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/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")
+})