feat: 通知发送层切换到群机器人 webhook, 排版精简

- wecom.py 重写: HTTP POST webhook(替代 aibot WebSocket 按需连接), 接口 send_markdown/send_text 不变, Secret Block wecom-webhook 存 URL
- webhook markdown 支持标题/引用/font 三色, 报告改为 '## 标题 + 单行结论 + 引用详情' 紧凑排版, 结论行用 info/warning 色
- alert_failure 改标题式排版; device_check 结论用 font 色, 去掉负载行
- 移除 wecom-aibot-sdk 依赖与 wecom_capture_chatid.py(镜像下次构建生效, 无需立即重建)

flows/monitor/alert_failure.py

@@ -102,14 +102,11 @@ def wecom_alert_failure(event: dict | str | None = None) -> dict:
             ended = detail.get("end_time") or detail.get("expected_start_time")
             occurred = occurred or ended
 
-        lines = [
-            f"🔴 **流程失败**  {flow_name or resource_name or '未知'}",
-        ]
-        if run_name and run_name != flow_name:
-            lines.append(f"> Run：{run_name}")
+        lines = [f"## 🔴 流程失败：{flow_name or resource_name or '未知'}"]
+        if run_name:
+            lines.append(f"> Run「{run_name}」 · {event_name.split('.')[-1]} · {_fmt_ts(occurred)}")
         if state_msg:
             lines.append(f"> 错误：{state_msg[:150].replace(chr(10), ' ')}")
-        lines.append(f"> {event_name} · {_fmt_ts(occurred)}")
         if run_id:
             lines.append(f"> [查看详情]({UI_BASE}/runs/flow-run/{run_id})")
         else:

flows/monitor/daily_report.py

@@ -27,7 +27,7 @@ def _affected_units(diff: dict) -> int:
 
 
 def _system_lines(name: str, report: dict, goods: dict, lines: list[str]) -> bool:
-    """单系统的核验两段:①数量是否一致(订单+商品) ②状态不符多少单。返回是否需关注。"""
+    """单系统一行结论:数量(远程 vs 本地,一致只显示一个数)+商品;状态不符进引用行。"""
     vr = (report.get("verifyReport") or {}) if isinstance(report, dict) else {}
     days_r = vr.get("days") or []
     post = vr.get("post")
@@ -36,35 +36,27 @@ def _system_lines(name: str, report: dict, goods: dict, lines: list[str]) -> boo
     else:
         remote_t = sum(d.get("remote", 0) for d in days_r)
         local_t = sum(d.get("local", 0) for d in days_r)
-    # 数量一致只看总量;状态差异属第二段,不混入数量结论
-    ok = remote_t == local_t
+    ok = remote_t == local_t  # 数量一致只看总量;状态差异属第二段,不混入数量结论
 
-    if ok:
-        lines.append(f"**{name} 订单** 远程 {remote_t:,} · 本地 {local_t:,} ✅")
-    else:
-        lines.append(f"**{name} 订单** 远程 {remote_t:,} · 本地 {local_t:,} ⚠️ 不一致")
+    g = goods or {}
+    zero = g.get("zeroGoodsOrders", 0)
+    goods_txt = f"{g.get('goods', 0):,} 行" + (f"（缺 {zero:,}）" if zero else "")
+    order_txt = f"订单 {remote_t:,} ✅" if ok else f"订单 远程 {remote_t:,} / 本地 {local_t:,} ⚠️"
+    lines.append(f"**{name}** {order_txt} · 商品 {goods_txt} {'✅' if not zero else '⚠️'}")
 
     diff_days = [d for d in days_r if not d.get("ok")]
     diff_units = sum(_affected_units(d.get("diff")) for d in diff_days)
     if diff_units:
-        lines.append(f"> 核验时发现约 {diff_units:,} 单状态不符（{len(diff_days)} 天），已自动刷新修复")
-
-    g = goods or {}
-    zero = g.get("zeroGoodsOrders", 0)
-    if zero:
-        lines.append(f"**{name} 商品** {g.get('goods', 0):,} 行 · {zero:,} 单缺商品 ⚠️")
-        return True
-    lines.append(f"**{name} 商品** {g.get('goods', 0):,} 行 · 无缺漏 ✅")
-    return not ok
+        lines.append(f"> 状态不符约 {diff_units:,} 单（{len(diff_days)} 天），已自动刷新修复")
+    return (not ok) or bool(zero)
 
