mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(kimi): force kimi-for-coding temperature to 0.6

Browse source
This commit is contained in:
helix4u 2026-04-17 16:17:15 -06:00 • committed by Teknium
parent c6fd2619f7
commit 2b60478fc2
3 changed files with 108 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

7
run_agent.py
View file

@ -7209,12 +7209,13 @@ class AIAgent:
# it's cheaper and avoids Codex Responses API incompatibility.
from agent.auxiliary_client import call_llm as _call_llm
_aux_available = True
_flush_temperature = 0.6 if str(self.model or "").strip().lower() == "kimi-for-coding" else 0.3
try:
response = _call_llm(
task="flush_memories",
messages=api_messages,
tools=[memory_tool_def],
temperature=0.3,
temperature=_flush_temperature,
max_tokens=5120,
# timeout resolved from auxiliary.flush_memories.timeout config
)
@ -7226,7 +7227,7 @@ class AIAgent:
# No auxiliary client -- use the Codex Responses path directly
codex_kwargs = self._build_api_kwargs(api_messages)
codex_kwargs["tools"] = self._responses_tools([memory_tool_def])
codex_kwargs["temperature"] = 0.3
codex_kwargs["temperature"] = _flush_temperature
if "max_output_tokens" in codex_kwargs:
codex_kwargs["max_output_tokens"] = 5120
response = self._run_codex_stream(codex_kwargs)
@ -7245,7 +7246,7 @@ class AIAgent:
"model": self.model,
"messages": api_messages,
"tools": [memory_tool_def],
"temperature": 0.3,
"temperature": _flush_temperature,
**self._max_tokens_param(5120),
}
from agent.auxiliary_client import _get_task_timeout