Compare commits

...
78 Commits
Author SHA1 Message Date
way add4891e27 docs: refine language switch links 2026-09-28 21:28:27 +08:00
way d789e34ab6 docs: split English and Chinese readmes 2026-09-28 20:03:13 +08:00
way f5c01407d5 docs: add bilingual project documentation 2026-09-27 23:31:25 +08:00
way 52a6e115f5 release: merge Device Agent v3.7.0 2026-09-27 23:17:45 +08:00
way ccf1e22514 docs: align project names and repository links 2026-09-27 22:37:54 +08:00
way c8c12b7b70 refactor: separate fleet manager from local monitoring 2026-09-27 22:28:03 +08:00
way ced0140450 style: simplify fan speed labels 2026-09-27 21:50:05 +08:00
way ddce873745 style: unify preference icon and text spacing 2026-09-27 21:48:18 +08:00
way 324390f647 style: align fan status with CPU frequency 2026-09-27 21:47:01 +08:00
way 1f581087b2 style: integrate globe icon into language selector 2026-09-27 21:44:03 +08:00
way 0dac42cd64 fix: show fan telemetry with CPU and space action rows 2026-09-27 21:42:57 +08:00
way 0d7a686c65 style: increase save status spacing 2026-09-27 21:22:16 +08:00
way 630a6a98da style: space plugin save actions below settings 2026-09-27 21:21:36 +08:00
way 7befb325fb feat: add machine management and resolved device identity 2026-09-27 21:20:44 +08:00
way f0bef66651 docs: clarify API token retrieval wording 2026-09-27 21:11:20 +08:00
way 7c4de5843d Merge standalone monitoring and plugin architecture for v3.7.0 2026-09-27 21:06:03 +08:00
way 2ec34bbd57 docs: present standalone monitoring and connected plugins 2026-09-27 21:05:43 +08:00
way 33e90eb535 docs: generalize plugin capability guidance 2026-09-27 21:02:52 +08:00
way c106b4c264 docs: clarify autonomous plugin telemetry and lease expiry 2026-09-27 20:54:06 +08:00
way 52f56eefc5 fix: show plugin refresh results and startup guidance 2026-09-27 20:33:28 +08:00
way 849fd016b6 fix: restore CPU meter and explain unavailable fan status 2026-09-27 20:31:29 +08:00
way 993d95bab1 refactor: separate monitoring from hardware plugins 2026-09-27 20:24:34 +08:00
way a976dfa3fa fix: quench RGB after fan register writes 2026-09-27 15:19:05 +08:00
way ae8f756749 fix: isolate fan writes from active RGB frames 2026-09-27 15:16:10 +08:00
way c3ed599198 refactor: isolate OLED and RGB workers 2026-09-27 15:07:16 +08:00
way 38362be824 fix: stabilize RGB startup and color transitions 2026-09-27 15:03:15 +08:00
way 2f82cc36b4 style: reorganize event log filters 2026-09-27 14:58:21 +08:00
way 260d8fad8f style: refine language and appearance controls 2026-09-27 14:55:03 +08:00
way 9babcfabc1 fix: preserve device hover across status refreshes 2026-09-27 14:50:35 +08:00
way 152ecc6e2b feat: add independent batch configuration sync 2026-09-27 14:48:03 +08:00
way a96cdb859d fix: align configuration target controls 2026-09-27 14:39:21 +08:00
way e2cec738c8 style: flatten inner cards and lift devices on hover 2026-09-27 14:37:36 +08:00
way f505f3c23b merge: multi-host monitoring and configuration 2026-09-27 14:34:46 +08:00
way b7a77a4661 fix: polish themes and language consistency 2026-09-27 14:29:20 +08:00
way 9824c54d6b feat: add multi-host monitoring and configuration 2026-09-27 14:20:38 +08:00
way 974121de99 merge: bilingual interface and appearance modes 2026-09-27 13:59:12 +08:00
way 5d744824a8 feat: add bilingual interface and appearance modes 2026-09-27 13:59:11 +08:00
way b08721fd15 Merge fix/monitor-pause-rgb-edges 2026-09-27 13:49:10 +08:00
way cd9bdd5970 fix: separate monitor pause and stabilize RGB edges 2026-09-27 13:49:09 +08:00
way 08c00aa370 Merge feature/log-query 2026-09-27 13:42:59 +08:00
way 13f6155096 feat: add searchable event log history 2026-09-27 13:42:58 +08:00
way 97598a48ad Merge fix/service-controls-layout 2026-09-27 13:29:12 +08:00
way 01c07658c0 fix: refine service monitor controls 2026-09-27 13:29:11 +08:00
way 4ba4d461db Merge fix/web-rgb-alignment 2026-09-27 13:24:07 +08:00
way 45c7b8c168 fix: align RGB color controls 2026-09-27 13:24:06 +08:00
way b39c7e5279 Merge feature/web-controls 2026-09-27 11:20:46 +08:00
way 2e5562fb3e feat: improve web configuration controls 2026-09-27 11:20:45 +08:00
way 03fd6d1cd8 Merge feature/web-config-ui 2026-09-27 11:00:42 +08:00
way 8cb71cbe9f feat: reorganize and localize web configuration 2026-09-27 11:00:41 +08:00
way 73907320c8 Merge fix/rgb-effect-commit-order 2026-09-27 10:46:20 +08:00
way ad25c08eb1 fix: commit MCU RGB effects in calibrated order 2026-09-27 10:46:18 +08:00
way 5d541d5ef6 Merge feature/normal-rgb 2026-09-27 10:36:33 +08:00
way a8ca071b56 feat: add configurable normal RGB effects 2026-09-27 10:36:32 +08:00
way 419d27b570 Merge fix/pigway-brand-force-install 2026-09-27 10:29:02 +08:00
way 73a60b4866 fix: standardize PIGWay branding and conflict override 2026-09-27 10:29:01 +08:00
way 576006b2fd Merge fix/i2c-owner-preflight 2026-09-27 10:25:57 +08:00
way 671fde1bfc fix: detect conflicting I2C controllers 2026-09-27 10:25:56 +08:00
way 99e086bd25 Merge feature/api-web for v3.6.0 2026-09-27 10:22:51 +08:00
way f42ea9d4bd feat: add lightweight API and web console 2026-09-27 10:21:12 +08:00
way fd4e2bf0f4 Merge feature/system-health for v3.5.0 2026-09-27 10:08:09 +08:00
way 5402dddd15 chore: release v3.5.0 2026-09-27 10:07:59 +08:00
way 6ca19b362b feat: configure RGB colors and flash timing 2026-09-27 10:04:15 +08:00
way adfa5524b8 refactor: use calibrated RGB alert flashes 2026-09-27 10:00:05 +08:00
way ac9bc4befd fix: align RGB colors with fault domains 2026-09-27 09:54:45 +08:00
way ad22dcced7 feat: distinguish RGB alerts by fault type 2026-09-27 09:47:03 +08:00
way 249af5a3e3 fix: use calibrated MCU RGB effects 2026-09-27 09:25:19 +08:00
way a84f4895ef fix: arbitrate display requests atomically 2026-09-26 23:01:15 +08:00
way 6fc428ef18 refactor: add single-owner display arbitration 2026-09-26 22:57:10 +08:00
way 34f334dd23 fix: unify active alert and RGB behavior 2026-09-26 22:35:23 +08:00
way d3ccca4b37 fix: redesign RGB alert engine 2026-09-26 22:24:43 +08:00
way 3a302b9c78 fix: harden P0 health monitoring RC2 2026-09-26 17:10:53 +08:00
way 83ec3f4379 fix: restore OLED font asset 2026-09-26 16:41:59 +08:00
way 2ef8007ccd feat: add P0 system health monitoring 2026-09-26 16:36:45 +08:00
way f65499f34b Merge pull request 'feat: active network interface status' (#1) from feature/network-interface-status into main
Reviewed-on: way/pigway-pi-control#1
2026-09-26 14:49:25 +08:00
way 2b70db10fc fix: update IP4/IP6 installer self-check 2026-09-26 14:38:17 +08:00
way 62db207c45 fix: import regex module for network detection 2026-09-26 14:31:49 +08:00
way b28ee63f38 fix: correct default route regex parsing 2026-09-26 14:25:39 +08:00
way cb0eca7aab feat: add active network interface status 2026-09-26 14:20:36 +08:00
13 changed files with 1219 additions and 803 deletions
+28 -358
View File
@@ -1,381 +1,51 @@
# Pigway Pi Control v3.1.0 — Release
# PIGWay Device Agent v3.7.0
适用于本套 Raspberry Pi 4B 散热扩展板的正式发布版。
[简体中文](README.zh-CN.md) | English
本包遵循一个原则:
> **一个程序 + 一个用户配置文件 + 一个说明文档。**
PIGWay Device Agent is a lightweight local monitoring service for Raspberry Pi and Linux. It monitors CPU, memory, temperature, disk, networking, services, processes, system health alerts, and journal events. It has no embedded Web UI and does not require a hardware plugin or Device Console.
正常使用时,不需要修改源码。
---
## 1. 功能
### OLED
配套 OLED 按卖家原生参数锁定为:
- SSD1306
- 128×32
- I²C `0x3C`
- MUX `0x1F`
- COM Pins `0x02`
- Page `0..3`
- 卖家同源 5×7 点阵字体
- 4行:`0 / 8 / 16 / 24`
主页:
```text
CPU 18.6% MEM 16.2%
TMP 46.3C FAN OFF
DSK 22.4% NET OK
IP4 192.168.89.130
```
IPv6 地址时自动显示 `IP6`。
主页左右两栏都是固定位置、左对齐。数据默认每秒刷新。
有告警时,OLED 会在 HOME 与所有当前告警之间轮播;默认每页停留10秒。
### 风扇
默认:
```text
< 50°C OFF
50~53°C L1
53~56°C L2
56~59°C L3
59~62°C L4
>= 62°C MAX
```
带降档回差,避免临界温度反复升降档。
### RGB 告警
正常状态 RGB 完全熄灭。
颜色表示“什么对象出问题”:
```text
CPU 黄
温度 红
内存 紫
磁盘 橙
网络 蓝
服务/进程 青
```
所有告警都使用闪烁;闪烁速度表示严重程度:
```text
Warning 慢
Critical 中
Emergency 快
```
亮度可配置,默认10%,适合暗环境。
### Dark Mode
默认关闭 Raspberry Pi 自身:
- PWR LED
- ACT LED
散热板 D1/D8 黄色硬件状态灯和独立电源模块绿色灯不属于已确认的软件控制接口,本程序不操作。
---
## 2. 全新 Raspberry Pi OS 安装
### 第一步:启用 I²C
```bash
sudo raspi-config
```
进入:
```text
Interface Options
→ I2C
→ Enable
```
然后:
```bash
sudo reboot
```
### 第二步:解压本安装包
进入解压后的目录:
```bash
cd pigway-pi-control-v3.1.0
```
### 第三步:安装
### Installation
```bash
sudo ./install.sh
# Explicitly enable the API:
sudo ./install.sh --enable-api
# Keep the API disabled:
sudo ./install.sh --disable-api
```
安装器会:
Interactive installation asks whether to enable the remote API and defaults to no. Non-interactive installation also keeps it disabled unless explicitly enabled. `--no-start` only updates files and configuration; it does not change the current service state.
1. 检查 `/dev/i2c-1`
2. 等待 APT/DPKG 锁
3. 安装必要的小型系统依赖
4. 检查 I²C 总线
5. 自动停止并禁用卖家旧 `temp-control.service`
6. 安装正式程序
7. 安装用户配置
8. 安装 systemd 服务并开机自启
9. 执行安装后自检
安装成功后查看:
The configuration file is `/etc/pigway-pi-control.conf`. Restart the Agent after changing monitoring settings:
```bash
systemctl status pigway-pi-control --no-pager -l
sudo systemctl restart pigway-pi-control.service
```
---
### Optional API
## 3. 安装后的文件在哪里
### 用户应该修改
只有:
```text
/etc/pigway-pi-control.conf
```
编辑:
The default is `[api] enabled = false`, with no network listener. To use centralized management, enable it and configure the bind address and port, then run:
```bash
sudo nano /etc/pigway-pi-control.conf
sudo systemctl enable --now pigway-pi-control-api.service
sudo cat /etc/pigway-pi-control-api.token
```
保存后:
The default port is 6001. Every read and write request requires `Authorization: Bearer <token>`. The token belongs only to this device and is not printed directly by the installer. The API exposes health, status, logs, configuration, services, plugins, and plugin configuration under `/api/v1`. It does not serve a Web UI, register multiple machines, or proxy remote requests.
### Console and hardware plugins
- [PIGWay Device Console](https://tea.pigway.com/way/pigway-device-console) can run on a NAS or remote server for dashboards, configuration, and batch synchronization.
- [PIGWay Yahboom Cooling HAT](https://tea.pigway.com/way/pigway-yahboom-cooling-hat) independently provides local telemetry, OLED, fan control, and RGB effects.
The remote API and local plugin integration are independent. After enabling plugin integration, register `yahboom-cooling-hat = /run/pigway-plugins/yahboom-cooling-hat/api.sock` under `[plugins]` and restart the Agent, or attach it through the Console. Discovery never binds a plugin automatically. Pausing or disconnecting integration does not stop the plugin's local functions.
