Merge branch 'main' into VPhung24/bun-for-nextjs-and-webapps

.gitea/workflows/fixturenet-eth-plugeth-arm-test.yml

@@ -9,10 +9,6 @@ on:
   schedule: # Note: coordinate with other tests to not overload runners at the same time of day
     - cron: '2 14 * * *'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 
 jobs:
   test:

.gitea/workflows/fixturenet-eth-plugeth-test.yml

@@ -9,10 +9,6 @@ on:
   schedule: # Note: coordinate with other tests to not overload runners at the same time of day
     - cron: '2 14 * * *'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 
 jobs:
   test:
@@ -41,10 +37,6 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
       - name: "Run fixturenet-eth tests"
         run: ./tests/fixturenet-eth-plugeth/run-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/fixturenet-eth-test.yml

@@ -7,10 +7,6 @@ on:
       - '!**'
       - '.gitea/workflows/triggers/fixturenet-eth-test'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 
 jobs:
   test:
@@ -39,10 +35,6 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
       - name: "Run fixturenet-eth tests"
         run: ./tests/fixturenet-eth/run-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/test-deploy.yml

@@ -10,9 +10,6 @@ on:
     paths-ignore:
       - '.gitea/workflows/triggers/*'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
 
 jobs:
   test:
@@ -41,10 +38,6 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
       - name: "Run deploy tests"
         run: ./tests/deploy/run-deploy-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/test-external-stack.yml

@@ -0,0 +1,58 @@
+name: External Stack Test
+
+on:
+  push:
+    branches: '*'
+    paths:
+      - '!**'
+      - '.gitea/workflows/triggers/test-external-stack'
+      - '.gitea/workflows/test-external-stack.yml'
+      - 'tests/external-stack/run-test.sh'
+  schedule: # Note: coordinate with other tests to not overload runners at the same time of day
+    - cron: '8 19 * * *'
+
+jobs:
+  test:
+    name: "Run external stack test suite"
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Clone project repository"
+        uses: actions/checkout@v3
+      # At present the stock setup-python action fails on Linux/aarch64
+      # Conditional steps below workaroud this by using deadsnakes for that case only
+      - name: "Install Python for ARM on Linux"
+        if: ${{ runner.arch == 'arm64' && runner.os == 'Linux' }}
+        uses: deadsnakes/action@v3.0.1
+        with:
+          python-version: '3.8'
+      - name: "Install Python cases other than ARM on Linux"
+        if: ${{ ! (runner.arch == 'arm64' && runner.os == 'Linux') }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.8'
+      - name: "Print Python version"
+        run: python3 --version
+      - name: "Install shiv"
+        run: pip install shiv
+      - name: "Generate build version file"
+        run: ./scripts/create_build_tag_file.sh
+      - name: "Build local shiv package"
+        run: ./scripts/build_shiv_package.sh
+      - name: "Run external stack tests"
+        run: ./tests/external-stack/run-test.sh
+      - name: Notify Vulcanize Slack on CI failure
+        if: ${{ always() && github.ref_name == 'main' }}
+        uses: ravsamhq/notify-slack-action@v2
+        with:
+          status: ${{ job.status }}
+          notify_when: 'failure'
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.VULCANIZE_SLACK_CI_ALERTS }}
+      - name: Notify DeepStack Slack on CI failure
+        if: ${{ always() && github.ref_name == 'main' }}
+        uses: ravsamhq/notify-slack-action@v2
+        with:
+          status: ${{ job.status }}
+          notify_when: 'failure'
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.DEEPSTACK_SLACK_CI_ALERTS }}

.gitea/workflows/test-webapp.yml

@@ -10,10 +10,6 @@ on:
     paths-ignore:
       - '.gitea/workflows/triggers/*'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 jobs:
   test:
     name: "Run webapp test suite"
@@ -43,10 +39,6 @@ jobs:
         run: ./scripts/build_shiv_package.sh
       - name: "Install wget" # 20240109 - Only needed until the executors are updated.
         run: apt update && apt install -y wget
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
       - name: "Run webapp tests"
         run: ./tests/webapp-test/run-webapp-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/test.yml

@@ -10,9 +10,6 @@ on:
     paths-ignore:
       - '.gitea/workflows/triggers/*'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
 
 jobs:
   test:
@@ -41,10 +38,6 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
       - name: "Run smoke tests"
         run: ./tests/smoke-test/run-smoke-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/triggers/fixturenet-laconicd-test

@@ -4,3 +4,4 @@ Trigger
 Trigger
 Trigger
 Trigger
+Trigger

.gitea/workflows/triggers/test-external-stack

@@ -0,0 +1,2 @@
+Change this file to trigger running the external-stack CI job
+trigger

setup.py

@@ -4,9 +4,11 @@ with open("README.md", "r", encoding="utf-8") as fh:
     long_description = fh.read()
 with open("requirements.txt", "r", encoding="utf-8") as fh:
     requirements = fh.read()
+with open("stack_orchestrator/data/version.txt", "r", encoding="utf-8") as fh:
+    version = fh.readlines()[-1].strip(" \n")
 setup(
     name='laconic-stack-orchestrator',
-    version='1.0.12',
+    version=version,
     author='Cerc',
     author_email='info@cerc.io',
     license='GNU Affero General Public License',

stack_orchestrator/build/build_containers.py

@@ -71,7 +71,7 @@ def process_container(build_context: BuildContext) -> bool:
 
     # Check if this is in an external stack
     if stack_is_external(build_context.stack):
-        container_parent_dir = Path(build_context.stack).joinpath("container-build")
+        container_parent_dir = Path(build_context.stack).parent.parent.joinpath("container-build")
         temp_build_dir = container_parent_dir.joinpath(build_context.container.replace("/", "-"))
         temp_build_script_filename = temp_build_dir.joinpath("build.sh")
         # Now check if the container exists in the external stack.

stack_orchestrator/build/build_util.py

@@ -21,11 +21,6 @@ from stack_orchestrator.util import get_parsed_stack_config, warn_exit
 
 def get_containers_in_scope(stack: str):
 
-    # See: https://stackoverflow.com/a/20885799/1701505
-    from stack_orchestrator import data
-    with importlib.resources.open_text(data, "container-image-list.txt") as container_list_file:
-        all_containers = container_list_file.read().splitlines()
-
     containers_in_scope = []
     if stack:
         stack_config = get_parsed_stack_config(stack)
@@ -33,11 +28,14 @@ def get_containers_in_scope(stack: str):
             warn_exit(f"stack {stack} does not define any containers")
         containers_in_scope = stack_config['containers']
     else:
-        containers_in_scope = all_containers
+        # See: https://stackoverflow.com/a/20885799/1701505
+        from stack_orchestrator import data
+        with importlib.resources.open_text(data, "container-image-list.txt") as container_list_file:
+            containers_in_scope = container_list_file.read().splitlines()
 
     if opts.o.verbose:
         print(f'Containers: {containers_in_scope}')
         if stack:
             print(f"Stack: {stack}")
 
-    return containers_in_scope
+    return containers_in_scope

stack_orchestrator/data/compose/docker-compose-grafana.yml

@@ -6,12 +6,20 @@ services:
     restart: always
     environment:
       GF_SERVER_ROOT_URL: ${GF_SERVER_ROOT_URL}
+      CERC_GRAFANA_ALERTS_SUBGRAPH_IDS: ${CERC_GRAFANA_ALERTS_SUBGRAPH_IDS}
     volumes:
       - ../config/monitoring/grafana/provisioning:/etc/grafana/provisioning
       - ../config/monitoring/grafana/dashboards:/etc/grafana/dashboards
+      - ../config/monitoring/update-grafana-alerts-config.sh:/update-grafana-alerts-config.sh
       - grafana_storage:/var/lib/grafana
+    user: root
+    entrypoint: ["bash", "-c"]
+    command: |
+      "/update-grafana-alerts-config.sh && /run.sh"
     ports:
       - "3000"
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
     healthcheck:
       test: ["CMD", "nc", "-vz", "localhost", "3000"]
       interval: 30s

stack_orchestrator/data/compose/docker-compose-graph-node.yml

@@ -16,8 +16,13 @@ services:
       postgres_pass: password
       postgres_db: graph-node
       ethereum: ${ETH_NETWORKS:-lotus-fixturenet:http://lotus-node-1:1234/rpc/v1}
+      # Env varaibles reference: https://git.vdb.to/cerc-io/graph-node/src/branch/master/docs/environment-variables.md
       GRAPH_LOG: debug
       ETHEREUM_REORG_THRESHOLD: 3
+      GRAPH_ETHEREUM_JSON_RPC_TIMEOUT: ${GRAPH_ETHEREUM_JSON_RPC_TIMEOUT:-180}
+      GRAPH_ETHEREUM_REQUEST_RETRIES: ${GRAPH_ETHEREUM_REQUEST_RETRIES:-10}
+      GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE: ${GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE:-2000}
+      GRAPH_ETHEREUM_BLOCK_INGESTOR_MAX_CONCURRENT_JSON_RPC_CALLS_FOR_TXN_RECEIPTS: ${GRAPH_ETHEREUM_BLOCK_INGESTOR_MAX_CONCURRENT_JSON_RPC_CALLS_FOR_TXN_RECEIPTS:-1000}
     entrypoint: ["bash", "-c"]
     # Wait for ETH RPC endpoint to be up when running with fixturenet-lotus
     command: |
@@ -27,6 +32,7 @@ services:
       - "8001"
       - "8020"
       - "8030"
+      - "8040"
     healthcheck:
       test: ["CMD", "nc", "-vz", "localhost", "8020"]
       interval: 30s

stack_orchestrator/data/compose/docker-compose-prom-server.yml

@@ -28,15 +28,37 @@ services:
     extra_hosts:
       - "host.docker.internal:host-gateway"
 
-  chain-head-exporter:
+  ethereum-chain-head-exporter:
     image: cerc/watcher-ts:local
     restart: always
     working_dir: /app/packages/cli
     environment:
-      ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
-      FIL_RPC_ENDPOINT: ${CERC_FIL_RPC_ENDPOINT}
+      ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT:-https://mainnet.infura.io/v3}
       ETH_RPC_API_KEY: ${CERC_INFURA_KEY}
-      PORT: ${CERC_METRICS_PORT}
+    command: ["sh", "-c", "yarn export-metrics:chain-heads"]
+    ports:
+      - '5000'
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+  filecoin-chain-head-exporter:
+    image: cerc/watcher-ts:local
+    restart: always
+    working_dir: /app/packages/cli
+    environment:
+      ETH_RPC_ENDPOINT: ${CERC_FIL_RPC_ENDPOINT:-https://api.node.glif.io/rpc/v1}
+    command: ["sh", "-c", "yarn export-metrics:chain-heads"]
+    ports:
+      - '5000'
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+  graph-node-upstream-head-exporter:
+    image: cerc/watcher-ts:local
+    restart: always
+    working_dir: /app/packages/cli
+    environment:
+      ETH_RPC_ENDPOINT: ${GRAPH_NODE_RPC_ENDPOINT}
     command: ["sh", "-c", "yarn export-metrics:chain-heads"]
     ports:
       - '5000'

stack_orchestrator/data/compose/docker-compose-snowballtools-base-backend.yml

@@ -1,13 +0,0 @@
-services:
-  snowballtools-base-backend:
-    image: cerc/snowballtools-base-backend:local
-    restart: always
-    volumes:
-      - data:/data
-      - config:/config:ro
-    ports:
-      - 8000
-
-volumes:
-  data:
-  config:

stack_orchestrator/data/compose/docker-compose-watcher-ajna.yml

@@ -29,7 +29,7 @@ services:
     image: cerc/watcher-ajna:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-job-runner.sh"]
     volumes:
       - ../config/watcher-ajna/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -37,7 +37,7 @@ services:
     ports:
       - "9000"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -55,16 +55,17 @@ services:
     image: cerc/watcher-ajna:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-server.sh"]
     volumes:
       - ../config/watcher-ajna/watcher-config-template.toml:/app/environments/watcher-config-template.toml
       - ../config/watcher-ajna/start-server.sh:/app/start-server.sh
+      - ajna_watcher_gql_logs_data:/app/gql-logs
     ports:
       - "3008"
       - "9001"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -74,3 +75,4 @@ services:
 
 volumes:
   ajna_watcher_db_data:
+  ajna_watcher_gql_logs_data:

