From becec33c1721fb619f2a439e666dbecd7872913a Mon Sep 17 00:00:00 2001
From: kerry <kerry@berri.ai>
Date: Tue, 22 Sep 2026 20:43:13 +0000
Subject: [PATCH] test(integration): failed dispatched requests keep estimated
 input tokens in spend logs (Pylon #7519)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 .../spend/test_failed_dispatch_tokens.py      | 50 +++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100644 tests/integration/spend/test_failed_dispatch_tokens.py

diff --git a/tests/integration/spend/test_failed_dispatch_tokens.py b/tests/integration/spend/test_failed_dispatch_tokens.py
new file mode 100644
index 00000000000..5778ff9654d
--- /dev/null
+++ b/tests/integration/spend/test_failed_dispatch_tokens.py
@@ -0,0 +1,50 @@
+import json
+import uuid
+from typing import Final
+
+import pytest
+from integration._support.client import Gateway, eventually
+from integration._support.database import read_rows
+from integration._support.wire import Reply, Request, wire_server
+
+
+@pytest.mark.covers("spend.failed_dispatch.failure_row_records_estimated_input_tokens")
+def test_provider_500_after_dispatch_records_estimated_prompt_tokens_on_failure_row(gateway: Gateway) -> None:
+    prompt: Final = "failed dispatch accounting " + uuid.uuid4().hex
+    system: Final = "You are a terse accounting assistant"
+
+    def provider(request: Request) -> Reply:
+        assert request.method == "POST" and request.target == "/v1/chat/completions"
+        body: Final = json.loads(request.body)
+        assert body["model"] == "gpt-4o-mini"
+        assert body["messages"] == [{"role": "system", "content": system}, {"role": "user", "content": prompt}]
+        return Reply(
+            status=500,
+            body=b'{"error":{"message":"synthetic provider outage","type":"server_error","code":"500"}}',
+        )
+
+    with wire_server(provider) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(api_base=wire.url + "/v1", num_retries=0)
+        key: Final = scenario.key(models=[model])
+        failed: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {"model": model, "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}]},
+            key=key,
+        )
+        assert failed.status_code == 500 and "synthetic provider outage" in failed.text, failed.text
+        call_id: Final = failed.headers["x-litellm-call-id"]
+        assert len(wire.drain()) == 1
+        rows: Final = eventually(
+            lambda: read_rows(
+                'SELECT status, spend, prompt_tokens, completion_tokens, total_tokens FROM "LiteLLM_SpendLogs" '
+                "WHERE request_id=%s",
+                (call_id,),
+            ),
+            lambda values: len(values) == 1,
+            seconds=70,
+        )
+        row: Final = rows[0]
+        assert row["status"] == "failure" and float(row["spend"]) == 0 and row["completion_tokens"] == 0, row
+        assert row["prompt_tokens"] > 0, f"failure row lost the dispatched input tokens: {row}"
+        assert row["total_tokens"] == row["prompt_tokens"], row