Miscellaneous fixes (0.18 beta) (#23763)
CI / AMD64 Build (push) Canceled after 0s
CI / ARM Build (push) Canceled after 0s
CI / Jetson Jetpack 6 (push) Canceled after 0s
CI / AMD64 Extra Build (push) Canceled after 0s
CI / ARM Extra Build (push) Canceled after 0s
CI / Synaptics Build (push) Canceled after 0s
CI / Assemble and push default build (push) Canceled after 0s

This commit is contained in:
Josh Hawkins
2026-07-21 06:44:33 -06:00
committed by GitHub
parent 6f80bcd19f
commit c0cf08ab4a
16 changed files with 347 additions and 47 deletions
+28
View File
@@ -491,6 +491,34 @@ class TestLlamaCppProvider(unittest.TestCase):
final = _final_message(self._run_with_lines(client, lines, MULTIMODAL_MESSAGES))
self.assertEqual(final["content"], "ok")
def _validated_client(self, server_context_size, provider_options=None):
"""Build a client as if the server reported the given context size."""
cfg = GenAIConfig(
provider="llamacpp",
model="m",
base_url="http://localhost:9999",
provider_options=provider_options or {},
)
info = {
"context_size": server_context_size,
"supports_vision": False,
"supports_audio": False,
"supports_tools": False,
"supports_reasoning": False,
"media_marker": "<__media__>",
}
cls = PROVIDERS[GenAIProviderEnum.llamacpp]
with patch.object(cls, "_get_model_info", return_value=info):
return cls(cfg, timeout=5)
def test_server_context_size_used_without_override(self):
client = self._validated_client(4096)
self.assertEqual(client.get_context_size(), 4096)
def test_provider_options_context_size_overrides_server(self):
client = self._validated_client(4096, {"context_size": 32768})
self.assertEqual(client.get_context_size(), 32768)
if __name__ == "__main__":
unittest.main()