 
 def build_daily_message(
     days: int, window: str, riin: dict, sds: dict,
     goods: dict, ocr_today: dict, ocr_pending: int, failures: list[dict],
 ) -> tuple[str, bool]:
-    """拼装日报 markdown,返回 (消息, 是否需关注)。"""
-    lines = [f"📊 **数据核验日报** {datetime.now().strftime('%m-%d %H:%M')}"
-             f"（近 {days} 天，{window}）", ""]
+    """拼装日报 markdown,返回 (消息, 是否需关注)。单行结论 + 引用详情的紧凑排版。"""
+    lines = [f"## 📊 数据核验日报 {datetime.now():%m-%d %H:%M}（近 {days} 天 {window}）"]
     attention = False
 
     for name, report in (("RIIN", riin), ("SDS", sds)):
@@ -73,30 +65,26 @@ def build_daily_message(
         except Exception as err:  # noqa: BLE001
             lines.append(f"**{name}** 核验结果解析失败：{err}")
             attention = True
-        lines.append("")
 
     processed, failed = (ocr_today or {}).get("processed", 0), (ocr_today or {}).get("failed", 0)
-    lines.append(f"**OCR 今日** 已处理 {processed:,} 单 · 识别失败 {failed:,} 单" + (" ✅" if not failed else ""))
+    ocr_txt = f"**OCR 今日** 处理 {processed:,} · 识别失败 {failed:,}" + (" ✅" if not failed else " ⚠️")
     if ocr_pending:
-        lines.append(f"> 累计待处理 {ocr_pending:,} 单")
-    lines.append("")
+        ocr_txt += f"（累计待处理 {ocr_pending:,}）"
+    lines.append(ocr_txt)
 
     if failures:
         attention = True
-        lines.append(f"**失败任务(24h)** 共 {len(failures)} 次 🔴")
+        lines.append(f"**失败任务(24h)** {len(failures)} 次 🔴")
         for f in failures[:6]:
             start = (f.get("start") or "")[5:]  # MM-DD HH:MM
-            lines.append(f"> {f.get('flow', '?')} · run「{f.get('name', '?')}」{f.get('state', '?')} · {start}")
+            lines.append(f"> {f.get('flow', '?')}「{f.get('name', '?')}」{f.get('state', '?')} · {start}")
         if len(failures) > 6:
             lines.append(f"> …等共 {len(failures)} 次")
     else:
-        lines.append("**失败任务(24h)** 0 次 ✅")
+        lines.append("**失败任务(24h)** 0 ✅")
 
-    lines.append("")
-    if attention:
-        lines.append("⚠️ **存在需关注项，见上**")
-    else:
-        lines.append("✅ **数据全部一致，无异常**")
+    lines.append('<font color="warning">⚠️ 存在需关注项，见上</font>' if attention
+                 else '<font color="info">✅ 数据全部一致，无异常</font>')
     return "\n".join(lines), attention
 
 

flows/monitor/device_check.py

@@ -291,11 +291,11 @@ def _check_services() -> dict:
 
 
 def _mark(pct: float | None, threshold: int) -> str:
-    """百分比展示:超阈值加粗+🔴(WeCom aibot markdown 不支持 font 标签和表格)。"""
+    """百分比展示:超阈值用 warning 色加粗+🔴。"""
     if pct is None:
         return "—"
     if pct >= threshold:
-        return f"**{pct:.0f}%**🔴"
+        return f'<font color="warning">**{pct:.0f}%** 🔴</font>'
     return f"{pct:.0f}%"
 
 
@@ -343,104 +343,94 @@ def device_check(alarm_threshold: int = 80) -> dict:
         print(f"[device-check] 磁盘检查失败: {err}")
 
     threshold = alarm_threshold
-    header = f"🖥 **设备日报** {datetime.now():%m-%d %H:%M}（过去 24h · 采样 {agg['count']} 次"
+    header = f"## 🖥 设备日报 {datetime.now():%m-%d %H:%M}（24h 采样 {agg['count']} 次"
     if agg.get("firstTs"):
         first = datetime.fromisoformat(agg["firstTs"])
         if first > datetime.now() - timedelta(hours=23):
             header += f" · 自 {first:%m-%d %H:%M} 起"
-    lines = [header + "）", ""]
+    lines = [header + "）"]
 
