update orion build retry and log handling (#2111)

* remove gcp in action

* update retry ui

* update orion build retry and log handling

Consolidate build retry behavior around the latest finished build, improve queued/failed build UI states, and add retry actions in the checks tab.

Make queued build timeout handling resilient by marking stale builds interrupted from both memory queue and DB fallback paths, while improving log persistence and avoiding duplicate/partial log reads.

Author: benjamin-747

.github/workflows/mono-engine-deploy.yml

@@ -19,7 +19,6 @@ on:
 env:
   REGISTRY_ALIAS: m8q5m4u3
   REPOSITORY: mega/mono-engine
-  GCP_PROJECT_ID: infra-20250121-20260121-0235
   IMAGE_TAG_BASE: latest
 
 # Using AWS access key for authentication
@@ -59,21 +58,9 @@ jobs:
           registry-type: public
 
       # -----------------------------
-      # GCP / Artifact Registry
+      # Build & push to ECR
       # -----------------------------
-      - name: Auth to GCP
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: ${{ secrets.GCP_SA_KEY }}
-
-      - name: Configure docker for GCP
-        run: |
-          gcloud auth configure-docker us-central1-docker.pkg.dev
-
-      # -----------------------------
-      # Build once, push to both
-      # -----------------------------
-      - name: Build & push image to ECR + GCP (amd64)
+      - name: Build & push image to ECR (amd64)
         env:
           ECR_REGISTRY: ${{ steps.login-ecr-public.outputs.registry }}
           IMAGE_TAG_BASE: ${{ env.IMAGE_TAG_BASE }}
@@ -84,12 +71,10 @@ jobs:
           IMAGE_TAG="${IMAGE_TAG_BASE}-${ARCH_SUFFIX}"
 
           ECR_IMAGE="$ECR_REGISTRY/${{ env.REGISTRY_ALIAS }}/${{ env.REPOSITORY }}:$IMAGE_TAG"
-          GCP_IMAGE="us-central1-docker.pkg.dev/${{ env.GCP_PROJECT_ID }}/${{ env.REPOSITORY }}:$IMAGE_TAG"
           ECR_CACHE_IMAGE="$ECR_REGISTRY/${{ env.REGISTRY_ALIAS }}/${{ env.REPOSITORY }}:buildcache-${ARCH_SUFFIX}"
           CACHE_SCOPE="mono-engine-${ARCH_SUFFIX}"
 
           echo "ECR_IMAGE=$ECR_IMAGE"
-          echo "GCP_IMAGE=$GCP_IMAGE"
           echo "ECR_CACHE_IMAGE=$ECR_CACHE_IMAGE"
           echo "CACHE_SCOPE=$CACHE_SCOPE"
 
@@ -100,7 +85,6 @@ jobs:
             --sbom=false \
             -f ./mono/Dockerfile \
             -t "$ECR_IMAGE" \
-            -t "$GCP_IMAGE" \
             --push .
 
   manifest:
@@ -126,12 +110,22 @@ jobs:
         env:
           REGISTRY: ${{ steps.login-ecr-public.outputs.registry }}
         run: |
+          set -euo pipefail
           IMAGE_BASE="$REGISTRY/${{ env.REGISTRY_ALIAS }}/${{ env.REPOSITORY }}"
+          SHORT_SHA="${GITHUB_SHA:0:7}"
+
+          # latest manifest
           docker manifest create "$IMAGE_BASE:${{ env.IMAGE_TAG_BASE }}" \
             "$IMAGE_BASE:${{ env.IMAGE_TAG_BASE }}-amd64" \
             "$IMAGE_BASE:${{ env.IMAGE_TAG_BASE }}-arm64"
           docker manifest push "$IMAGE_BASE:${{ env.IMAGE_TAG_BASE }}"
 
+          # commit-hash manifest (same digests as latest for this commit)
+          docker manifest create "$IMAGE_BASE:$SHORT_SHA" \
+            "$IMAGE_BASE:${{ env.IMAGE_TAG_BASE }}-amd64" \
+            "$IMAGE_BASE:${{ env.IMAGE_TAG_BASE }}-arm64"
+          docker manifest push "$IMAGE_BASE:$SHORT_SHA"
+
   deploy-aws:
     needs: manifest
     if: ${{ github.repository == 'web3infra-foundation/mega' }}
@@ -156,33 +150,3 @@ jobs:
           AWS_REGION: ap-southeast-2
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-
-  deploy-gcp:
-    needs: manifest
-    if: ${{ github.repository == 'web3infra-foundation/mega' }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Auth to GCP
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: ${{ secrets.GCP_SA_KEY }}
-
-      - name: Deploy to Cloud Run (force new revision)
-        env:
-          REGION: asia-east1
-          SERVICE_NAME: buck2hub-mono
-        run: |
-          set -euo pipefail
-
-          IMAGE=$(gcloud run services describe $SERVICE_NAME \
-            --project "$GCP_PROJECT_ID" \
-            --region "$REGION" \
-            --format="value(spec.template.spec.containers[0].image)")
-
-          echo "Current image: $IMAGE"
-
-          gcloud run deploy $SERVICE_NAME \
-            --image "$IMAGE" \
-            --region "$REGION" \
-            --project "$GCP_PROJECT_ID" \
-            --quiet