### Operations
```bash
sudo systemctl restart pigway-pi-control
sudo /usr/local/sbin/pigway-pi-control --diagnose
sudo journalctl -u pigway-pi-control.service -f
```
### 用户通常不要修改
程序:
```text
/usr/local/sbin/pigway-pi-control
```
systemd:
```text
/etc/systemd/system/pigway-pi-control.service
```
这些由安装包维护。
因此安装成功后,解压出来的 `pigway-pi-control-v3.1.0/` 文件夹可以删除。
建议把 ZIP 保存到 Mac / NAS,供以后重装。
---
## 4. 用户可以自定义什么
全部集中在:
```text
/etc/pigway-pi-control.conf
```
其中包括:
- 数据采样周期
- OLED刷新周期
- 告警页面停留时间
- 网络检查周期
- 服务检查周期
- 风扇温度曲线
- 风扇降档回差
- CPU告警阈值和持续时间
- 内存告警阈值和持续时间
- 温度普通/严重告警
- 磁盘普通/严重告警
- RGB亮度
- Warning/Critical/Emergency 闪烁周期
- Pi PWR/ACT灯
- 要监控的systemd服务
- 要监控的普通进程
**每个参数在配置文件中都已经写有详细中文注释。**
---
## 5. 增加一个服务监控
编辑:
```bash
sudo nano /etc/pigway-pi-control.conf
```
找到:
```ini
[services]
SSH = ssh.service
AWESUN = runawesun.service
```
例如安装了 Tailscale:
```ini
TAILSCALE = tailscaled.service
```
保存后:
```bash
sudo systemctl restart pigway-pi-control
```
先确认服务真实名称:
```bash
systemctl status tailscaled.service
```
暂时不想监控,行首加 `#`:
```ini
# TAILSCALE = tailscaled.service
```
---
## 6. 监控没有 systemd service 的程序
配置:
```ini
[processes]
MYAPP = /opt/myapp/server
```
先测试:
```bash
pgrep -af '/opt/myapp/server'
```
能找到进程再加入监控。
---
## 7. 常用维护
状态:
```bash
systemctl status pigway-pi-control --no-pager -l
```
日志:
```bash
journalctl -u pigway-pi-control -f
```
重启:
```bash
sudo systemctl restart pigway-pi-control
```
停止:
```bash
sudo systemctl stop pigway-pi-control
```
启动:
```bash
sudo systemctl start pigway-pi-control
```
查看配置:
```bash
cat /etc/pigway-pi-control.conf
```
---
## 8. 升级
新版安装包直接:
```bash
sudo ./install.sh
```
安装器会保留用户已有的 `[services]` 和 `[processes]` 监控列表,并备份旧配置。
升级后检查:
```bash
systemctl status pigway-pi-control --no-pager -l
```
---
## 9. 卸载
在安装包目录执行:
```bash
sudo ./uninstall.sh
```
卸载程序默认保留:
```text
/etc/pigway-pi-control.conf
```
避免误删用户自定义配置。
确认以后不再使用时可手工删除:
```bash
sudo rm /etc/pigway-pi-control.conf
```
---
## 10. 重装树莓派时最短流程
以后即使完全忘记之前怎么安装,只需要:
```text
1. 安装 Raspberry Pi OS
2. raspi-config 开启 I²C
3. 重启
4. 解压本 ZIP
5. cd pigway-pi-control-v3.1.0
6. sudo ./install.sh
```
完成。
Logs follow the system journal retention policy; no additional database is created. Uninstalling one project never uninstalls either of the others. See [Plugin API v1](docs/HARDWARE_PLUGIN_API.md).
+53
View File
@@ -0,0 +1,53 @@
# PIGWay Device Agent v3.7.0
简体中文 | [English](README.md)
极轻的 Raspberry Pi / Linux 本地监控服务:CPU、内存、温度、磁盘、网络、服务/进程、系统健康告警与 journal 日志。无 Web 界面;无需硬件插件,也无需管理中心。
## 安装
```bash
sudo ./install.sh
# 显式启用 API:
sudo ./install.sh --enable-api
# 不启用 API:
sudo ./install.sh --disable-api
```
交互安装询问是否启用远程 API,默认否;非交互安装未指定时也关闭。`--no-start` 仅更新文件和配置,不改变现有服务运行状态,接口开关在下次启动生效。
配置文件:`/etc/pigway-pi-control.conf`。修改监控配置后执行:
```bash
sudo systemctl restart pigway-pi-control.service
```
## 可选 API
默认 `[api] enabled = false`,没有网络监听。需要集中管理时改为 `true`,设置 bind/port,然后:
```bash
sudo systemctl enable --now pigway-pi-control-api.service
sudo cat /etc/pigway-pi-control-api.token
```
默认端口6001。读取及写入都需要 `Authorization: Bearer <token>`。令牌只用于该设备;安装器显示查询方法,不直接显示令牌内容。关闭 API:配置改为 false,执行 `sudo systemctl disable --now pigway-pi-control-api.service`。
API 提供 `/api/v1/health`、`/status`、`/logs`、`/config`、`/services`、`/plugins` 和 `/plugin/config`(均以 `/api/v1` 开头)。不提供网页、多机登记或远程转发。
## 独立管理中心与插件
- [PIGWay Device Console](https://tea.pigway.com/way/pigway-device-console):可部署在 NAS 或远端,登记设备地址与令牌,统一看板、配置和批量同步。
- [PIGWay Yahboom Cooling HAT](https://tea.pigway.com/way/pigway-yahboom-cooling-hat):独立本地采集、OLED、风扇与 RGB。
远程 API 与本地插件联动相互独立。插件启用接入后,可在 `[plugins]` 显式登记 `yahboom-cooling-hat = /run/pigway-plugins/yahboom-cooling-hat/api.sock` 并重启监控,或通过管理中心接入。发现不会自动绑定;暂停/断开联动不停止插件本地功能。
## 运维
```bash
sudo /usr/local/sbin/pigway-pi-control --diagnose
sudo journalctl -u pigway-pi-control.service -f
```
日志依照系统 journal 的保留策略,不额外建库。卸载任何一个项目不会卸载另外两个项目。插件协议见 [API v1](docs/HARDWARE_PLUGIN_API.md)。
+11 -7
View File
@@ -1,7 +1,11 @@
ef212ae05c0fedd3d8b9e83b6a7d0c7f2bff08a9292c306ce081f04c50fc1998 README.md
72c46162c33f9587c6ccb01ad53fbaaf4ecec8cd21014b909e87e8707e253e36 app/oled_font_5x7.bin
0cc9404165553e873e54980b2becd32fbe6dcf19460983aee98ec04fd67e4e88 app/pigway_pi_control.py
48eca3a160da8cb0dd3fdbbc66880ac61098ed2389b1c31954f5a98d8f914086 config/pigway-pi-control.conf
7ec3e507169ab82234897dcf39569a8c82dfa07089ba1a30cfbe0e4d07b7a38c install.sh
81aea0a89b298b2512fcb9bf6418618ba7a66474d425390cf95a0128c4093474 systemd/pigway-pi-control.service
a3d74973cafbabaf58a660a8c83d28347d1c06d9fd2dab3ecfce5b7607f6fee2 uninstall.sh
7ed31dd9c626c8d3b576fb7976e7c75f2ed1e6f32cbc73c517e608831e440c6e README.md
ddb6c2fb89001f0a7c2736534cc0b125ee4563ea2fc4f8d001752f5866f81e6f README.zh-CN.md
0f1ebcb0e9fa63744fcf0c0045fe4db3fa6eedcf22c333b46d6079d9105fad5c app/pigway_pi_control.py
f91af58e7dd752fa97c168ae419e14e6ee5099ea58d8252568f7ce72affd219f app/pigway_pi_control_api.py
3a8a368bbf299eb2d6cccc968a4aacf070058bddebdc5176083a97ac579d720d app/plugin_api.py
60665659712a0c7311e7bfa8fd09b300b0ea164cf53746feda91c7cc2a28145d config/pigway-pi-control.conf
e3bf3e7070ea62c0526791bed922688c3fb49fee36ca9c375d080119968feb72 docs/HARDWARE_PLUGIN_API.md
5223c7b71c8d18b3dd9b946a24f398b80afd0bf115e1273bac0f01df8e2ce46d install.sh
5e16c1d5d592fa3e129cde0077da6b089784c82f452205a349d4824f48eb3a66 systemd/pigway-pi-control-api.service
35ec68e1c3040e7affad43961fbb77e9e29f3474b92aed1005502629f9acb549 systemd/pigway-pi-control.service
9f59e7313ee58e687ae6dd29d175c67082674254ac5c5f54168b2735b64c20a4 uninstall.sh
Binary file not shown.
+394 -264
View File
@@ -1,91 +1,114 @@
#!/usr/bin/env python3
import os,time,socket,subprocess,configparser,signal
import time,socket,subprocess,configparser,signal,re,argparse,json,os,platform
from pathlib import Path
APP_VERSION="3.1.0"
from smbus2 import SMBus
from PIL import Image
APP_VERSION="3.7.0"
import sys
sys.path.append("/usr/local/share/pigway-pi-control")
from shutil import disk_usage
from plugin_api import Publisher,registered,discover
OLED=0x3C; MCU=0x0D; W,H=128,32
CFG="/etc/pigway-pi-control.conf"
STATUS_PATH="/run/pigway-pi-control/status.json"
running=True
def stop(*_):
global running; running=False
signal.signal(signal.SIGTERM,stop); signal.signal(signal.SIGINT,stop)
bus=SMBus(1)
FONT_PATH="/usr/local/share/pigway-pi-control/oled_font_5x7.bin"
FONT5=Path(FONT_PATH).read_bytes()
fan_level=0
def log(level,event,**fields):
parts=[f"level={level}",f"event={event}"]
for k,v in fields.items(): parts.append(f"{k}={str(v).replace(chr(32),'_')}")
print(" ".join(parts),flush=True)
def uptime_seconds():
try:return int(float(Path("/proc/uptime").read_text().split()[0]))
except Exception:return 0
def load_average():
try:
x=Path("/proc/loadavg").read_text().split();return (float(x[0]),float(x[1]),float(x[2]))
except Exception:return (0.0,0.0,0.0)
def memory_usage():
try:
values={}
for line in Path("/proc/meminfo").read_text().splitlines():
key,value=line.split(":",1); values[key]=int(value.split()[0])*1024
total=values["MemTotal"]; available=values.get("MemAvailable",values.get("MemFree",0))
used=max(0,total-available)
return total,used,available,(used*100.0/total if total else 0.0)
except Exception:return 0,0,0,0.0
def wifi_percent(metric):
try:return max(0,min(100,round((float(metric)+100.0)*2.0)))
except Exception:return None
def device_details():
info={}
try:
for line in Path("/proc/cpuinfo").read_text().splitlines():
if ":" in line:
key,value=(x.strip() for x in line.split(":",1))
if key in ("Serial","Revision","Hardware","Model"): info[key.lower()]=value
except Exception: pass
try: info["model"]=Path("/proc/device-tree/model").read_bytes().rstrip(b"\0").decode()
except Exception: pass
# Device tree identifies ARM boards; DMI covers PCs and many other vendors.
for key,files in {
"manufacturer":["/sys/class/dmi/id/sys_vendor"],
"model":["/sys/firmware/devicetree/base/model","/sys/class/dmi/id/product_name"],
"revision":["/sys/class/dmi/id/product_version","/sys/class/dmi/id/board_version"],
"serial":["/sys/class/dmi/id/product_serial"],
}.items():
if info.get(key):continue
for filename in files:
try:value=Path(filename).read_text().strip().strip("\0")
except (OSError,UnicodeError):continue
if value and value.lower() not in ("none","unknown","default string","to be filled by o.e.m."):
info[key]=value;break
if not info.get("manufacturer"):
try:info["manufacturer"]=Path("/sys/firmware/devicetree/base/compatible").read_bytes().split(b"\0")[0].decode().split(',')[0]
except (OSError,UnicodeError):pass
try:
os_release={}
for line in Path("/etc/os-release").read_text().splitlines():
if "=" in line:
key,value=line.split("=",1); os_release[key]=value.strip().strip('"')
info["os"]=os_release.get("PRETTY_NAME",platform.platform())
except Exception: info["os"]=platform.platform()
info.update({"hostname":socket.gethostname(),"kernel":platform.release(),
"architecture":platform.machine(),"cpu_count":os.cpu_count() or 0})
return info
def cpu_freq_mhz():
for q in ("/sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq","/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq"):
try:return int(Path(q).read_text().strip())/1000.0
except Exception:pass
return 0.0
def root_readonly():
try:
for line in Path("/proc/mounts").read_text().splitlines():
a=line.split()
if len(a)>=4 and a[1]=="/":return "ro" in a[3].split(",")
except Exception:pass
return False
def throttled_state():
raw=_run(["vcgencmd","get_throttled"])
m=re.search(r"0x([0-9a-fA-F]+)",raw);v=int(m.group(1),16) if m else 0
if not m: return {"raw":"UNKNOWN","error":"vcgencmd get_throttled unavailable or invalid"}
return {"raw":f"0x{v:x}","under_voltage_now":bool(v&1),"freq_capped_now":bool(v&2),"throttled_now":bool(v&4),"soft_temp_limit_now":bool(v&8),"under_voltage_occurred":bool(v&(1<<16)),"freq_capped_occurred":bool(v&(1<<17)),"throttled_occurred":bool(v&(1<<18)),"soft_temp_limit_occurred":bool(v&(1<<19))}
prev_cpu=None
page=0; page_since=time.monotonic()
cpu_hi=mem_hi=0
net_ok=link_ok=True
ip="NO IP"
net_iface=""; net_kind="NET"; net_metric="DOWN"; ip_label="IP4"; ip="NO IP"
wifi_weak_since=None; wifi_weak_active=False
last_net=last_watch=0
watch_state=[]
def cmd(c): bus.write_byte_data(OLED,0x00,c)
def oled_init():
# Seller-native physical 128x32 configuration.
for c in [0xAE,0xD5,0x80,0xA8,0x1F,0xD3,0x00,0x40,0x8D,0x14,
0x20,0x00,0xA1,0xC8,0xDA,0x02,0x81,0x7F,0xD9,0xF1,
0xDB,0x40,0xA4,0xA6,0xAF]:
cmd(c)
def draw_text_5x7(pix,x,y,text):
for ch in text:
code=ord(ch)
if code<0 or code>255: code=ord("?")
