Merge fix/monitor-pause-rgb-edges

README.md

@@ -73,7 +73,7 @@ CHECK STORAGE
 
 ### 5. RGB 正常状态与告警引擎
 
-没有 active alert 时，RGB 默认全灭。`[led] normal_mode` 可改为自定义颜色常亮/闪烁，或 MCU 已确认的流水、呼吸、跑马、彩虹和炫彩效果。常亮与闪烁使用 0..255 的自定义 R/G/B；内置流水/呼吸使用 MCU 固定的红、绿、蓝、黄、紫、青、白七色和慢/中/快三档速度，跑马/彩虹/炫彩由 MCU 自行配色。内置效果只在模式切换时写一次寄存器，不循环刷 I²C。
+没有 active alert 时，RGB 默认全灭。`[led] normal_mode` 可改为自定义颜色常亮/闪烁，或 MCU 已确认的流水、呼吸、跑马、彩虹和炫彩效果。常亮与闪烁使用 0..255 的自定义 R/G/B；内置流水/呼吸使用 MCU 固定的红、绿、蓝、黄、紫、青、白七色和慢/中/快三档速度，跑马/彩虹/炫彩由 MCU 自行配色。内置效果只在模式切换时按 speed → color → effect 的实机校准顺序写一次寄存器，不循环刷 I²C。
 
 任何 active alert 都会立即抢占正常效果。RGB 告警模式由当前 OLED 告警页决定；OLED 位于主页时则使用最高优先级 active owner。颜色表示故障对象：CPU负载、频率、throttling、温度与散热相关为红色，供电/欠压为橙色，内存为紫色，存储为白色，网络/Wi-Fi 为蓝色，服务/进程为青色。频率表示严重等级：默认 Warning 为1500ms亮/1500ms灭，Critical 为750ms亮/750ms灭，Emergency 为300ms亮/300ms灭。`[led]` 可分别配置六类对象的 R/G/B 值，以及三个严重等级的亮灯和灭灯时长，非法颜色值会限制到0..255，间隔最小为50ms。每次点亮使用 v3.2.0 已验证的完整 selector/R/G/B 写入顺序，只在亮/灭边沿写 MCU，不做高频软件 PWM。相邻页面 RGB mode 相同时不关闭、不重启节奏。动画不写循环日志，owner 变化记录 `DISPLAY_OWNER`，实际模式变化才记录 `RGB_MODE`。
 
@@ -162,8 +162,11 @@ GET /api/v1/health
 GET /api/v1/status
 GET /api/v1/logs?limit=200
 GET /api/v1/config
+GET /api/v1/services
 ```
 
+日志接口支持 `since`、`until` Unix 时间戳，`severity`、`event`、`search` 筛选，`timestamp` / `severity` / `event` / `message` 排序，以及 `limit` / `offset` 分页。Web 提供今天、昨天、本周、本月和全部快捷范围。日志直接读取 systemd journal 的现有保留数据，不建立重复的 SQLite 日志副本。
+
 配置写入接口：
 
 ```text
@@ -174,6 +177,10 @@ Content-Type: application/json
 {"updates":{"led":{"service_b":"96"},"api":{"port":"6001"}}}
 ```
 
+服务监控页面会列出本机 systemd 服务，并标识“已监控/未监控”。添加、编辑或删除监控使用 `PUT /api/v1/services`；启动或停止服务使用 `PUT /api/v1/services/control`，两者均要求 Bearer Token。API 服务不能通过自己的请求停止自身，其他服务由用户自行管理。监控备注保存在配置文件的 `[service_notes]`，不会参与硬件 Agent 的监控判断。
+
+“暂停监控/恢复监控”只改变 PIGWay 是否检查该服务，不会启动或停止 systemd unit；暂停状态保存在 `[service_monitor_disabled]`。只有明确标注为“启动服务/停止服务”的按钮才会调用 systemctl。
+
 读取 token：
 
