From f4a030243d53dcc6bd27ffae84d685d513674c67 Mon Sep 17 00:00:00 2001
From: Federico Kamelhar <federico.kamelhar@oracle.com>
Date: Wed, 10 Jun 2026 11:47:41 -0400
Subject: [PATCH] fix(oci): route all OpenAI commercial models to
 maxCompletionTokens

OCI serves OpenAI models (gpt-4.1, gpt-5.1 through 5.5, o-series) that
the litellm catalog doesn't track, so the supports_reasoning lookup
returned False for them and the provider sent maxTokens, which the
reasoning families reject with HTTP 400. With the injected default
maxTokens this broke every request to those models, not just ones with
an explicit max_tokens. Route the whole openai.* vendor prefix to
maxCompletionTokens since OpenAI accepts max_completion_tokens on every
chat model; the openai.gpt-oss-* open weights are served by OCI's own
stack and keep maxTokens. Verified live against gpt-5.2, gpt-5, gpt-4o,
gpt-4.1, gpt-oss-120b, llama-3.3, command-a and grok-3-mini
---
 litellm/llms/oci/chat/transformation.py       | 15 +++++---
 .../llms/oci/chat/test_oci_generic_chat.py    | 35 +++++++++++++++++++
 2 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/litellm/llms/oci/chat/transformation.py b/litellm/llms/oci/chat/transformation.py
index 72d01c34ded..627d0ae8072 100644
--- a/litellm/llms/oci/chat/transformation.py
+++ b/litellm/llms/oci/chat/transformation.py
@@ -88,15 +88,20 @@ STREAMING_TIMEOUT = 60 * 5
 def _model_uses_max_completion_tokens(model: str) -> bool:
     """Return True for OCI-hosted models that require ``maxCompletionTokens``.
 
-    Reasoning models on OCI (e.g. the OpenAI GPT-5 family) reject ``maxTokens``
-    with HTTP 400 and require ``maxCompletionTokens`` per OpenAI's reasoning-API
-    convention. Driven by ``supports_reasoning`` in
-    ``model_prices_and_context_window.json`` so new model families are picked
-    up via a catalog update rather than a code change.
+    OpenAI commercial models proxied through OCI (``openai.*``) reject
+    ``maxTokens`` with HTTP 400 on the reasoning families (gpt-5.x, o-series)
+    and accept ``maxCompletionTokens`` everywhere, so route the whole vendor
+    prefix to it rather than chasing each new release in
+    ``model_prices_and_context_window.json``. The ``openai.gpt-oss-*`` open
+    weights are served by OCI's own stack and keep ``maxTokens``. Any other
+    vendor falls back to the catalog's ``supports_reasoning`` flag.
     """
     if not model:
         return False
     name = model[4:] if model.lower().startswith("oci/") else model
+    lowered = name.lower()
+    if lowered.startswith("openai."):
+        return not lowered.startswith("openai.gpt-oss")
     return supports_reasoning(model=name, custom_llm_provider="oci")
 
 
diff --git a/tests/test_litellm/llms/oci/chat/test_oci_generic_chat.py b/tests/test_litellm/llms/oci/chat/test_oci_generic_chat.py
index 7583e3bc183..b2c93d0458f 100644
--- a/tests/test_litellm/llms/oci/chat/test_oci_generic_chat.py
+++ b/tests/test_litellm/llms/oci/chat/test_oci_generic_chat.py
@@ -382,6 +382,41 @@ class TestGpt5MaxCompletionTokens:
         assert _model_uses_max_completion_tokens("cohere.command-latest") is False
         assert _model_uses_max_completion_tokens("") is False
 
+    def test_helper_covers_openai_models_absent_from_catalog(self):
+        """OCI keeps adding OpenAI models (gpt-4.1, gpt-5.1..5.5, o-series)
+        faster than the litellm catalog tracks them. The vendor-prefix rule
+        must route them to maxCompletionTokens even with no catalog entry,
+        since OpenAI accepts max_completion_tokens on every chat model while
+        the reasoning families hard-reject max_tokens."""
+        import litellm
+        from litellm.llms.oci.chat.transformation import (
+            _model_uses_max_completion_tokens,
+        )
+
+        for name in (
+            "openai.gpt-5.2",
+            "openai.gpt-4.1",
+            "openai.o3",
+            "oci/openai.gpt-5.1-codex",
+        ):
+            assert f"oci/{name.removeprefix('oci/')}" not in litellm.model_cost
+            assert _model_uses_max_completion_tokens(name) is True
+
+        assert _model_uses_max_completion_tokens("openai.gpt-oss-20b") is False
+
+    def test_default_injection_uses_max_completion_tokens_for_uncataloged_gpt(self):
+        """Regression: with the injected default maxTokens, a GPT model absent
+        from the catalog got "maxTokens" on every request and OCI returned 400
+        ("Use 'max_completion_tokens' instead") even when the caller never set
+        max_tokens."""
+        from litellm.constants import DEFAULT_OCI_CHAT_MAX_TOKENS
+        from litellm.llms.oci.chat.transformation import OCIChatConfig, OCIVendors
+
+        cfg = OCIChatConfig()
+        out = cfg._get_optional_params(OCIVendors.GENERIC, {}, model="openai.gpt-5.2")
+        assert out.get("maxCompletionTokens") == DEFAULT_OCI_CHAT_MAX_TOKENS
+        assert "maxTokens" not in out
+
     def test_gpt5_routes_max_tokens_to_max_completion_tokens(
         self, _register_oci_gpt5_in_catalog
     ):