stack_orchestrator/data/compose/docker-compose-watcher-azimuth.yml

@@ -32,8 +32,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CERC_HISTORICAL_BLOCK_RANGE: 500
       CONTRACT_ADDRESS: 0x223c067F8CF28ae173EE5CafEa60cA44C335fecB
       CONTRACT_NAME: Azimuth
@@ -47,7 +47,7 @@ services:
     ports:
       - "9000"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -66,18 +66,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/azimuth-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/azimuth-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/azimuth-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/azimuth-watcher/start-server.sh
+      - azimuth_watcher_gql_logs_data:/app/packages/azimuth-watcher/gql-logs
     ports:
       - "3001"
+      - "9001"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3001"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3001"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -94,8 +96,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x325f68d32BdEe6Ed86E7235ff2480e2A433D6189
       CONTRACT_NAME: Censures
       STARTING_BLOCK: 6784954
@@ -108,7 +110,7 @@ services:
     ports:
       - "9002"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9002"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9002"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -127,18 +129,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/censures-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/censures-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/censures-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/censures-watcher/start-server.sh
+      - censures_watcher_gql_logs_data:/app/packages/censures-watcher/gql-logs
     ports:
       - "3002"
+      - "9003"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3002"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3002"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -155,8 +159,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0xe7e7f69b34D7d9Bd8d61Fb22C33b22708947971A
       CONTRACT_NAME: Claims
       STARTING_BLOCK: 6784941
@@ -169,7 +173,7 @@ services:
     ports:
       - "9004"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9004"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9004"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -188,18 +192,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/claims-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/claims-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/claims-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/claims-watcher/start-server.sh
+      - claims_watcher_gql_logs_data:/app/packages/claims-watcher/gql-logs
     ports:
       - "3003"
+      - "9005"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3003"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3003"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -216,8 +222,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x8C241098C3D3498Fe1261421633FD57986D74AeA
       CONTRACT_NAME: ConditionalStarRelease
       STARTING_BLOCK: 6828004
@@ -230,7 +236,7 @@ services:
     ports:
       - "9006"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9006"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9006"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -249,18 +255,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/conditional-star-release-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/conditional-star-release-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/conditional-star-release-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/conditional-star-release-watcher/start-server.sh
+      - conditional_star_release_watcher_gql_logs_data:/app/packages/conditional-star-release-watcher/gql-logs
     ports:
       - "3004"
+      - "9007"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3004"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3004"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -277,8 +285,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0xf6b461fE1aD4bd2ce25B23Fe0aff2ac19B3dFA76
       CONTRACT_NAME: DelegatedSending
       STARTING_BLOCK: 6784956
@@ -291,7 +299,7 @@ services:
     ports:
       - "9008"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -310,18 +318,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/delegated-sending-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/delegated-sending-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/delegated-sending-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/delegated-sending-watcher/start-server.sh
+      - delegated_sending_watcher_gql_logs_data:/app/packages/delegated-sending-watcher/gql-logs
     ports:
       - "3005"
+      - "9009"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3005"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3005"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -338,8 +348,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x33EeCbf908478C10614626A9D304bfe18B78DD73
       CONTRACT_NAME: Ecliptic
       STARTING_BLOCK: 13692129
@@ -352,7 +362,7 @@ services:
     ports:
       - "9010"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9010"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9010"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -371,18 +381,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/ecliptic-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/ecliptic-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/ecliptic-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/ecliptic-watcher/start-server.sh
+      - ecliptic_watcher_gql_logs_data:/app/packages/ecliptic-watcher/gql-logs
     ports:
       - "3006"
+      - "9011"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3006"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3006"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -399,8 +411,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x86cd9cd0992F04231751E3761De45cEceA5d1801
       CONTRACT_NAME: LinearStarRelease
       STARTING_BLOCK: 6784943
@@ -413,7 +425,7 @@ services:
     ports:
       - "9012"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9012"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9012"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -432,18 +444,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/linear-star-release-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/linear-star-release-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/linear-star-release-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/linear-star-release-watcher/start-server.sh
+      - linear_star_release_watcher_gql_logs_data:/app/packages/linear-star-release-watcher/gql-logs
     ports:
       - "3007"
+      - "9013"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3007"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3007"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -460,8 +474,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x7fEcaB617c868Bb5996d99D95200D2Fa708218e4
       CONTRACT_NAME: Polls
       STARTING_BLOCK: 6784912
@@ -474,7 +488,7 @@ services:
     ports:
       - "9014"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9014"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9014"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -493,18 +507,20 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/polls-watcher
     command: "./start-server.sh"
     volumes:
       - ../config/watcher-azimuth/watcher-config-template.toml:/app/packages/polls-watcher/environments/watcher-config-template.toml
       - ../config/watcher-azimuth/merge-toml.js:/app/packages/polls-watcher/merge-toml.js
       - ../config/watcher-azimuth/start-server.sh:/app/packages/polls-watcher/start-server.sh
+      - polls_watcher_gql_logs_data:/app/packages/polls-watcher/gql-logs
     ports:
       - "3008"
+      - "9015"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -542,7 +558,7 @@ services:
     ports:
       - "0.0.0.0:4000:4000"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "4000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "4000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -552,3 +568,11 @@ services:
 
 volumes:
   watcher_db_data:
+  azimuth_watcher_gql_logs_data:
+  censures_watcher_gql_logs_data:
+  claims_watcher_gql_logs_data:
+  conditional_star_release_watcher_gql_logs_data:
+  delegated_sending_watcher_gql_logs_data:
+  ecliptic_watcher_gql_logs_data:
+  linear_star_release_watcher_gql_logs_data:
+  polls_watcher_gql_logs_data:

stack_orchestrator/data/compose/docker-compose-watcher-merkl-sushiswap-v3.yml

@@ -29,7 +29,7 @@ services:
     image: cerc/watcher-merkl-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-job-runner.sh"]
     volumes:
       - ../config/watcher-merkl-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -37,7 +37,7 @@ services:
     ports:
       - "9002:9000"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -55,16 +55,17 @@ services:
     image: cerc/watcher-merkl-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-server.sh"]
     volumes:
       - ../config/watcher-merkl-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
       - ../config/watcher-merkl-sushiswap-v3/start-server.sh:/app/start-server.sh
+      - merkl_sushiswap_v3_watcher_gql_logs_data:/app/gql-logs
     ports:
       - "127.0.0.1:3007:3008"
       - "9003:9001"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -74,3 +75,4 @@ services:
 
 volumes:
   merkl_sushiswap_v3_watcher_db_data:
+  merkl_sushiswap_v3_watcher_gql_logs_data:

stack_orchestrator/data/compose/docker-compose-watcher-sushiswap-v3.yml

@@ -29,7 +29,7 @@ services:
     image: cerc/watcher-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-job-runner.sh"]
     volumes:
       - ../config/watcher-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -37,7 +37,7 @@ services:
     ports:
       - "9000:9000"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -55,16 +55,17 @@ services:
     image: cerc/watcher-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-server.sh"]
     volumes:
       - ../config/watcher-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
       - ../config/watcher-sushiswap-v3/start-server.sh:/app/start-server.sh
+      - sushiswap_v3_watcher_gql_logs_data:/app/gql-logs
     ports:
       - "127.0.0.1:3008:3008"
       - "9001:9001"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -74,3 +75,4 @@ services:
 
 volumes:
   sushiswap_v3_watcher_db_data:
+  sushiswap_v3_watcher_gql_logs_data:

stack_orchestrator/data/config/monitoring/grafana/provisioning/datasources/graph-node-postgres.yml

@@ -0,0 +1,20 @@
+apiVersion: 1
+
+datasources:
+  - name: Graph Node Postgres
+    type: postgres
+    jsonData:
+      database: graph-node
+      sslmode: 'disable'
+      maxOpenConns: 100
+      maxIdleConns: 100
+      maxIdleConnsAuto: true
+      connMaxLifetime: 14400
+      postgresVersion: 1411 # 903=9.3, 1000=10, 1411=14.11
+      timescaledb: false
+    user: graph-node
+    # # Add URL for graph-node database
+    # url: graph-node-db:5432
+    # # Set password for graph-node database
+    # secureJsonData:
+    #   password: 'password'

stack_orchestrator/data/config/monitoring/prometheus/prometheus.yml

@@ -45,7 +45,18 @@ scrape_configs:
     metrics_path: /metrics
     scheme: http
     static_configs:
-      - targets: ['chain-head-exporter:5000']
+      - targets: ['ethereum-chain-head-exporter:5000']
+        labels:
+          instance: 'external'
+          chain: 'ethereum'
+      - targets: ['filecoin-chain-head-exporter:5000']
+        labels:
+          instance: 'external'
+          chain: 'filecoin'
+      - targets: ['graph-node-upstream-head-exporter:5000']
+        labels:
+          instance: 'graph-node'
+          chain: 'filecoin'
 
   - job_name: 'postgres'
     scrape_interval: 30s
@@ -74,3 +85,11 @@ scrape_configs:
       # - targets: ['example-host:1317']
     params:
       format: ['prometheus']
+
+  - job_name: graph-node
+    metrics_path: /metrics
+    scrape_interval: 30s
+    scheme: http
+    static_configs:
+      # Add graph-node targets to be monitored below
+      # - targets: ['graph-node:8040']

stack_orchestrator/data/config/monitoring/subgraph-alert-rules.yml

@@ -0,0 +1,64 @@
+apiVersion: 1
+groups:
+  - orgId: 1
+    name: subgraph
+    folder: SubgraphAlerts
+    interval: 30s
+    rules:
+      - uid: b2a9144b-6104-46fc-92b5-352f4e643c4c
+        title: subgraph_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                  type: prometheus
+                  uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: ethereum_chain_head_number - on(network) group_right deployment_head{deployment=~"REPLACE_WITH_SUBGRAPH_IDS"}
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                  - evaluator:
+                      params:
+                          - 15
+                          - 0
+                      type: gt
+                    operator:
+                      type: and
+                    query:
+                      params: []
+                    reducer:
+                      params: []
+                      type: avg
+                    type: query
+              datasource:
+                  name: Expression
+                  type: __expr__
+                  uid: __expr__
+              expression: diff
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: threshold
+        noDataState: OK
+        execErrState: Alerting
+        for: 5m
+        annotations:
+          summary: Subgraph deployment {{ index $labels "deployment" }} is falling behind head by {{ index $values "diff" }}
+        labels: {}
+        isPaused: false

stack_orchestrator/data/config/monitoring/update-grafana-alerts-config.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+echo Using CERC_GRAFANA_ALERTS_SUBGRAPH_IDS ${CERC_GRAFANA_ALERTS_SUBGRAPH_IDS}
+
+# Replace subgraph ids in subgraph alerting config
+# Note: Requires the grafana container to be run with user root
+if [ -n "$CERC_GRAFANA_ALERTS_SUBGRAPH_IDS" ]; then
+  sed -i "s/REPLACE_WITH_SUBGRAPH_IDS/$CERC_GRAFANA_ALERTS_SUBGRAPH_IDS/g" /etc/grafana/provisioning/alerting/subgraph-alert-rules.yml
+fi

stack_orchestrator/data/config/monitoring/watcher-alert-rules.yml

@@ -24,7 +24,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -100,7 +100,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -176,7 +176,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -252,7 +252,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -328,7 +328,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -404,7 +404,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -480,7 +480,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="linear_star_release", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="linear_star_release", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -556,7 +556,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -634,7 +634,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -710,7 +710,7 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true
@@ -788,7 +788,85 @@ groups:
                 uid: PBFA97CFB590B2093
               disableTextWrap: false
               editorMode: code
-              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="ajna", instance="ajna", kind="latest_indexed"}
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="ajna", instance="ajna", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="filecoin"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+      
+      # Secured Finance
+      - uid: secured_finance_diff_external
+        title: secured_finance_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number{instance="external"} - on(chain) group_right sync_status_block_number{job="secured-finance", instance="secured-finance", kind="latest_indexed"}
               fullMetaSearch: false
               includeNullMetadata: true
               instant: true

stack_orchestrator/data/config/watcher-ajna/start-job-runner.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-ajna/start-server.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-ajna/watcher-config-template.toml

@@ -2,7 +2,6 @@
   host = "0.0.0.0"
   port = 3008
   kind = "active"
-  gqlPath = "/"
 
   # Checkpointing state.
   checkpointing = true
@@ -22,23 +21,30 @@
   # Interval in number of blocks at which to clear entities cache.
   clearEntitiesCacheInterval = 1000
 