 ```bash

SHA256SUMS

@@ -1,10 +1,10 @@
-40154b1fabac7bdfc7e4a6cd1a88ffa42e6842ef1da625594d5d9e4b904e99b9  README.md
+78e914f6fa8e86c4eb09bae63e7e9566d404941a275f7808e7e5f433f95c6edb  README.md
 72c46162c33f9587c6ccb01ad53fbaaf4ecec8cd21014b909e87e8707e253e36  app/oled_font_5x7.bin
-c3062ad1122c36a762bc3ca9d44ebcb5a6a5a37446a85fb68312de4fd8aa5db9  app/pigway_pi_control.py
-3a13b4e8f9d306e77f82eba78b78fe9b1932488884d6f3f976754bfa94f0153d  app/pigway_pi_control_api.py
-75fa662ed21138a8e394de83e46281dab039433cc0d7a8f787e1a049f4b47ec8  config/pigway-pi-control.conf
-1276369d600e9fd560d03e26146bcaeb40a353829978d1ebaa578d385b27af72  install.sh
+ba34a479584345590f1903851b6d7e13000c4034c0c9db39e591eb4382be4229  app/pigway_pi_control.py
+a833c5598813b3695ac5a65daacf7b503abd8036f20f2e6cb75d8a99307a1095  app/pigway_pi_control_api.py
+72dc248b8f7020b81bc4069e52cc11175a7b42e00d3b484cb6ca5beca624a90b  config/pigway-pi-control.conf
+f34eac1df180a3da3a6998d650c06435fd89728c10b090f6162df82e53986dd0  install.sh
 4f6e8db3698a62f57823d3298a0e6814593de6fa3d31e4751b7ea4a76e553e35  systemd/pigway-pi-control.service
 aa21cef9a06593371ccff005335b6c0c826fbf4b5c48e4255b5f4b75ce6e9217  systemd/pigway-pi-control-api.service
 9f59e7313ee58e687ae6dd29d175c67082674254ac5c5f54168b2735b64c20a4  uninstall.sh
-7694998270db13407c197707ee41f8fb8d8d9ffa8d2325f20d7dd7719ab46815  web/index.html
+1255575ab76939073e83cfc728989b88facc7cc16b147870fd0d7d380bcf6b1e  web/index.html

app/pigway_pi_control.py

@@ -210,7 +210,9 @@ 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()
@@ -471,12 +473,11 @@ def rgb_normal_effect(mode):
     effect_name=mode.removeprefix("NORMAL_").lower()
     state=("effect",effect_name,NORMAL_EFFECT_SPEED,NORMAL_EFFECT_COLOR)
     if _last_rgb==state: return
-    # Seller protocol: close the previous RGB state, then set effect, speed and
-    # the limited built-in palette.  Write this sequence once per mode change.
-    mcu(0x07,0x00); time.sleep(0.001)
-    mcu(0x04,RGB_EFFECTS[effect_name]); time.sleep(0.001)
-    mcu(0x05,NORMAL_EFFECT_SPEED); time.sleep(0.001)
-    mcu(0x06,RGB_EFFECT_COLORS[NORMAL_EFFECT_COLOR])
+    # Hardware-calibrated order: speed and color are parameters; the final
+    # effect register write commits and starts the selected MCU animation.
+    mcu(0x05,NORMAL_EFFECT_SPEED); time.sleep(RGB_WRITE_DELAY_MS/1000.0)
+    mcu(0x06,RGB_EFFECT_COLORS[NORMAL_EFFECT_COLOR]); time.sleep(RGB_WRITE_DELAY_MS/1000.0)
+    mcu(0x04,RGB_EFFECTS[effect_name])
     _last_rgb=state
 
 def render_home(cpu,temp,mem,disk):
@@ -667,7 +668,8 @@ class DisplayController:
             }
 
