llm-intelligence/scripts/run_daily.sh

#!/bin/bash
# run_daily.sh - 每日数据采集与报告生成流水线
# Sprint 3: 完整调度脚本（采集→质量检查→报告生成→归档→通知）
set -euo pipefail

PROJECT_DIR="/home/long/project/llm-intelligence"
. "$PROJECT_DIR/scripts/report_utils.sh"
DB_URL="${DATABASE_URL:-host=/var/run/postgresql dbname=llm_intelligence user=long sslmode=disable}"
REPORT_DATE="$(report_date_value)"
LOG_FILE="/tmp/llm_hub_daily_${REPORT_DATE}.log"
FEISHU_WEBHOOK="${FEISHU_WEBHOOK:-}"
MODEL_COUNT=""

# 日志函数
log() {
    echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE"
}

# 错误处理
error_exit() {
    local output_path=""
    log "❌ 错误: $1"
    # 降级：复制昨日报告
    fallback_report
    if [ -f "$(report_markdown_path "$REPORT_DATE")" ]; then
        output_path="$(report_markdown_path "$REPORT_DATE")"
    fi
    track_report_state "$DB_URL" "$REPORT_DATE" "failed" "${MODEL_COUNT:-}" "" "$output_path" "$1" >> "$LOG_FILE" 2>&1 || true
    # 发送告警
    if [ -n "$FEISHU_WEBHOOK" ]; then
        send_alert "$1"
    fi
    exit 1
}

# 降级：复制昨日报告
fallback_report() {
    local yesterday yesterday_md today_md yesterday_html today_html
    yesterday=$(date -d "yesterday" +%Y-%m-%d)
    yesterday_md="${PROJECT_DIR}/$(report_markdown_path "$yesterday")"
    today_md="${PROJECT_DIR}/$(report_markdown_path "$REPORT_DATE")"
    yesterday_html="${PROJECT_DIR}/$(report_html_path "$yesterday")"
    today_html="${PROJECT_DIR}/$(report_html_path "$REPORT_DATE")"
    
    if [ -f "$yesterday_md" ]; then
        cp "$yesterday_md" "$today_md"
        sed -i "s/${yesterday}/${REPORT_DATE}/g" "$today_md"
        sed -i "1s/^/# [数据延迟] /" "$today_md"
        if [ -f "$yesterday_html" ]; then
            cp "$yesterday_html" "$today_html"
            sed -i "s/${yesterday}/${REPORT_DATE}/g" "$today_html"
        fi
        if [ -f "$today_md" ] && [ -f "$today_html" ]; then
            archive_report_artifacts "$REPORT_DATE" >> "$LOG_FILE" 2>&1 || true
        fi
        log "⚠️ 已复制昨日报告并标记[数据延迟]"
    else
        log "⚠️ 无昨日报告可供复制"
    fi
}

# 发送飞书告警
send_alert() {
    local msg="$1"
    local payload="{\"msg_type\":\"text\",\"content\":{\"text\":\"🚨 LLM Hub 日报失败\\n日期: ${REPORT_DATE}\\n错误: ${msg}\\n请检查日志: ${LOG_FILE}\"}}"
    
    curl -s -X POST -H "Content-Type: application/json" \
        -d "$payload" \
        "$FEISHU_WEBHOOK" > /dev/null || true
    log "📢 飞书告警已发送"
}

# 主流程
log "🚀 开始每日流水线: ${REPORT_DATE}"

cd "$PROJECT_DIR"

# 1. 数据采集
log "1️⃣ 数据采集..."
if ! go run scripts/fetch_openrouter.go >> "$LOG_FILE" 2>&1; then
    error_exit "数据采集失败"
fi
log "✅ 数据采集完成"

# 2. 数据质量检查
log "2️⃣ 数据质量检查..."
MODEL_COUNT=$(psql "$DB_URL" -t -c "SELECT COUNT(*) FROM models WHERE deleted_at IS NULL" 2>/dev/null | tr -d ' ')
if [ "$MODEL_COUNT" -lt 10 ]; then
    error_exit "模型数量不足: ${MODEL_COUNT} < 10"
fi
log "✅ 数据质量检查通过 (模型数: ${MODEL_COUNT})"

# 3. 生成日报
log "3️⃣ 生成日报..."
export DATABASE_URL="$DB_URL"
if ! go run scripts/generate_daily_report.go >> "$LOG_FILE" 2>&1; then
    error_exit "日报生成失败"
fi
log "✅ 日报生成完成"

# 4. 校验归档
log "4️⃣ 校验归档..."
if [ ! -f "$(report_archive_markdown_path "$REPORT_DATE")" ] || [ ! -f "$(report_archive_html_path "$REPORT_DATE")" ]; then
    error_exit "日报归档失败"
fi
log "✅ 归档完成"

# 5. 校验运行记录
log "5️⃣ 校验运行记录..."
if ! psql "$DB_URL" -Atqc "select count(*) from daily_report where report_date = DATE '${REPORT_DATE}' and status = 'generated';" | awk '{ exit !($1 >= 1) }'; then
    error_exit "daily_report 未写入 generated 记录"
fi
if ! psql "$DB_URL" -Atqc "select count(*) from report_runs where report_date = DATE '${REPORT_DATE}' and status = 'generated';" | awk '{ exit !($1 >= 1) }'; then
    error_exit "report_runs 未写入 generated 记录"
fi
log "✅ 日报记录更新完成"

log "🎉 每日流水线全部完成！"
log "📄 Markdown: $(report_markdown_path "$REPORT_DATE")"
log "🌐 HTML: $(report_html_path "$REPORT_DATE")"

exit 0