-  # Max block range for which to return events in eventsInRange GQL query.
-  # Use -1 for skipping check on block range.
-  maxEventsBlockRange = 1000
-
   # Flag to specify whether RPC endpoint supports block hash as block tag parameter
   rpcSupportsBlockHashParam = false
 
-  # GQL cache settings
-  [server.gqlCache]
-    enabled = true
+  # Server GQL config
+  [server.gql]
+    path = "/"
 
-    # Max in-memory cache size (in bytes) (default 8 MB)
-    # maxCacheSize
+    # Max block range for which to return events in eventsInRange GQL query.
+    # Use -1 for skipping check on block range.
+    maxEventsBlockRange = 1000
 
-    # GQL cache-control max-age settings (in seconds)
-    maxAge = 15
-    timeTravelMaxAge = 86400 # 1 day
+    # Log directory for GQL requests
+    logDir = "./gql-logs"
+
+    # GQL cache settings
+    [server.gql.cache]
+      enabled = true
+
+      # Max in-memory cache size (in bytes) (default 8 MB)
+      # maxCacheSize
+
+      # GQL cache-control max-age settings (in seconds)
+      maxAge = 15
+      timeTravelMaxAge = 86400 # 1 day
 
 [metrics]
   host = "0.0.0.0"
@@ -58,7 +64,7 @@
 
 [upstream]
   [upstream.ethServer]
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_ETH_RPC_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
     # Boolean flag to specify if rpc-eth-client should be used for RPC endpoint instead of ipld-eth-client (ipld-eth-server GQL client)
     rpcClient = true
@@ -85,6 +91,9 @@
   # Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
   blockDelayInMilliSecs = 30000
 
+  # Number of blocks by which block processing lags behind head
+  blockProcessingOffset = 0
+
   # Boolean to switch between modes of processing events when starting the server.
   # Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.
   # Setting to false will fetch blocks consecutively with its events and then process them (Behaviour is followed in realtime processing near head).
@@ -96,3 +105,6 @@
   # Max block range of historical processing after which it waits for completion of events processing
   # If set to -1 historical processing does not wait for events processing and completes till latest canonical block
   historicalMaxFetchAhead = 10000
+
+  # Max number of retries to fetch new block after which watcher will failover to other RPC endpoints
+  maxNewBlockRetries = 3

stack_orchestrator/data/config/watcher-azimuth/start-job-runner.sh

@@ -4,16 +4,19 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
-echo "Using IPLD ETH RPC endpoint ${CERC_IPLD_ETH_RPC}"
-echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
+echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL_ENDPOINT}"
 echo "Using historicalLogsBlockRange ${CERC_HISTORICAL_BLOCK_RANGE:-2000}"
 
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 # Replace env variables in template TOML file
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_IPLD_ETH_RPC|${CERC_IPLD_ETH_RPC}|g; \
-          s|REPLACE_WITH_CERC_IPLD_ETH_GQL|${CERC_IPLD_ETH_GQL}|g; \
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}|g; \
+          s|REPLACE_WITH_CERC_IPLD_ETH_GQL_ENDPOINT|${CERC_IPLD_ETH_GQL_ENDPOINT}|g; \
           s|REPLACE_WITH_CERC_HISTORICAL_BLOCK_RANGE|${CERC_HISTORICAL_BLOCK_RANGE:-2000}| ")
 
 # Write the modified content to a new file

stack_orchestrator/data/config/watcher-azimuth/start-server.sh

@@ -4,16 +4,19 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
-echo "Using IPLD ETH RPC endpoint ${CERC_IPLD_ETH_RPC}"
-echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
+echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL_ENDPOINT}"
 echo "Using historicalLogsBlockRange ${CERC_HISTORICAL_BLOCK_RANGE:-2000}"
 
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 # Replace env variables in template TOML file
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_IPLD_ETH_RPC|${CERC_IPLD_ETH_RPC}|g; \
-          s|REPLACE_WITH_CERC_IPLD_ETH_GQL|${CERC_IPLD_ETH_GQL}|g; \
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}|g; \
+          s|REPLACE_WITH_CERC_IPLD_ETH_GQL_ENDPOINT|${CERC_IPLD_ETH_GQL_ENDPOINT}|g; \
           s|REPLACE_WITH_CERC_HISTORICAL_BLOCK_RANGE|${CERC_HISTORICAL_BLOCK_RANGE:-2000}| ")
 
 # Write the modified content to a new file

stack_orchestrator/data/config/watcher-azimuth/watcher-config-template.toml

@@ -1,6 +1,7 @@
 [server]
   host = "0.0.0.0"
-  maxSimultaneousRequests = -1
+  [server.gql]
+    maxSimultaneousRequests = -1
 
 [metrics]
   host = "0.0.0.0"
@@ -13,8 +14,8 @@
 
 [upstream]
   [upstream.ethServer]
-    gqlApiEndpoint = "REPLACE_WITH_CERC_IPLD_ETH_GQL"
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_IPLD_ETH_RPC"
+    gqlApiEndpoint = "REPLACE_WITH_CERC_IPLD_ETH_GQL_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
 [jobQueue]
   historicalLogsBlockRange = REPLACE_WITH_CERC_HISTORICAL_BLOCK_RANGE

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/start-job-runner.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/start-server.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/watcher-config-template.toml

@@ -2,7 +2,6 @@
   host = "0.0.0.0"
   port = 3008
   kind = "active"
-  gqlPath = '/'
 
   # Checkpointing state.
   checkpointing = true
@@ -22,23 +21,30 @@
   # Interval in number of blocks at which to clear entities cache.
   clearEntitiesCacheInterval = 1000
 
-  # Max block range for which to return events in eventsInRange GQL query.
-  # Use -1 for skipping check on block range.
-  maxEventsBlockRange = 1000
-
   # Flag to specify whether RPC endpoint supports block hash as block tag parameter
   rpcSupportsBlockHashParam = false
 
-  # GQL cache settings
-  [server.gqlCache]
-    enabled = true
+  # Server GQL config
+  [server.gql]
+    path = "/"
 
-    # Max in-memory cache size (in bytes) (default 8 MB)
-    # maxCacheSize
+    # Max block range for which to return events in eventsInRange GQL query.
+    # Use -1 for skipping check on block range.
+    maxEventsBlockRange = 1000
 
-    # GQL cache-control max-age settings (in seconds)
-    maxAge = 15
-    timeTravelMaxAge = 86400 # 1 day
+    # Log directory for GQL requests
+    logDir = "./gql-logs"
+
+    # GQL cache settings
+    [server.gql.cache]
+      enabled = true
+
+      # Max in-memory cache size (in bytes) (default 8 MB)
+      # maxCacheSize
+
+      # GQL cache-control max-age settings (in seconds)
+      maxAge = 15
+      timeTravelMaxAge = 86400 # 1 day
 
 [metrics]
   host = "0.0.0.0"
@@ -58,7 +64,7 @@
 
 [upstream]
   [upstream.ethServer]
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_ETH_RPC_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
     # Boolean flag to specify if rpc-eth-client should be used for RPC endpoint instead of ipld-eth-client (ipld-eth-server GQL client)
     rpcClient = true
@@ -69,7 +75,7 @@
     # Boolean flag to filter event logs by contracts
     filterLogsByAddresses = true
     # Boolean flag to filter event logs by topics
-    filterLogsByTopics = false
+    filterLogsByTopics = true
 
   [upstream.cache]
     name = "requests"
@@ -85,6 +91,9 @@
   # Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
   blockDelayInMilliSecs = 30000
 
+  # Number of blocks by which block processing lags behind head
+  blockProcessingOffset = 0
+
   # Boolean to switch between modes of processing events when starting the server.
   # Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.
   # Setting to false will fetch blocks consecutively with its events and then process them (Behaviour is followed in realtime processing near head).
@@ -96,3 +105,6 @@
   # Max block range of historical processing after which it waits for completion of events processing
   # If set to -1 historical processing does not wait for events processing and completes till latest canonical block
   historicalMaxFetchAhead = 10000
+
+  # Max number of retries to fetch new block after which watcher will failover to other RPC endpoints
+  maxNewBlockRetries = 3

stack_orchestrator/data/config/watcher-sushiswap-v3/start-job-runner.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-sushiswap-v3/start-server.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-sushiswap-v3/watcher-config-template.toml

@@ -2,7 +2,6 @@
   host = "0.0.0.0"
   port = 3008
   kind = "active"
-  gqlPath = "/"
 
   # Checkpointing state.
   checkpointing = true
@@ -22,23 +21,30 @@
   # Interval in number of blocks at which to clear entities cache.
   clearEntitiesCacheInterval = 1000
 
-  # Max block range for which to return events in eventsInRange GQL query.
-  # Use -1 for skipping check on block range.
-  maxEventsBlockRange = 1000
-
   # Flag to specify whether RPC endpoint supports block hash as block tag parameter
   rpcSupportsBlockHashParam = false
 
-  # GQL cache settings
-  [server.gqlCache]
-    enabled = true
+  # Server GQL config
+  [server.gql]
+    path = "/"
 
-    # Max in-memory cache size (in bytes) (default 8 MB)
-    # maxCacheSize
+    # Max block range for which to return events in eventsInRange GQL query.
+    # Use -1 for skipping check on block range.
+    maxEventsBlockRange = 1000
 
-    # GQL cache-control max-age settings (in seconds)
-    maxAge = 15
-    timeTravelMaxAge = 86400 # 1 day
+    # Log directory for GQL requests
+    logDir = "./gql-logs"
+
+    # GQL cache settings
+    [server.gql.cache]
+      enabled = true
+
+      # Max in-memory cache size (in bytes) (default 8 MB)
+      # maxCacheSize
+
+      # GQL cache-control max-age settings (in seconds)
+      maxAge = 15
+      timeTravelMaxAge = 86400 # 1 day
 
 [metrics]
   host = "0.0.0.0"
@@ -58,7 +64,7 @@
 
 [upstream]
   [upstream.ethServer]
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_ETH_RPC_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
     # Boolean flag to specify if rpc-eth-client should be used for RPC endpoint instead of ipld-eth-client (ipld-eth-server GQL client)
     rpcClient = true
@@ -85,6 +91,9 @@
   # Filecoin block time: https://docs.filecoin.io/basics/the-blockchain/blocks-and-tipsets#blocktime
   blockDelayInMilliSecs = 30000
 
+  # Number of blocks by which block processing lags behind head
+  blockProcessingOffset = 0
+
   # Boolean to switch between modes of processing events when starting the server.
   # Setting to true will fetch filtered events and required blocks in a range of blocks and then process them.
   # Setting to false will fetch blocks consecutively with its events and then process them (Behaviour is followed in realtime processing near head).
@@ -96,3 +105,6 @@
   # Max block range of historical processing after which it waits for completion of events processing
   # If set to -1 historical processing does not wait for events processing and completes till latest canonical block
   historicalMaxFetchAhead = 10000
+
+  # Max number of retries to fetch new block after which watcher will failover to other RPC endpoints
+  maxNewBlockRetries = 3

stack_orchestrator/data/container-build/cerc-snowballtools-base-backend/Dockerfile

@@ -1,6 +0,0 @@
-FROM cerc/snowballtools-base-backend-base:local
-
-WORKDIR /app/packages/backend
-COPY run.sh .
-
-ENTRYPOINT ["./run.sh"]

stack_orchestrator/data/container-build/cerc-snowballtools-base-backend/Dockerfile-base