     # ---- 内存 / swap ----
     mem, swap = agg.get("mem"), agg.get("swap")
     if mem:
-        lines.append(f"**内存** 平均 {mem['avg']:.0f}% · 峰值 {_mark(mem['peak'], threshold)} · 最低 {mem['min']:.0f}%"
-                     + (f"（共 {_gb((agg.get('memTotal') or 0) * (1 << 30))}）" if agg.get("memTotal") else ""))
+        total_txt = f"（共 {_gb((agg.get('memTotal') or 0) * (1 << 30))}）" if agg.get("memTotal") else ""
+        lines.append(f"**内存** 均 {mem['avg']:.0f}% · 峰 {_mark(mem['peak'], threshold)} · 低 {mem['min']:.0f}%{total_txt}")
     else:
         try:
             now_mem = _check_memory()
-            lines.append(f"**内存** 当前 {_mark(now_mem['pct'], threshold)}（{now_mem['used']}/{now_mem['total']}，无采样数据）")
+            lines.append(f"**内存** 当前 {_mark(now_mem['pct'], threshold)}（{now_mem['used']}/{now_mem['total']}，无采样）")
             mem = {"peak": now_mem["pct"]}
         except Exception:  # noqa: BLE001
             lines.append("**内存** 检查失败")
             mem = None
     if swap:
-        lines.append(f"**交换内存** 平均 {swap['avg']:.0f}% · 峰值 {_mark(swap['peak'], threshold)} · 最低 {swap['min']:.0f}%"
-                     + (f"（共 {_gb((agg.get('swapTotal') or 0) * (1 << 30))}）" if agg.get("swapTotal") else ""))
+        total_txt = f"（共 {_gb((agg.get('swapTotal') or 0) * (1 << 30))}）" if agg.get("swapTotal") else ""
+        lines.append(f"**交换内存** 均 {swap['avg']:.0f}% · 峰 {_mark(swap['peak'], threshold)} · 低 {swap['min']:.0f}%{total_txt}")
     else:
         lines.append("**交换内存** 无采样数据")
         swap = None
 
     # ---- 磁盘:总体 / 根目录 / home ----
-    lines.append("**磁盘**")
     if overall:
-        lines.append(f"> 总体 已用 {_gb(overall['used'])} · 剩余 {_gb(overall['free'])}（{_mark(overall['pct'], threshold)}）")
+        lines.append(f"**磁盘** 总体 已用 {_gb(overall['used'])} · 剩 {_gb(overall['free'])}"
+                     f"（{_mark(overall['pct'], threshold)}）")
+    else:
+        lines.append("**磁盘** 检查不可用")
     label_map = {"/": "root", "/home": "home"}
     for m in mounts:
         g = growth.get(label_map.get(m["label"], ""))
-        growth_txt = ""
-        if g and g.get("dir"):
-            growth_txt = f"｜增长最快 {g['dir']} {_fmt_growth(g['growth'])}"
-        elif m["label"] in ("/", "/home"):
-            growth_txt = "｜增长数据不足" if not g else ""
-        lines.append(f"> {m['label']} 已用 {_gb(m['used'])} · 剩余 {_gb(m['free'])}"
-                     f"（{_mark(m['pct'], threshold)}）{growth_txt}")
-    if not mounts:
-        lines.append("> 磁盘检查不可用")
+        growth_txt = f" · 增长最快 {g['dir']} {_fmt_growth(g['growth'])}" if g and g.get("dir") else ""
+        lines.append(f"> {m['label']} {_mark(m['pct'], threshold)} · 已用 {_gb(m['used'])} · 剩 {_gb(m['free'])}{growth_txt}")
 
     # ---- GPU ----
     gpu_stats = agg.get("gpus") or []
     if gpu_stats:
         for g in gpu_stats:
-            name = f"{g['name']}（GPU{g['index']}）" if g.get("name") else f"GPU{g['index']}"
+            name = g.get("name") or f"GPU{g['index']}"
             util = g.get("util")
-            util_txt = f"利用率 平均 {util['avg']:.0f}% · 峰值 {util['peak']:.0f}% · 最低 {util['min']:.0f}%" if util else "利用率 无数据"
-            mem_peak = g.get("memPeakUsed")
-            mem_total = g.get("memTotal")
+            util_txt = (f"利用率 均 {util['avg']:.0f}% · 峰 {util['peak']:.0f}% · 低 {util['min']:.0f}%"
+                        if util else "利用率 无数据")
+            mem_peak, mem_total = g.get("memPeakUsed"), g.get("memTotal")
             if mem_peak is not None and mem_total:
-                mem_pct = mem_peak / mem_total * 100
-                mem_txt = f"显存峰值 {_gb(mem_peak * (1 << 30))}/{_gb(mem_total * (1 << 30))}（{_mark(mem_pct, threshold)}）"
+                mem_txt = (f"显存峰 {_gb(mem_peak * (1 << 30))}/{_gb(mem_total * (1 << 30))}"
+                           f"（{_mark(mem_peak / mem_total * 100, threshold)}）")
             else:
                 mem_txt = "显存 无数据"
             temp_peak = g.get("tempPeak")
-            if temp_peak is not None:
-                temp_txt = f"温度峰值 {temp_peak:.0f}°C" + ("🔴 过热" if temp_peak >= GPU_TEMP_WARN else " 正常 ✅")
-            else:
-                temp_txt = "温度 无数据"
-            lines.append(f"**GPU** {name}｜{util_txt}｜{mem_txt}｜{temp_txt}")
+            temp_txt = (f"温度峰 {temp_peak:.0f}°C" + (" 🔴过热" if temp_peak >= GPU_TEMP_WARN else " ✅")
+                        if temp_peak is not None else "温度 无数据")
+            lines.append(f"**GPU** {name} {util_txt} ｜ {mem_txt} ｜ {temp_txt}")
     else:
         gpus_now = _check_gpus()
         if isinstance(gpus_now, list) and gpus_now:
             for g in gpus_now:
-                lines.append(f"**GPU** {g['name']}｜利用率 {g['utilPct']:.0f}%｜显存 {g['memUsed']}/{g['memTotal']}"
-                             f"（无采样数据）")
+                lines.append(f"**GPU** {g['name']} 利用率 {g['utilPct']:.0f}% · 显存 {g['memUsed']}/{g['memTotal']}（无采样）")
         else:
             lines.append(f"**GPU** {gpus_now if isinstance(gpus_now, str) else '未检测到'}")
 
