[OT-311] [CHORE]: 그라파나 탬플릿 적용 및 필요 설정 추가#171
Merged
arlen02-01 merged 6 commits intodevelopfrom Mar 16, 2026
Merged
Conversation
WalkthroughCI/CD 워크플로우에 node-exporter SSM 파라미터 저장 및 원격 배포 단계를 추가하고, Prometheus 스크랩 설정에 node-exporter 대상과 Changes
Sequence Diagram(s)sequenceDiagram
participant CI as "CI/CD 워크플로우"
participant EC2 as "EC2 인스턴스"
participant SSM as "AWS SSM"
participant Prom as "Prometheus"
CI->>EC2: 대상 인스턴스 선택 및 PrivateIpAddress 조회
EC2-->>CI: PrivateIpAddress
CI->>SSM: SSM에 "<private_ip>:9100" 저장 (NODE_EXPORTER_*_SSM_PARAM)
CI->>EC2: 기존 node-exporter 컨테이너 제거, 이미지 풀, node-exporter 실행
EC2-->>CI: node-exporter 프로세스 실행 확인
Prom->>SSM: NODE_EXPORTER_TARGET / MACHINE_NODE_EXPORTER_TARGET 조회
SSM-->>Prom: 타겟 주소(IP:9100) 반환
Prom->>Prom: scrape job으로 node-exporter 메트릭 수집
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested labels
Suggested reviewers
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
Author
|
@CodeRabbit 코드 리뷰 해주고 컨맨션 문제도 확인해서 각각을 코맨트 분리해서 달아줘 |
|
각 리뷰 항목은 별도의 댓글로 분리하여 작성해 주세요. 코드 품질 및 컨벤션 이슈 모두 포함해 주세요. 🧠 Learnings used✅ Actions performedFull review triggered. |
Contributor
Author
|
@CodeRabbit 리뷰 하고있니..? |
|
🧠 Learnings used✅ Actions performedFull review triggered. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
🧹 Nitpick comments (1)
.github/workflows/deploy-monitoring.yml (1)
110-116: 타깃 검증 실패 메시지에 누락된 키를 포함해 주세요.Line 110-116은 유효성 검증 자체는 맞지만, 현재 에러 메시지가 포괄적이라 어떤 타깃이 비었는지 즉시 파악하기 어렵습니다. 운영 장애 대응 속도를 위해 누락 키를 함께 출력하는 쪽이 좋습니다.
🔧 제안 수정안
- if [ -z "$USER_API_TARGET" ] || [ "$USER_API_TARGET" = "None" ] || \ - [ -z "$ADMIN_API_TARGET" ] || [ "$ADMIN_API_TARGET" = "None" ] || \ - [ -z "$TRANSCODER_TARGET" ] || [ "$TRANSCODER_TARGET" = "None" ] || \ - [ -z "$NODE_EXPORTER_TARGET" ] || [ "$NODE_EXPORTER_TARGET" = "None" ] || \ - [ -z "$MACHINE_NODE_EXPORTER_TARGET" ] || [ "$MACHINE_NODE_EXPORTER_TARGET" = "None" ]; then - echo "One or more scrape targets are empty. Check SSM parameter values." >&2 + MISSING_KEYS=() + [ -z "$USER_API_TARGET" ] || [ "$USER_API_TARGET" = "None" ] && MISSING_KEYS+=("USER_API_TARGET") + [ -z "$ADMIN_API_TARGET" ] || [ "$ADMIN_API_TARGET" = "None" ] && MISSING_KEYS+=("ADMIN_API_TARGET") + [ -z "$TRANSCODER_TARGET" ] || [ "$TRANSCODER_TARGET" = "None" ] && MISSING_KEYS+=("TRANSCODER_TARGET") + [ -z "$NODE_EXPORTER_TARGET" ] || [ "$NODE_EXPORTER_TARGET" = "None" ] && MISSING_KEYS+=("NODE_EXPORTER_TARGET") + [ -z "$MACHINE_NODE_EXPORTER_TARGET" ] || [ "$MACHINE_NODE_EXPORTER_TARGET" = "None" ] && MISSING_KEYS+=("MACHINE_NODE_EXPORTER_TARGET") + if [ "${`#MISSING_KEYS`[@]}" -gt 0 ]; then + echo "Empty scrape targets: ${MISSING_KEYS[*]}. Check SSM parameter values." >&2 exit 1 fi🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/deploy-monitoring.yml around lines 110 - 116, The current validation block that checks USER_API_TARGET, ADMIN_API_TARGET, TRANSCODER_TARGET, NODE_EXPORTER_TARGET, and MACHINE_NODE_EXPORTER_TARGET should be changed to build a list of which variables are empty or "None" and include those keys in the error message; locate the if-check referencing those variables, compute a missing_targets string/array by testing each variable (e.g., append "USER_API_TARGET" when [ -z "$USER_API_TARGET" ] || [ "$USER_API_TARGET" = "None" ]), and replace the generic echo with an echo that prints "Missing or empty scrape targets: $missing_targets" (then exit 1) so the failing keys are clearly reported.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/workflows/deploy-ai.yml:
- Around line 146-153: The deploy step currently swallows all errors with "||
true" when calling aws ec2 authorize-security-group-ingress (using
MONITORING_SG_ID and MACHINE_SG_ID), which hides real failures; remove the
blanket "|| true", run the aws command and capture its stderr/exit code, then
only ignore the call if the error indicates a duplicate rule (e.g. error string
or code like "InvalidPermission.Duplicate" / "InvalidPermission.Duplicate" in
stderr), otherwise print the aws error and exit non-zero so permission/SG/quota
problems fail the workflow; implement this logic around the aws ec2
authorize-security-group-ingress invocation.