@@ -1,26 +0,0 @@
-FROM ubuntu:22.04 as builder
-
-RUN apt update && \
-      apt install -y --no-install-recommends --no-install-suggests \
-      ca-certificates curl gnupg
-
-# Node
-ARG NODE_MAJOR=20
-RUN curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg && \
-      echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_$NODE_MAJOR.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list && \
-      apt update && apt install -y nodejs
-
-# npm setup
-RUN npm config set @cerc-io:registry https://git.vdb.to/api/packages/cerc-io/npm/ && npm install -g yarn
-
-COPY . /app/
-WORKDIR /app/
-
-RUN find . -name 'node_modules' | xargs -n1 rm -rf
-RUN yarn && yarn build --ignore frontend
-
-FROM cerc/webapp-base:local
-
-COPY --from=builder /app /app
-
-WORKDIR /app/packages/backend

stack_orchestrator/data/container-build/cerc-snowballtools-base-backend/build.sh

@@ -1,10 +0,0 @@
-#!/usr/bin/env bash
-# Build cerc/webapp-deployer-backend
-
-source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
-
-# See: https://stackoverflow.com/a/246128/1701505
-SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-
-docker build -t cerc/snowballtools-base-backend-base:local ${build_command_args} -f ${SCRIPT_DIR}/Dockerfile-base ${CERC_REPO_BASE_DIR}/snowballtools-base
-docker build -t cerc/snowballtools-base-backend:local ${build_command_args} ${SCRIPT_DIR} 

stack_orchestrator/data/container-build/cerc-snowballtools-base-backend/run.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-
-
-LACONIC_HOSTED_CONFIG_FILE=${LACONIC_HOSTED_CONFIG_FILE}
-if [ -z "${LACONIC_HOSTED_CONFIG_FILE}" ]; then
-  if [ -f "/config/laconic-hosted-config.yml" ]; then
-    LACONIC_HOSTED_CONFIG_FILE="/config/laconic-hosted-config.yml"
-  elif [ -f "/config/config.yml" ]; then
-    LACONIC_HOSTED_CONFIG_FILE="/config/config.yml"
-  fi
-fi
-
-if [ -f "${LACONIC_HOSTED_CONFIG_FILE}" ]; then
-  /scripts/apply-webapp-config.sh $LACONIC_HOSTED_CONFIG_FILE "`pwd`/dist"
-fi
-
-/scripts/apply-runtime-env.sh "`pwd`/dist"
-
-yarn start

stack_orchestrator/data/container-build/cerc-test-container/build.sh

@@ -2,4 +2,4 @@
 # Build cerc/test-container
 source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-docker build -t cerc/test-container:local -f ${SCRIPT_DIR}/Dockerfile ${build_command_args} $SCRIPT_DIR
+docker build -t cerc/test-container:local -f ${SCRIPT_DIR}/Dockerfile ${build_command_args} $SCRIPT_DIR

stack_orchestrator/data/container-build/cerc-watcher-ajna/Dockerfile

@@ -6,5 +6,10 @@ WORKDIR /app
 
 COPY . .
 
+# Get the latest Git commit hash and set in package.json
+RUN COMMIT_HASH=$(git rev-parse HEAD) && \
+  jq --arg commitHash "$COMMIT_HASH" '.commitHash = $commitHash' package.json > tmp.json && \
+  mv tmp.json package.json
+
 RUN echo "Installing dependencies and building ajna-watcher-ts" && \
   yarn && yarn build

stack_orchestrator/data/container-build/cerc-watcher-azimuth/Dockerfile

@@ -1,11 +1,20 @@
 FROM node:18.16.0-alpine3.16
 
-RUN apk --update --no-cache add git python3 alpine-sdk
+RUN apk --update --no-cache add git python3 alpine-sdk jq
 
 WORKDIR /app
 
 COPY . .
 
+# Get the latest Git commit hash and set it in package.json of all watchers
+RUN COMMIT_HASH=$(git rev-parse HEAD) && \
+    find . -name 'package.json' -exec sh -c ' \
+    for packageFile; do \
+        jq --arg commitHash "$0" ".commitHash = \$commitHash" "$packageFile" > "$packageFile.tmp" && \
+        mv "$packageFile.tmp" "$packageFile"; \
+    done \
+    ' "$COMMIT_HASH" {} \;
+
 RUN echo "Building azimuth-watcher-ts" && \
     yarn && yarn build
 

stack_orchestrator/data/container-build/cerc-watcher-merkl-sushiswap-v3/Dockerfile

@@ -6,5 +6,10 @@ WORKDIR /app
 
 COPY . .
 
+# Get the latest Git commit hash and set in package.json
+RUN COMMIT_HASH=$(git rev-parse HEAD) && \
+  jq --arg commitHash "$COMMIT_HASH" '.commitHash = $commitHash' package.json > tmp.json && \
+  mv tmp.json package.json
+
 RUN echo "Installing dependencies and building merkl-sushiswap-v3-watcher-ts" && \
   yarn && yarn build

stack_orchestrator/data/container-build/cerc-watcher-sushiswap-v3/Dockerfile

@@ -6,5 +6,10 @@ WORKDIR /app
 
 COPY . .
 
+# Get the latest Git commit hash and set in package.json
+RUN COMMIT_HASH=$(git rev-parse HEAD) && \
+  jq --arg commitHash "$COMMIT_HASH" '.commitHash = $commitHash' package.json > tmp.json && \
+  mv tmp.json package.json
+
 RUN echo "Installing dependencies and building sushiswap-v3-watcher-ts" && \
   yarn && yarn build

stack_orchestrator/data/container-build/cerc-webapp-base/Dockerfile

@@ -34,7 +34,7 @@ RUN \
 
 # [Optional] Uncomment this section to install additional OS packages.
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
-    && apt-get -y install --no-install-recommends jq gettext-base
+    && apt-get -y install --no-install-recommends jq gettext-base git
 
 # [Optional] Uncomment if you want to install an additional version of node using nvm
 # ARG EXTRA_NODE_VERSION=10

stack_orchestrator/data/container-build/cerc-webapp-base/scripts/start-serving-app.sh

@@ -8,21 +8,27 @@ CERC_WEBAPP_FILES_DIR="${CERC_WEBAPP_FILES_DIR:-/data}"
 CERC_ENABLE_CORS="${CERC_ENABLE_CORS:-false}"
 CERC_SINGLE_PAGE_APP="${CERC_SINGLE_PAGE_APP}"
 
-if [ -z "${CERC_SINGLE_PAGE_APP}" ]; then
-  if [ 1 -eq $(find "${CERC_WEBAPP_FILES_DIR}" -name '*.html' | wc -l) ] && [ -d "${CERC_WEBAPP_FILES_DIR}/static" ]; then
+if [ -z "${CERC_SINGLE_PAGE_APP}" ]; then 
+  # If there is only one HTML file, assume an SPA.
+  if [ 1 -eq $(find "${CERC_WEBAPP_FILES_DIR}" -name '*.html' | wc -l) ]; then
     CERC_SINGLE_PAGE_APP=true
   else
     CERC_SINGLE_PAGE_APP=false
   fi
 fi
 
-if [ "true" == "$CERC_ENABLE_CORS" ]; then
+# ${var,,} is a lower-case comparison
+if [ "true" == "${CERC_ENABLE_CORS,,}" ]; then
   CERC_HTTP_EXTRA_ARGS="$CERC_HTTP_EXTRA_ARGS --cors"
 fi
 
-if [ "true" == "$CERC_SINGLE_PAGE_APP" ]; then
+# ${var,,} is a lower-case comparison
+if [ "true" == "${CERC_SINGLE_PAGE_APP,,}" ]; then
+  echo "Serving content as single-page app.  If this is wrong, set 'CERC_SINGLE_PAGE_APP=false'"
   # Create a catchall redirect back to /
   CERC_HTTP_EXTRA_ARGS="$CERC_HTTP_EXTRA_ARGS --proxy http://localhost:${CERC_LISTEN_PORT}?"
+else
+  echo "Serving content normally.  If this is a single-page app, set 'CERC_SINGLE_PAGE_APP=true'"
 fi
 
 LACONIC_HOSTED_CONFIG_FILE=${LACONIC_HOSTED_CONFIG_FILE}
@@ -39,4 +45,4 @@ if [ -f "${LACONIC_HOSTED_CONFIG_FILE}" ]; then
 fi
 
 /scripts/apply-runtime-env.sh ${CERC_WEBAPP_FILES_DIR}
-http-server $CERC_HTTP_EXTRA_ARGS -p ${CERC_LISTEN_PORT} "${CERC_WEBAPP_FILES_DIR}"
+http-server $CERC_HTTP_EXTRA_ARGS -p ${CERC_LISTEN_PORT} "${CERC_WEBAPP_FILES_DIR}"

stack_orchestrator/data/stacks/ajna/README.md

@@ -53,7 +53,7 @@ Inside deployment directory, open the `config.env` file  and set following env v
 
 ```bash
 # External Filecoin (ETH RPC) endpoint to point the watcher to
-CERC_ETH_RPC_ENDPOINT=https://example-lotus-endpoint/rpc/v1
+CERC_ETH_RPC_ENDPOINTS=https://example-lotus-endpoint-1/rpc/v1,https://example-lotus-endpoint-2/rpc/v1
 ```
 
 ### Start the deployment

stack_orchestrator/data/stacks/ajna/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: ajna
 description: "Ajna watcher stack"
 repos:
-  - git.vdb.to/cerc-io/ajna-watcher-ts@v0.1.1
+  - git.vdb.to/cerc-io/ajna-watcher-ts@v0.1.13
 containers:
   - cerc/watcher-ajna
 pods:

stack_orchestrator/data/stacks/azimuth/README.md

@@ -4,7 +4,7 @@ Instructions to setup and deploy Azimuth Watcher stack
 
 ## Setup
 
-Prerequisite: `ipld-eth-server` RPC and GQL endpoints
+Prerequisite: External RPC endpoints
 
 Clone required repositories:
 
@@ -44,34 +44,42 @@ network:
      - 0.0.0.0:9000:9000
     azimuth-watcher-server:
      - 0.0.0.0:3001:3001
+     - 0.0.0.0:9001:9001
     censures-watcher-job-runner:
      - 0.0.0.0:9002:9002
     censures-watcher-server:
      - 0.0.0.0:3002:3002
+     - 0.0.0.0:9003:9003
     claims-watcher-job-runner:
      - 0.0.0.0:9004:9004
     claims-watcher-server:
      - 0.0.0.0:3003:3003
+     - 0.0.0.0:9005:9005
     conditional-star-release-watcher-job-runner:
      - 0.0.0.0:9006:9006
     conditional-star-release-watcher-server:
      - 0.0.0.0:3004:3004
+     - 0.0.0.0:9007:9007
     delegated-sending-watcher-job-runner:
      - 0.0.0.0:9008:9008
     delegated-sending-watcher-server:
      - 0.0.0.0:3005:3005
+     - 0.0.0.0:9009:9009
     ecliptic-watcher-job-runner:
      - 0.0.0.0:9010:9010
     ecliptic-watcher-server:
      - 0.0.0.0:3006:3006
+     - 0.0.0.0:9011:9011
     linear-star-release-watcher-job-runner:
      - 0.0.0.0:9012:9012
     linear-star-release-watcher-server:
      - 0.0.0.0:3007:3007
+     - 0.0.0.0:9013:9013
     polls-watcher-job-runner:
      - 0.0.0.0:9014:9014
     polls-watcher-server:
      - 0.0.0.0:3008:3008
+     - 0.0.0.0:9015:9015
     gateway-server:
      - 0.0.0.0:4000:4000
 ...
@@ -94,7 +102,7 @@ Inside the deployment directory, open the file `config.env` and add variable to
 
   ```bash
   # External RPC endpoints
-  CERC_IPLD_ETH_RPC=
+  CERC_ETH_RPC_ENDPOINTS=https://example-rpc-endpoint-1,https://example-rpc-endpoint-2
   ```
 
 * NOTE: If RPC endpoint is on the host machine, use `host.docker.internal` as the hostname to access the host port, or use the `ip a` command to find the IP address of the `docker0` interface (this will usually be something like `172.17.0.1` or `172.18.0.1`)
@@ -120,4 +128,7 @@ To stop all azimuth services and also delete data:
 
 ```bash
 laconic-so deployment --dir azimuth-deployment stop --delete-volumes
+
+# Remove deployment directory (deployment will have to be recreated for a re-run)
+rm -r azimuth-deployment
 ```

stack_orchestrator/data/stacks/azimuth/stack.yml

@@ -1,7 +1,7 @@
 version: "1.0"
 name: azimuth
 repos:
-  - github.com/cerc-io/azimuth-watcher-ts@v0.1.3
+  - github.com/cerc-io/azimuth-watcher-ts@0.1.6
 containers:
   - cerc/watcher-azimuth
 pods:

stack_orchestrator/data/stacks/graph-node/README.md

@@ -43,16 +43,18 @@ customized by editing the "spec" file generated by `laconic-so deploy init`.
 ```
 $ cat graph-node-spec.yml
 stack: graph-node
-ports:
-  graph-node:
-    - '8000:8000'
-    - '8001'
-    - '8020:8020'
-    - '8030'
-  ipfs:
-    - '8080'
-    - '4001'
-    - '5001:5001'
+network:
+  ports:
+    graph-node:
+      - '8000:8000'
+      - '8001'
+      - '8020:8020'
+      - '8030'
+      - '8040'
+    ipfs:
+      - '8080'
+      - '4001'
+      - '5001:5001'
 ...
 ```
 
