mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
3cba81ebed
Kimi's gateway selects the correct temperature server-side based on the active mode (thinking -> 1.0, non-thinking -> 0.6). Sending any temperature value — even the previously "correct" one — conflicts with gateway-managed defaults. Replaces the old approach of forcing specific temperature values (0.6 for non-thinking, 1.0 for thinking) with an OMIT_TEMPERATURE sentinel that tells all call sites to strip the temperature key from API kwargs entirely. Changes: - agent/auxiliary_client.py: OMIT_TEMPERATURE sentinel, _is_kimi_model() prefix check (covers all kimi-* models), _fixed_temperature_for_model() returns sentinel for kimi models. _build_call_kwargs() strips temp. - run_agent.py: _build_api_kwargs, flush_memories, and summary generation paths all handle the sentinel by popping/omitting temperature. - trajectory_compressor.py: _effective_temperature_for_model returns None for kimi (sentinel mapped), direct client calls use kwargs dict to conditionally include temperature. - mini_swe_runner.py: same sentinel handling via wrapper function. - 6 test files updated: all 'forces temperature X' assertions replaced with 'temperature not in kwargs' assertions. Net: -76 lines (171 added, 247 removed). Inspired by PR #13137 (@kshitijk4poor).
60 lines
2 KiB
Python
60 lines
2 KiB
Python
from types import SimpleNamespace
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
|
|
def test_run_task_kimi_omits_temperature():
|
|
"""Kimi models should NOT have client-side temperature overrides.
|
|
|
|
The Kimi gateway selects the correct temperature server-side.
|
|
"""
|
|
with patch("openai.OpenAI") as mock_openai:
|
|
client = MagicMock()
|
|
client.chat.completions.create.return_value = SimpleNamespace(
|
|
choices=[SimpleNamespace(message=SimpleNamespace(content="done", tool_calls=[]))]
|
|
)
|
|
mock_openai.return_value = client
|
|
|
|
from mini_swe_runner import MiniSWERunner
|
|
|
|
runner = MiniSWERunner(
|
|
model="kimi-for-coding",
|
|
base_url="https://api.kimi.com/coding/v1",
|
|
api_key="test-key",
|
|
env_type="local",
|
|
max_iterations=1,
|
|
)
|
|
runner._create_env = MagicMock()
|
|
runner._cleanup_env = MagicMock()
|
|
|
|
result = runner.run_task("2+2")
|
|
|
|
assert result["completed"] is True
|
|
assert "temperature" not in client.chat.completions.create.call_args.kwargs
|
|
|
|
|
|
def test_run_task_public_moonshot_kimi_k2_5_omits_temperature():
|
|
"""kimi-k2.5 on the public Moonshot API should not get a forced temperature."""
|
|
with patch("openai.OpenAI") as mock_openai:
|
|
client = MagicMock()
|
|
client.base_url = "https://api.moonshot.ai/v1"
|
|
client.chat.completions.create.return_value = SimpleNamespace(
|
|
choices=[SimpleNamespace(message=SimpleNamespace(content="done", tool_calls=[]))]
|
|
)
|
|
mock_openai.return_value = client
|
|
|
|
from mini_swe_runner import MiniSWERunner
|
|
|
|
runner = MiniSWERunner(
|
|
model="kimi-k2.5",
|
|
base_url="https://api.moonshot.ai/v1",
|
|
api_key="test-key",
|
|
env_type="local",
|
|
max_iterations=1,
|
|
)
|
|
runner._create_env = MagicMock()
|
|
runner._cleanup_env = MagicMock()
|
|
|
|
result = runner.run_task("2+2")
|
|
|
|
assert result["completed"] is True
|
|
assert "temperature" not in client.chat.completions.create.call_args.kwargs
|