From 8ce365511f84d863fb4e43600a7823733ece4f35 Mon Sep 17 00:00:00 2001
From: mubashir1osmani <mubashir.osmani777@gmail.com>
Date: Sat, 25 Jul 2026 10:54:28 -0700
Subject: [PATCH] test(e2e): cover /openai chat passthrough cost logging
 (#34470)

The /openai/{endpoint} passthrough forwards a raw OpenAI-format request to
api.openai.com (or OPENAI_API_BASE) with the proxy's OPENAI_API_KEY swapped in,
and still logs a costed pass_through_endpoint SpendLogs row. Nothing exercised
that path end to end.

Adds a live /openai/v1/chat/completions passthrough test that asserts a 2xx
completion and a costed row with custom_llm_provider=openai, mirroring the
gemini and anthropic passthrough cost tests, and registers
llm.chat_completions.openai.passthrough.nonstream.cost_logged.
---
 .../coverage_registry/llm_conversational.yaml |  1 +
 .../e2e/llm_translation/passthrough_client.py | 19 +++++++++++++++++++
 .../llm_translation/test_passthrough_e2e.py   | 12 ++++++++++++
 3 files changed, 32 insertions(+)

diff --git a/tests/e2e/coverage_registry/llm_conversational.yaml b/tests/e2e/coverage_registry/llm_conversational.yaml
index fc3a61c078f..6cb60c19247 100644
--- a/tests/e2e/coverage_registry/llm_conversational.yaml
+++ b/tests/e2e/coverage_registry/llm_conversational.yaml
@@ -2,6 +2,7 @@
 - {id: llm.chat_completions.openai.basic.nonstream.works, module: llm, tier: P0, subject_endpoint: chat_completions, route: openai, capability: basic, streaming: nonstream, assertions: [works], source: "proxy_server.py:8455", rationale: "Core endpoint/route/capability"}
 - {id: llm.chat_completions.openai.basic.stream.works, module: llm, tier: P0, subject_endpoint: chat_completions, route: openai, capability: basic, streaming: stream, assertions: [works], source: "proxy_server.py:8455", rationale: "Core streaming"}
 - {id: llm.chat_completions.openai.basic.nonstream.cost_logged, module: llm, tier: P0, subject_endpoint: chat_completions, route: openai, capability: basic, streaming: nonstream, assertions: [works, cost_logged], source: "proxy_server.py:8455", rationale: "Cost logging regression catch"}
+- {id: llm.chat_completions.openai.passthrough.nonstream.cost_logged, module: llm, tier: P1, subject_endpoint: chat_completions, route: openai, capability: basic, streaming: nonstream, assertions: [works, cost_logged], source: "test_passthrough_e2e.py", rationale: "OpenAI-format chat via the raw /openai/{endpoint} passthrough (/openai/v1/chat/completions); proxy swaps in OPENAI_API_KEY and still logs a costed pass_through_endpoint row (LIT-4752)"}
 - {id: llm.chat_completions.openai.tool_use.nonstream.works, module: llm, tier: P0, subject_endpoint: chat_completions, route: openai, capability: tool_use, streaming: nonstream, assertions: [works], source: "model_prices json", rationale: "OpenAI function_calling; high usage"}
 - {id: llm.chat_completions.openai.tool_use.stream.works, module: llm, tier: P0, subject_endpoint: chat_completions, route: openai, capability: tool_use, streaming: stream, assertions: [works], source: "model_prices json", rationale: "Tool calls over streaming"}
 - {id: llm.chat_completions.openai.vision.nonstream.works, module: llm, tier: P0, subject_endpoint: chat_completions, route: openai, capability: vision, streaming: nonstream, assertions: [works], source: "model_prices json", rationale: "gpt-4o vision; high usage"}
diff --git a/tests/e2e/llm_translation/passthrough_client.py b/tests/e2e/llm_translation/passthrough_client.py
index c74da3e9abc..7aa2eb793ad 100644
--- a/tests/e2e/llm_translation/passthrough_client.py
+++ b/tests/e2e/llm_translation/passthrough_client.py
@@ -102,6 +102,12 @@ class AnthropicMessageBody(BaseModel):
     stream: bool = False
 
 
+class OpenAIChatBody(BaseModel):
+    model: str
+    messages: list[ChatMessage]
+    max_tokens: int = 64
+
+
 class VllmChatBody(BaseModel):
     model: str
     messages: list[ChatMessage]
@@ -191,6 +197,19 @@ class PassthroughClient:
             stream=stream,
         )
 
+    def openai_chat(
+        self, key: str, model: str, text: str, *, max_tokens: int = 64
+    ) -> StreamingResponse:
+        return self.proxy.transport.send(
+            "/openai/v1/chat/completions",
+            headers=self.proxy.transport.bearer(key),
+            json=OpenAIChatBody(
+                model=model,
+                max_tokens=max_tokens,
+                messages=[ChatMessage(role="user", content=text)],
+            ),
+        )
+
     def vllm_chat(
         self, key: str, model: str, text: str, *, max_tokens: int = 64
     ) -> StreamingResponse:
diff --git a/tests/e2e/llm_translation/test_passthrough_e2e.py b/tests/e2e/llm_translation/test_passthrough_e2e.py
index ed5c657d23e..b7d4d7cd668 100644
--- a/tests/e2e/llm_translation/test_passthrough_e2e.py
+++ b/tests/e2e/llm_translation/test_passthrough_e2e.py
@@ -160,6 +160,18 @@ def test_anthropic_passthrough_tool_call_logs_cost(
     assert row.custom_llm_provider == "anthropic"
 
 
+@pytest.mark.covers("llm.chat_completions.openai.passthrough.nonstream.cost_logged")
+def test_openai_passthrough_nonstreaming_logs_cost(
+    client: PassthroughClient, scoped_key: str
+) -> None:
+    result = client.openai_chat(scoped_key, "gpt-5.4-mini", "Say hello in one word")
+    require_successful_call(result)
+
+    row = _fetch_cost_breakdown(client, result)
+    assert row.custom_llm_provider == "openai"
+    assert "gpt-5" in (row.model or "")
+
+
 class TestPassthroughModelAllowlist:
     """A passthrough route must honor the calling key's model allow-list.