Repair official collection and retire exhausted material tasks

web/src/common/apis/calendar/type.ts

@@ -12,7 +12,7 @@ export interface CalendarItem {
   unit: string | null
   importance: number
   scheduled_at: string
-  status: "scheduled" | "waiting" | "delayed" | "released" | "withdrawn" | "error" | "historical" | "unavailable" | "recorded"
+  status: "retired" | "scheduled" | "waiting" | "delayed" | "released" | "withdrawn" | "error" | "historical" | "unavailable" | "recorded"
   actual: string | null
   previous: string | null
   forecast: string | null

web/src/common/apis/crawler/type.ts

@@ -37,6 +37,7 @@ export interface SourceInfo {
 }
 
 export interface CollectionRetry {
+  retired_at?: string
   document: { url: string, canonical?: string }
   attempts: number
   next_at: number
@@ -51,6 +52,8 @@ export interface SourcesInfo {
 }
 
 export interface CalendarSourceInfo {
+  enabled: boolean
+  retired_count: number
   code: string
   name: string
   region_code: string

web/src/pages/calendar/index.vue

@@ -26,7 +26,7 @@ const detail = ref<CalendarItem | null>(null)
 const country = ref("")
 const impactLabels = { pending: "待公布", bullish: "利多", bearish: "利空", neutral: "影响较小", uncertain: "待判断" }
 const countries = computed(() => data.value?.countries ?? [])
-const labels = { scheduled: "待公布", waiting: "获取中", delayed: "取数延迟", released: "已公布", withdrawn: "已撤回", error: "采集异常", historical: "仅有日程", unavailable: "官方未公布", recorded: "已收录" }
+const labels = { retired: "已停止采集", scheduled: "待公布", waiting: "获取中", delayed: "取数延迟", released: "已公布", withdrawn: "已撤回", error: "采集异常", historical: "仅有日程", unavailable: "官方未公布", recorded: "已收录" }
 const formatted = (time: string) => dayjs(time).tz(zone).format("MM-DD HH:mm:ss")
 const groups = computed(() => {
   const result = new Map<string, CalendarItem[]>()

web/src/pages/crawler/components/CalendarSourcePanel.vue

@@ -16,12 +16,13 @@ const date = (at: string | null) => at ? formatTime(at) : "尚无记录"
           日历
         </el-tag>
         <div class="flex-1" />
-        <el-tag :type="!source.worker_alive ? 'danger' : source.errors.length ? 'warning' : source.schedule_success_at ? 'success' : 'info'" size="small">
-          {{ !source.worker_alive ? "进程离线" : source.errors.length ? "采集异常" : source.schedule_success_at ? "同步正常" : "待同步" }}
+        <el-tag :type="!source.enabled ? 'info' : !source.worker_alive ? 'danger' : source.errors.length ? 'warning' : source.schedule_success_at ? 'success' : 'info'" size="small">
+          {{ !source.enabled ? "已停用" : !source.worker_alive ? "进程离线" : source.errors.length ? "采集异常" : source.schedule_success_at ? "同步正常" : "待同步" }}
         </el-tag>
       </div>
     </template>
     <dl class="grid grid-cols-[auto_1fr] gap-x-3 gap-y-2 text-xs text-slate-500">
+      <dt>已停止采集</dt><dd>{{ source.retired_count }} 场（历史资料保留）</dd>
       <dt>进程心跳</dt><dd>{{ date(source.heartbeat_at) }}</dd>
       <dt>日程最近检查</dt><dd>{{ date(source.schedule_checked_at) }}</dd>
       <dt>日程最近成功</dt><dd>{{ date(source.schedule_success_at) }}</dd>