off=code*5
if off+5>len(FONT5): code=ord("?"); off=code*5
for cx in range(5):
col=FONT5[off+cx]
for cy in range(7):
if col & (1<<cy):
xx=x+cx; yy=y+cy
if 0<=xx<W and 0<=yy<H: pix[xx,yy]=1
x+=6
if x>W-6: break
def oled_show(lines_lr, title_zh=False):
im=Image.new("1",(W,H),0); pix=im.load()
for row,(left,right) in enumerate(lines_lr[:4]):
y=row*8
draw_text_5x7(pix,0,y,left)
if right:
draw_text_5x7(pix,max(0,W-len(right)*6),y,right)
data=[]
for pg in range(4):
for x in range(W):
v=0
for bit in range(8):
if pix[x,pg*8+bit]: v|=1<<bit
data.append(v)
cmd(0x21);cmd(0);cmd(127);cmd(0x22);cmd(0);cmd(3)
for i in range(0,len(data),16):
bus.write_i2c_block_data(OLED,0x40,data[i:i+16])
def mcu(reg,val): bus.write_byte_data(MCU,reg,val)
_last_rgb=None
def rgb_off():
global _last_rgb
if _last_rgb != ("off",):
mcu(0x07,0x00) # seller closeRGB(): true OFF
_last_rgb=("off",)
def rgb(r,g,b):
global _last_rgb
scale=max(0,min(100,LED_BRIGHT))/100.0
state=(int(r*scale),int(g*scale),int(b*scale))
if _last_rgb==state: return
mcu(0x07,0x00) # stop built-in effect first
mcu(0x00,0xff) # seller protocol: >=3 => all three LEDs
mcu(0x01,state[0]); mcu(0x02,state[1]); mcu(0x03,state[2])
_last_rgb=state
def set_pi_led(name,off=True):
base=Path("/sys/class/leds")/name
try:
@@ -99,24 +122,6 @@ def apply_dark_mode():
if DARK_PWR: set_pi_led("PWR",True)
if DARK_ACT: set_pi_led("ACT",True)
FAN_REG=[0x00,0x04,0x06,0x08,0x09,0x01]
FAN_NAME=["OFF","L1","L2","L3","L4","MAX"]
def fan_target(t):
if t<FAN_T[0]: return 0
if t<FAN_T[1]: return 1
if t<FAN_T[2]: return 2
if t<FAN_T[3]: return 3
if t<FAN_T[4]: return 4
return 5
def update_fan(t):
global fan_level
want=fan_target(t); old=fan_level
if want>fan_level: fan_level=want
elif want<fan_level:
boundary = FAN_T[max(0,fan_level-1)] - FAN_HYST
if t < boundary: fan_level-=1
if old!=fan_level: mcu(0x08,FAN_REG[fan_level])
def cpu_pct():
global prev_cpu
p=list(map(int,Path("/proc/stat").read_text().splitlines()[0].split()[1:9]))
@@ -133,10 +138,36 @@ def mem_pct():
return 100*(vals["MemTotal"]-vals["MemAvailable"])/vals["MemTotal"]
def disk_pct():
d=disk_usage("/"); return 100*d.used/d.total
def _run(args,timeout=2):
try: return subprocess.check_output(args,text=True,stderr=subprocess.DEVNULL,timeout=timeout).strip()
except Exception: return ""
def primary_network():
out=_run(["ip","-4","route","get","1.1.1.1"])
dev=re.search(r"\bdev\s+(\S+)",out); src=re.search(r"\bsrc\s+(\S+)",out); label="IP4"
if not dev:
out=_run(["ip","-6","route","get","2606:4700:4700::1111"])
dev=re.search(r"\bdev\s+(\S+)",out); src=re.search(r"\bsrc\s+(\S+)",out); label="IP6"
if not dev: return "","NET","DOWN","IP4","NO IP"
iface=dev.group(1); ipval=src.group(1) if src else ""
if Path(f"/sys/class/net/{iface}/wireless").exists():
kind="WIF"; metric="--"
try:
for line in Path("/proc/net/wireless").read_text().splitlines():
if line.lstrip().startswith(iface+":"):
metric=str(int(float(line.split()[3].rstrip(".")))); break
except Exception: pass
else:
kind="ETH"; metric="UP"
try:
n=int(Path(f"/sys/class/net/{iface}/speed").read_text().strip())
metric=f"{n//1000}G" if n>=1000 and n%1000==0 else str(n)
except Exception: pass
return iface,kind,metric,label,(ipval or "NO IP")
def get_ip():
try:
s=socket.socket(socket.AF_INET,socket.SOCK_DGRAM);s.connect(("1.1.1.1",53));v=s.getsockname()[0];s.close();return v
except: return "NO IP"
return primary_network()[4]
def internet():
try:
s=socket.create_connection(("1.1.1.1",53),0.5);s.close();return True
@@ -148,7 +179,9 @@ def load_cfg():
if c.has_section("services"):
for label,target in c["services"].items():
target=target.strip()
if target and not target.startswith("#"): watches.append(("service",label.upper(),target))
paused=c.getboolean("service_monitor_disabled",label,fallback=False)
if target and not target.startswith("#") and not paused:
watches.append(("service",label.upper(),target))
if c.has_section("processes"):
for label,target in c["processes"].items():
target=target.strip()
@@ -160,11 +193,15 @@ def cf(section,key,default,cast=float):
try: return cast(cfg.get(section,key))
except: return default
DEVICE_ID=cf("device","identifier","auto",str).strip()
if not DEVICE_ID or DEVICE_ID.lower()=="auto": DEVICE_ID=socket.gethostname()
DEVICE_NAME=cf("device","name",DEVICE_ID,str).strip() or DEVICE_ID
if DEVICE_NAME.lower()=="auto": DEVICE_NAME=DEVICE_ID
DEVICE_INFO=device_details()
SENSOR_INTERVAL=cf("timing","sensor_interval",1.0)
OLED_REFRESH=cf("timing","oled_refresh_interval",1.0)
PAGE_INTERVAL=cf("timing","page_interval",10.0)
NETWORK_INTERVAL=cf("timing","network_interval",5.0)
SERVICE_INTERVAL=cf("timing","service_interval",5.0)
HEALTH_INTERVAL=cf("timing","health_interval",1.0)
CPU_HIGH=cf("alerts","cpu_high",90.0)
CPU_RECOVER=cf("alerts","cpu_recover",75.0)
@@ -176,192 +213,285 @@ TEMP_HIGH=cf("alerts","temp_high",68.0)
TEMP_CRIT=cf("alerts","temp_critical",75.0)
DISK_HIGH=cf("alerts","disk_high",90.0)
DISK_CRIT=cf("alerts","disk_critical",95.0)
WIFI_WEAK=cf("alerts","wifi_weak",-75.0)
WIFI_RECOVER=cf("alerts","wifi_recover",-68.0)
WIFI_WEAK_SECONDS=cf("alerts","wifi_weak_seconds",30.0)
FAN_T=[cf("fan","start",50.0),cf("fan","level2",53.0),cf("fan","level3",56.0),
cf("fan","level4",59.0),cf("fan","max",62.0)]
FAN_HYST=cf("fan","hysteresis",1.5)
ROW_Y=[cf("display","row1_y",0,int),cf("display","row2_y",8,int),cf("display","row3_y",16,int),cf("display","row4_y",24,int)]
DARK_PWR=cf("dark_mode","pi_pwr_led",True,lambda x: str(x).strip().lower() in ("off","0","false","no"))
DARK_ACT=cf("dark_mode","pi_act_led",True,lambda x: str(x).strip().lower() in ("off","0","false","no"))
LED_BRIGHT=cf("led","brightness",10,int)
LED_WARN_ON=cf("led","warning_on_ms",300,int); LED_WARN_OFF=cf("led","warning_off_ms",2700,int)
LED_CRIT_ON=cf("led","critical_on_ms",400,int); LED_CRIT_OFF=cf("led","critical_off_ms",1100,int)
LED_EMERG_ON=cf("led","emergency_on_ms",400,int); LED_EMERG_OFF=cf("led","emergency_off_ms",400,int)
ALERT_CATEGORIES={
"ROOT_READONLY":"STORAGE",
"TEMP_CRITICAL":"CPU","TEMP_HIGH":"CPU","SOFT_TEMP_LIMIT":"CPU",
"THROTTLED":"CPU","FREQ_CAPPED":"CPU","CPU_HIGH":"CPU",
"POWER_UNDERVOLT":"POWER",
"MEMORY_HIGH":"MEMORY",
"DISK_CRITICAL":"STORAGE","DISK_HIGH":"STORAGE",
"NETWORK_DOWN":"NETWORK","INTERNET_DOWN":"NETWORK","WIFI_WEAK":"NETWORK",
"SERVICE_DOWN":"SERVICE","PROCESS_DOWN":"SERVICE",
}
def check_watch(w):
typ,label,target=w
if typ=="service":
r=subprocess.run(["systemctl","is-active","--quiet",target])
else:
r=subprocess.run(["pgrep","-f",target],stdout=subprocess.DEVNULL)
return r.returncode==0
def alert(title,l2="",l3="",l4="",sev=1,color=(20,16,0),blink=0):
return {"title":title[:21],"l2":l2[:21],"l3":l3[:21],"l4":l4[:21],
"sev":sev,"color":color,"blink":blink}
def make_alerts(cpu,temp,mem,disk):
global cpu_hi,mem_hi
a=[]
cpu_hi=cpu_hi+1 if cpu>=CPU_HIGH else 0 if cpu<CPU_RECOVER else cpu_hi
mem_hi=mem_hi+1 if mem>=MEM_HIGH else 0 if mem<MEM_RECOVER else mem_hi
if cpu_hi>=CPU_HIGH_SEC:a.append(alert("CPU LOAD HIGH",f"LOAD {cpu:.1f}%",f"TEMP {temp:.1f}C","FOR >=30 SEC",1,(24,18,0)))
if temp>=TEMP_CRIT:a.append(alert("TEMP CRITICAL",f"TEMP {temp:.1f}C",f"FAN {FAN_NAME[fan_level]}","CHECK COOLING",3,(32,0,0),2))
elif temp>=TEMP_HIGH:a.append(alert("TEMP HIGH",f"TEMP {temp:.1f}C",f"FAN {FAN_NAME[fan_level]}","CHECK COOLING",1,(24,0,0)))
if mem_hi>=MEM_HIGH_SEC:a.append(alert("MEMORY HIGH",f"USED {mem:.1f}%","CHECK PROCESS","",1,(18,0,24)))
if disk>=DISK_CRIT:a.append(alert("DISK CRITICAL",f"USED {disk:.1f}%","FREE < 5%","CHECK STORAGE",2,(28,6,0),2))
elif disk>=DISK_HIGH:a.append(alert("DISK SPACE LOW",f"USED {disk:.1f}%","FREE < 10%","CHECK STORAGE",1,(28,8,0)))
if not link_ok:a.append(alert("NETWORK DOWN","NO LAN / WIFI","NO IP ADDRESS","",2,(0,8,28),1))
elif not net_ok:a.append(alert("INTERNET DOWN","LOCAL LINK OK",ip,"",2,(0,8,28),1))
for w,ok in zip(watches,watch_state):
if not ok:a.append(alert("SERVICE DOWN",w[1],"CHECK / RESTART","",2,(0,24,24),1))
a.sort(key=lambda x:x["sev"],reverse=True)
return a
def led_for(a):
# Color = fault object. Blink frequency = severity. All alerts blink.
if not a:
rgb_off(); return
if a["sev"]>=3: on_ms,off_ms=LED_EMERG_ON,LED_EMERG_OFF
elif a["sev"]>=2: on_ms,off_ms=LED_CRIT_ON,LED_CRIT_OFF
else: on_ms,off_ms=LED_WARN_ON,LED_WARN_OFF
cycle=max(1,on_ms+off_ms)
phase=int(time.monotonic()*1000)%cycle
rgb(*a["color"]) if phase<on_ms else rgb_off()
def render_home(cpu,temp,mem,disk):