@@ -64,7 +66,7 @@ laconic-so --stack graph-node deploy create --spec-file graph-node-spec.yml --de
 
 ## Start the stack
 
-Create an env file with the following values to be set before starting the stack:
+Update `config.env` file inside deployment directory with the following values before starting the stack:
 
 ```bash
 # Set ETH RPC endpoint the graph node will use
@@ -76,21 +78,35 @@ export ETH_RPC_PORT=
 # The etherum network(s) graph-node will connect to
 # Set this to a space-separated list of the networks where each entry has the form NAME:URL
 export ETH_NETWORKS=
+
+# Optional:
+
+# Timeout for ETH RPC requests in seconds (default: 180s)
+export GRAPH_ETHEREUM_JSON_RPC_TIMEOUT=
+
+# Number of times to retry ETH RPC requests (default: 10)
+export GRAPH_ETHEREUM_REQUEST_RETRIES=
+
+# Maximum number of blocks to scan for triggers in each request (default: 2000)
+export GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE=
+
+# Maximum number of concurrent requests made against Ethereum for requesting transaction receipts during block ingestion (default: 1000)
+export GRAPH_ETHEREUM_BLOCK_INGESTOR_MAX_CONCURRENT_JSON_RPC_CALLS_FOR_TXN_RECEIPTS=
+
+# Ref: https://git.vdb.to/cerc-io/graph-node/src/branch/master/docs/environment-variables.md
 ```
 
-Example env file:
+Example `config.env` file:
 
 ```bash
 export ETH_RPC_HOST=filecoin.chainup.net
 export ETH_RPC_PORT=443
 
 export ETH_NETWORKS=filecoin:https://filecoin.chainup.net/rpc/v1
-```
 
-Set the environment variables:
-
-```bash
-source <PATH_TO_ENV_FILE>
+export GRAPH_ETHEREUM_JSON_RPC_TIMEOUT=360
+export GRAPH_ETHEREUM_REQUEST_RETRIES=5
+export GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE=50
 ```
 
 Deploy the stack:

stack_orchestrator/data/stacks/graph-node/stack.yml

@@ -3,7 +3,9 @@ name: graph-node
 description: "Stack for running graph-node"
 repos:
   - github.com/graphprotocol/graph-node
+  - github.com/cerc-io/watcher-ts@v0.2.92
 containers:
   - cerc/graph-node
+  - cerc/watcher-ts
 pods:
   - graph-node

stack_orchestrator/data/stacks/mainnet-laconic/deploy/commands.py

@@ -14,10 +14,11 @@
 # along with this program.  If not, see <http:#www.gnu.org/licenses/>.
 
 from stack_orchestrator.util import get_yaml
-from stack_orchestrator.deploy.deploy_types import DeployCommandContext, LaconicStackSetupCommand, DeploymentContext
+from stack_orchestrator.deploy.deploy_types import DeployCommandContext, LaconicStackSetupCommand
+from stack_orchestrator.deploy.deployment_context import DeploymentContext
 from stack_orchestrator.deploy.stack_state import State
 from stack_orchestrator.deploy.deploy_util import VolumeMapping, run_container_command
-from stack_orchestrator.command_types import CommandOptions
+from stack_orchestrator.opts import opts
 from enum import Enum
 from pathlib import Path
 from shutil import copyfile, copytree
@@ -61,7 +62,7 @@ def _get_node_moniker_from_config(network_dir: Path):
     return moniker
 
 
-def _get_node_key_from_gentx(options: CommandOptions, gentx_file_name: str):
+def _get_node_key_from_gentx(gentx_file_name: str):
     gentx_file_path = Path(gentx_file_name)
     if gentx_file_path.exists():
         with open(Path(gentx_file_name), "rb") as f:
@@ -76,24 +77,24 @@ def _comma_delimited_to_list(list_str: str):
     return list_str.split(",") if list_str else []
 
 
-def _get_node_keys_from_gentx_files(options: CommandOptions, gentx_file_list: str):
+def _get_node_keys_from_gentx_files(gentx_file_list: str):
     node_keys = []
     gentx_files = _comma_delimited_to_list(gentx_file_list)
     for gentx_file in gentx_files:
-        node_key = _get_node_key_from_gentx(options, gentx_file)
+        node_key = _get_node_key_from_gentx(gentx_file)
         if node_key:
             node_keys.append(node_key)
     return node_keys
 
 
-def _copy_gentx_files(options: CommandOptions, network_dir: Path, gentx_file_list: str):
+def _copy_gentx_files(network_dir: Path, gentx_file_list: str):
     gentx_files = _comma_delimited_to_list(gentx_file_list)
     for gentx_file in gentx_files:
         gentx_file_path = Path(gentx_file)
         copyfile(gentx_file_path, os.path.join(network_dir, "config", "gentx", os.path.basename(gentx_file_path)))
 
 
-def _remove_persistent_peers(options: CommandOptions, network_dir: Path):
+def _remove_persistent_peers(network_dir: Path):
     config_file_path = _config_toml_path(network_dir)
     if not config_file_path.exists():
         print("Error: config.toml not found")
@@ -107,7 +108,7 @@ def _remove_persistent_peers(options: CommandOptions, network_dir: Path):
         output_file.write(config_file_content)
 
 
-def _insert_persistent_peers(options: CommandOptions, config_dir: Path, new_persistent_peers: str):
+def _insert_persistent_peers(config_dir: Path, new_persistent_peers: str):
     config_file_path = config_dir.joinpath("config.toml")
     if not config_file_path.exists():
         print("Error: config.toml not found")
@@ -150,7 +151,7 @@ def _phase_from_params(parameters):
 
 def setup(command_context: DeployCommandContext, parameters: LaconicStackSetupCommand, extra_args):
 
-    options = command_context.cluster_context.options
+    options = opts.o
 
     currency = "stake"  # Does this need to be a parameter?
 
@@ -237,7 +238,7 @@ def setup(command_context: DeployCommandContext, parameters: LaconicStackSetupCo
                 print("Error: --gentx-files must be supplied")
                 sys.exit(1)
             # First look in the supplied gentx files for the other nodes' keys
-            other_node_keys = _get_node_keys_from_gentx_files(options, parameters.gentx_file_list)
+            other_node_keys = _get_node_keys_from_gentx_files(parameters.gentx_file_list)
             # Add those keys to our genesis, with balances we determine here (why?)
             for other_node_key in other_node_keys:
                 outputk, statusk = run_container_command(
@@ -246,7 +247,7 @@ def setup(command_context: DeployCommandContext, parameters: LaconicStackSetupCo
             if options.debug:
                 print(f"Command output: {outputk}")
             # Copy the gentx json files into our network dir
-            _copy_gentx_files(options, network_dir, parameters.gentx_file_list)
+            _copy_gentx_files(network_dir, parameters.gentx_file_list)
             # Now we can run collect-gentxs
             output1, status1 = run_container_command(
                 command_context, "laconicd", f"laconicd collect-gentxs --home {laconicd_home_path_in_container}", mounts)
@@ -255,7 +256,7 @@ def setup(command_context: DeployCommandContext, parameters: LaconicStackSetupCo
             print(f"Generated genesis file, please copy to other nodes as required: \
                 {os.path.join(network_dir, 'config', 'genesis.json')}")
             # Last thing, collect-gentxs puts a likely bogus set of persistent_peers in config.toml so we remove that now
-            _remove_persistent_peers(options, network_dir)
+            _remove_persistent_peers(network_dir)
         # In both cases we validate the genesis file now
         output2, status1 = run_container_command(
             command_context, "laconicd", f"laconicd validate-genesis --home {laconicd_home_path_in_container}", mounts)
@@ -266,7 +267,7 @@ def setup(command_context: DeployCommandContext, parameters: LaconicStackSetupCo
         sys.exit(1)
 
 
-def create(context: DeploymentContext, extra_args):
+def create(deployment_context: DeploymentContext, extra_args):
     network_dir = extra_args[0]
     if network_dir is None:
         print("Error: --network-dir must be supplied")
@@ -285,15 +286,15 @@ def create(context: DeploymentContext, extra_args):
         sys.exit(1)
     # Copy the network directory contents into our deployment
     # TODO: change this to work with non local paths
-    deployment_config_dir = context.deployment_dir.joinpath("data", "laconicd-config")
+    deployment_config_dir = deployment_context.deployment_dir.joinpath("data", "laconicd-config")
     copytree(config_dir_path, deployment_config_dir, dirs_exist_ok=True)
     # If supplied, add the initial persistent peers to the config file
     if extra_args[1]:
         initial_persistent_peers = extra_args[1]
-        _insert_persistent_peers(context.command_context.cluster_context.options, deployment_config_dir, initial_persistent_peers)
+        _insert_persistent_peers(deployment_config_dir, initial_persistent_peers)
     # Copy the data directory contents into our deployment
     # TODO: change this to work with non local paths
-    deployment_data_dir = context.deployment_dir.joinpath("data", "laconicd-data")
+    deployment_data_dir = deployment_context.deployment_dir.joinpath("data", "laconicd-data")
     copytree(data_dir_path, deployment_data_dir, dirs_exist_ok=True)
 
 

stack_orchestrator/data/stacks/merkl-sushiswap-v3/README.md

@@ -53,7 +53,7 @@ Inside deployment directory, open the `config.env` file  and set following env v
 
 ```bash
 # External Filecoin (ETH RPC) endpoint to point the watcher to
-CERC_ETH_RPC_ENDPOINT=https://example-lotus-endpoint/rpc/v1
+CERC_ETH_RPC_ENDPOINTS=https://example-lotus-endpoint-1/rpc/v1,https://example-lotus-endpoint-2/rpc/v1
 ```
 
 ### Start the deployment

stack_orchestrator/data/stacks/merkl-sushiswap-v3/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: merkl-sushiswap-v3
 description: "SushiSwap v3 watcher stack"
 repos:
-  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.7
+  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.14
 containers:
   - cerc/watcher-merkl-sushiswap-v3
 pods:

stack_orchestrator/data/stacks/monitoring/README.md

@@ -134,6 +134,29 @@ Note: Use `host.docker.internal` as host to access ports on the host machine
 
 Place the dashboard json files in grafana dashboards config directory (`monitoring-deployment/config/monitoring/grafana/dashboards`) in the deployment folder
 
+#### Graph Node Config
+
+For graph-node dashboard postgres datasource needs to be setup in `monitoring-deployment/config/monitoring/grafana/provisioning/datasources/graph-node-postgres.yml` (in deployment folder)
+
+```yml
+# graph-node-postgres.yml
+...
+datasources:
+  - name: Graph Node Postgres
+    type: postgres
+    jsonData:
+      # Set name to remote graph-node database name
+      database: graph-node
+      ...
+    # Set user to remote graph-node database username
+    user: graph-node
+    # Add URL for remote graph-node database
+    url: graph-node-db:5432
+    # Set password for graph-node database
+    secureJsonData:
+      password: 'password'
+```
+
 ### Env
 
