Fix official news retries, date boundaries and collection status

Bound document retries across realtime and history lanes, preserve safe completed reads on failed rounds, and retain unresolved gaps. Honor the longest access-block cooldown and measure retries from the actual failure time.

Filter dated official listings at the collection boundary, handle empty Federal Register days, and distinguish active rounds from waiting or failed processes in the console. Add captured-response regressions and isolated checkpoint validation.

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

@@ -7,6 +7,7 @@ import { useSessionScope } from "@@/composables/useSessionScope"
 import { formatTime } from "@@/utils/text"
 import { CircleCheck, RefreshRight } from "@element-plus/icons-vue"
 import dayjs from "dayjs"
+import { sourceStatus } from "../sourceStatus"
 
 /** logs 只用来发现「本轮完成」以刷新最新入库；alert 为连续失败达到告警阈值 */
 const props = defineProps<{
@@ -87,22 +88,7 @@ async function cancelHistory() {
   emit("changed")
 }
 
-const statusTag = computed(() => {
-  if (props.source.configuration_error)
-    return { type: "warning", text: props.source.configuration_error } as const
-  const process = props.source.process
-  if (props.restarting || process?.state === "restarting")
-    return { type: "warning", text: "重启中" } as const
-  if (!process)
-    return { type: "danger", text: "管理进程未运行" } as const
-  if (process.state === "stopped")
-    return { type: "danger", text: "子进程未运行" } as const
-  if (!props.source.enabled)
-    return { type: "info", text: "已停用" } as const
-  if (props.source.paused_until && new Date(props.source.paused_until) > new Date())
-    return { type: "warning", text: "失败退避中" } as const
-  return { type: "success", text: "运行中" } as const
-})
+const statusTag = computed(() => sourceStatus(props.source, props.restarting))
 
 onMounted(loadLatest)
 </script>
@@ -163,6 +149,9 @@ onMounted(loadLatest)
     <div v-if="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">
+      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>
     <div v-if="source.collection_stats?.discovered" class="text-xs text-slate-500">
       本轮发现 {{ source.collection_stats.discovered }}；筛除 {{ source.collection_stats.excluded ?? 0 }}；不完整包 {{ source.collection_stats.partial ?? 0 }}
     </div>

web/src/pages/crawler/index.vue

@@ -1,5 +1,5 @@
 <script lang="ts" setup>
-import type { SourcesInfo } from "@@/apis/crawler/type"
+import type { SourceInfo, SourcesInfo } from "@@/apis/crawler/type"
 import { createRssApi, listSourcesApi, restartCrawlerApi } from "@@/apis/crawler"
 import { useSessionScope } from "@@/composables/useSessionScope"
 import { formatTime } from "@@/utils/text"
@@ -8,6 +8,7 @@ import { logRequestError } from "@/http/axios"
 import CalendarSourcePanel from "./components/CalendarSourcePanel.vue"
 import SourcePanel from "./components/SourcePanel.vue"
 import { useCrawlerLogs } from "./composables/useCrawlerLogs"
+import { sourceStatus } from "./sourceStatus"
 
 const rssVisible = ref(false)
 const rssSaving = ref(false)
@@ -178,10 +179,10 @@ onMounted(async () => {
             {{ regions[row.region_code as keyof typeof regions] ?? row.region_code }}
           </template>
         </el-table-column>
-        <el-table-column label="状态" width="110">
+        <el-table-column label="状态" min-width="130">
           <template #default="{ row }">
-            <el-tag size="small" :type="row.enabled && row.process?.state === 'running' ? 'success' : 'info'">
-              {{ !row.enabled ? '已停用' : row.process?.state === 'running' ? '运行中' : '未运行' }}
+            <el-tag size="small" :type="sourceStatus(row as SourceInfo, restarting.has(row.code)).type">
+              {{ sourceStatus(row as SourceInfo, restarting.has(row.code)).text }}
             </el-tag>
           </template>
         </el-table-column>

web/src/pages/crawler/sourceStatus.ts

@@ -0,0 +1,21 @@
+import type { SourceInfo } from "@@/apis/crawler/type"
+
+export function sourceStatus(source: SourceInfo, restarting = false, now = Date.now()) {
+  if (source.configuration_error)
+    return { type: "warning", text: source.configuration_error } as const
+  if (!source.enabled)
+    return { type: "info", text: "已停用" } as const
+  if (restarting || source.process?.state === "restarting")
+    return { type: "warning", text: "重启中" } as const
+  if (!source.process || source.process.state === "stopped")
+    return { type: "danger", text: "采集进程未运行" } as const
+  if (source.paused_until && new Date(source.paused_until).getTime() > now)
+    return { type: "warning", text: "失败退避中" } as const
+  if (source.collection_stats?.round_running)
+    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)
+    return { type: "warning", text: "存在文档缺口" } as const
+  return { type: "info", text: "等待调度" } as const
+}

web/tests/crawler.test.ts

@@ -0,0 +1,37 @@
+import type { SourceInfo } from "../src/common/apis/crawler/type.ts"
+import assert from "node:assert/strict"
+import { test } from "node:test"
+import { sourceStatus } from "../src/pages/crawler/sourceStatus.ts"
+
+test("crawler status distinguishes process health from collection results", () => {
+  const source: SourceInfo = {
+    code: "test",
+    name: "Test",
+    region_code: null,
+    list_url: "https://example.invalid",
+    interval_seconds: 60,
+    backfill_hours: 72,
+    last_success_at: null,
+    last_error: null,
+    paused_until: null,
+    supports_history: false,
+    history_target: null,
+    history_position: null,
+    history_done: false,
+    today_new: 0,
+    today_revised: 0,
+    total_items: 0,
+    enabled: true,
+    consecutive_failures: 0,
+    process: { state: "running", pid: 1, started_at: null, next_run_at: "2026-11-05T00:00:00Z" },
+    collection_stats: { round_running: 0 }
+  }
+  assert.equal(sourceStatus(source).text, "等待调度")
+  assert.equal(sourceStatus({ ...source, collection_stats: { round_running: 1 } }).text, "采集中")
+  assert.equal(sourceStatus({ ...source, consecutive_failures: 2 }).text, "失败待重试")
+  assert.equal(sourceStatus({ ...source, paused_until: "2026-11-06T00:00:00Z" }, false, Date.parse("2026-11-05")).text, "失败退避中")
+  assert.equal(sourceStatus({ ...source, collection_stats: { document_gaps: 2 } }).text, "存在文档缺口")
+  assert.equal(sourceStatus({ ...source, enabled: false, consecutive_failures: 3 }).text, "已停用")
+  assert.equal(sourceStatus({ ...source, configuration_error: "待配置 CRAWLER_CONTACT_EMAIL" }).type, "warning")
+  assert.equal(sourceStatus({ ...source, process: null }).text, "采集进程未运行")
+})