# 128x32 fixed columns. Both columns are LEFT-aligned.
# Seller 5x7 font has 6px character pitch; right column starts at x=72.
im=Image.new("1",(W,H),0); pix=im.load()
left=[
f"CPU {cpu:.1f}%",
f"TMP {temp:.1f}C",
f"DSK {disk:.1f}%",
("IP6 " if ":" in ip else "IP4 ")+ip,
]
right=[
f"MEM {mem:.1f}%",
f"FAN {FAN_NAME[fan_level]}",
f"NET {'OK' if net_ok else 'DOWN'}",
"",
]
for row in range(4):
y=row*8
draw_text_5x7(pix,0,y,left[row])
if right[row]:
draw_text_5x7(pix,72,y,right[row])
data=[]
for pg in range(4):
for x in range(W):
v=0
for bit in range(8):
if pix[x,pg*8+bit]: v|=1<<bit
data.append(v)
cmd(0x21);cmd(0);cmd(127);cmd(0x22);cmd(0);cmd(3)
for i in range(0,len(data),16):
bus.write_i2c_block_data(OLED,0x40,data[i:i+16])
def render_alert(a,idx,total):
oled_show([(a["title"],f"{idx}/{total}"),
(a["l2"],""),(a["l3"],""),(a["l4"],"")])
oled_init(); rgb_off(); apply_dark_mode()
watch_state=[check_watch(w) for w in watches]
last_sensor=last_render=0.0
last_net=last_watch=time.monotonic()
latest=(0.0,0.0,0.0,0.0)
active=[]
# Page state is a snapshot queue. Live sensor refreshes NEVER choose another page.
# Each cycle is HOME + every alert captured at the cycle boundary.
cycle_pages=["HOME"]
cycle_pos=0
page_started=time.monotonic()
current_alert_key=None
def alert_key(a):
# Stable identity: title + monitored object/primary detail.
return f"{a['title']}|{a['l2']}"
def find_live_alert(key, live):
for a in live:
if alert_key(a)==key: return a
return None
while running:
args=["systemctl","is-active","--quiet",target] if typ=="service" else ["pgrep","-f","--",target]
try:
now=time.monotonic()
r=subprocess.run(args,stdout=subprocess.DEVNULL,stderr=subprocess.DEVNULL,timeout=2)
return r.returncode==0
except (OSError,subprocess.TimeoutExpired):
return False
# Independent clocks: update data/state only.
if now-last_sensor >= SENSOR_INTERVAL:
c=cpu_pct(); t=temp_c(); m=mem_pct(); d=disk_pct()
latest=(c,t,m,d); update_fan(t); last_sensor=now
def diagnose():
print("Agent:")
print(f"version={APP_VERSION} uptime_seconds={uptime_seconds()} config={CFG}")
print(f"machine_id={DEVICE_ID} machine_name={DEVICE_NAME} hostname={socket.gethostname()}")
print("loop_errors=UNAVAILABLE scope=separate_diagnostic_process")
print("System:")
print(f"load_average={load_average()} cpu_freq_mhz={cpu_freq_mhz():.0f} root_readonly={root_readonly()}")
print("Power:")
power=throttled_state()
print("throttled="+power["raw"])
for key in ("under_voltage_now","freq_capped_now","throttled_now","soft_temp_limit_now",
"under_voltage_occurred","freq_capped_occurred","throttled_occurred","soft_temp_limit_occurred"):
print(f"{key}={power.get(key,'UNKNOWN')}")
if "error" in power: print("error="+power["error"])
iface,kind,metric,label,address=primary_network()
print("Network:")
print(f"primary_interface={iface or 'NONE'} kind={kind} metric={metric} signal_percent={wifi_percent(metric) if kind=='WIF' else 'N/A'} ip_label={label} IP={address} internet={internet()}")
print("Plugins (read-only API discovery; no hardware access):")
for plugin in discover(cfg):
print(f"plugin={plugin['id']} linked={plugin['linked']} online={plugin['online']}")
print("Watches:")
for w in watches:
print(f"watch {w[1]}={'UP' if check_watch(w) else 'DOWN'} type={w[0]} target={w[2]}")
return 0
if now-last_net >= NETWORK_INTERVAL:
ip=get_ip(); link_ok=ip!="NO IP"; net_ok=internet() if link_ok else False
last_net=now
if now-last_watch >= SERVICE_INTERVAL:
watch_state=[check_watch(w) for w in watches]
last_watch=now
ALERT_PRIORITIES={
"ROOT_READONLY":100,
"TEMP_CRITICAL":90,
"SOFT_TEMP_LIMIT":85,
"POWER_UNDERVOLT":80,
"THROTTLED":75,
"FREQ_CAPPED":70,
"NETWORK_DOWN":65,
"INTERNET_DOWN":65,
"SERVICE_DOWN":60,
"PROCESS_DOWN":60,
"DISK_CRITICAL":55,
"TEMP_HIGH":50,
"CPU_HIGH":45,
"MEMORY_HIGH":45,
"DISK_HIGH":40,
"WIFI_WEAK":30,
"NORMAL_HOME":0,
}
c,t,m,d=latest
active=make_alerts(c,t,m,d)
def alert_priority(request_id):
return ALERT_PRIORITIES[request_id.split("|",1)[0]]
# If the currently displayed alert truly disappeared, skip it immediately.
if cycle_pages[cycle_pos]!="HOME":
key=cycle_pages[cycle_pos]
if find_live_alert(key,active) is None:
cycle_pos += 1
if cycle_pos>=len(cycle_pages):
# End of cycle: capture a fresh snapshot.
cycle_pages=["HOME"]+[alert_key(a) for a in active]
cycle_pos=0
page_started=now
def transition(key,active,on_event,off_event,**fields):
old=event_state.get(key,False)
if active!=old:
event_state[key]=active
log("WARN" if active else "INFO",on_event if active else off_event,**fields)
# ONLY this timer performs normal page changes.
if now-page_started >= PAGE_INTERVAL:
cycle_pos += 1
if cycle_pos>=len(cycle_pages):
# A complete cycle ended. Snapshot all currently active alerts.
cycle_pages=["HOME"]+[alert_key(a) for a in active]
cycle_pos=0
page_started=now
def update_active_alerts(cpu,temp,mem,disk,sample_elapsed=0.0):
global wifi_weak_since,wifi_weak_active
global cpu_hi,mem_hi
cpu_hi=cpu_hi+sample_elapsed if cpu>=CPU_HIGH else 0 if cpu<CPU_RECOVER else cpu_hi
mem_hi=mem_hi+sample_elapsed if mem>=MEM_HIGH else 0 if mem<MEM_RECOVER else mem_hi
if cpu_hi>=CPU_HIGH_SEC: alert_manager.request("CPU_HIGH",1,"CPU LOAD HIGH",f"LOAD {cpu:.1f}%",f"TEMP {temp:.1f}C","CHECK LOAD")
else: alert_manager.clear("CPU_HIGH")
if temp>=TEMP_CRIT:
alert_manager.request("TEMP_CRITICAL",3,"TEMP CRITICAL",f"TEMP {temp:.1f}C","CHECK COOLING","CHECK COOLING")
alert_manager.clear("TEMP_HIGH")
elif temp>=TEMP_HIGH:
alert_manager.request("TEMP_HIGH",1,"TEMP HIGH",f"TEMP {temp:.1f}C","CHECK COOLING","CHECK COOLING")
alert_manager.clear("TEMP_CRITICAL")
else:
alert_manager.clear("TEMP_HIGH"); alert_manager.clear("TEMP_CRITICAL")
if mem_hi>=MEM_HIGH_SEC: alert_manager.request("MEMORY_HIGH",1,"MEMORY HIGH",f"USED {mem:.1f}%","CHECK PROCESS","")
else: alert_manager.clear("MEMORY_HIGH")
if disk>=DISK_CRIT:
alert_manager.request("DISK_CRITICAL",2,"DISK CRITICAL",f"USED {disk:.1f}%","FREE < 5%","CHECK STORAGE")
alert_manager.clear("DISK_HIGH")
elif disk>=DISK_HIGH:
alert_manager.request("DISK_HIGH",1,"DISK SPACE LOW",f"USED {disk:.1f}%","FREE < 10%","CHECK STORAGE")
alert_manager.clear("DISK_CRITICAL")
else:
alert_manager.clear("DISK_HIGH"); alert_manager.clear("DISK_CRITICAL")
if not link_ok:
alert_manager.request("NETWORK_DOWN",2,"NETWORK DOWN","NO LAN / WIFI","NO IP ADDRESS","")
alert_manager.clear("INTERNET_DOWN")
elif not net_ok:
alert_manager.request("INTERNET_DOWN",2,"INTERNET DOWN","LOCAL LINK OK",ip,"")
alert_manager.clear("NETWORK_DOWN")
else:
alert_manager.clear("NETWORK_DOWN"); alert_manager.clear("INTERNET_DOWN")
for w,ok in zip(watches,watch_state):
alert_id=("SERVICE_DOWN" if w[0]=="service" else "PROCESS_DOWN")+"|"+w[1]
if not ok:
alert_manager.request(alert_id,2,"SERVICE DOWN" if w[0]=="service" else "PROCESS DOWN",w[1],"CHECK / RESTART","CRITICAL",{"target":w[2]})
else: alert_manager.clear(alert_id)
if net_kind=="WIF" and str(net_metric).lstrip("-").isdigit():
rssi=float(net_metric)
if not wifi_weak_active:
if rssi <= WIFI_WEAK:
if wifi_weak_since is None: wifi_weak_since=time.monotonic()
if time.monotonic()-wifi_weak_since >= WIFI_WEAK_SECONDS: wifi_weak_active=True
else: wifi_weak_since=None
elif rssi >= WIFI_RECOVER:
wifi_weak_active=False; wifi_weak_since=None
if wifi_weak_active:
alert_manager.request("WIFI_WEAK",1,"WIFI SIGNAL WEAK",f"RSSI {rssi:.0f} dBm",f"IF {net_iface}","CHECK SIGNAL")
else: alert_manager.clear("WIFI_WEAK")
else:
wifi_weak_since=None; wifi_weak_active=False; alert_manager.clear("WIFI_WEAK")
if health.get("under_voltage_now"):
alert_manager.request("POWER_UNDERVOLT",2,"POWER LOW","UNDERVOLTAGE","CHECK POWER","CRITICAL",{"raw":health.get("raw","")})
else: alert_manager.clear("POWER_UNDERVOLT")
if health.get("throttled_now"):
alert_manager.request("THROTTLED",2,"CPU THROTTLED",f"FREQ {cpu_freq_mhz():.0f}M",health.get("raw",""),"CHECK POWER")
else: alert_manager.clear("THROTTLED")
if health.get("freq_capped_now"):
alert_manager.request("FREQ_CAPPED",2,"FREQ CAPPED",f"FREQ {cpu_freq_mhz():.0f}M",health.get("raw",""),"CHECK POWER")
else: alert_manager.clear("FREQ_CAPPED")
if health.get("soft_temp_limit_now"):
alert_manager.request("SOFT_TEMP_LIMIT",2,"SOFT TEMP LIMIT","CPU TEMP LIMITED",health.get("raw",""),"CHECK COOLING")
else: alert_manager.clear("SOFT_TEMP_LIMIT")
if fs_readonly: alert_manager.request("ROOT_READONLY",3,"FILESYSTEM RO","ROOT READ ONLY","CHECK STORAGE","EMERGENCY")
else: alert_manager.clear("ROOT_READONLY")
# Special case: while idle on HOME with no alert pages queued, begin a new
# alert cycle immediately when the first alert appears. HOME keeps its
# current 10-second slot; alerts follow it and cannot be kicked out by refresh.
if cycle_pages==["HOME"] and active:
cycle_pages=["HOME"]+[alert_key(a) for a in active]
class AlertManager:
"""Current monitoring facts. Hardware plugins own all display decisions."""
def __init__(self):
self.requests={}
# Render CURRENT page only. 1-second refresh does not affect cycle_pos.
if now-last_render >= OLED_REFRESH:
current=cycle_pages[cycle_pos]
if current=="HOME":
render_home(c,t,m,d)
else:
a=find_live_alert(current,active)
if a:
# Number refers to this cycle's alert slot, all using same 6x8 font.
render_alert(a,cycle_pos,len(cycle_pages)-1)
else:
render_home(c,t,m,d)
last_render=now
def request(self,request_id,severity,title,l2="",l3="",l4="",metadata=None):
now=time.monotonic();old=self.requests.get(request_id)
value={"id":request_id,"priority":alert_priority(request_id),"severity":severity,
"category":ALERT_CATEGORIES[request_id.split("|",1)[0]].lower(),
"title":title[:21],"l2":l2[:21],"l3":l3[:21],"l4":l4[:21],
"first_seen":old["first_seen"] if old else now,"metadata":metadata or {}}
value["last_changed"]=old["last_changed"] if old and all(old[k]==v for k,v in value.items()) else now
self.requests[request_id]=value
if old is None:log("WARN","ALERT_ACTIVE",alert=request_id,severity=severity,detail=l2)
