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

scripts/pipeline.sh

@@ -43,10 +43,33 @@ STEP_LOG="$LOG_DIR/pipeline_$(date +%Y%m%d_%H%M%S).log"
 LOG "══════ 全链路管道开始（resume=${RESUME}）═══════"
 LOG "步骤日志: ${STEP_LOG}（终端实时显示完整进度）"
 
+# ── AI 模型信息读取（供阶段 banner 显性展示供应商/模型）──
+ai_model_info() {
+    # $1: 场景名（translation / daily_report）或 "embedding"
+    # 输出格式: "供应商 / 模型"
+    .venv/bin/python3 -c "
+import sys, yaml
+scene = sys.argv[1]
+raw = yaml.safe_load(open('configs/system.yaml', encoding='utf-8'))
+if scene == 'embedding':
+    cfg = raw.get('embedding', {})
+    p = cfg.get('provider', '?')
+    m = cfg.get('dashscope_model', '?')
+else:
+    base = raw.get('llm', {})
+    sc = (raw.get('llm_scenes', {}) or {}).get(scene, {})
+    merged = {**base, **sc}
+    p = merged.get('provider', '?')
+    m = merged.get('model') or merged.get(p + '_model', '?')
+print(f'{p} / {m}')
+" "$1"
+}
+
 # 加载 .env
 export $(grep -v '^#' .env | grep -v '^$' | xargs 2>/dev/null || true)
 
 # ── M2: 正文提取 ──
+LOG "━━━ M2 正文提取 ━━━"
 step_run M2_extract .venv/bin/python3 -c "
 from extractor.pipeline import process_all_sources
 stats = process_all_sources()
@@ -54,20 +77,23 @@ print(f'M2: {stats[\"total_articles\"]} 篇, {stats[\"elapsed_sec\"]:.0f}s')
 "
 
 # ── M3: 去重 ──
+LOG "━━━ M3 三层去重 ━━━"
 step_run M3_dedup .venv/bin/python3 -c "
 from dedup.pipeline import dedup_all_sources
 stats = dedup_all_sources()
 print(f'M3: 唯一 {stats[\"unique\"]}/重复 {stats[\"duplicate\"]}, {stats[\"elapsed_sec\"]:.0f}s')
 "
 
-# ── M4: 翻译+事件 ──
+# ── M4: 翻译+事件（AI 大模型）──
+LOG "━━━ M4 翻译+事件抽取（AI 大模型: $(ai_model_info translation)）━━━"
 step_run M4_translate .venv/bin/python3 -c "
 from llm.pipeline import translate_all_deduped
 stats = translate_all_deduped()
 print(f'M4: {stats[\"success\"]}/{stats[\"total\"]} 篇, {stats[\"elapsed_sec\"]:.0f}s')
 "
 
-# ── M5: 向量生成 ──
+# ── M5: 向量生成（AI 大模型）──
+LOG "━━━ M5 向量生成（AI 大模型: $(ai_model_info embedding)）━━━"
 step_run M5_embed .venv/bin/python3 -c "
 from embedding.pipeline import embed_all_events
 stats = embed_all_events()
@@ -75,13 +101,15 @@ print(f'M5: {stats[\"success\"]}/{stats[\"total\"]} 篇, {stats[\"elapsed_sec\"]
 "
 
 # ── M6: Qdrant 入库 ──
+LOG "━━━ M6 Qdrant 入库 ━━━"
 step_run M6_index .venv/bin/python3 -c "
 from vectorstore.pipeline import ingest_all_embeddings
 stats = ingest_all_embeddings()
 print(f'M6: {stats[\"ingested\"]}/{stats[\"total\"]} 条, {stats[\"elapsed_sec\"]:.0f}s')
 "
 
-# ── 日报 ──
+# ── 日报（AI 大模型）──
+LOG "━━━ 日报生成（AI 大模型: $(ai_model_info daily_report)）━━━"
 step_run report .venv/bin/python3 -c "
 from scheduler.reporter import generate_report
 report_id = generate_report()