 Set the following env variables in the deployment env config file (`monitoring-deployment/config.env`):
@@ -156,6 +179,11 @@ Set the following env variables in the deployment env config file (`monitoring-d
   # Grafana server host URL (used in various links in alerts, etc.)
   # (Optional, default: http://localhost:3000)
   GF_SERVER_ROOT_URL=
+
+  
+  # RPC endpoint used by graph-node for upstream head metric
+  # (Optional, default: https://mainnet.infura.io/v3)
+  GRAPH_NODE_RPC_ENDPOINT=
   ```
 
 ## Start the stack

stack_orchestrator/data/stacks/monitoring/monitoring-watchers.md

@@ -57,35 +57,35 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
     metrics_path: /metrics
     scheme: http
     static_configs:
-      - targets: ['AZIMUTH_WATCHER_HOST:AZIMUTH_WATCHER_PORT']
+      - targets: ['AZIMUTH_WATCHER_HOST:AZIMUTH_WATCHER_METRICS_PORT', 'AZIMUTH_WATCHER_HOST:AZIMUTH_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'azimuth'
           chain: 'ethereum'
-      - targets: ['CENSURES_WATCHER_HOST:CENSURES_WATCHER_PORT']
+      - targets: ['CENSURES_WATCHER_HOST:CENSURES_WATCHER_METRICS_PORT', 'CENSURES_WATCHER_HOST:CENSURES_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'censures'
           chain: 'ethereum'
-      - targets: ['CLAIMS_WATCHER_HOST:CLAIMS_WATCHER_PORT']
+      - targets: ['CLAIMS_WATCHER_HOST:CLAIMS_WATCHER_METRICS_PORT', 'CLAIMS_WATCHER_HOST:CLAIMS_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'claims'
           chain: 'ethereum'
-      - targets: ['CONDITIONAL_STAR_RELEASE_WATCHER_HOST:CONDITIONAL_STAR_RELEASE_WATCHER_PORT']
+      - targets: ['CONDITIONAL_STAR_RELEASE_WATCHER_HOST:CONDITIONAL_STAR_RELEASE_WATCHER_METRICS_PORT', 'CONDITIONAL_STAR_RELEASE_WATCHER_HOST:CONDITIONAL_STAR_RELEASE_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'conditional_star_release'
           chain: 'ethereum'
-      - targets: ['DELEGATED_SENDING_WATCHER_HOST:DELEGATED_SENDING_WATCHER_PORT']
+      - targets: ['DELEGATED_SENDING_WATCHER_HOST:DELEGATED_SENDING_WATCHER_METRICS_PORT', 'DELEGATED_SENDING_WATCHER_HOST:DELEGATED_SENDING_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'delegated_sending'
           chain: 'ethereum'
-      - targets: ['ECLIPTIC_WATCHER_HOST:ECLIPTIC_WATCHER_PORT']
+      - targets: ['ECLIPTIC_WATCHER_HOST:ECLIPTIC_WATCHER_METRICS_PORT', 'ECLIPTIC_WATCHER_HOST:ECLIPTIC_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'ecliptic'
           chain: 'ethereum'
-      - targets: ['LINEAR_STAR_WATCHER_HOST:LINEAR_STAR_WATCHER_PORT']
+      - targets: ['LINEAR_STAR_WATCHER_HOST:LINEAR_STAR_WATCHER_METRICS_PORT', 'LINEAR_STAR_WATCHER_HOST:LINEAR_STAR_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'linear_star_release'
           chain: 'ethereum'
-      - targets: ['POLLS_WATCHER_HOST:POLLS_WATCHER_PORT']
+      - targets: ['POLLS_WATCHER_HOST:POLLS_WATCHER_METRICS_PORT', 'POLLS_WATCHER_HOST:POLLS_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'polls'
           chain: 'ethereum'
@@ -95,11 +95,11 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
     metrics_path: /metrics
     scheme: http
     static_configs:
-      - targets: ['SUSHISWAP_WATCHER_HOST:SUSHISWAP_WATCHER_PORT']
+      - targets: ['SUSHISWAP_WATCHER_HOST:SUSHISWAP_WATCHER_METRICS_PORT', 'SUSHISWAP_WATCHER_HOST:SUSHISWAP_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'sushiswap'
           chain: 'filecoin'
-      - targets: ['MERKLE_SUSHISWAP_WATCHER_HOST:MERKLE_SUSHISWAP_WATCHER_PORT']
+      - targets: ['MERKLE_SUSHISWAP_WATCHER_HOST:MERKLE_SUSHISWAP_WATCHER_METRICS_PORT', 'MERKLE_SUSHISWAP_WATCHER_HOST:MERKLE_SUSHISWAP_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'merkl_sushiswap'
           chain: 'filecoin'
@@ -109,25 +109,35 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
     metrics_path: /metrics
     scheme: http
     static_configs:
-      - targets: ['AJNA_WATCHER_HOST:AJNA_WATCHER_PORT']
+      - targets: ['AJNA_WATCHER_HOST:AJNA_WATCHER_METRICS_PORT', 'AJNA_WATCHER_HOST:AJNA_WATCHER_GQL_METRICS_PORT']
         labels:
           instance: 'ajna'
           chain: 'filecoin'
+
+  - job_name: graph-node
+    metrics_path: /metrics
+    scrape_interval: 30s
+    static_configs:
+      - targets: ['GRAPH_NODE_HOST:GRAPH_NODE_HOST_METRICS_PORT']
   ```
 
 Add scrape config as done above for any additional watcher to add it to the Watchers dashboard.
 
 ### Grafana alerts config
 
-Place the pre-configured watcher alerts rules in Grafana provisioning directory:
+Place the pre-configured alerts rules in Grafana provisioning directory:
 
   ```bash
+  # watcher alert rules
   cp monitoring-watchers-deployment/config/monitoring/watcher-alert-rules.yml monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/
+
+  # subgraph alert rules
+  cp monitoring-watchers-deployment/config/monitoring/subgraph-alert-rules.yml monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/
   ```
 
 Update the alerting contact points config (`monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/contactpoints.yml`) with desired contact points
 
-Add corresponding routes to the notification policies config (`monitoring-watchers-deployment/monitoring/grafana/provisioning/alerting/policies.yaml`) with appropriate object-matchers:
+Add corresponding routes to the notification policies config (`monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/policies.yml`) with appropriate object-matchers:
 
   ```yml
   ...
@@ -135,7 +145,7 @@ Add corresponding routes to the notification policies config (`monitoring-watche
       - receiver: SlackNotifier
       object_matchers:
         # Add matchers below
-        - ['grafana_folder', '=', 'WatcherAlerts']
+        - ['grafana_folder', '=~', 'WatcherAlerts|SubgraphAlerts']
   ```
 
 ### Env
@@ -149,6 +159,9 @@ Set the following env variables in the deployment env config file (`monitoring-w
   # Grafana server host URL to be used
   # (Optional, default: http://localhost:3000)
   GF_SERVER_ROOT_URL=
+
+  # List of subgraph ids to configure alerts for (separated by |)
+  CERC_GRAFANA_ALERTS_SUBGRAPH_IDS=
   ```
 
 ## Start the stack

stack_orchestrator/data/stacks/monitoring/stack.yml

@@ -1,7 +1,7 @@
 version: "0.1"
 name: monitoring
 repos:
-  - github.com/cerc-io/watcher-ts@v0.2.81
+  - github.com/cerc-io/watcher-ts@v0.2.92
 containers:
   - cerc/watcher-ts
 pods:

stack_orchestrator/data/stacks/snowballtools-base-backend/stack.yml

@@ -1,10 +0,0 @@
-version: "1.0"
-name: snowballtools-base-backend
-description: "snowballtools-base-backend"
-repos:
-  - github.com/snowball-tools/snowballtools-base
-containers:
-  - cerc/webapp-base
-  - cerc/snowballtools-base-backend
-pods:
-  - snowballtools-base-backend

stack_orchestrator/data/stacks/sushiswap-v3/README.md

@@ -53,7 +53,7 @@ Inside deployment directory, open the `config.env` file  and set following env v
 
