From dd92067be19885942c94c9cc3bf97f2942e2c71b Mon Sep 17 00:00:00 2001
From: kerry <kerry@berri.ai>
Date: Tue, 22 Sep 2026 21:36:34 +0000
Subject: [PATCH] test(integration): chat over responses deployment returns
 finish_reason length when output tokens run out (Pylon #7784)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 tests/integration/contracts.json              |  3 +
 .../test_responses_bridge_incomplete.py       | 64 +++++++++++++++++++
 2 files changed, 67 insertions(+)
 create mode 100644 tests/integration/providers/test_responses_bridge_incomplete.py

diff --git a/tests/integration/contracts.json b/tests/integration/contracts.json
index d12e3ae4620..e343f850c05 100644
--- a/tests/integration/contracts.json
+++ b/tests/integration/contracts.json
@@ -45,6 +45,9 @@
     "tests/integration/providers/test_request_boundary.py::test_upstream_rejects_corruption_and_accepts_supported_metadata": [
       "other.provider_wire.validator_rejects_corruption"
     ],
+    "tests/integration/providers/test_responses_bridge_incomplete.py::test_chat_over_responses_deployment_returns_length_when_output_tokens_run_out": [
+      "other.provider_wire.responses_bridge.max_output_tokens_incomplete_maps_to_length"
+    ],
     "tests/integration/pricing/test_configured_prices.py::test_loaded_router_preserves_cached_defaults_during_real_requests": [
       "quota_management.spend_tracking.default_prices.loaded_router_preserves_cached_defaults"
     ],
diff --git a/tests/integration/providers/test_responses_bridge_incomplete.py b/tests/integration/providers/test_responses_bridge_incomplete.py
new file mode 100644
index 00000000000..3352ca5775e
--- /dev/null
+++ b/tests/integration/providers/test_responses_bridge_incomplete.py
@@ -0,0 +1,64 @@
+import json
+import uuid
+from typing import Final
+
+import pytest
+from integration._support.client import Gateway
+from integration._support.wire import Reply, Request, wire_server
+
+
+@pytest.mark.covers("other.provider_wire.responses_bridge.max_output_tokens_incomplete_maps_to_length")
+def test_chat_over_responses_deployment_returns_length_when_output_tokens_run_out(gateway: Gateway) -> None:
+    identity: Final = "responses-incomplete-" + uuid.uuid4().hex
+
+    def respond(request: Request) -> Reply:
+        assert request.method == "POST" and request.target == "/responses", request.target
+        assert request.headers["authorization"] == "Bearer synthetic-openai-key"
+        body: Final = json.loads(request.body)
+        assert body["model"] == "gpt-5.3-codex"
+        assert body["max_output_tokens"] == 16
+        assert body["reasoning"] == {"effort": "high"}
+        assert body["input"] == [
+            {
+                "type": "message",
+                "role": "user",
+                "content": [{"type": "input_text", "text": f"explain the plan in detail {identity}"}],
+            }
+        ]
+        return Reply(
+            body=json.dumps(
+                {
+                    "id": f"resp_{identity}",
+                    "object": "response",
+                    "created_at": 1789788253,
+                    "status": "incomplete",
+                    "incomplete_details": {"reason": "max_output_tokens"},
+                    "model": "gpt-5.3-codex",
+                    "output": [{"type": "reasoning", "id": f"rs_{identity}", "summary": []}],
+                    "usage": {"input_tokens": 12, "output_tokens": 16, "total_tokens": 28},
+                }
+            ).encode()
+        )
+
+    with wire_server(respond) as wire, gateway.scenario() as scenario:
+        model: Final = scenario.model(
+            model="openai/responses/gpt-5.3-codex", api_base=wire.url, api_key="synthetic-openai-key"
+        )
+        response: Final = gateway.request(
+            "POST",
+            "/v1/chat/completions",
+            {
+                "model": model,
+                "messages": [{"role": "user", "content": f"explain the plan in detail {identity}"}],
+                "reasoning_effort": "high",
+                "max_completion_tokens": 16,
+            },
+        )
+        assert response.status_code == 200, response.text
+        body: Final = response.json()
+        assert len(wire.drain()) == 1
+        assert [choice["finish_reason"] for choice in body["choices"]] == ["length"], response.text
+        assert body["choices"][0]["message"]["content"] == "", response.text
+        assert body["choices"][0]["message"]["role"] == "assistant", response.text
+        assert body["usage"]["prompt_tokens"] == 12 and body["usage"]["completion_tokens"] == 16, response.text
+        assert body["usage"]["total_tokens"] == 28, response.text