-    # ---- Docker / 失败任务 / 探活 ----
+    # ---- Docker / 探活 / 失败任务 ----
     docker = checks.get("docker") or {}
     issues = docker.get("issues") or []
+    svc = checks.get("services") or {}
     if docker.get("running") is None:
-        lines.append(f"**Docker** {issues[0]['issue'] if issues else '不可用'}")
+        docker_txt = issues[0]["issue"] if issues else "不可用"
     else:
-        docker_line = f"**Docker** 运行 {docker['running']}/{docker.get('total', '?')}"
-        if docker.get("stopped"):
-            docker_line += f" · 已停用 {docker['stopped']}"
-        docker_line += f" · 异常 **{len(issues)}**🔴" if issues else " · 异常 0"
-        lines.append(docker_line)
+        docker_txt = f"运行 {docker['running']}/{docker.get('total', '?')} · 异常 {len(issues)}" + ("🔴" if issues else "")
+    if svc:
+        docker_txt += f" ｜ OCR {'✅' if svc.get('ocr') else '🔴'} ｜ PG {'✅' if svc.get('pg') else '🔴'}"
+    lines.append(f"**Docker** {docker_txt}")
     for it in issues[:8]:
         lines.append(f"> 🔴 {it['name']}：{it['issue']}")
 
     failures = checks.get("prefectFailures") or []
-    lines.append(f"**失败任务(24h)** {len(failures)} 次" + (" ✅" if not failures else "🔴"))
-    for f in failures[:5]:
-        lines.append(f"> 🔴 {f['flow']} ·「{f['name']}」{f['state']} · {f['start']}")
-    if len(failures) > 5:
-        lines.append(f"> …共 {len(failures)} 次")
-
-    svc = checks.get("services") or {}
-    if svc:
-        lines.append(f"**探活** OCR {'✅' if svc.get('ocr') else '🔴'}｜PG {'✅' if svc.get('pg') else '🔴'}"
-                     f"｜负载 {os.getloadavg()[0]:.1f}")
+    if failures:
+        lines.append(f"**失败任务(24h)** {len(failures)} 次 🔴")
+        for f in failures[:5]:
+            lines.append(f"> {f['flow']}「{f['name']}」{f['state']} · {(f.get('start') or '')[5:]}")
+        if len(failures) > 5:
+            lines.append(f"> …共 {len(failures)} 次")
+    else:
+        lines.append("**失败任务(24h)** 0 ✅")
 
     mem_peak_for_alarm = mem.get("peak") if mem else None
     swap_peak_for_alarm = swap.get("peak") if swap else None
@@ -452,7 +442,8 @@ def device_check(alarm_threshold: int = 80) -> dict:
         or any((g.get("tempPeak") or 0) >= GPU_TEMP_WARN for g in gpu_stats)
         or bool(issues) or bool(failures) or not svc.get("ocr") or not svc.get("pg")
     )
-    lines += ["", ("🔴 **有项目需要处理，见上**" if alarms else "✅ **一切正常**")]
+    lines.append('<font color="warning">🔴 有项目需要处理，见上</font>' if alarms
+                 else '<font color="info">✅ 一切正常</font>')
 
     content = "\n".join(lines)
     sent = send_markdown(content)