# LED follows OLED page; HOME reflects highest currently active risk.
current=cycle_pages[cycle_pos]
if current=="HOME":
led_for(active[0] if active else None)
else:
a=find_live_alert(current,active)
led_for(a if a else (active[0] if active else None))
def clear(self,request_id):
if self.requests.pop(request_id,None) is not None:log("INFO","ALERT_RECOVERED",alert=request_id)
time.sleep(0.20)
except Exception as e:
print("loop error:",e,flush=True); time.sleep(1)
def status_snapshot(self):
values=sorted(self.requests.values(),key=lambda a:(-a["priority"],a["first_seen"],a["id"]))
return {"owner":values[0]["id"] if values else "NORMAL_HOME","alerts":values}
rgb_off(); mcu(0x08,0x00); bus.close()
def cleanup():
publisher.close()
log("INFO","STOP",loop_errors=agent["loop_errors"])
try:Path(STATUS_PATH).unlink(missing_ok=True)
except Exception as e:log("ERROR","SHUTDOWN_CLEANUP",step="status_file",error=repr(e))
def write_status(cpu,temp,mem,disk):
display_state=alert_manager.status_snapshot()
memory_total,memory_used,memory_available,memory_calculated=memory_usage()
disk_total,disk_used,disk_free=disk_usage("/")
signal=wifi_percent(net_metric) if net_kind=="WIF" else None
state={
"version":APP_VERSION,"timestamp":int(time.time()),"uptime_seconds":uptime_seconds(),
"machine":{"id":DEVICE_ID,"name":DEVICE_NAME,"hostname":socket.gethostname()},
"device":DEVICE_INFO,
"system":{"load_average":load_average(),"cpu_percent":round(cpu,1),
"cpu_freq_mhz":round(cpu_freq_mhz()),"temperature_c":round(temp,1),
"memory_percent":round(memory_calculated if memory_total else mem,1),
"memory_total_bytes":memory_total,"memory_used_bytes":memory_used,
"memory_available_bytes":memory_available,
"disk_percent":round(disk,1),"disk_total_bytes":disk_total,
"disk_used_bytes":disk_used,"disk_free_bytes":disk_free,
"root_readonly":bool(fs_readonly)},
"power":health,
"network":{"interface":net_iface,"kind":net_kind,"metric":net_metric,
"signal_percent":signal,
"ip_label":ip_label,"ip":ip,"link":bool(link_ok),"internet":bool(net_ok)},
"watches":[{"type":w[0],"name":w[1],"target":w[2],"up":bool(ok)}
for w,ok in zip(watches,watch_state)],
"display":display_state,
"agent":{"loop_errors":agent["loop_errors"]},
"plugins":publisher.current_status(),
}
publisher.publish(state)
path=Path(STATUS_PATH); path.parent.mkdir(mode=0o755,parents=True,exist_ok=True)
temporary=path.with_suffix(".tmp")
temporary.write_text(json.dumps(state,ensure_ascii=False,separators=(",",":")))
temporary.chmod(0o644); temporary.replace(path)
# Dispatch only after all shared checks and configuration have been initialized.
parser=argparse.ArgumentParser()
parser.add_argument("--diagnose",action="store_true")
args=parser.parse_args()
if args.diagnose: raise SystemExit(diagnose())
watch_state=[]
last_sensor=last_status=0.0
last_net=last_watch=last_health=0.0
health={}; fs_readonly=False
agent={"last_sensor_ok":0.0,"last_network_ok":0.0,"last_watch_ok":0.0,"last_health_ok":0.0,"loop_errors":0}
event_state={}
history_logged=set()
latest=(0.0,0.0,0.0,0.0)
alert_manager=AlertManager()
publisher=Publisher({k:v for k,v in registered(cfg).items() if not cfg.getboolean("plugin_paused",k,fallback=False)},DEVICE_ID,log)
try:
apply_dark_mode()
log("INFO","START",version=APP_VERSION,uptime=uptime_seconds())
while running:
try:
now=time.monotonic()
sample_elapsed=0.0
# Independent clocks: update data/state only.
if now-last_sensor >= SENSOR_INTERVAL:
sample_elapsed=now-last_sensor if last_sensor else 0.0
c=cpu_pct(); t=temp_c(); m=mem_pct(); d=disk_pct()
latest=(c,t,m,d); last_sensor=now; agent["last_sensor_ok"]=now
if now-last_net >= NETWORK_INTERVAL:
old_id=(net_iface,ip)
net_iface,net_kind,net_metric,ip_label,ip=primary_network(); link_ok=ip!="NO IP"; net_ok=internet() if link_ok else False
new_id=(net_iface,ip)
if new_id!=old_id:
log("INFO","NET_SWITCH",old_if=old_id[0],old_ip=old_id[1],new_if=net_iface,new_ip=ip)
transition("network_down",not link_ok,"NETWORK_DOWN","NETWORK_RECOVERED",iface=net_iface,ip=ip)
transition("internet_down",link_ok and not net_ok,"INTERNET_DOWN","INTERNET_RECOVERED",iface=net_iface,ip=ip)
last_net=now; agent["last_network_ok"]=now
if now-last_watch >= SERVICE_INTERVAL:
watch_state=[check_watch(w) for w in watches]
for w,ok in zip(watches,watch_state):
transition("watch:"+w[0]+":"+w[1],not ok,"WATCH_DOWN","WATCH_RECOVERED",name=w[1],target=w[2])
last_watch=now; agent["last_watch_ok"]=now
if now-last_health >= HEALTH_INTERVAL:
power_sample=throttled_state(); fs_readonly=root_readonly()
transition("power_check", "error" in power_sample,"POWER_CHECK_ERROR","POWER_CHECK_RECOVERED")
# An unavailable reading is not evidence that an existing fault recovered.
if "error" not in power_sample: health=power_sample
transition("undervoltage",health.get("under_voltage_now",False),"POWER_LOW","POWER_RECOVERED",raw=health.get("raw"))
transition("throttled",health.get("throttled_now",False) or health.get("freq_capped_now",False),"THROTTLED","THROTTLE_RECOVERED",raw=health.get("raw"),freq_mhz=f"{cpu_freq_mhz():.0f}")
transition("soft_temp",health.get("soft_temp_limit_now",False),"SOFT_TEMP_LIMIT","SOFT_TEMP_RECOVERED",raw=health.get("raw"))
transition("root_ro",fs_readonly,"FILESYSTEM_RO","FILESYSTEM_RW")
for k in ("under_voltage_occurred","freq_capped_occurred","throttled_occurred","soft_temp_limit_occurred"):
if health.get(k) and k not in history_logged:
history_logged.add(k); log("WARN","HISTORY_FLAG",flag=k,raw=health.get("raw"))
agent["last_health_ok"]=now; last_health=now
c,t,m,d=latest
update_active_alerts(c,t,m,d,sample_elapsed)
if now-last_status >= 1.0:
write_status(c,t,m,d); last_status=now
time.sleep(0.20)
except Exception as e:
agent["loop_errors"]+=1; log("ERROR","LOOP_ERROR",count=agent["loop_errors"],error=repr(e)); time.sleep(1)
finally:
cleanup()
+398
View File
@@ -0,0 +1,398 @@
#!/usr/bin/env python3
import sys
sys.path.append("/usr/local/share/pigway-pi-control")
from plugin_api import discover,registered,request as plugin_request,socket_path
import configparser,ipaddress,json,re,secrets,shutil,subprocess,threading,time,socket
from concurrent.futures import ThreadPoolExecutor,as_completed
from http import HTTPStatus
from http.server import BaseHTTPRequestHandler,ThreadingHTTPServer
from pathlib import Path
from urllib.parse import parse_qs,urlencode,urlparse
from urllib.request import Request,urlopen
APP_VERSION="3.7.0"
CFG=Path("/etc/pigway-pi-control.conf")
STATUS=Path("/run/pigway-pi-control/status.json")
TOKEN=Path("/etc/pigway-pi-control-api.token")
ALLOWED_SECTIONS={"device","services","processes","alerts","timing","dark_mode","api"}
NAME_RE=re.compile(r"^[A-Za-z0-9_.-]{1,64}$")
UNIT_RE=re.compile(r"^[A-Za-z0-9_.@:-]{1,128}\.service$")
RGB_KEY_RE=re.compile(r"^(cpu|power|memory|storage|network|service|normal)_[rgb]$")
FLASH_KEY_RE=re.compile(r"^(warning|critical|emergency|normal)_flash_(on|off)_ms$")
NORMAL_MODES={"off","solid","flash","flow","breathe","marquee","rainbow","colorful"}
EFFECT_COLORS={"red","green","blue","yellow","purple","cyan","white"}
PROTECTED_UNITS={"pigway-pi-control-api.service"}
def plugin_inventory():
cfg=load_cfg();items=discover(cfg)
for item in items:item["paused"]=cfg.getboolean("plugin_paused",item["id"],fallback=False)
return items
def find_plugin(plugin_id):
for item in plugin_inventory():
if item["id"]==plugin_id:return item
raise ValueError("unknown plugin")
def plugin_operation(body):
plugin_id=str(body.get("id",""))
if not NAME_RE.fullmatch(plugin_id):raise ValueError("invalid plugin id")
item=find_plugin(plugin_id);operation=body.get("operation")
if operation=="link":
if not item["online"]:raise ValueError("plugin is offline")
text=replace_ini_value("plugins",plugin_id,socket_path(item["socket"]))
save_ini_text(text,"plugin-link")
text=replace_ini_value("plugin_paused",plugin_id,"false")
elif operation in {"pause","resume","unlink"}:
if not item["linked"]:raise ValueError("plugin is not linked")
text=replace_ini_value("plugins",plugin_id,None) if operation=="unlink" else replace_ini_value("plugin_paused",plugin_id,"true" if operation=="pause" else "false")
else:raise ValueError("invalid plugin operation")
backup=save_ini_text(text,"plugin")
# Only reload a monitor that is already running. Never start hardware here.
subprocess.run(["systemctl","try-restart","pigway-pi-control.service"],check=True,timeout=15)
if operation in {"pause","unlink"}:
try:plugin_request(item["socket"],"DELETE","/v1/state",{})
except Exception:pass # An offline plugin expires its lease independently.
return {"ok":True,"backup":backup}
def machine_identity():
cfg=load_cfg(); identifier=cfg.get("device","identifier",fallback="auto").strip()
if not identifier or identifier.lower()=="auto": identifier=socket.gethostname()
name=cfg.get("device","name",fallback=identifier).strip() or identifier
if name.lower()=="auto": name=identifier
return {"id":identifier,"name":name,"hostname":socket.gethostname(),"local":True,"url":""}
def load_cfg():
cfg=configparser.ConfigParser(); cfg.read(CFG)
return cfg
def api_setting(key,default,cast=str):
try:return cast(load_cfg().get("api",key))
except Exception:return default
def config_json():
cfg=load_cfg()
return {section:{k:v for k,v in cfg.items(section) if not (section=="timing" and k in {"oled_refresh_interval","page_interval"})} for section in cfg.sections() if section in ALLOWED_SECTIONS}
def validate_value(section,key,value,existing):
if section=="api" and key=="enabled":
if value.lower() not in {"true","false"}:raise ValueError("enabled must be true or false")
return
if section=="timing" and key in {"oled_refresh_interval","page_interval"}:raise ValueError("display timing is managed by the hardware plugin")
if section not in {"services","processes"} and key not in existing.get(section,set()):
raise ValueError(f"unsupported option: {section}.{key}")
if section=="hardware" and key=="cooling_hat_enabled":
if value.lower() not in ("true","false"): raise ValueError("cooling_hat_enabled must be true or false")
elif section=="led" and key=="alert_mode":
if value.lower() not in ("breathe","flash"): raise ValueError("alert_mode must be breathe or flash")
elif section=="led" and key=="custom_min_hold_ms":
if not 1500<=int(value)<=60000: raise ValueError("custom_min_hold_ms must be 1500..60000")
elif RGB_KEY_RE.fullmatch(key):
number=int(value)
if not 0<=number<=255: raise ValueError(f"{key} must be 0..255")
elif FLASH_KEY_RE.fullmatch(key):
number=int(value)
if not 50<=number<=60000: raise ValueError(f"{key} must be 50..60000")
elif section=="led" and key=="normal_mode":
if value.lower() not in NORMAL_MODES: raise ValueError("normal_mode must be off, solid, flash, flow, breathe, marquee, rainbow or colorful")
elif section=="led" and key=="normal_effect_speed":
if int(value) not in (1,2,3): raise ValueError("normal_effect_speed must be 1, 2 or 3")
elif section=="led" and key=="normal_effect_color":
if value.lower() not in EFFECT_COLORS: raise ValueError("normal_effect_color must be red, green, blue, yellow, purple, cyan or white")
elif section=="api" and key=="port":
number=int(value)
if not 1<=number<=65535: raise ValueError("api.port must be 1..65535")
elif section=="api" and key=="log_limit":
number=int(value)
if not 1<=number<=1000: raise ValueError("api.log_limit must be 1..1000")
elif section=="api" and key=="bind":
ipaddress.ip_address(value)
elif section=="device" and key=="identifier" and value.lower()!="auto" and not NAME_RE.fullmatch(value):
raise ValueError("device.identifier must be auto or 1..64 letters, numbers, dot, underscore or dash")
def replace_ini_value(section,key,value):
text=CFG.read_text()
section_match=re.search(rf"(?mi)^\[{re.escape(section)}\][ \t]*$",text)
if not section_match:
if value is not None: text=text.rstrip()+f"\n\n[{section}]\n{key} = {value}\n"
return text
next_section=re.search(r"(?m)^\[[^\]\r\n]+\]",text[section_match.end():])
end=section_match.end()+(next_section.start() if next_section else len(text)-section_match.end())
chunk=text[section_match.end():end]
key_match=re.search(rf"(?mi)^[ \t]*{re.escape(key)}\s*=.*(?:\n|$)",chunk)
if key_match:
start=section_match.end()+key_match.start(); stop=section_match.end()+key_match.end()
return text[:start]+((f"{key} = {value}\n") if value is not None else "")+text[stop:]
if value is not None:return text[:end].rstrip()+f"\n{key} = {value}\n\n"+text[end:].lstrip("\n")
return text
def save_ini_text(text,prefix="api"):
parsed=configparser.ConfigParser(); parsed.read_string(text)
backup=CFG.with_name(f"{CFG.name}.bak.{prefix}-{time.strftime('%Y%m%d-%H%M%S')}")
shutil.copy2(CFG,backup)
temporary=CFG.with_suffix(".tmp"); temporary.write_text(text); temporary.chmod(0o644); temporary.replace(CFG)
return str(backup)
def update_ini(updates):
if not isinstance(updates,dict): raise ValueError("updates must be an object")
text=CFG.read_text()
current=load_cfg(); existing={section:set(current.options(section)) for section in current.sections()}
for section,values in updates.items():
if section not in ALLOWED_SECTIONS or not isinstance(values,dict):
raise ValueError(f"unsupported section: {section}")
for key,value in values.items():
if not NAME_RE.fullmatch(str(key)): raise ValueError(f"invalid key: {key}")
if value is None:
raise ValueError(f"null is not allowed: {section}.{key}")
value=str(value).strip()
if not value or len(value)>256 or any(c in value for c in "\r\n\x00"):
raise ValueError(f"invalid value: {section}.{key}")
validate_value(section,str(key),value,existing)