     def _rgb_worker(self):
-        previous_error=None; applied_mode="OFF"; applied_flash=False; animation_started=time.monotonic()
+        previous_error=None; applied_mode="OFF"; applied_flash=False
+        flash_on=None; animation_started=time.monotonic()
         while not self.stop_event.is_set():
             try:
                 with self.lock: wanted_mode=self.current_rgb_mode
@@ -684,6 +686,7 @@ class DisplayController:
                         else: raise ValueError(f"unsupported RGB mode: {wanted_mode}")
                     log("INFO","RGB_MODE",old=applied_mode,new=wanted_mode)
                     applied_mode=wanted_mode; animation_started=time.monotonic()
+                    flash_on=True if wanted_mode.endswith("_FLASH") else None
                 applied_flash=applied_mode.endswith("_FLASH")
                 if applied_flash:
                     elapsed_ms=(time.monotonic()-animation_started)*1000.0
@@ -692,10 +695,12 @@ class DisplayController:
                     elif "_CRITICAL_" in applied_mode: on_ms,off_ms=CRITICAL_FLASH
                     else: on_ms,off_ms=WARNING_FLASH
                     on=elapsed_ms%(on_ms+off_ms)<on_ms
+                    if on!=flash_on:
                         with bus_lock:
                             if applied_mode=="NORMAL_FLASH":
                                 rgb_static(NORMAL_COLOR,"normal_flash_on") if on else rgb_off()
                             else: rgb_flash(applied_mode,on)
+                        flash_on=on
                 if previous_error is not None: log("INFO","RGB_RECOVERED")
                 previous_error=None
             except Exception as e:

app/pigway_pi_control_api.py

@@ -12,10 +12,12 @@ TOKEN=Path("/etc/pigway-pi-control-api.token")
 WEB=Path("/usr/local/share/pigway-pi-control/web/index.html")
 ALLOWED_SECTIONS={"services","processes","alerts","fan","led","timing","dark_mode","display","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 load_cfg():
     cfg=configparser.ConfigParser(); cfg.read(CFG)
@@ -89,18 +91,118 @@ def update_ini(updates):
     temporary.write_text(text); temporary.chmod(0o644); temporary.replace(CFG)
     return str(backup)
 
-def journal(limit):
-    result=subprocess.run(["journalctl","-u","pigway-pi-control.service","-n",str(limit),
-                           "--no-pager","-o","json"],capture_output=True,text=True,timeout=5)
+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)
-            rows.append({"timestamp":item.get("__REALTIME_TIMESTAMP"),"priority":item.get("PRIORITY"),
-                         "message":item.get("MESSAGE","")})
+            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
-    return rows
+    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)^\[{re.escape(section)}\]\s*$",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)^\[.+\]\s*$",text[section_match.end():])
+        end=section_match.end()+(next_section.start() if next_section else len(text)-section_match.end())
+        chunk=text[section_match.end():end]
+        key_match=re.search(rf"(?mi)^\s*{re.escape(key)}\s*=.*(?:\n|$)",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/3.6"
@@ -142,18 +244,44 @@ class Handler(BaseHTTPRequestHandler):
                 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":
-                limit=min(max(int(parse_qs(parsed.query).get("limit",[api_setting("log_limit",200,int)])[0]),1),1000)
-                self.send_json(200,{"logs":journal(limit)}); return
+                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),500)
+                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")
+                if sort not in {"timestamp","severity","event","message"}: 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=="/api/v1/config":
                 self.send_json(200,{"config":config_json(),"write_requires_token":True}); return
+            if parsed.path=="/api/v1/services":
+                self.send_json(200,{"services":service_inventory()}); 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):
-        if urlparse(self.path).path!="/api/v1/config": self.send_json(404,{"error":"not found"}); return
+        path=urlparse(self.path).path
+        if path not in {"/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(); updates=body.get("updates")
+            body=self.read_json()
+            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

config/pigway-pi-control.conf

@@ -271,6 +271,12 @@ 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

install.sh

@@ -107,6 +107,7 @@ sections={
     ("normal_r",0),("normal_g",0),("normal_b",0),
     ("normal_flash_on_ms",1000),("normal_flash_off_ms",1000),
     ("normal_effect_speed",2),("normal_effect_color","green"),
+    ("write_delay_ms",10),
     ("cpu_r",255),("cpu_g",0),("cpu_b",0),
     ("power_r",255),("power_g",40),("power_b",0),
     ("memory_r",255),("memory_g",0),("memory_b",255),