In @.github/workflows/deploy-ec2-docker.yml:
- Around line 136-143: When promtail_role equals "user-api" ensure the script
fails fast if private_ip is missing or invalid instead of silently skipping SSM
update: inside the conditional around promtail_role/private_ip (the block that
currently sets NODE_EXPORTER_TARGET_SSM_PARAM) add a guard that checks
private_ip for emptiness or the literal "None" and, if invalid, emit an error
message and exit non‑zero so the workflow stops immediately rather than
proceeding without updating NODE_EXPORTER_TARGET_SSM_PARAM.
In `@apps/monitoring/docker-compose.yml`:
- Around line 53-56: The external network name is hardcoded as backend_default
(networks: backend_shared -> name: backend_default), which breaks when the
Compose project name differs; update the monitoring compose to derive the
network name from an env var instead of hardcoding (e.g., set
networks.backend_shared.name to something like
${COMPOSE_PROJECT_NAME:-backend}_default) or alternatively remove external:true
and document/expect the root docker-compose to declare an explicit shared
network; change the networks definition in apps/monitoring/docker-compose.yml to
reference the env-var-based name (or make it non-external) so Prometheus will
attach to the correct project network.
In `@apps/monitoring/grafana/provisioning/dashboards/json/loki-logs-15324.json`:
- Around line 132-205: The Loki panel queries (see the target expressions
"sum(count_over_time({namespace=\"$namespace\", pod=~\"$pod\"} |~
\"$search\"[$__interval]))" and "{namespace=\"$namespace\", pod=~\"$pod\"} |~
\"$search\"") assume stream labels "namespace" and "pod" that your
Promtail/Prometheus stack does not emit; replace those label matchers with the
actual labels your stack provides (or remove them) or alternatively enable/emit
the missing Kubernetes labels in Promtail/Prometheus so the queries match real
streams; update the two target expressions and any templating variables to use
the correct label keys so the dashboard returns non-empty results.
In `@apps/monitoring/prometheus/prometheus.prod.yml.tpl`:
- Around line 43-55: The prod Prometheus scrape jobs "node-exporter" and
"machine-node-exporter" only set the label app and lack the application label
expected by the Grafana dashboard (jvm-micrometer-4701.json) which uses
label_values(application) and selectors like {application="$application"};
update the template for those jobs (job_name "node-exporter" and
"machine-node-exporter") to include an application label alongside app (e.g.
application: "<appropriate value or template variable>") for both targets
(__NODE_EXPORTER_TARGET__ and __MACHINE_NODE_EXPORTER_TARGET__), then
regenerate/sync the resulting prometheus.prod.yml so prod matches the local
prometheus.yml label schema.