 ```bash
 # External Filecoin (ETH RPC) endpoint to point the watcher to
-CERC_ETH_RPC_ENDPOINT=https://example-lotus-endpoint/rpc/v1
+CERC_ETH_RPC_ENDPOINTS=https://example-lotus-endpoint-1/rpc/v1,https://example-lotus-endpoint-2/rpc/v1
 ```
 
 ### Start the deployment

stack_orchestrator/data/stacks/sushiswap-v3/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: sushiswap-v3
 description: "SushiSwap v3 watcher stack"
 repos:
-  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.7
+  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.14
 containers:
   - cerc/watcher-sushiswap-v3
 pods:

stack_orchestrator/data/stacks/webapp-deployer-backend/stack.yml

@@ -2,10 +2,10 @@ version: "1.0"
 name: webapp-deployer-backend
 description: "Deployer for webapps"
 repos:
-  - git.vdb.to/telackey/webapp-deployment-status-api
+  - git.vdb.to/cerc-io/webapp-deployment-status-api
 containers:
   - cerc/webapp-deployer-backend
 pods:
   - name: webapp-deployer-backend
-    repository: git.vdb.to/telackey/webapp-deployment-status-api
+    repository: git.vdb.to/cerc-io/webapp-deployment-status-api
     path: ./

stack_orchestrator/deploy/deploy.py

@@ -26,7 +26,15 @@ import click
 from pathlib import Path
 from stack_orchestrator import constants
 from stack_orchestrator.opts import opts
-from stack_orchestrator.util import include_exclude_check, get_parsed_stack_config, global_options2, get_dev_root_path
+from stack_orchestrator.util import (
+    get_stack_path,
+    include_exclude_check,
+    get_parsed_stack_config,
+    global_options2,
+    get_dev_root_path,
+    stack_is_in_deployment,
+    resolve_compose_file,
+)
 from stack_orchestrator.deploy.deployer import Deployer, DeployerException
 from stack_orchestrator.deploy.deployer_factory import getDeployer
 from stack_orchestrator.deploy.deploy_types import ClusterContext, DeployCommandContext
@@ -59,6 +67,7 @@ def command(ctx, include, exclude, env_file, cluster, deploy_to):
     if deploy_to is None:
         deploy_to = "compose"
 
+    stack = get_stack_path(stack)
     ctx.obj = create_deploy_context(global_options2(ctx), None, stack, include, exclude, cluster, env_file, deploy_to)
     # Subcommand is executed now, by the magic of click
 
@@ -273,16 +282,12 @@ def _make_default_cluster_name(deployment, compose_dir, stack, include, exclude)
 
 # stack has to be either PathLike pointing to a stack yml file, or a string with the name of a known stack
 def _make_cluster_context(ctx, stack, include, exclude, cluster, env_file):
-
     dev_root_path = get_dev_root_path(ctx)
 
-    # TODO: huge hack, fix this
-    # If the caller passed a path for the stack file, then we know that we can get the compose files
-    # from the same directory
-    deployment = False
-    if isinstance(stack, os.PathLike):
-        compose_dir = stack.parent.joinpath("compose")
-        deployment = True
+    # TODO: hack, this should be encapsulated by the deployment context.
+    deployment = stack_is_in_deployment(stack)
+    if deployment:
+        compose_dir = stack.joinpath("compose")
     else:
         # See: https://stackoverflow.com/questions/25389095/python-get-path-of-root-project-structure
         compose_dir = Path(__file__).absolute().parent.parent.joinpath("data", "compose")
@@ -324,7 +329,10 @@ def _make_cluster_context(ctx, stack, include, exclude, cluster, env_file):
         pod_path = pod["path"]
         if include_exclude_check(pod_name, include, exclude):
             if pod_repository is None or pod_repository == "internal":
-                compose_file_name = os.path.join(compose_dir, f"docker-compose-{pod_path}.yml")
+                if deployment:
+                    compose_file_name = os.path.join(compose_dir, f"docker-compose-{pod_path}.yml")
+                else:
+                    compose_file_name = resolve_compose_file(stack, pod_name)
             else:
                 if deployment:
                     compose_file_name = os.path.join(compose_dir, f"docker-compose-{pod_name}.yml")
@@ -336,6 +344,7 @@ def _make_cluster_context(ctx, stack, include, exclude, cluster, env_file):
                     if pod_post_start_command is not None:
                         post_start_commands.append(os.path.join(script_dir, pod_post_start_command))
                 else:
+                    # TODO: fix this code for external stack with scripts
                     pod_root_dir = os.path.join(dev_root_path, pod_repository.split("/")[-1], pod["path"])
                     compose_file_name = os.path.join(pod_root_dir, f"docker-compose-{pod_name}.yml")
                     pod_pre_start_command = pod.get("pre_start_command")

stack_orchestrator/deploy/deploy_util.py

@@ -16,7 +16,7 @@
 import os
 from typing import List, Any
 from stack_orchestrator.deploy.deploy_types import DeployCommandContext, VolumeMapping
-from stack_orchestrator.util import get_parsed_stack_config, get_yaml, get_compose_file_dir, get_pod_list
+from stack_orchestrator.util import get_parsed_stack_config, get_yaml, get_pod_list, resolve_compose_file
 from stack_orchestrator.opts import opts
 
 
@@ -27,7 +27,7 @@ def _container_image_from_service(stack: str, service: str):
     pods = get_pod_list(parsed_stack)
     yaml = get_yaml()
     for pod in pods:
-        pod_file_path = os.path.join(get_compose_file_dir(), f"docker-compose-{pod}.yml")
+        pod_file_path = resolve_compose_file(stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         if "services" in parsed_pod_file:
             services = parsed_pod_file["services"]

stack_orchestrator/deploy/deployment.py

@@ -50,15 +50,15 @@ def command(ctx, dir):
 
 def make_deploy_context(ctx) -> DeployCommandContext:
     context: DeploymentContext = ctx.obj
-    stack_file_path = context.get_stack_file()
     env_file = context.get_env_file()
     cluster_name = context.get_cluster_id()
     if constants.deploy_to_key in context.spec.obj:
         deployment_type = context.spec.obj[constants.deploy_to_key]
     else:
         deployment_type = constants.compose_deploy_type
-    return create_deploy_context(ctx.parent.parent.obj, context, stack_file_path, None, None, cluster_name, env_file,
-                                 deployment_type)
+    stack = context.deployment_dir
+    return create_deploy_context(ctx.parent.parent.obj, context, stack, None, None,
+                                 cluster_name, env_file, deployment_type)
 
 
 @command.command()
@@ -123,6 +123,7 @@ def push_images(ctx):
 @click.argument('extra_args', nargs=-1)  # help: command: port <service1> <service2>
 @click.pass_context
 def port(ctx, extra_args):
+    ctx.obj = make_deploy_context(ctx)
     port_operation(ctx, extra_args)
 
 

stack_orchestrator/deploy/deployment_create.py

@@ -24,9 +24,10 @@ from secrets import token_hex
 import sys
 from stack_orchestrator import constants
 from stack_orchestrator.opts import opts
-from stack_orchestrator.util import (get_stack_file_path, get_parsed_deployment_spec, get_parsed_stack_config,
+from stack_orchestrator.util import (get_stack_path, get_parsed_deployment_spec, get_parsed_stack_config,
                                      global_options, get_yaml, get_pod_list, get_pod_file_path, pod_has_scripts,
-                                     get_pod_script_paths, get_plugin_code_paths, error_exit, env_var_map_from_file)
+                                     get_pod_script_paths, get_plugin_code_paths, error_exit, env_var_map_from_file,
+                                     resolve_config_dir)
 from stack_orchestrator.deploy.spec import Spec
 from stack_orchestrator.deploy.deploy_types import LaconicStackSetupCommand
 from stack_orchestrator.deploy.deployer_factory import getDeployerConfigGenerator
@@ -43,7 +44,7 @@ def _get_ports(stack):
     pods = get_pod_list(parsed_stack)
     yaml = get_yaml()
     for pod in pods:
-        pod_file_path = get_pod_file_path(parsed_stack, pod)
+        pod_file_path = get_pod_file_path(stack, parsed_stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         if "services" in parsed_pod_file:
             for svc_name, svc in parsed_pod_file["services"].items():
@@ -79,7 +80,7 @@ def _get_named_volumes(stack):
         return ret
 
     for pod in pods:
-        pod_file_path = get_pod_file_path(parsed_stack, pod)
+        pod_file_path = get_pod_file_path(stack, parsed_stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         if "volumes" in parsed_pod_file:
             volumes = parsed_pod_file["volumes"]
@@ -237,6 +238,11 @@ def _find_extra_config_dirs(parsed_pod_file, pod):
                         config_dir = host_path.split("/")[2]
                         if config_dir != pod:
                             config_dirs.add(config_dir)
+        for env_file in service_info.get("env_file", []):
+            if env_file.startswith("../config"):
+                config_dir = env_file.split("/")[2]
+                if config_dir != pod:
+                    config_dirs.add(config_dir)
     return config_dirs
 
 
@@ -453,7 +459,7 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
     _check_volume_definitions(parsed_spec)
     stack_name = parsed_spec["stack"]
     deployment_type = parsed_spec[constants.deploy_to_key]
-    stack_file = get_stack_file_path(stack_name)
+    stack_file = get_stack_path(stack_name).joinpath(constants.stack_file_name)
     parsed_stack = get_parsed_stack_config(stack_name)
     if opts.o.debug:
         print(f"parsed spec: {parsed_spec}")
@@ -466,7 +472,7 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
     os.mkdir(deployment_dir_path)
     # Copy spec file and the stack file into the deployment dir
     copyfile(spec_file, deployment_dir_path.joinpath(constants.spec_file_name))
-    copyfile(stack_file, deployment_dir_path.joinpath(os.path.basename(stack_file)))
+    copyfile(stack_file, deployment_dir_path.joinpath(constants.stack_file_name))
     _create_deployment_file(deployment_dir_path)
     # Copy any config varibles from the spec file into an env file suitable for compose
     _write_config_file(spec_file, deployment_dir_path.joinpath(constants.config_file_name))
@@ -480,10 +486,9 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
     os.mkdir(destination_compose_dir)
     destination_pods_dir = deployment_dir_path.joinpath("pods")
     os.mkdir(destination_pods_dir)
-    data_dir = Path(__file__).absolute().parent.parent.joinpath("data")
     yaml = get_yaml()
     for pod in pods:
-        pod_file_path = get_pod_file_path(parsed_stack, pod)
+        pod_file_path = get_pod_file_path(stack_name, parsed_stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         extra_config_dirs = _find_extra_config_dirs(parsed_pod_file, pod)
         destination_pod_dir = destination_pods_dir.joinpath(pod)
@@ -497,7 +502,7 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
         config_dirs = {pod}
         config_dirs = config_dirs.union(extra_config_dirs)
         for config_dir in config_dirs:
-            source_config_dir = data_dir.joinpath("config", config_dir)
+            source_config_dir = resolve_config_dir(stack_name, config_dir)
             if os.path.exists(source_config_dir):
                 destination_config_dir = deployment_dir_path.joinpath("config", config_dir)
                 # If the same config dir appears in multiple pods, it may already have been copied

stack_orchestrator/deploy/images.py

@@ -29,16 +29,29 @@ def _image_needs_pushed(image: str):
     return image.endswith(":local")
 
 
+def _remote_tag_for_image(image: str, remote_repo_url: str):
+    # Turns image tags of the form: foo/bar:local into remote.repo/org/bar:deploy
+    major_parts = image.split("/", 2)
+    image_name_with_version = major_parts[1] if 2 == len(major_parts) else major_parts[0]
+    (image_name, image_version) = image_name_with_version.split(":")
+    if image_version == "local":
+        return f"{remote_repo_url}/{image_name}:deploy"
+    else:
+        return image
+
+
+# Note: do not add any calls this function
 def remote_image_exists(remote_repo_url: str, local_tag: str):
     docker = DockerClient()
     try:
-        remote_tag = remote_tag_for_image(local_tag, remote_repo_url)
+        remote_tag = _remote_tag_for_image(local_tag, remote_repo_url)
         result = docker.manifest.inspect(remote_tag)
         return True if result else False
     except Exception:  # noqa: E722
         return False
 
 
+# Note: do not add any calls this function
 def add_tags_to_image(remote_repo_url: str, local_tag: str, *additional_tags):
     if not additional_tags:
         return
@@ -47,18 +60,20 @@ def add_tags_to_image(remote_repo_url: str, local_tag: str, *additional_tags):
         raise Exception(f"{local_tag} does not exist in {remote_repo_url}")
 
     docker = DockerClient()
-    remote_tag = remote_tag_for_image(local_tag, remote_repo_url)
-    new_remote_tags = [remote_tag_for_image(tag, remote_repo_url) for tag in additional_tags]
+    remote_tag = _remote_tag_for_image(local_tag, remote_repo_url)
+    new_remote_tags = [_remote_tag_for_image(tag, remote_repo_url) for tag in additional_tags]
     docker.buildx.imagetools.create(sources=[remote_tag], tags=new_remote_tags)
 
 
-def remote_tag_for_image(image: str, remote_repo_url: str):
+def remote_tag_for_image_unique(image: str, remote_repo_url: str, deployment_id: str):
     # Turns image tags of the form: foo/bar:local into remote.repo/org/bar:deploy
     major_parts = image.split("/", 2)
     image_name_with_version = major_parts[1] if 2 == len(major_parts) else major_parts[0]
     (image_name, image_version) = image_name_with_version.split(":")
     if image_version == "local":
-        return f"{remote_repo_url}/{image_name}:deploy"
+        # Salt the tag with part of the deployment id to make it unique to this deployment
+        deployment_tag = deployment_id[-8:]
+        return f"{remote_repo_url}/{image_name}:deploy-{deployment_tag}"
     else:
         return image
 
@@ -73,14 +88,14 @@ def push_images_operation(command_context: DeployCommandContext, deployment_cont
     docker = DockerClient()
     for image in images:
         if _image_needs_pushed(image):
-            remote_tag = remote_tag_for_image(image, remote_repo_url)
+            remote_tag = remote_tag_for_image_unique(image, remote_repo_url, deployment_context.id)
             if opts.o.verbose:
                 print(f"Tagging {image} to {remote_tag}")
             docker.image.tag(image, remote_tag)
     # Run docker push commands to upload
     for image in images:
         if _image_needs_pushed(image):
-            remote_tag = remote_tag_for_image(image, remote_repo_url)
+            remote_tag = remote_tag_for_image_unique(image, remote_repo_url, deployment_context.id)
             if opts.o.verbose:
                 print(f"Pushing image {remote_tag}")
             docker.image.push(remote_tag)

stack_orchestrator/deploy/k8s/cluster_info.py

@@ -26,7 +26,7 @@ from stack_orchestrator.deploy.k8s.helpers import envs_from_environment_variable
 from stack_orchestrator.deploy.deploy_util import parsed_pod_files_map_from_file_names, images_for_deployment
 from stack_orchestrator.deploy.deploy_types import DeployEnvVars
 from stack_orchestrator.deploy.spec import Spec, Resources, ResourceLimits
-from stack_orchestrator.deploy.images import remote_tag_for_image
+from stack_orchestrator.deploy.images import remote_tag_for_image_unique
 
 DEFAULT_VOLUME_RESOURCES = Resources({
     "reservations": {"storage": "2Gi"}
@@ -326,8 +326,11 @@ class ClusterInfo:
                 if opts.o.debug:
                     print(f"Merged envs: {envs}")
                 # Re-write the image tag for remote deployment
-                image_to_use = remote_tag_for_image(
-                    image, self.spec.get_image_registry()) if self.spec.get_image_registry() is not None else image