section_match=re.search(rf"(?mi)^\[{re.escape(section)}\][ \t]*$",text)
if not section_match:
text=text.rstrip()+f"\n\n[{section}]\n{key} = {value}\n"
continue
next_section=re.search(r"(?m)^\[[^\]\r\n]+\]",text[section_match.end():])
end=section_match.end()+(next_section.start() if next_section else len(text)-section_match.end())
chunk=text[section_match.end():end]
key_match=re.search(rf"(?mi)^(\s*{re.escape(str(key))}\s*=\s*).*$",chunk)
if key_match:
start=section_match.end()+key_match.start(); stop=section_match.end()+key_match.end()
replacement=key_match.group(1)+value
text=text[:start]+replacement+text[stop:]
else:
text=text[:end].rstrip()+f"\n{key} = {value}\n\n"+text[end:].lstrip("\n")
parsed=configparser.ConfigParser(); parsed.read_string(text)
backup=CFG.with_name(f"{CFG.name}.bak.api-{time.strftime('%Y%m%d-%H%M%S')}")
shutil.copy2(CFG,backup)
temporary=CFG.with_suffix(".tmp")
temporary.write_text(text); temporary.chmod(0o644); temporary.replace(CFG)
return str(backup)
def journal_query(since=None,until=None,severity="",event="",search="",sort="timestamp",order="desc",limit=100,offset=0):
command=["journalctl","-u","pigway-pi-control.service","--no-pager","-o","json"]
if since is not None: command.extend(["--since",f"@{since}"])
if until is not None: command.extend(["--until",f"@{until}"])
result=subprocess.run(command,capture_output=True,text=True,timeout=15)
if result.returncode: raise RuntimeError(result.stderr.strip() or "journalctl failed")
rows=[]
for line in result.stdout.splitlines():
try:
item=json.loads(line)
message=item.get("MESSAGE","")
level_match=re.search(r"(?:^|\s)level=([A-Z]+)(?:\s|$)",message)
event_match=re.search(r"(?:^|\s)event=([^ ]+)",message)
priority=str(item.get("PRIORITY","6"))
level=(level_match.group(1) if level_match else
{"0":"EMERGENCY","1":"ALERT","2":"CRITICAL","3":"ERROR","4":"WARN","5":"NOTICE","6":"INFO","7":"DEBUG"}.get(priority,"INFO"))
rows.append({"timestamp":int(item.get("__REALTIME_TIMESTAMP",0)),"priority":priority,
"severity":level,"event":event_match.group(1) if event_match else "SYSTEM",
"message":message})
except json.JSONDecodeError: pass
severities={x.strip().upper() for x in severity.split(",") if x.strip()}
if severities: rows=[x for x in rows if x["severity"] in severities]
event_types=sorted({x["event"] for x in rows})
if event: rows=[x for x in rows if x["event"]==event]
if search:
needle=search.casefold(); rows=[x for x in rows if needle in x["message"].casefold()]
severity_rank={"EMERGENCY":0,"ALERT":1,"CRITICAL":2,"ERROR":3,"WARN":4,"NOTICE":5,"INFO":6,"DEBUG":7}
keys={"timestamp":lambda x:x["timestamp"],"severity":lambda x:severity_rank.get(x["severity"],99),
"event":lambda x:x["event"],"message":lambda x:x["message"]}
rows.sort(key=keys[sort],reverse=order=="desc")
total=len(rows)
return {"logs":rows[offset:offset+limit],"total":total,"offset":offset,"limit":limit,
"event_types":event_types,"retention":"systemd-journal"}
def service_inventory():
cfg=load_cfg()
monitored={target.lower():(name,target) for name,target in cfg.items("services")} if cfg.has_section("services") else {}
notes=dict(cfg.items("service_notes")) if cfg.has_section("service_notes") else {}
files=subprocess.run(["systemctl","list-unit-files","--type=service","--no-legend","--no-pager"],
capture_output=True,text=True,timeout=10,check=True)
units={}
for line in files.stdout.splitlines():
parts=line.split()
if len(parts)>=2 and UNIT_RE.fullmatch(parts[0]):
units[parts[0]]={"unit":parts[0],"enabled":parts[1],"active":"inactive","description":""}
states=subprocess.run(["systemctl","list-units","--all","--type=service","--no-legend","--no-pager","--plain"],
capture_output=True,text=True,timeout=10,check=True)
for line in states.stdout.splitlines():
parts=line.split(None,4)
if len(parts)>=4 and UNIT_RE.fullmatch(parts[0]):
item=units.setdefault(parts[0],{"unit":parts[0],"enabled":"unknown"})
item.update({"active":parts[2],"description":parts[4] if len(parts)>4 else ""})
for name,target in monitored.values():
item=units.setdefault(target,{"unit":target,"enabled":"not-found","active":"inactive","description":""})
paused=cfg.getboolean("service_monitor_disabled",name,fallback=False)
item.update({"monitored":True,"paused":paused,"monitor_name":name.upper(),"note":notes.get(name,"")})
for item in units.values():
item.setdefault("monitored",False); item.setdefault("paused",False)
item.setdefault("monitor_name",""); item.setdefault("note","")
item["protected"]=item["unit"] in PROTECTED_UNITS
return sorted(units.values(),key=lambda x:(not x["monitored"],x["unit"]))
def edit_service_monitor(operation,name,target,note="",previous_name=""):
if operation not in {"save","delete","pause","resume"}: raise ValueError("invalid monitor operation")
if not NAME_RE.fullmatch(name): raise ValueError("invalid monitor name")
if not UNIT_RE.fullmatch(target): raise ValueError("invalid systemd service name")
if len(note)>120 or any(c in note for c in "\r\n\x00"): raise ValueError("invalid note")
if previous_name and not NAME_RE.fullmatch(previous_name): raise ValueError("invalid previous monitor name")
cfg=load_cfg(); old_target=cfg.get("services",name,fallback=None)
previous=previous_name or name
was_paused=cfg.getboolean("service_monitor_disabled",previous,fallback=False)
text=CFG.read_text()
def change(section,key,value):
nonlocal text
section_match=re.search(rf"(?mi)^\[{re.escape(section)}\][ \t]*$",text)
if not section_match:
if value is not None: text=text.rstrip()+f"\n\n[{section}]\n{key} = {value}\n"
return
next_section=re.search(r"(?m)^\[[^\]\r\n]+\]",text[section_match.end():])
end=section_match.end()+(next_section.start() if next_section else len(text)-section_match.end())
chunk=text[section_match.end():end]
key_match=re.search(rf"(?mi)^[ \t]*{re.escape(key)}\s*=.*(?:\n|$)",chunk)
if key_match:
start=section_match.end()+key_match.start(); stop=section_match.end()+key_match.end()
text=text[:start]+((f"{key} = {value}\n") if value is not None else "")+text[stop:]
elif value is not None:
text=text[:end].rstrip()+f"\n{key} = {value}\n\n"+text[end:].lstrip("\n")
if operation=="delete":
if old_target is None: raise ValueError("monitor not found")
change("services",name,None); change("service_notes",name,None); change("service_monitor_disabled",name,None)
elif operation in {"pause","resume"}:
if old_target is None: raise ValueError("monitor not found")
change("service_monitor_disabled",name,"true" if operation=="pause" else None)
else:
if previous_name and previous_name.lower()!=name.lower():
change("services",previous_name,None); change("service_notes",previous_name,None)
change("service_monitor_disabled",previous_name,None)
change("services",name,target); change("service_notes",name,note or None)
if was_paused: change("service_monitor_disabled",name,"true")
parsed=configparser.ConfigParser(); parsed.read_string(text)
backup=CFG.with_name(f"{CFG.name}.bak.api-{time.strftime('%Y%m%d-%H%M%S')}")
shutil.copy2(CFG,backup)
temporary=CFG.with_suffix(".tmp"); temporary.write_text(text); temporary.chmod(0o644); temporary.replace(CFG)
subprocess.run(["systemctl","restart","pigway-pi-control.service"],check=True,timeout=10)
return str(backup)
def control_service(unit,action):
if not UNIT_RE.fullmatch(unit): raise ValueError("invalid systemd service name")
if action not in {"start","stop"}: raise ValueError("action must be start or stop")
if unit in PROTECTED_UNITS and action=="stop": raise ValueError("protected remote-management service cannot be stopped here")
result=subprocess.run(["systemctl",action,unit],capture_output=True,text=True,timeout=20)
if result.returncode: raise RuntimeError(result.stderr.strip() or f"systemctl {action} failed")
class Handler(BaseHTTPRequestHandler):
server_version="PIGWayAPI/3.7"
def log_message(self,fmt,*args):
return
def send_json(self,status,payload):
data=json.dumps(payload,ensure_ascii=False,separators=(",",":")).encode()
self.send_response(status); self.send_header("Content-Type","application/json; charset=utf-8")
self.send_header("Content-Length",str(len(data))); self.security_headers(); self.end_headers(); self.wfile.write(data)
def security_headers(self):
self.send_header("Cache-Control","no-store")
self.send_header("X-Content-Type-Options","nosniff")
self.send_header("X-Frame-Options","DENY")
self.send_header("Content-Security-Policy","default-src 'self'; style-src 'self' 'unsafe-inline'; script-src 'self' 'unsafe-inline'")
def authorized(self):
try: expected=TOKEN.read_text().strip()
except OSError: return False
supplied=self.headers.get("Authorization","")
return supplied.startswith("Bearer ") and secrets.compare_digest(supplied[7:],expected)
def read_json(self):
length=int(self.headers.get("Content-Length","0"))
if length<=0 or length>65536: raise ValueError("invalid request size")
return json.loads(self.rfile.read(length))
def do_GET(self):
parsed=urlparse(self.path)
try:
if not self.authorized():self.send_json(401,{"error":"bearer token required"});return
if parsed.path=="/api/v1/health":
self.send_json(200,{"ok":True,"version":APP_VERSION,"status_available":STATUS.exists()});return
if parsed.path=="/api/v1/status":
if not STATUS.exists(): self.send_json(503,{"error":"agent status unavailable"}); return
self.send_json(200,json.loads(STATUS.read_text())); return
if parsed.path=="/api/v1/logs":
query=parse_qs(parsed.query)
value=lambda key,default="":query.get(key,[default])[0]
limit=min(max(int(value("limit",api_setting("log_limit",200,int))),1),50000)
offset=max(int(value("offset",0)),0)
since=int(value("since")) if value("since") else None
until=int(value("until")) if value("until") else None
if since is not None and until is not None and since>until: raise ValueError("since must not be after until")
sort=value("sort","timestamp"); order=value("order","desc")
allowed_sort={"timestamp","severity","event","message"}
if sort not in allowed_sort: raise ValueError("invalid log sort")
if order not in {"asc","desc"}: raise ValueError("invalid log order")
severity=value("severity").upper(); event=value("event"); search=value("search")
if len(event)>80 or len(search)>120: raise ValueError("log filter is too long")
self.send_json(200,journal_query(since,until,severity,event,search,sort,order,limit,offset)); return
if parsed.path in {"/api/v1/plugins","/api/v1/plugin/config"}:
query=parse_qs(parsed.query);host_id=query.get("host",[""])[0]
plugin_id=query.get("id",[""])[0]
if parsed.path.endswith("/plugins"):
self.send_json(200,{"plugins":plugin_inventory()});return
item=find_plugin(plugin_id)
self.send_json(200,plugin_request(item["socket"],"GET","/v1/config"));return
if parsed.path=="/api/v1/config":
query=parse_qs(parsed.query); host_id=query.get("host",[""])[0]
self.send_json(200,{"config":config_json(),"write_requires_token":True,"machine":machine_identity()}); return
if parsed.path=="/api/v1/services":
query=parse_qs(parsed.query); host_id=query.get("host",[""])[0]
self.send_json(200,{"services":service_inventory(),"machine":machine_identity()}); return
self.send_json(404,{"error":"not found"})
except ValueError as e: self.send_json(400,{"error":str(e)})
except Exception as e: self.send_json(500,{"error":str(e)})
def do_PUT(self):
path=urlparse(self.path).path
if path not in {"/api/v1/plugins","/api/v1/plugin/config","/api/v1/config","/api/v1/services","/api/v1/services/control"}: self.send_json(404,{"error":"not found"}); return
if not self.authorized(): self.send_json(401,{"error":"bearer token required"}); return
try:
body=self.read_json()
if path in {"/api/v1/plugins","/api/v1/plugin/config"}:
host_id=str(body.get("host",""))
if path.endswith("/plugins"):self.send_json(200,plugin_operation(body));return
item=find_plugin(str(body.get("id","")))
self.send_json(200,plugin_request(item["socket"],"PUT","/v1/config",{"updates":body.get("updates")}));return
if path=="/api/v1/services/control":
control_service(str(body.get("unit","")),str(body.get("action","")))
print(f"SERVICE_CONTROL action={body.get('action')} unit={body.get('unit')}",flush=True)
self.send_json(200,{"ok":True}); return
if path=="/api/v1/services":
backup=edit_service_monitor(str(body.get("operation","")),str(body.get("name","")),
str(body.get("target","")),str(body.get("note","")),
str(body.get("previous_name","")))
print(f"SERVICE_MONITOR_UPDATED operation={body.get('operation')} target={body.get('target')} backup={backup}",flush=True)
self.send_json(200,{"ok":True,"backup":backup}); return
updates=body.get("updates")
backup=update_ini(updates)
subprocess.run(["systemctl","restart","pigway-pi-control.service"],check=True,timeout=10)
restart_api="api" in updates
print(f"CONFIG_UPDATED sections={','.join(sorted(updates))} backup={backup}",flush=True)
self.send_json(200,{"ok":True,"backup":backup,"api_restart":restart_api})
if restart_api: threading.Timer(0.2,self.server.shutdown).start()
except (ValueError,json.JSONDecodeError) as e: self.send_json(400,{"error":str(e)})
except Exception as e: self.send_json(500,{"error":str(e)})
def main():
if not load_cfg().getboolean("api","enabled",fallback=False):
print("API_DISABLED",flush=True);sys.exit(78)
host=api_setting("bind","0.0.0.0")
port=api_setting("port",6001,int)
server=ThreadingHTTPServer((host,port),Handler)
print(f"API_START version={APP_VERSION} bind={host} port={port}",flush=True)
try: server.serve_forever()
finally: server.server_close()
if __name__=="__main__": main()
+109
View File
@@ -0,0 +1,109 @@
"""Hardware-independent client for the versioned local plugin API."""
