upgrade for higher limits", "reached your session usage limit",
             # Daily / monthly / weekly quota exhaustion keywords
             "quota exceeded", "quota_exceeded",
             "too many tokens per day", "daily limit",
diff --git a/tests/agent/test_auxiliary_client.py b/tests/agent/test_auxiliary_client.py
index dac9956b494..060a817998e 100644
--- a/tests/agent/test_auxiliary_client.py
+++ b/tests/agent/test_auxiliary_client.py
@@ -1406,6 +1406,21 @@ class TestIsPaymentError:
         exc.status_code = 404
         assert _is_payment_error(exc) is True
 
+    def test_403_subscription_required_is_payment(self):
+        exc = Exception(
+            "this model requires a subscription, upgrade for access: "
+            "https://ollama.com/upgrade"
+        )
+        setattr(exc, "status_code", 403)
+        assert _is_payment_error(exc) is True
+
+    def test_429_session_usage_limit_is_payment(self):
+        exc = Exception(
+            "you have reached your session usage limit, upgrade for higher limits"
+        )
+        setattr(exc, "status_code", 429)
+        assert _is_payment_error(exc) is True
+
     def test_404_generic_not_found_is_not_payment(self):
         exc = Exception("Not Found")
         exc.status_code = 404