---
Nitpick comments:
In @.github/workflows/deploy-monitoring.yml:
- Around line 110-116: The current validation block that checks USER_API_TARGET,
ADMIN_API_TARGET, TRANSCODER_TARGET, NODE_EXPORTER_TARGET, and
MACHINE_NODE_EXPORTER_TARGET should be changed to build a list of which
variables are empty or "None" and include those keys in the error message;
locate the if-check referencing those variables, compute a missing_targets
string/array by testing each variable (e.g., append "USER_API_TARGET" when [ -z
"$USER_API_TARGET" ] || [ "$USER_API_TARGET" = "None" ]), and replace the
generic echo with an echo that prints "Missing or empty scrape targets:
$missing_targets" (then exit 1) so the failing keys are clearly reported.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: dbea28c5-1bd9-4e63-a031-c54d5041155e
📒 Files selected for processing (14)
.github/workflows/deploy-ai.yml.github/workflows/deploy-ec2-docker.yml.github/workflows/deploy-monitoring.ymlapps/monitoring/docker-compose.ymlapps/monitoring/grafana/provisioning/dashboards/json/New dashboard-1772584885701.json.disabledapps/monitoring/grafana/provisioning/dashboards/json/jvm-micrometer-4701.jsonapps/monitoring/grafana/provisioning/dashboards/json/loki-logs-15324.jsonapps/monitoring/grafana/provisioning/dashboards/json/node-exporter-full-1860.jsonapps/monitoring/grafana/provisioning/dashboards/json/rabbitmq-overview-10991.jsonapps/monitoring/grafana/provisioning/dashboards/json/spring-boot-3x-20727.jsonapps/monitoring/prometheus/prometheus.prod.ymlapps/monitoring/prometheus/prometheus.prod.yml.tplapps/monitoring/prometheus/prometheus.ymldocker-compose.yml
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
.github/workflows/deploy-ec2-docker.yml (1)
136-147:⚠️ Potential issue | 🟡 Minor
user-apiprivate IP 누락 시 경고만 출력하고 있습니다.현재 구현은 private IP가 없을 때
::warning::만 출력하고 워크플로우를 계속 진행합니다. 그러나deploy-monitoring.yml의 "Resolve scrape targets from SSM" 단계에서NODE_EXPORTER_TARGET값이 비어있거나 "None"이면 배포가 실패합니다.이 접근 방식이 의도된 것이라면 괜찮지만, user-api 배포 시 private IP 해결 실패가 다운스트림 모니터링 배포 실패로 이어질 수 있습니다.
🔧 fail-fast 방식으로 변경하려면
if [ "$promtail_role" = "user-api" ]; then - if [ -n "$private_ip" ] && [ "$private_ip" != "None" ]; then + if [ -z "$private_ip" ] || [ "$private_ip" = "None" ]; then + echo "Failed to resolve private IP for ${target_tag}; cannot update ${NODE_EXPORTER_TARGET_SSM_PARAM}" >&2 + exit 1 + fi aws ssm put-parameter \ --region "$AWS_REGION" \ --name "$NODE_EXPORTER_TARGET_SSM_PARAM" \ --type String \ --overwrite \ --value "${private_ip}:9100" >/dev/null - else - echo "::warning::user-api private IP is missing. NODE_EXPORTER_TARGET SSM parameter was not updated." - fi fi🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/deploy-ec2-docker.yml around lines 136 - 147, 현재 promtail_role이 "user-api"인 경우 private_ip가 비어있거나 "None"이면 단순히 경고만 출력하고 계속 진행하는데, 이로 인해 deploy-monitoring.yml의 "Resolve scrape targets from SSM" 단계에서 NODE_EXPORTER_TARGET이 비어 있어 배포가 실패할 수 있으므로 fail-fast로 변경해야 합니다; 수정 방법은 해당 조건의 else 블록에서 echo "::warning::user-api private IP is missing. NODE_EXPORTER_TARGET SSM parameter was not updated."를 오류로 바꾸고 즉시 종료하도록 처리(예: echo "::error::..." 후 exit 1)해 NODE_EXPORTER_TARGET_SSM_PARAM이 설정되지 않은 상태로 진행되지 않게 하세요, 점검 대상 변수/심볼: promtail_role, private_ip, NODE_EXPORTER_TARGET_SSM_PARAM 및 관련 deploy-monitoring.yml의 "Resolve scrape targets from SSM" 단계를 참고하세요.
