增加sys/debug 部署测试；agent dev/user/instance元信息提取优化；sys/tests 优化 (#26)

Reviewed-on: #26
Reviewed-by: xuxt <xuxt@zgclab.edu.cn>
Reviewed-by: huhy <husteryezi@163.com>
Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>

src/sys/debug/scripts/07_logs_send_and_assert.sh

@@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+log "Sending logs and asserting ES counts"
+
+get_count() {
+  local idx="$1"
+  curl -s "http://localhost:9200/${idx}/_count?ignore_unavailable=true&allow_no_indices=true" | sed -E 's/.*"count":([0-9]+).*/\1/' | awk 'NF{print $0;exit} END{if(NR==0)print 0}'
+}
+
+train0=$(get_count "train-*")
+infer0=$(get_count "infer-*")
+base=$((train0 + infer0))
+log "initial counts: train=${train0} infer=${infer0} total=${base}"
+
+service_id() {
+  compose ps -q "$1"
+}
+
+send_logs() {
+  local sid="$1"; local hosttag="$2"
+  docker exec "$sid" sh -lc 'mkdir -p /logs/train /logs/infer'
+  docker exec "$sid" sh -lc "ts=\
+\$(date '+%F %T'); echo \"\$ts INFO [$hosttag] training step=1 loss=1.23 model=bert\" >> /logs/train/train-demo.log"
+  docker exec "$sid" sh -lc "ts=\
+\$(date '+%F %T'); echo \"\$ts INFO [$hosttag] training step=2 loss=1.10 model=bert\" >> /logs/train/train-demo.log"
+  docker exec "$sid" sh -lc "ts=\
+\$(date '+%F %T'); echo \"\$ts WARN [$hosttag] inference slow on batch=2 latency=1.9s\" >> /logs/infer/infer-demo.log"
+}
+
+CID_A="$(service_id node-a)"
+CID_B="$(service_id node-b)"
+
+[[ -n "$CID_A" && -n "$CID_B" ]] || { echo "[ERR] node containers not found" >&2; exit 1; }
+
+send_logs "$CID_A" "host01"
+send_logs "$CID_B" "host02"
+
+log "Waiting for ES to ingest"
+sleep 10
+
+train1=$(get_count "train-*")
+infer1=$(get_count "infer-*")
+final=$((train1 + infer1))
+log "final counts: train=${train1} infer=${infer1} total=${final}"
+
+if (( final <= base )); then
+  echo "[ERR] ES total did not increase (${base} -> ${final})" >&2
+  exit 1
+fi
+
+if (( final < 4 )); then
+  echo "[ERR] ES total below expected threshold: ${final} < 4" >&2
+  exit 1
+fi
+
+es_health=$(curl -s "http://localhost:9200/_cluster/health" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
+if [[ "$es_health" != "green" && "$es_health" != "yellow" ]]; then
+  echo "[ERR] ES health not green/yellow: $es_health" >&2
+  exit 1
+fi
+
+if ! curl -fs "http://localhost:5601/api/status" >/dev/null 2>&1; then
+  echo "[WARN] Kibana status endpoint not available"
+fi
+
+log "ES counts increased and services healthy"