Skip to content

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

C

server: clamp max_tokens to the server cap instead of rejecting it (fixes #260)

JustVuggda260c38cbaf
diff --git a/c/openai_server.py b/c/openai_server.py
index f31e8f7b..ba19e437 100644
--- a/c/openai_server.py
+++ b/c/openai_server.py
@@ -410,8 +410,11 @@ def generation_options(body, limit):
top_p = body.get("top_p")
temperature = 0.7 if temperature is None else temperature
top_p = 0.9 if top_p is None else top_p
- if isinstance(maximum, bool) or not isinstance(maximum, int) or not 1 <= maximum <= limit:
- raise APIError(400, f"`{maximum_param}` must be an integer between 1 and {limit}.", maximum_param)
+ if isinstance(maximum, bool) or not isinstance(maximum, int) or maximum < 1:
+ raise APIError(400, f"`{maximum_param}` must be a positive integer.", maximum_param)
+ if maximum > limit:
+ maximum = limit # clamp to the server's --max-tokens cap instead of 400 (#260): OpenAI
+ # clients (opencode/ai-sdk) default to large max_tokens; rejecting breaks them.
if (isinstance(temperature, bool) or not isinstance(temperature, (int, float)) or
not math.isfinite(temperature) or not 0 <= temperature <= 2):
raise APIError(400, "`temperature` must be between 0 and 2.", "temperature")
diff --git a/c/tests/test_openai_server.py b/c/tests/test_openai_server.py
index 00640707..f8aec86a 100644
--- a/c/tests/test_openai_server.py
+++ b/c/tests/test_openai_server.py
@@ -72,8 +72,13 @@ class TemplateTest(unittest.TestCase):
def test_validates_generation_limits(self):
self.assertEqual(generation_options({"max_tokens": 4, "temperature": 0, "top_p": 1}, 8),
(4, 0.0, 1.0))
+ # max_tokens above the server cap is clamped, not rejected (#260): OpenAI
+ # clients default to large values; erroring breaks them.
+ self.assertEqual(generation_options({"max_tokens": 9, "temperature": 0, "top_p": 1}, 8),
+ (8, 0.0, 1.0))
+ # non-positive / non-int max_tokens is still a hard error
with self.assertRaises(APIError):
- generation_options({"max_tokens": 9}, 8)
+ generation_options({"max_tokens": 0}, 8)
with self.assertRaises(APIError):
generation_options({"temperature": math.nan}, 8)
with self.assertRaises(APIError):