🧹 Nitpick comments (1)
apps/monitoring/prometheus/prometheus.prod.yml.tpl (1)
46-60: node-exporter job들에relabel_configs가 없습니다.기존 user-api, admin-api, transcoder job들은
relabel_configs로instance라벨을 명시적으로 설정하고 있습니다. node-exporter와 machine-node-exporter에도 동일한 패턴을 적용하면 대시보드에서 instance 라벨 기반 필터링이 일관성 있게 동작합니다.♻️ 일관성을 위한 relabel_configs 추가 제안
- job_name: "node-exporter" static_configs: - targets: ["__NODE_EXPORTER_TARGET__"] labels: app: "node-exporter" application: "node-exporter" env: "prod" + relabel_configs: + - target_label: instance + replacement: "node-exporter" - job_name: "machine-node-exporter" static_configs: - targets: ["__MACHINE_NODE_EXPORTER_TARGET__"] labels: app: "machine" application: "machine" env: "prod" + relabel_configs: + - target_label: instance + replacement: "machine"🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@apps/monitoring/prometheus/prometheus.prod.yml.tpl` around lines 46 - 60, Add a relabel_configs block to the node-exporter and machine-node-exporter scrape jobs so they explicitly set the instance label like the other jobs do; locate the job entries identified by job_name: "node-exporter" and job_name: "machine-node-exporter" in the Prometheus template and insert a relabel_configs section that maps __address__ (or the target) to the instance label (matching the pattern used by user-api/admin-api/transcoder jobs) so dashboards can consistently filter by instance.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/workflows/deploy-ai.yml:
- Around line 137-144: The script currently skips updating the SSM parameter
when MACHINE_PRIVATE_IP is empty or "None" (the if block checking
MACHINE_PRIVATE_IP) without warning, which later causes deploy-monitoring.yml to
fail; modify that branch to explicitly log a clear error or warning and exit
non-zero (or fail the workflow) when MACHINE_PRIVATE_IP is missing/equals "None"
so the pipeline fails fast, or alternatively set a deliberate fallback value and
emit a warning before continuing; update the section that references
MACHINE_PRIVATE_IP and SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM to implement this
explicit error handling.
---
Duplicate comments:
In @.github/workflows/deploy-ec2-docker.yml:
- Around line 136-147: 현재 promtail_role이 "user-api"인 경우 private_ip가 비어있거나
"None"이면 단순히 경고만 출력하고 계속 진행하는데, 이로 인해 deploy-monitoring.yml의 "Resolve scrape
targets from SSM" 단계에서 NODE_EXPORTER_TARGET이 비어 있어 배포가 실패할 수 있으므로 fail-fast로
변경해야 합니다; 수정 방법은 해당 조건의 else 블록에서 echo "::warning::user-api private IP is
missing. NODE_EXPORTER_TARGET SSM parameter was not updated."를 오류로 바꾸고 즉시 종료하도록
처리(예: echo "::error::..." 후 exit 1)해 NODE_EXPORTER_TARGET_SSM_PARAM이 설정되지 않은 상태로
진행되지 않게 하세요, 점검 대상 변수/심볼: promtail_role, private_ip,
NODE_EXPORTER_TARGET_SSM_PARAM 및 관련 deploy-monitoring.yml의 "Resolve scrape
targets from SSM" 단계를 참고하세요.
---
Nitpick comments:
In `@apps/monitoring/prometheus/prometheus.prod.yml.tpl`:
- Around line 46-60: Add a relabel_configs block to the node-exporter and
machine-node-exporter scrape jobs so they explicitly set the instance label like
the other jobs do; locate the job entries identified by job_name:
"node-exporter" and job_name: "machine-node-exporter" in the Prometheus template
and insert a relabel_configs section that maps __address__ (or the target) to
the instance label (matching the pattern used by user-api/admin-api/transcoder
jobs) so dashboards can consistently filter by instance.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: c27546c9-6ffa-420a-b1e8-0d6aaf61202d
📒 Files selected for processing (6)
.github/workflows/deploy-ai.yml.github/workflows/deploy-ec2-docker.ymlapps/monitoring/docker-compose.ymlapps/monitoring/grafana/provisioning/dashboards/json/loki-logs-15324.jsonapps/monitoring/prometheus/prometheus.prod.ymlapps/monitoring/prometheus/prometheus.prod.yml.tpl
🚧 Files skipped from review as they are similar to previous changes (3)
- apps/monitoring/prometheus/prometheus.prod.yml
- apps/monitoring/grafana/provisioning/dashboards/json/loki-logs-15324.json
- apps/monitoring/docker-compose.yml
yubin012
approved these changes
Mar 16, 2026
…ckend into OT-311-chore/grafana-template
There was a problem hiding this comment.
♻️ Duplicate comments (2)
.github/workflows/deploy-ai.yml (2)
137-144:⚠️ Potential issue | 🟡 Minor
MACHINE_PRIVATE_IP누락 시 명시적 에러 처리가 필요합니다.
