Releases: vernesong/mihomo
Releases · vernesong/mihomo
Mihomo Alpha with Smart Group
[声明] 本分支是在上游代码的基础上增加Smart策略组功能，关于Smart策略组的任何问题均与上游无关!
[Announcement] This branch is based on the upstream code to add Smart Groups functionality, any questions about Smart Groups are not related to the upstream!
Release created at Sun Oct 26 22:19:08 CST 2025
Synchronize Alpha branch code updates, keeping only the latest version
我应该下载哪个文件? / Which file should I download?
二进制文件筛选 / Binary file selector
查看文档 / Docs
LightGBM Model
Date: 2025-10-05
Usage:
# enable model auto update, the default is false
lgbm-auto-update: true
# model auto update interval, the default is 72 (hours)
lgbm-update-interval: 72
# model update url
lgbm-url: "https://github.com/vernesong/mihomo/releases/download/LightGBM-Model/Model.bin"
profile:
#smart-collector-size: data collection file size, the default is 100 (MB)
smart-collector-size: 100
proxy-groups:
- name: Smart Group
type: smart
# policy-priority: <1 means lower priority, >1 means higher priority, the default is 1, pattern support regex and string
policy-priority: "Premium:0.9;SG:1.3"
# uselightgbm: use LightGBM model predict weight
uselightgbm: false
# collectdata: collect datas for model training
collectdata: false
# strategy: 'sticky-sessions' or 'round-robin', not support 'consistent-hashing'
# the default is 'sticky-sessions' with more stable&smoothly nodes switch logic when datas collecting
strategy: sticky-sessions
# sample-rate: data acquisition rate, desirable values are 0-1, the default is 1
sample-rate: 1
# prefer-asn: force and lookup asn first when nodes select, the default is false
prefer-asn: true
...- LightGBM for weight prediction (option: uselightgbm: true)，need Model.bin file exist HomeDir (.config/mihomo/Model.bin) or use in OpenClash: (/etc/openclash/Model.bin)
- Data collection function to facilitate for yourself-training of weight prediction models (option: collectdata: true), path in HomeDir (.config/mihomo/smart_weight_data.csv) or (/etc/openclash/smart_weight_data.csv) in OpenClash
- If you need to train the model yourself, you could use feature transforms and must training by LightGBM version 3.3.5
Api:
# Show proxy weight
curl -H 'Authorization: Bearer ${secret}' -X GET http://${controller-api}/group/${groupname}/weights
curl -H 'Authorization: Bearer ${secret}' -X GET http://${controller-api}/group/weights
# Flush cache data
curl -H 'Authorization: Bearer ${secret}' -X POST http://${controller-api}/cache/smart/flush
curl -H 'Authorization: Bearer ${secret}' -X POST http://${controller-api}/cache/smart/flush/${configname}
# Block(degrade) connections - node result to forceing choice another best
curl -H 'Authorization: Bearer ${secret}' -X DELETE http://${controller-api}/connections/smart/${id}
# LightGBM model upgrade
curl -H 'Authorization: Bearer ${secret}' -X POST http://${controller-api}/upgrade/lgbmPredicting performance (Large)
RMSE: 0.080149 MAE: 0.040632 R²: 0.934709
train_time=2025-10-05 17:35:42
rmse=0.080149
mae=0.040632
r2=0.934709
objective=regression;metric=rmse;verbosity=-1;boosting_type=gbdt;num_leaves=192;learning_rate=0.01;max_depth=12;max_bin=127;num_boost_round=1800;early_stopping_rounds=200;min_child_samples=2928;bagging_fraction=0.6274629722391256;feature_fraction=0.629643701208391;lambda_l1=0.28786675811749307;lambda_l2=3.476332518783713;min_split_gain=0.5963275240701651;bagging_freq=8;device=gpu;num_threads=2;gpu_use_dp=False;gpu_platform_id=0;gpu_device_id=0
data_shape=(2108278, 27)
weight_min=0.174000
weight_max=1.752602
weight_mean=0.812941
weight_std=0.313670