ops(repair-bot): 主機白名單修復腳本 (Sprint 3)

110: sentry/harbor/gitea/gitea-runner/langfuse/alertmanager/signoz
188: openclaw/minio/signoz (docker compose) + redis/nginx/ollama (systemd)

安全設計: SSH command= 限制 + 嚴格白名單 + /var/log/awoooi-repair-bot.log
已部署: 110:/home/wooo/bin/ + 188:/home/ollama/bin/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
OG T
2026-04-05 11:11:55 +08:00
parent 7a6fa6359e
commit 77253a5d87
2 changed files with 152 additions and 0 deletions

View File

@@ -0,0 +1,67 @@
#!/bin/bash
# scripts/repair-bot/repair-bot-110.sh
# 修復機器人白名單腳本 — 110 主機 (DevOps 金庫)
# 2026-04-05 Claude Code: Sprint 3 Host Auto-Repair
#
# 安全設計:
# - SSH authorized_keys 的 command= 指向此腳本
# - 只允許執行 COMPOSE_DIRS 中定義的修復指令
# - 格式: repair:<component>
# - SSH key 洩漏也只能執行白名單內的 docker compose up -d
#
# 部署位置: /home/wooo/bin/repair-bot-110.sh (on 192.168.0.110)
# 使用者: wooo
LOG="/var/log/awoooi-repair-bot.log"
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG"; }
# 白名單: component → compose dir
declare -A COMPOSE_DIRS=(
["sentry"]="/opt/sentry"
["harbor"]="/home/wooo/harbor/harbor"
["gitea"]="/home/wooo/gitea"
["gitea-runner"]="/home/wooo/act-runner"
["langfuse"]="/home/wooo/langfuse"
["alertmanager"]="/home/wooo/monitoring"
["signoz"]="/home/wooo/signoz/deploy/docker"
)
CMD="${SSH_ORIGINAL_COMMAND:-}"
log "repair-bot-110 invoked: CMD=$CMD"
if [[ "$CMD" =~ ^repair:([a-z0-9_-]+)$ ]]; then
COMPONENT="${BASH_REMATCH[1]}"
DIR="${COMPOSE_DIRS[$COMPONENT]}"
if [ -z "$DIR" ]; then
log "DENIED: unknown component '$COMPONENT'"
echo "REPAIR_DENIED:unknown_component:$COMPONENT"
exit 1
fi
if [ ! -d "$DIR" ]; then
log "DENIED: directory not found '$DIR'"
echo "REPAIR_DENIED:dir_not_found:$DIR"
exit 1
fi
log "EXECUTING: cd $DIR && docker compose up -d"
cd "$DIR" && docker compose up -d 2>&1 | tail -5
EXIT_CODE=$?
if [ $EXIT_CODE -eq 0 ]; then
log "REPAIR_OK: $COMPONENT"
echo "REPAIR_OK:$COMPONENT"
else
log "REPAIR_FAIL: $COMPONENT (exit $EXIT_CODE)"
echo "REPAIR_FAIL:$COMPONENT:exit_$EXIT_CODE"
exit 1
fi
elif [ "$CMD" = "health" ]; then
# 健康檢查 — 允許連線測試
echo "REPAIR_BOT_HEALTHY:110"
else
log "DENIED: invalid command '$CMD'"
echo "REPAIR_DENIED:invalid_command"
exit 1
fi

View File

@@ -0,0 +1,85 @@
#!/bin/bash
# scripts/repair-bot/repair-bot-188.sh
# 修復機器人白名單腳本 — 188 主機 (主服務主機)
# 2026-04-05 Claude Code: Sprint 3 Host Auto-Repair
#
# 安全設計:
# - SSH authorized_keys 的 command= 指向此腳本
# - Docker Compose 類: docker compose up -d
# - Systemd 類: sudo systemctl restart
#
# 部署位置: /home/ollama/bin/repair-bot-188.sh (on 192.168.0.188)
# 使用者: ollama
LOG="/var/log/awoooi-repair-bot.log"
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG"; }
# 白名單: component → 修復方式
declare -A COMPOSE_DIRS=(
["openclaw"]="/home/ollama/clawbot-v5"
["minio"]="/home/ollama/minio"
["signoz"]="/home/ollama/signoz/deploy/docker"
)
declare -A SYSTEMD_SERVICES=(
["redis"]="redis-server"
["nginx"]="nginx"
["ollama"]="ollama"
)
CMD="${SSH_ORIGINAL_COMMAND:-}"
log "repair-bot-188 invoked: CMD=$CMD"
if [[ "$CMD" =~ ^repair:([a-z0-9_-]+)$ ]]; then
COMPONENT="${BASH_REMATCH[1]}"
# Docker Compose 類
DIR="${COMPOSE_DIRS[$COMPONENT]}"
if [ -n "$DIR" ]; then
if [ ! -d "$DIR" ]; then
log "DENIED: directory not found '$DIR'"
echo "REPAIR_DENIED:dir_not_found:$DIR"
exit 1
fi
log "EXECUTING: cd $DIR && docker compose up -d"
cd "$DIR" && docker compose up -d 2>&1 | tail -5
EXIT_CODE=$?
if [ $EXIT_CODE -eq 0 ]; then
log "REPAIR_OK: $COMPONENT"
echo "REPAIR_OK:$COMPONENT"
else
log "REPAIR_FAIL: $COMPONENT (exit $EXIT_CODE)"
echo "REPAIR_FAIL:$COMPONENT:exit_$EXIT_CODE"
exit 1
fi
exit 0
fi
# Systemd 類
SVC="${SYSTEMD_SERVICES[$COMPONENT]}"
if [ -n "$SVC" ]; then
log "EXECUTING: sudo systemctl restart $SVC"
sudo systemctl restart "$SVC" 2>&1
EXIT_CODE=$?
if [ $EXIT_CODE -eq 0 ]; then
log "REPAIR_OK: $COMPONENT"
echo "REPAIR_OK:$COMPONENT"
else
log "REPAIR_FAIL: $COMPONENT (exit $EXIT_CODE)"
echo "REPAIR_FAIL:$COMPONENT:exit_$EXIT_CODE"
exit 1
fi
exit 0
fi
log "DENIED: unknown component '$COMPONENT'"
echo "REPAIR_DENIED:unknown_component:$COMPONENT"
exit 1
elif [ "$CMD" = "health" ]; then
echo "REPAIR_BOT_HEALTHY:188"
else
log "DENIED: invalid command '$CMD'"
echo "REPAIR_DENIED:invalid_command"
exit 1
fi