web/src/pages/crawler/components/SourcePanel.vue

@@ -144,21 +144,24 @@ onMounted(loadLatest)
         </div>
       </div>
     </div>
-    <div v-if="source.collection_stats?.unresolved_bills" class="text-xs text-amber-600">
+    <div v-if="source.collection_stats?.active_gaps !== 0 && source.collection_stats?.unresolved_bills" class="text-xs text-amber-600">
       待核验法案 {{ source.collection_stats.unresolved_bills }}；待重试 {{ source.collection_stats.bill_retry_pending }}；重试已耗尽 {{ source.collection_stats.bill_retry_exhausted }}
     </div>
-    <div v-if="source.collection_stats?.attachment_gaps" class="text-xs text-amber-600">
+    <div v-if="source.collection_stats?.active_gaps !== 0 && source.collection_stats?.attachment_gaps" class="text-xs text-amber-600">
       附件待核验文档 {{ source.collection_stats.attachment_gaps }}；待重试 {{ source.collection_stats.attachment_retry_pending }}；重试已耗尽 {{ source.collection_stats.attachment_retry_exhausted }}，请核对原文
     </div>
-    <div v-if="source.collection_stats?.document_gaps" class="text-xs text-amber-600">
+    <div v-if="source.collection_stats?.active_gaps !== 0 && source.collection_stats?.document_gaps" class="text-xs text-amber-600">
       正文待核验 {{ source.collection_stats.document_gaps }}；待重试 {{ source.collection_stats.document_retry_pending }}；重试已耗尽 {{ source.collection_stats.document_retry_exhausted }}，请核对来源日志
     </div>
+    <p v-if="source.collection_stats?.retired_count" class="text-xs text-slate-500">
+      已停止采集 {{ source.collection_stats.retired_count }} 条，原因及原文保留在详情中。
+    </p>
     <details v-if="gaps.length" class="text-xs text-amber-700">
       <summary class="cursor-pointer">
         缺口详情（{{ gaps.length }}）
       </summary>
       <div v-for="gap in gaps" :key="gap.key" class="mt-2 border border-amber-200 rounded border-solid p-2">
-        <div>{{ gap.label }}；已尝试 {{ gap.attempts }} 次；{{ gap.exhausted ? "重试已耗尽" : `下次重试不早于 ${formatTime(gap.nextAt)}` }}</div>
+        <div>{{ gap.label }}；已尝试 {{ gap.attempts }} 次；{{ gap.retired ? "已停止采集" : gap.exhausted ? "重试已耗尽" : `下次重试不早于 ${formatTime(gap.nextAt)}` }}</div>
         <div class="my-1 whitespace-pre-wrap break-words">
           {{ gap.error }}
         </div>

web/src/pages/crawler/sourceStatus.ts

@@ -15,7 +15,7 @@ export function sourceStatus(source: SourceInfo, restarting = false, now = Date.
     return { type: "primary", text: "采集中" } as const
   if (source.consecutive_failures)
     return { type: "danger", text: "失败待重试" } as const
-  if (source.collection_stats?.document_gaps || source.collection_stats?.attachment_gaps || source.collection_stats?.unresolved_bills)
+  if ((source.collection_stats?.active_gaps ?? (source.collection_stats?.document_gaps || source.collection_stats?.attachment_gaps || source.collection_stats?.unresolved_bills)))
     return { type: "warning", text: "存在采集缺口" } as const
   return { type: "info", text: "等待调度" } as const
 }
@@ -49,6 +49,7 @@ export function collectionGaps(source: Pick<SourceInfo, "history_cursor">) {
     url: originalUrl(retry.document.canonical ?? retry.document.url),
     error: retry.error || "历史记录未保存具体原因，请核对原文",
     attempts: retry.attempts,
+    retired: !!retry.retired_at,
     exhausted: retry.attempts >= 3,
     nextAt: new Date(retry.next_at * 1000).toISOString()
   })))

web/tests/crawler.test.ts

@@ -102,3 +102,32 @@ test("gap links preserve canonical pages and do not rewrite unrelated URLs", ()
     assert.equal(collectionGaps(source)[0].url, url)
   }
 })
+
+test("retired gaps retain evidence without an active warning", () => {
+  const source = {
+    enabled: true,
+    consecutive_failures: 0,
+    code: "doj",
+    name: "DOJ",
+    region_code: "US",
+    list_url: "https://www.justice.gov/",
+    interval_seconds: 60,
+    backfill_hours: 72,
+    last_success_at: null,
+    last_error: null,
+    paused_until: null,
+    supports_history: true,
+    history_target: null,
+    history_position: null,
+    history_done: false,
+    today_new: 0,
+    today_revised: 0,
+    total_items: 0,
+    process: { state: "running", pid: 1, started_at: null, next_run_at: "2026-11-05T00:00:00Z" },
+    collection_stats: { active_gaps: 0, document_gaps: 1, retired_count: 1 },
+    history_cursor: { document_retries: { old: { document: { url: "https://www.justice.gov/old" }, attempts: 3, next_at: 1, error: "HTTP 503", retired_at: "2026-11-05T00:00:00Z" } } }
+  } as SourceInfo
+  assert.equal(sourceStatus(source).text, "等待调度")
+  assert.equal(collectionGaps(source)[0].retired, true)
+  assert.equal(collectionGaps(source)[0].error, "HTTP 503")
+})