From feb6dab2cbb71d48cf09d61c6787086b393d104c Mon Sep 17 00:00:00 2001
From: laulauraluo <12486304+laulauraluo@users.noreply.github.com>
Date: Wed, 14 Oct 2026 21:50:09 -0700
Subject: [PATCH 1/2] fix(server): accept max_completion_tokens in chat
 requests

---
 CHANGELOG.md               |  2 ++
 llama_cpp/server/types.py  |  3 ++-
 tests/test_server_types.py | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_server_types.py

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5c34e2729e..cf634002f2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+- fix(server): accept max_completion_tokens in chat requests by @laulauraluo
+
 ## [0.3.36]
 
 - feat: update llama.cpp to ggml-org/llama.cpp@0c1e57098
diff --git a/llama_cpp/server/types.py b/llama_cpp/server/types.py
index eda2b92801..055d39ef5d 100644
--- a/llama_cpp/server/types.py
+++ b/llama_cpp/server/types.py
@@ -3,7 +3,7 @@
 from typing import List, Optional, Union, Dict
 from typing_extensions import TypedDict, Literal
 
-from pydantic import BaseModel, Field
+from pydantic import AliasChoices, BaseModel, Field
 
 import llama_cpp
 
@@ -212,6 +212,7 @@ class CreateChatCompletionRequest(BaseModel):
     )  # TODO: verify
     max_tokens: Optional[int] = Field(
         default=None,
+        validation_alias=AliasChoices("max_tokens", "max_completion_tokens"),
         description="The maximum number of tokens to generate. Defaults to inf",
     )
     min_tokens: int = min_tokens_field
diff --git a/tests/test_server_types.py b/tests/test_server_types.py
new file mode 100644
index 0000000000..bf765cefb4
--- /dev/null
+++ b/tests/test_server_types.py
@@ -0,0 +1,33 @@
+import pytest
+from pydantic import ValidationError
+
+from llama_cpp.server.types import CreateChatCompletionRequest
+
+
+@pytest.mark.parametrize(
+    ("limits", "expected"),
+    [
+        ({}, None),
+        ({"max_tokens": 3}, 3),
+        ({"max_completion_tokens": 3}, 3),
+        ({"max_tokens": None}, None),
+        ({"max_completion_tokens": None}, None),
+        ({"max_tokens": 7, "max_completion_tokens": 3}, 7),
+        ({"max_tokens": None, "max_completion_tokens": 3}, None),
+    ],
+)
+def test_chat_completion_token_limit(limits, expected):
+    request = CreateChatCompletionRequest(
+        messages=[{"role": "user", "content": "Hello"}], **limits
+    )
+
+    assert request.max_tokens == expected
+    payload = request.model_dump()
+    assert payload["max_tokens"] == expected
+    assert "max_completion_tokens" not in payload
+
+
+@pytest.mark.parametrize("field", ["max_tokens", "max_completion_tokens"])
+def test_chat_completion_token_limit_validation(field):
+    with pytest.raises(ValidationError):
+        CreateChatCompletionRequest(**{field: "invalid"})

From e055c3f359850f586d96f7ee735b236a6d6d1c85 Mon Sep 17 00:00:00 2001
From: laulauraluo <12486304+laulauraluo@users.noreply.github.com>
Date: Wed, 14 Oct 2026 21:51:28 -0700
Subject: [PATCH 2/2] docs: link token limit fix in changelog

---
 CHANGELOG.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index cf634002f2..2d859fe0d8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,7 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-- fix(server): accept max_completion_tokens in chat requests by @laulauraluo
+- fix(server): accept max_completion_tokens in chat requests by @laulauraluo in #2386
 
 ## [0.3.36]