feat: 脚本执行显性输出当前阶段与 AI 模型供应商/名称

- pipeline.sh 每阶段 banner(━━━ M4 翻译+事件抽取(AI 大模型: deepseek / deepseek-v4-flash)━━━)
- ai_model_info() 从 system.yaml 读取场景模型(translation/daily_report/embedding)
- Python 层:M4/M5/日报 显性打印 provider/model(场景标注)
- 已同步 pi5 实测:客户端初始化日志含供应商/模型
This commit is contained in:
2026-08-12 11:20:51 +08:00
parent bdd936a3e4
commit 012cb615d3
7 changed files with 65 additions and 12 deletions
+2 -2
View File
@@ -46,14 +46,14 @@ export $(grep -v '^#' .env | grep -v '^$' | xargs 2>/dev/null || true)
# 部分源抓取失败不阻塞管道(原语义);抓取本身按 URL 去重(index.jsonl),
# 已抓取过的 URL 不会重复写入;输出实时显示每源进度
if step_should_run M1_crawl; then
LOG "[1/2] Pi M1 抓取(8G headful + HTTP 代理)..."
LOG "━━━ [1/2] M1 抓取(headful Playwright + HTTP 代理)━━━"
bash "$SCRIPT_DIR/domestic_crawl_8g.sh" 2>&1 | tee -a "$FULL_LOG" \
|| LOG "WARNING: 部分源抓取失败,继续管道"
step_mark M1_crawl
fi
# ── 2. M2→M6 管道(含日报)──
LOG "[2/2] 全链路管道..."
LOG "━━━ [2/2] M2→M6 管道 + 日报 ━━━"
if [ "$RESUME" = "1" ]; then
bash "$SCRIPT_DIR/pipeline.sh" --resume 2>&1 | tee -a "$FULL_LOG"
else