mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-11 03:31:55 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

fix(agent): honor configured model max tokens

Browse source
This commit is contained in:
LeonSGP43 2026-05-04 09:36:43 +08:00 • committed by Teknium
parent 52e2777821
commit a78e622dfe
4 changed files with 102 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

24
tests/gateway/test_agent_cache.py
View file

@ -127,6 +127,21 @@ class TestAgentConfigSignature:
)
assert sig1 != sig2
def test_max_tokens_change_busts_cache(self):
"""Editing model.max_tokens in config must produce a new signature."""
from gateway.run import GatewayRunner
runtime = {"api_key": "k", "base_url": "u", "provider": "p"}
sig1 = GatewayRunner._agent_config_signature(
"m", runtime, [], "",
cache_keys={"model.max_tokens": 4096},
)
sig2 = GatewayRunner._agent_config_signature(
"m", runtime, [], "",
cache_keys={"model.max_tokens": 8192},
)
assert sig1 != sig2
def test_compression_threshold_change_busts_cache(self):
from gateway.run import GatewayRunner
@ -195,9 +210,16 @@ class TestExtractCacheBustingConfig:
from gateway.run import GatewayRunner
out = GatewayRunner._extract_cache_busting_config(
{"model": {"context_length": 272_000, "provider": "openrouter"}}
{
"model": {
"context_length": 272_000,
"max_tokens": 4096,
"provider": "openrouter",
}
}
)
assert out["model.context_length"] == 272_000
assert out["model.max_tokens"] == 4096
def test_reads_compression_subkeys(self):
from gateway.run import GatewayRunner