MACHINE_PRIVATE_IP가 비어있거나 "None"인 경우 SSM 파라미터 업데이트가 조용히 생략됩니다. 이후deploy-monitoring.yml에서 해당 타겟을 사용할 때 배포가 실패할 수 있습니다.,
🔧 명시적 에러 처리 추가 제안
- if [ -n "$MACHINE_PRIVATE_IP" ] && [ "$MACHINE_PRIVATE_IP" != "None" ]; then + if [ -z "$MACHINE_PRIVATE_IP" ] || [ "$MACHINE_PRIVATE_IP" = "None" ]; then + echo "::error::Failed to resolve private IP for ${TARGET_TAG}; cannot update ${SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM}" >&2 + exit 1 + fi + aws ssm put-parameter \ --region "$AWS_REGION" \ --name "$SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM" \ --type String \ --overwrite \ --value "${MACHINE_PRIVATE_IP}:9100" >/dev/null - fi🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/deploy-ai.yml around lines 137 - 144, The workflow silently skips setting SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM when MACHINE_PRIVATE_IP is empty or "None", which later breaks deploy-monitoring.yml; add an explicit failure path: check MACHINE_PRIVATE_IP (the same variable used in the if condition) and if it's empty or "None" print a clear error referencing SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM and exit non‑zero so the job fails early; update the conditional block around MACHINE_PRIVATE_IP to include an else branch that echoes the error and exits 1 (so downstream deploy-monitoring.yml won't run with a missing target).
146-161:⚠️ Potential issue | 🟡 Minor보안 그룹 인그레스 에러 처리가 개선되었으나, 실패 시 워크플로우 중단 고려가 필요합니다.
InvalidPermission.Duplicate처리가 추가되어 이전|| true방식보다 개선되었습니다. 다만, 권한 부족이나 잘못된 SG ID 같은 실제 오류 발생 시 경고만 출력하고 계속 진행되므로, node-exporter가 Prometheus에서 접근 불가능한 상태로 배포될 수 있습니다.,
🔧 실패 시 워크플로우 중단 제안
if ! INGRESS_OUTPUT=$(aws ec2 authorize-security-group-ingress \ --region "$AWS_REGION" \ --group-id "$MACHINE_SG_ID" \ --protocol tcp \ --port 9100 \ --source-group "$MONITORING_SG_ID" 2>&1); then if echo "$INGRESS_OUTPUT" | grep -q "InvalidPermission.Duplicate"; then echo "Node exporter ingress rule already exists." else - echo "::warning::Failed to open node-exporter ingress (monitoring -> ai)." + echo "::error::Failed to open node-exporter ingress (monitoring -> ai)." echo "$INGRESS_OUTPUT" + exit 1 fi fi🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/deploy-ai.yml around lines 146 - 161, The current authorize-security-group-ingress block captures errors into INGRESS_OUTPUT and only warns on failures other than InvalidPermission.Duplicate, but then continues; change the error handling so that if the aws ec2 authorize-security-group-ingress command fails and the output does NOT contain "InvalidPermission.Duplicate" (i.e., INGRESS_OUTPUT check), you print the error and then exit non‑zero (e.g., exit 1) to fail the workflow and prevent continuing with a potentially inaccessible node-exporter; reference the aws ec2 authorize-security-group-ingress invocation and variables MONITORING_SG_ID, MACHINE_SG_ID, and INGRESS_OUTPUT when making this change.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In @.github/workflows/deploy-ai.yml:
- Around line 137-144: The workflow silently skips setting
SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM when MACHINE_PRIVATE_IP is empty or
"None", which later breaks deploy-monitoring.yml; add an explicit failure path:
check MACHINE_PRIVATE_IP (the same variable used in the if condition) and if
it's empty or "None" print a clear error referencing
SSM_MACHINE_NODE_EXPORTER_TARGET_PARAM and exit non‑zero so the job fails early;
update the conditional block around MACHINE_PRIVATE_IP to include an else branch
that echoes the error and exits 1 (so downstream deploy-monitoring.yml won't run
with a missing target).
- Around line 146-161: The current authorize-security-group-ingress block
captures errors into INGRESS_OUTPUT and only warns on failures other than
InvalidPermission.Duplicate, but then continues; change the error handling so
that if the aws ec2 authorize-security-group-ingress command fails and the
output does NOT contain "InvalidPermission.Duplicate" (i.e., INGRESS_OUTPUT
check), you print the error and then exit non‑zero (e.g., exit 1) to fail the
workflow and prevent continuing with a potentially inaccessible node-exporter;
reference the aws ec2 authorize-security-group-ingress invocation and variables
MONITORING_SG_ID, MACHINE_SG_ID, and INGRESS_OUTPUT when making this change.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: f725fce7-04af-4013-a1c6-b1242b48aae0
📒 Files selected for processing (2)
.github/workflows/deploy-ai.ymldocker-compose.yml
🚧 Files skipped from review as they are similar to previous changes (1)
- docker-compose.yml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
📝 작업 내용
☑️ 체크 리스트
#️⃣ 연관된 이슈
Summary by CodeRabbit
릴리스 노트
새 기능
인프라 업데이트