refactor: 清理历史 AI Agent 文档残留 + 重构 docs/ + Pipeline 健壮性修复

- docs: 删除 CLAUDE.md / continuation.md / english-news-plan.md 及旧版 intlnews_usage.*，
        统一迁移到 docs/{README,architecture,quickstart,usage,pipeline,configuration,deployment,development,faq}.md
- README: 精简为仓库入口，指向 docs/
- configs/sources.yaml: 更新注释指向新文档
- .env.example: 修正 DashScope Embedding 端点说明

Pipeline 修复：
- dedup/llm/embedding/vectorstore/reporter: 过滤 M2 no_content / 空正文，避免污染下游与 Qdrant
- dedup/pipeline: 改为先写唯一文件再写指纹，避免崩溃导致文章永久丢失
- crawler/orchestrator: sources_crawled 改为“尝试数”，成功数 = crawled - failed
- crawler/storage: write_index_jsonl 从文章路径推断日期，修复跨天/测试路径问题
- scheduler/pipeline: STEP_TIMEOUTS 实际生效（SIGALRM）
- scheduler/reporter: emb_count 排除 index.json；日报跳过无原文事件
- vectorstore/pipeline: payload 增加 source_ids；--recreate --all 时空日期也重建 collection
- app/cli: extract/dedup/translate/embed/index/pipeline 支持 --date；embed/index 支持 --all；crawl 全源失败返回非零
- scripts: domestic_full/crawl_8g/crawl_2g/pipeline 安全加载 .env；M1 全失败不标记且最终退出码=1

scheduler/pipeline.py

@@ -4,6 +4,7 @@
 """
 
 import logging
+import signal
 import time
 from dataclasses import dataclass, field
 from datetime import datetime
@@ -30,6 +31,47 @@ STEP_TIMEOUTS: dict[str, int] = {
 }
 
 
+class _StepTimeout(Exception):
+    """步骤超时专用异常，避免与业务 TimeoutError 混淆。"""
+
+
+def _run_step_with_timeout(func, name: str, date_str: str, timeout: int | None) -> "StepResult":
+    """在支持 SIGALRM 的主线程中为单步执行添加超时保护。"""
+    if timeout is None:
+        return func(date_str)
+
+    started = datetime.now()
+
+    if not hasattr(signal, "SIGALRM"):
+        return func(date_str)
+
+    def _handler(signum, frame):  # noqa: ARG001
+        raise _StepTimeout(f"step {name} timed out after {timeout}s")
+
+    try:
+        old_handler = signal.getsignal(signal.SIGALRM)
+    except (ValueError, OSError):
+        # 非主线程无法设置信号处理器，直接不启用超时
+        return func(date_str)
+
+    signal.signal(signal.SIGALRM, _handler)
+    signal.setitimer(signal.ITIMER_REAL, timeout)
+    try:
+        return func(date_str)
+    except _StepTimeout:
+        elapsed = (datetime.now() - started).total_seconds()
+        return StepResult(
+            name=name,
+            success=False,
+            elapsed_sec=elapsed,
+            message=f"超时（>{timeout}s）",
+            started_at=started,
+        )
+    finally:
+        signal.setitimer(signal.ITIMER_REAL, 0)
+        signal.signal(signal.SIGALRM, old_handler)
+
+
 @dataclass
 class StepResult:
     """单步执行结果。"""
@@ -210,7 +252,9 @@ def run_pipeline(
             continue
 
         logger.info("── 步骤 %s 开始 ──", name)
-        sr = func(date_str)
+        sr = _run_step_with_timeout(
+            func, name, date_str, STEP_TIMEOUTS.get(name)
+        )
         result.steps.append(sr)
 
         flag = "✅" if sr.success else "❌"

scheduler/reporter.py

@@ -210,6 +210,9 @@ def _load_events_window(now: datetime) -> list[dict]:
                 continue
             try:
                 data = json.loads(fp.read_text(encoding="utf-8"))
+                # 防御性过滤：M2 no_content 残留不应进入日报统计/摘要。
+                if not (data.get("content_en") or "").strip():
+                    continue
                 # 时间过滤：publish_time 在 25 小时内
                 pt_str = data.get("publish_time", "")
                 pt = _try_parse_time(pt_str)
@@ -267,7 +270,11 @@ def _collect_stats_window(now: datetime) -> dict:
             deduped += len(list(dedup_dir.glob("*.json")))
         emb_dir = Path(f"data/embeddings/{day_str}")
         if emb_dir.is_dir():
-            emb_count += len(list(emb_dir.glob("*.json")))
+            # 不把 index.json 计入实际向量文章数
+            emb_count += len([
+                f for f in emb_dir.glob("*.json")
+                if f.name != "index.json"
+            ])
         for idx in Path("data/raw").glob(f"*/{day_str}/index.jsonl"):
             src = idx.parent.parent.name
             n = sum(1 for _ in open(idx, encoding="utf-8"))