import copy
from contextlib import closing
import http.client
import json
import socket
import threading
import uuid
from pathlib import Path
PLUGIN_ROOT=Path('/run/pigway-plugins')
def socket_path(value):
path=Path(value)
if not path.is_absolute() or '..' in path.parts or path.name!='api.sock' or PLUGIN_ROOT not in path.parents:
raise ValueError('plugin socket must be /run/pigway-plugins/<plugin>/api.sock')
return str(path)
class Connection(http.client.HTTPConnection):
def __init__(self,path):
super().__init__('localhost',timeout=.8);self.path=socket_path(path)
def connect(self):
self.sock=socket.socket(socket.AF_UNIX,socket.SOCK_STREAM)
self.sock.settimeout(self.timeout)
try:self.sock.connect(self.path)
except Exception:self.sock.close();raise
def request(path,method,endpoint,payload=None):
with closing(Connection(path)) as conn:
body=None if payload is None else json.dumps(payload,allow_nan=False).encode()
conn.request(method,endpoint,body,{'Content-Type':'application/json'})
response=conn.getresponse();raw=response.read(262145)
if len(raw)>262144:raise ValueError('plugin response too large')
value=json.loads(raw)
if response.status>=400:raise ValueError(value.get('error','plugin request failed'))
return value
def registered(cfg):
if not cfg.has_section('plugins'):return {}
return {k:socket_path(v) for k,v in cfg.items('plugins') if v.strip()}
def discover(cfg):
linked=registered(cfg);paths={v for v in linked.values()}
paths.update(str(p) for p in PLUGIN_ROOT.glob('*/api.sock'))
result=[]
for path in sorted(paths)[:32]:
key=next((k for k,v in linked.items() if v==path),None)
try:
d=request(path,'GET','/v1/descriptor')
if d.get('api_version')!=1:raise ValueError('incompatible plugin API version')
status=request(path,'GET','/v1/status')
result.append({'id':key or d['id'],'socket':path,'linked':key is not None,'online':True,'descriptor':d,'status':status})
except Exception as exc:
result.append({'id':key or Path(path).parent.name,'socket':path,'linked':key is not None,'online':False,'error':str(exc)})
return result
class Publisher:
"""One replaceable snapshot, not an unbounded queue of animation commands."""
def __init__(self,plugins,source,log):
self.plugins=plugins;self.source=source;self.log=log
self.session=str(uuid.uuid4());self.revision=0;self.snapshot=None
self.lock=threading.Lock();self.stop_event=threading.Event();self.status={}
self.threads=[threading.Thread(target=self.run,args=(key,path),name='plugin-'+key,daemon=True)
for key,path in plugins.items()]
for thread in self.threads:thread.start()
def publish(self,state):
with self.lock:self.snapshot=copy.deepcopy(state)
def current_status(self):
with self.lock:return copy.deepcopy(self.status)
def run(self,key,path):
previous_error=None;revision=0;descriptor=None
while not self.stop_event.is_set():
with self.lock:state=self.snapshot
if state is not None:
revision+=1
payload={'api_version':1,'source':self.source,'session':self.session,'revision':revision,
'ttl_seconds':10,'system':state['system'],'network':state['network'],'alerts':state['display']['alerts']}
try:
if descriptor is None:
descriptor=request(path,'GET','/v1/descriptor')
if descriptor.get('api_version')!=1:raise ValueError('incompatible plugin API version')
request(path,'PUT','/v1/state',payload)
status=request(path,'GET','/v1/status')
with self.lock:self.status[key]={'online':True,'status':status,'name':descriptor.get('name',key),'capabilities':descriptor.get('capabilities',{})}
if previous_error is not None:self.log('INFO','PLUGIN_RECOVERED',plugin=key)
previous_error=None
except Exception as exc:
descriptor=None
error=str(exc)
with self.lock:self.status[key]={'online':False,'error':error}
if previous_error!=error:self.log('WARN','PLUGIN_UNAVAILABLE',plugin=key,error=error)
previous_error=error
self.stop_event.wait(1)
try:request(path,'DELETE','/v1/state',{'source':self.source,'session':self.session})
except Exception:pass # Server-side leases expire if transport is unavailable.
def close(self):
self.stop_event.set()
for thread in self.threads:thread.join()
+44 -98
View File
@@ -1,45 +1,34 @@
# =============================================================================
# Pigway Pi Control v3.1.0 - 用户配置文件
# =============================================================================
#
# 正式安装后的配置路径:
# /etc/pigway-pi-control.conf
#
# 编辑:
# sudo nano /etc/pigway-pi-control.conf
#
# 保存后让配置生效:
# sudo systemctl restart pigway-pi-control
#
# 查看运行状态:
# systemctl status pigway-pi-control --no-pager -l
#
# 查看实时日志:
# journalctl -u pigway-pi-control -f
#
# 重要:
# 1. 只建议修改本文件,不要直接修改 /usr/local/sbin/pigway-pi-control。
# 2. “#” 开头是注释,不生效。要启用示例项,删除行首的 #。
# 3. 数值单位和建议范围见每项上方注释。
# 4. 配置写错导致服务无法启动时,可查看 journalctl 日志并修正本文件。
# =============================================================================
# PIGWay system monitoring. Hardware plugins are separately installed.
# 系统监控不依赖散热板;在 Web 的硬件插件页面确认接入后才发送状态。
[plugins]
# No automatic attachment. Example (prefer Web discovery):
# yahboom-cooling-hat = /run/pigway-plugins/yahboom-cooling-hat/api.sock
[device]
# 多机监控中使用的稳定机器标识。auto 表示读取本机 hostname。
# 多台机器的 identifier 必须唯一;修改后重启监控 Agent 和 API 服务。
identifier = auto
# Web 页面显示名称。auto 表示使用 identifier。
name = auto
[api]
# 默认关闭远程 API。开启后所有请求均需令牌;本地监控和插件联动不受此开关影响。
enabled = false
# API 监听地址和端口。0.0.0.0 允许局域网访问;
# 如只允许本机访问可改为 127.0.0.1。修改后重启 API 服务生效。
bind = 0.0.0.0
port = 6001
log_limit = 200
[timing]
# 传感器采样周期,单位:秒。
# CPU / 内存 / 温度 / 磁盘以及风扇控制按此周期更新。
# CPU / 内存 / 温度 / 磁盘按此周期更新。
# 推荐:1。通常不要低于 1。
sensor_interval = 1
# OLED 当前页面刷新周期,单位:秒。
# 这只是刷新当前页面数据,不负责切换页面。
# 推荐:1。
oled_refresh_interval = 1
# HOME / 各告警页面的轮播停留时间,单位:秒。
# 推荐:10。觉得切换太慢可改为 5~8。
page_interval = 10
# 网络状态检查周期,单位:秒。
# 推荐:5。太短会产生不必要的网络探测。
network_interval = 5
@@ -48,40 +37,10 @@ network_interval = 5
# 推荐:5。
service_interval = 5
[fan]
# 风扇温控档位,单位:摄氏度。
#
# 默认曲线:
# < 50°C OFF
# 50~53°C L1
# 53~56°C L2
# 56~59°C L3
# 59~62°C L4
# >= 62°C MAX
#
# 如希望更安静,可适当提高阈值;如更重视散热,可降低。
# 建议保持 start < level2 < level3 < level4 < max。
# 低于此温度,风扇完全停止。
start = 50
# L2 起始温度;start 到 level2 之间为 L1。
level2 = 53
# L3 起始温度。
level3 = 56
# L4 起始温度。
level4 = 59
# MAX 全速起始温度。
max = 62
# 降档回差,单位:°C。
# 防止温度在临界值附近上下波动时风扇频繁升降档。
# 推荐:1.0~2.0。
hysteresis = 1.5
# 本机健康检查周期,单位:秒。
# 检查 Raspberry Pi 欠压/降频状态、根文件系统只读状态等。
# 推荐:1。当前电源状态及时更新告警与插件快照;历史状态仅记录一次日志。
health_interval = 1
[alerts]
@@ -120,43 +79,24 @@ disk_high = 90
# 根分区使用率达到此百分比触发严重告警。
disk_critical = 95
# ---------------- Wi-Fi 信号 ----------------
# 仅当 Wi-Fi 是 Linux 当前默认路由/主接口时生效。
# RSSI 单位 dBm,越接近0越强;约 -50很好,-70一般,-80较弱。
# 连续低于 wifi_weak 达到 wifi_weak_seconds 后触发弱信号告警。
wifi_weak = -75
[led]
# RGB 规则:
# 正常状态 = 完全熄灭
# 颜色 = 哪一类对象发生故障
# 闪烁频率 = 严重程度,越严重闪得越快
#
# 当前颜色语义:
# CPU负载 = 黄
# 温度/散热 = 红
# 内存 = 紫
# 磁盘 = 橙
# 网络 = 蓝
# 服务/进程 = 青
#
# brightness 是 RGB 最大输出百分比(0~100)。
# 3颗 RGB 会一起亮,卧室建议 5~15。
brightness = 10
# 已告警后恢复到该值以上才解除,形成滞回避免反复闪烁。
wifi_recover = -68
# Warning:慢闪。以下单位均为毫秒。
warning_on_ms = 300
warning_off_ms = 2700
# Critical:中速闪烁。
critical_on_ms = 400
critical_off_ms = 1100
# Emergency:快速闪烁。
emergency_on_ms = 400
emergency_off_ms = 400
# 弱信号持续多少秒才正式告警。
wifi_weak_seconds = 30
[dark_mode]
# Raspberry Pi 4 板载 PWR / ACT LED。
# 本机硬件只支持开/关,不支持真正的 PWM 调暗。
#
# off = Pigway Pi Control 启动时关闭该灯。
# off = PIGWay Pi Control 启动时关闭该灯。
# 若不希望程序干预,可改为 on。
#
# 注意:
@@ -202,6 +142,12 @@ AWESUN = runawesun.service
# NGINX = nginx.service
[service_monitor_disabled]
# Web 中“暂停监控”的状态保存在这里。
# 名称对应 [services] 左侧名称;true 表示保留配置和备注,但 Agent 暂不检查。
# 通常由 Web 自动维护,无需手工编辑。
[processes]
# =============================================================================
# 普通进程监控
+91
View File
@@ -0,0 +1,91 @@
# Local hardware plugin API v1
The monitor and plugins are separate applications. The monitor has no hardware
library dependency. Plugins alone own their hardware. Installing or discovering
a plugin does not connect it or start another service.
## Transport and authorization
HTTP/1.0 or HTTP/1.1 over `/run/pigway-plugins/<id>/api.sock`. No TCP listener.
The parent directory is root-owned, mode 0750, and the socket is 0660 with group
`pigway-hardware`. Root and deliberately enrolled group members may control the
plugin. The monitor Web API authenticates mutations with its existing bearer
token before proxying local requests. Remote machine operations require that
machine's token too. API v1 clients reject incompatible descriptor versions.
## Endpoints
- `GET /v1/descriptor`: `api_version`, `id`, `name`, `version`, `capabilities`, `schema`.
- `GET /v1/status`: availability, connection state and capability-specific actual
or commanded state. A missing tachometer must never be presented as measured RPM.
- `GET /v1/config`: `config` plus `schema`.
- `PUT /v1/config`: `{"updates":{"section":{"key":"value"}}}`; validate the complete
candidate before persisting or applying anything. Does not restart the monitor.
- `PUT /v1/state`: replace the complete monitoring snapshot, never append commands.
- `DELETE /v1/state`: release a lease. Publisher passes `source` and `session`;
authorized local administration may use `{}` to detach the current source.
Example snapshot:
```json
{
"api_version": 1,
"source": "raspberrypi",
"session": "a-new-uuid-for-each-monitor-process",
"revision": 1,
"ttl_seconds": 10,
"system": {"cpu_percent": 12, "temperature_c": 50, "memory_percent": 20, "disk_percent": 30},
"network": {"kind": "WIF", "metric": "-60", "ip_label": "IP4", "ip": "192.168.1.2"},
"alerts": [{"id":"SERVICE_DOWN|APP","category":"service","severity":2,"priority":60,
"title":"SERVICE DOWN","l2":"APP","l3":"CHECK SERVICE","l4":"CRITICAL"}]
}
```
Alert categories: `cpu`, `power`, `memory`, `storage`, `network`, `service`.
The producer sends only current alerts, never historical power flags. Empty
`alerts` clears all previous alerts. A source/session owns its lease until
release or expiry; a competing source and repeated/out-of-order revisions are
rejected. Leases use the receiving process's monotonic clock, 3–30 seconds.
A new monitor session retries until the old lease expires if the old process
could not release it. Each plugin has an independent bounded-time publisher and
one replaceable latest snapshot, so an offline plugin cannot queue stale frames
or block monitoring or other plugins.
## Capability-driven UI
`fan` declares levels or PWM, RPM availability, autonomous operation and ownership.
`display` declares dimensions and pages. `rgb` declares modes, preset colors and
experimental custom flashing. Absent capability means absent controls. A plugin
with only a fan does not imply a screen or lighting device. New hardware needs
its own driver; I2C, PWM GPIO and power-only fans are not interchangeable.
`schema` groups fields by section. Each field provides bilingual `label`, `type`
(`number`/`enum`), numeric limits or choices, unit and optional visibility rules.
Optional `color_group` and `channel` (`r`/`g`/`b`) associate three numeric fields
with a color picker. Plugins remain authoritative for all validation.
## Failures and independent cooling
Monitoring continues without installed or reachable plugins. Hardware plugins
continue local temperature control without the monitor. Expired snapshots must
not keep showing stale alerts as live faults. The Yahboom implementation returns
to its locally sampled home and configured normal RGB mode on expiry or detach.
It samples CPU, memory, disk, temperature and primary network independently.
API v1 system/network fields remain accepted for compatibility but never override
local telemetry. Monitor connectivity only supplies additional alerts.
Its thermal read failure and service shutdown request full fan speed as a cooling
fallback; actual execution still depends on functioning hardware.
Stopping a monitor, pausing its link, or unlinking a plugin does not stop the
plugin service. No API/Web service has a systemd Wants dependency that starts the
other application. Do not run two drivers for the same MCU, GPIO or fan.
## Optional listeners
Agent network API defaults to disabled (`[api] enabled=false`) and has no Web UI.
When enabled, every request requires a device bearer token.
Hardware plugin integration defaults to disabled (`[integration] enabled=false`):
no Unix API socket is created, while local telemetry and hardware workers continue.
Change integration locally and restart the plugin. Monitor-to-plugin linkage does
not require the Agent network API. The independent Web Manager stores registered
device addresses and tokens; it is not implicitly a monitored device.
+65 -72
View File
@@ -1,82 +1,75 @@
#!/bin/bash
set -euo pipefail
cd "$(dirname "$0")"
echo "[1/7] 检查 Raspberry Pi I2C..."
[ -e /dev/i2c-1 ] || { echo "错误:/dev/i2c-1 不存在。先 sudo raspi-config -> Interface Options -> I2C -> Enable,然后重启。"; exit 1; }
echo "[2/7] 等待 APT/DPKG..."
for i in $(seq 1 60); do
if ! fuser /var/lib/dpkg/lock-frontend /var/lib/apt/lists/lock /var/cache/apt/archives/lock >/dev/null 2>&1; then break; fi
[ "$i" = 60 ] && { echo "APT 锁等待超时,请稍后重试。"; exit 1; }
echo "软件包管理器忙,等待 5 秒... ($i/60)"
sleep 5
NO_START=0
API_ENABLED=""
for arg in "$@"; do
case "$arg" in
--enable-api) API_ENABLED=true ;;
--disable-api) API_ENABLED=false ;;
--no-start) NO_START=1 ;;
-h|--help) echo 'Usage: sudo ./install.sh [--no-start] [--enable-api|--disable-api]'; exit 0 ;;
*) echo "ERROR: unknown option: $arg (hardware is installed separately)" >&2; exit 2 ;;
esac
done
echo "[3/7] 安装依赖..."
apt update
apt install -y python3 python3-pil python3-smbus2 i2c-tools
echo "[4/7] 检查硬件地址..."
SCAN="$(i2cdetect -y 1)"; echo "$SCAN"
echo "$SCAN" | grep -qi '3c' || echo "警告:未扫描到 OLED 0x3C"
echo "$SCAN" | grep -qi '0d' || echo "警告:未扫描到控制 MCU 0x0D"
echo "[5/7] 安装程序与配置..."
if systemctl list-unit-files 2>/dev/null | grep -q '^temp-control.service'; then
echo "检测到旧 temp-control.service,正在停止并禁用..."
systemctl disable --now temp-control.service 2>/dev/null || true
fi
pkill -f '/temp_control/temp_control' 2>/dev/null || true
for required in app/pigway_pi_control.py app/plugin_api.py app/pigway_pi_control_api.py config/pigway-pi-control.conf systemd/pigway-pi-control.service systemd/pigway-pi-control-api.service; do
[ -f "$required" ] || { echo "ERROR: required file missing: $required" >&2; exit 1; }
done
[ "$(id -u)" -eq 0 ] || { echo 'ERROR: run installer as root' >&2; exit 1; }
# The monitor has no I2C, GPIO, Pillow, smbus2 or cooling-board requirement.
command -v python3 >/dev/null || { apt-get update; apt-get install -y python3; }
mkdir -p /usr/local/share/pigway-pi-control
install -m 0644 app/oled_font_5x7.bin /usr/local/share/pigway-pi-control/oled_font_5x7.bin
install -m 0644 app/plugin_api.py /usr/local/share/pigway-pi-control/plugin_api.py
install -m 0755 app/pigway_pi_control.py /usr/local/sbin/pigway-pi-control
NEW=/tmp/pigway-pi-control.conf.new
cp config/pigway-pi-control.conf "$NEW"
install -m 0755 app/pigway_pi_control_api.py /usr/local/sbin/pigway-pi-control-api
if [ -f /etc/pigway-pi-control.conf ]; then
cp /etc/pigway-pi-control.conf "/etc/pigway-pi-control.conf.bak.$(date +%Y%m%d-%H%M%S)"
# Preserve user's [services] and [processes] sections; adopt new defaults elsewhere.
python3 - "$NEW" /etc/pigway-pi-control.conf <<'PY'
import configparser,sys
newf,oldf=sys.argv[1:]
n=configparser.ConfigParser(); n.optionxform=str; n.read(newf)
o=configparser.ConfigParser(); o.optionxform=str; o.read(oldf)
for sec in ("services","processes"):
if o.has_section(sec):
if n.has_section(sec): n.remove_section(sec)
n.add_section(sec)
for k,v in o.items(sec): n.set(sec,k,v)
with open(newf,"w") as f:n.write(f)
PY
else
install -m 0644 config/pigway-pi-control.conf /etc/pigway-pi-control.conf
fi
install -m 0644 "$NEW" /etc/pigway-pi-control.conf
rm -f "$NEW"
install -m 0644 systemd/pigway-pi-control.service /etc/systemd/system/pigway-pi-control.service
echo "[6/7] 启用/重启服务..."
# Legacy hardware sections are deliberately preserved for explicit migration,
# but ignored by the monitor and never exposed as monitor configuration.
python3 - <<'PY'
from pathlib import Path
import configparser
p=Path('/etc/pigway-pi-control.conf');c=configparser.ConfigParser();c.read(p)
with p.open('a') as f:
for section,values in {'device':{'identifier':'auto','name':'auto'},'plugins':{},'api':{'bind':'0.0.0.0','port':'6001','log_limit':'200'}}.items():
if not c.has_section(section):
f.write('\n['+section+']\n'+''.join(k+' = '+v+'\n' for k,v in values.items()))
PY
if [ ! -s /etc/pigway-pi-control-api.token ]; then
(umask 077; python3 -c 'import secrets; print(secrets.token_urlsafe(32))' > /etc/pigway-pi-control-api.token)
fi
chmod 0600 /etc/pigway-pi-control-api.token
install -m 0644 systemd/pigway-pi-control.service /etc/systemd/system/
install -m 0644 systemd/pigway-pi-control-api.service /etc/systemd/system/
if [ -z "$API_ENABLED" ]; then
API_ENABLED=false
if [ -t 0 ]; then
read -r -p 'Enable remote management API? [y/N] ' answer
case "$answer" in y|Y|yes|YES) API_ENABLED=true ;; esac
fi
fi
API_ENABLED="$API_ENABLED" python3 - <<'PYAPI'
import os,sys
sys.path.insert(0,'app')
import pigway_pi_control_api as api
api.save_ini_text(api.replace_ini_value('api','enabled',os.environ['API_ENABLED']),'install')
PYAPI
systemctl daemon-reload
systemctl enable pigway-pi-control.service >/dev/null
systemctl restart pigway-pi-control.service
echo "[7/8] 安装后自检..."
FAIL=0
check() { if eval "$2"; then printf " %-30s PASS\n" "$1"; else printf " %-30s FAIL\n" "$1"; FAIL=1; fi; }
check "Version 3.1.0" "grep -q 'APP_VERSION=\"3.1.0\"' /usr/local/sbin/pigway-pi-control"
check "OLED physical 128x32" "grep -q 'W,H=128,32' /usr/local/sbin/pigway-pi-control"
check "OLED MUX 0x1F" "grep -q '0xA8,0x1F' /usr/local/sbin/pigway-pi-control"
check "OLED pages 0..3" "grep -q 'cmd(0x22);cmd(0);cmd(3)' /usr/local/sbin/pigway-pi-control"
check "UI CPU/TMP/DSK" "grep -q 'f\"TMP {temp:.1f}C\"' /usr/local/sbin/pigway-pi-control"
check "UI IP4/IP6" "grep -q 'IP6 .*IP4 ' /usr/local/sbin/pigway-pi-control"
check "UI right column x=72" "grep -q \"draw_text_5x7(pix,72,y,right\\[row\\])\" /usr/local/sbin/pigway-pi-control"
check "Legacy service stopped" "! systemctl is-active --quiet temp-control.service"
check "Service running" "systemctl is-active --quiet pigway-pi-control.service"
if [ "$FAIL" -ne 0 ]; then echo "错误:安装后自检未全部通过。"; exit 1; fi
echo "[8/8] 状态..."
systemctl --no-pager --full status pigway-pi-control.service || true
echo
echo "完成。程序:/usr/local/sbin/pigway-pi-control"
echo "配置:/etc/pigway-pi-control.conf"
if [ "$NO_START" -eq 0 ]; then
systemctl enable pigway-pi-control.service >/dev/null
systemctl restart pigway-pi-control.service
systemctl is-active --quiet pigway-pi-control.service
if [ "$API_ENABLED" = true ]; then
systemctl enable pigway-pi-control-api.service >/dev/null
systemctl restart pigway-pi-control-api.service
systemctl is-active --quiet pigway-pi-control-api.service
else
systemctl disable --now pigway-pi-control-api.service
fi
fi
echo 'Monitor installed. Hardware plugins are installed and connected separately.'
echo 'Config: /etc/pigway-pi-control.conf'
echo 'API token: sudo cat /etc/pigway-pi-control-api.token'
+19
View File
@@ -0,0 +1,19 @@
[Unit]
Description=PIGWay Device Agent optional local API
After=network.target pigway-pi-control.service
Wants=network.target
[Service]
Type=simple
ExecStart=/usr/local/sbin/pigway-pi-control-api
Restart=always
RestartPreventExitStatus=78
SuccessExitStatus=78
RestartSec=2
User=root
NoNewPrivileges=true
PrivateTmp=true
ProtectHome=true
[Install]
WantedBy=multi-user.target
+3 -3
View File
@@ -1,7 +1,7 @@
[Unit]
Description=Pigway Raspberry Pi OLED/Fan/RGB Monitor
After=multi-user.target network.target
Wants=network.target
Description=PIGWay system monitor
After=local-fs.target systemd-modules-load.service
Before=multi-user.target
[Service]
Type=simple
+4 -1
View File
@@ -1,8 +1,11 @@
#!/bin/bash
set -euo pipefail
systemctl disable --now pigway-pi-control.service 2>/dev/null || true
systemctl disable --now pigway-pi-control-api.service pigway-pi-control.service 2>/dev/null || true
rm -f /etc/systemd/system/pigway-pi-control-api.service
rm -f /etc/systemd/system/pigway-pi-control.service
rm -f /usr/local/sbin/pigway-pi-control
rm -f /usr/local/sbin/pigway-pi-control-api
rm -f /etc/pigway-pi-control-api.token
rm -rf /usr/local/share/pigway-pi-control
systemctl daemon-reload
echo "程序已卸载。为防误删自定义内容,配置 /etc/pigway-pi-control.conf 已保留。"