+                # Note self.app_name has the same value as deployment_id
+                image_to_use = remote_tag_for_image_unique(
+                    image,
+                    self.spec.get_image_registry(),
+                    self.app_name) if self.spec.get_image_registry() is not None else image
                 volume_mounts = volume_mounts_for_service(self.parsed_pod_yaml_map, service_name)
                 container = client.V1Container(
                     name=container_name,

stack_orchestrator/deploy/webapp/deploy_webapp_from_registry.py

@@ -24,7 +24,7 @@ import uuid
 
 import click
 
-from stack_orchestrator.deploy.images import remote_image_exists, add_tags_to_image
+from stack_orchestrator.deploy.images import remote_image_exists
 from stack_orchestrator.deploy.webapp import deploy_webapp
 from stack_orchestrator.deploy.webapp.util import (LaconicRegistryClient, TimedLogger,
                                                    build_container_image, push_container_image,
@@ -39,11 +39,12 @@ def process_app_deployment_request(
     app_deployment_request,
     deployment_record_namespace,
     dns_record_namespace,
-    dns_suffix,
+    default_dns_suffix,
     deployment_parent_dir,
     kube_config,
     image_registry,
     force_rebuild,
+    fqdn_policy,
     logger
 ):
     logger.log("BEGIN - process_app_deployment_request")
@@ -56,14 +57,15 @@ def process_app_deployment_request(
     requested_name = hostname_for_deployment_request(app_deployment_request, laconic)
     logger.log(f"Determined requested name: {requested_name}")
 
-    # HACK
     if "." in requested_name:
-        raise Exception("Only unqualified hostnames allowed at this time.")
-
-    fqdn = f"{requested_name}.{dns_suffix}"
+        if "allow" == fqdn_policy or "preexisting" == fqdn_policy:
+            fqdn = requested_name
+        else:
+            raise Exception(f"{requested_name} is invalid: only unqualified hostnames are allowed.")
+    else:
+        fqdn = f"{requested_name}.{default_dns_suffix}"
 
     # 3. check ownership of existing dnsrecord vs this request
-    # TODO: Support foreign DNS
     dns_crn = f"{dns_record_namespace}/{fqdn}"
     dns_record = laconic.get_record(dns_crn)
     if dns_record:
@@ -75,7 +77,9 @@ def process_app_deployment_request(
             logger.log(f"Matched DnsRecord ownership: {matched_owner}")
         else:
             raise Exception("Unable to confirm ownership of DnsRecord %s for request %s" %
-                            (dns_record.id, app_deployment_request.id))
+                            (dns_crn, app_deployment_request.id))
+    elif "preexisting" == fqdn_policy:
+        raise Exception(f"No pre-existing DnsRecord {dns_crn} could be found for request {app_deployment_request.id}.")
 
     # 4. get build and runtime config from request
     env_filename = None
@@ -95,44 +99,62 @@ def process_app_deployment_request(
 
     deployment_record = laconic.get_record(app_deployment_crn)
     deployment_dir = os.path.join(deployment_parent_dir, fqdn)
+    # At present we use this to generate a unique but stable ID for the app's host container
+    # TODO: implement support to derive this transparently from the already-unique deployment id
+    unique_deployment_id = hashlib.md5(fqdn.encode()).hexdigest()[:16]
     deployment_config_file = os.path.join(deployment_dir, "config.env")
-    # TODO: Is there any reason not to simplify the hash input to the app_deployment_crn?
-    deployment_container_tag = "laconic-webapp/%s:local" % hashlib.md5(deployment_dir.encode()).hexdigest()
+    deployment_container_tag = "laconic-webapp/%s:local" % unique_deployment_id
     app_image_shared_tag = f"laconic-webapp/{app.id}:local"
     #   b. check for deployment directory (create if necessary)
     if not os.path.exists(deployment_dir):
         if deployment_record:
             raise Exception("Deployment record %s exists, but not deployment dir %s. Please remove name." %
                             (app_deployment_crn, deployment_dir))
-        print("deploy_webapp", deployment_dir)
+        logger.log(f"Creating webapp deployment in: {deployment_dir} with container id: {deployment_container_tag}")
         deploy_webapp.create_deployment(ctx, deployment_dir, deployment_container_tag,
                                         f"https://{fqdn}", kube_config, image_registry, env_filename)
     elif env_filename:
         shutil.copyfile(env_filename, deployment_config_file)
 
     needs_k8s_deploy = False
+    if force_rebuild:
+        logger.log("--force-rebuild is enabled so the container will always be built now, even if nothing has changed in the app")
     # 6. build container (if needed)
-    if not deployment_record or deployment_record.attributes.application != app.id:
+    # TODO: add a comment that explains what this code is doing (not clear to me)
+    if not deployment_record or deployment_record.attributes.application != app.id or force_rebuild:
         needs_k8s_deploy = True
         # check if the image already exists
         shared_tag_exists = remote_image_exists(image_registry, app_image_shared_tag)
+        # Note: in the code below, calls to add_tags_to_image() won't work at present.
+        # This is because SO deployment code in general re-names the container image
+        # to be unique to the deployment. This is done transparently
+        # and so when we call add_tags_to_image() here and try to add tags to the remote image,
+        # we get the image name wrong. Accordingly I've disabled the relevant code for now.
+        # This is safe because we are running with --force-rebuild at present
         if shared_tag_exists and not force_rebuild:
             # simply add our unique tag to the existing image and we are done
-            logger.log(f"Using existing app image {app_image_shared_tag} for {deployment_container_tag}")
-            add_tags_to_image(image_registry, app_image_shared_tag, deployment_container_tag)
+            logger.log(
+                f"(SKIPPED) Existing image found for this app: {app_image_shared_tag} "
+                "tagging it with: {deployment_container_tag} to use in this deployment"
+                )
+            # add_tags_to_image(image_registry, app_image_shared_tag, deployment_container_tag)
             logger.log("Tag complete")
         else:
             extra_build_args = []  # TODO: pull from request
-            logger.log(f"Building container image {deployment_container_tag}")
+            logger.log(f"Building container image: {deployment_container_tag}")
             build_container_image(app, deployment_container_tag, extra_build_args, logger)
             logger.log("Build complete")
-            logger.log(f"Pushing container image {deployment_container_tag}")
+            logger.log(f"Pushing container image: {deployment_container_tag}")
             push_container_image(deployment_dir, logger)
             logger.log("Push complete")
             # The build/push commands above will use the unique deployment tag, so now we need to add the shared tag.
-            logger.log(f"Updating app image tag {app_image_shared_tag} from build of {deployment_container_tag}")
-            add_tags_to_image(image_registry, deployment_container_tag, app_image_shared_tag)
+            logger.log(
+                f"(SKIPPED) Adding global app image tag: {app_image_shared_tag} to newly built image: {deployment_container_tag}"
+                )
+            # add_tags_to_image(image_registry, deployment_container_tag, app_image_shared_tag)
             logger.log("Tag complete")
+    else:
+        logger.log("Requested app is already deployed, skipping build and image push")
 
     # 7. update config (if needed)
     if not deployment_record or file_hash(deployment_config_file) != deployment_record.attributes.meta.config:
@@ -191,6 +213,7 @@ def dump_known_requests(filename, requests, status="SEEN"):
 @click.option("--state-file", help="File to store state about previously seen requests.")
 @click.option("--only-update-state", help="Only update the state file, don't process any requests anything.", is_flag=True)
 @click.option("--dns-suffix", help="DNS domain to use eg, laconic.servesthe.world")
+@click.option("--fqdn-policy", help="How to handle requests with an FQDN: prohibit, allow, preexisting", default="prohibit")
 @click.option("--record-namespace-dns", help="eg, crn://laconic/dns")
 @click.option("--record-namespace-deployments", help="eg, crn://laconic/deployments")
 @click.option("--dry-run", help="Don't do anything, just report what would be done.", is_flag=True)
@@ -201,7 +224,7 @@ def dump_known_requests(filename, requests, status="SEEN"):
 @click.pass_context
 def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_dir,  # noqa: C901
             request_id, discover, state_file, only_update_state,
-            dns_suffix, record_namespace_dns, record_namespace_deployments, dry_run,
+            dns_suffix, fqdn_policy, record_namespace_dns, record_namespace_deployments, dry_run,
             include_tags, exclude_tags, force_rebuild, log_dir):
     if request_id and discover:
         print("Cannot specify both --request-id and --discover", file=sys.stderr)
@@ -220,6 +243,10 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
             print("--dns-suffix, --record-namespace-dns, and --record-namespace-deployments are all required", file=sys.stderr)
             sys.exit(2)
 
+    if fqdn_policy not in ["prohibit", "allow", "preexisting"]:
+        print("--fqdn-policy must be one of 'prohibit', 'allow', or 'preexisting'", file=sys.stderr)
+        sys.exit(2)
+
     # Split CSV and clean up values.
     include_tags = [tag.strip() for tag in include_tags.split(",") if tag]
     exclude_tags = [tag.strip() for tag in exclude_tags.split(",") if tag]
@@ -247,7 +274,10 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
     requests_by_name = {}
     skipped_by_name = {}
     for r in requests:
-        # TODO: Do this _after_ filtering deployments and cancellations to minimize round trips.
+        if r.id in previous_requests and previous_requests[r.id].get("status", "") != "RETRY":
+            print(f"Skipping request {r.id}, we've already seen it.")
+            continue
+
         app = laconic.get_record(r.attributes.application)
         if not app:
             print("Skipping request %s, cannot locate app." % r.id)
@@ -334,6 +364,7 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
                     kube_config,
                     image_registry,
                     force_rebuild,
+                    fqdn_policy,
                     logger
                 )
                 status = "DEPLOYED"

stack_orchestrator/deploy/webapp/util.py

@@ -242,6 +242,7 @@ def determine_base_container(clone_dir, app_type="webapp"):
 def build_container_image(app_record, tag, extra_build_args=[], logger=None):
     tmpdir = tempfile.mkdtemp()
 
+    # TODO: determine if this code could be calling into the Python git library like setup-repositories
     try:
         record_id = app_record["id"]
         ref = app_record.attributes.repository_ref
@@ -249,6 +250,16 @@ def build_container_image(app_record, tag, extra_build_args=[], logger=None):
         clone_dir = os.path.join(tmpdir, record_id)
 
         logger.log(f"Cloning repository {repo} to {clone_dir} ...")
+        # Set github credentials if present running a command like:
+        # git config --global url."https://${TOKEN}:@github.com/".insteadOf "https://github.com/"
+        github_token = os.environ.get("DEPLOYER_GITHUB_TOKEN")
+        if github_token:
+            logger.log("Github token detected, setting it in the git environment")
+            git_config_args = [
+                "git", "config", "--global", f"url.https://{github_token}:@github.com/.insteadOf", "https://github.com/"
+                ]
+            result = subprocess.run(git_config_args, stdout=logger.file, stderr=logger.file)
+            result.check_returncode()
         if ref:
             # TODO: Determing branch or hash, and use depth 1 if we can.
             git_env = dict(os.environ.copy())
@@ -265,6 +276,7 @@ def build_container_image(app_record, tag, extra_build_args=[], logger=None):
                 logger.log(f"git checkout failed.  Does ref {ref} exist?")
                 raise e
         else:
+            # TODO: why is this code different vs the branch above (run vs check_call, and no prompt disable)?
             result = subprocess.run(["git", "clone", "--depth", "1", repo, clone_dir], stdout=logger.file, stderr=logger.file)
             result.check_returncode()
 
@@ -299,11 +311,12 @@ def push_container_image(deployment_dir, logger):
 
 def deploy_to_k8s(deploy_record, deployment_dir, logger):
     if not deploy_record:
-        command = "up"
+        command = "start"
     else:
         command = "update"
 
     logger.log("Deploying to k8s ...")
+    logger.log(f"Running {command} command on deployment dir: {deployment_dir}")
     result = subprocess.run([sys.argv[0], "deployment", "--dir", deployment_dir, command],
                             stdout=logger.file, stderr=logger.file)
     result.check_returncode()

stack_orchestrator/main.py

@@ -17,6 +17,7 @@ import click
 
 from stack_orchestrator.command_types import CommandOptions
 from stack_orchestrator.repos import setup_repositories
+from stack_orchestrator.repos import fetch_stack
 from stack_orchestrator.build import build_containers, fetch_containers
 from stack_orchestrator.build import build_npms
 from stack_orchestrator.build import build_webapp
@@ -50,6 +51,7 @@ def cli(ctx, stack, quiet, verbose, dry_run, local_stack, debug, continue_on_err
     ctx.obj = command_options
 
 
+cli.add_command(fetch_stack.command, "fetch-stack")
 cli.add_command(setup_repositories.command, "setup-repositories")
 cli.add_command(build_containers.command, "build-containers")
 cli.add_command(fetch_containers.command, "fetch-containers")

stack_orchestrator/repos/fetch_stack.py

@@ -0,0 +1,45 @@
+# Copyright © 2022, 2023 Vulcanize
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http:#www.gnu.org/licenses/>.
+
+# env vars:
+# CERC_REPO_BASE_DIR defaults to ~/cerc
+
+
+import click
+import os
+
+from decouple import config
+from git import exc
+
+from stack_orchestrator.opts import opts
+from stack_orchestrator.repos.setup_repositories import process_repo
+from stack_orchestrator.util import error_exit
+
+
+@click.command()
+@click.argument('stack-locator')
+@click.option('--git-ssh', is_flag=True, default=False)
+@click.option('--check-only', is_flag=True, default=False)
+@click.option('--pull', is_flag=True, default=False)
+@click.pass_context
+def command(ctx, stack_locator, git_ssh, check_only, pull):
+    '''optionally resolve then git clone a repository containing one or more stack definitions'''
+    dev_root_path = os.path.expanduser(config("CERC_REPO_BASE_DIR", default="~/cerc"))
+    if not opts.o.quiet:
+        print(f"Dev Root is: {dev_root_path}")
+    try:
+        process_repo(pull, check_only, git_ssh, dev_root_path, None, stack_locator)
+    except exc.GitCommandError as error:
+        error_exit(f"\n******* git command returned error exit status:\n{error}")

stack_orchestrator/repos/setup_repositories.py

@@ -20,13 +20,12 @@ import os
 import sys
 from decouple import config
 import git
+from git.exc import GitCommandError
 from tqdm import tqdm
 import click
 import importlib.resources
-from pathlib import Path
-import yaml
-from stack_orchestrator.constants import stack_file_name
-from stack_orchestrator.util import include_exclude_check, stack_is_external, error_exit, warn_exit
+from stack_orchestrator.opts import opts
+from stack_orchestrator.util import get_parsed_stack_config, include_exclude_check, error_exit, warn_exit
 
 
 class GitProgress(git.RemoteProgress):
@@ -80,15 +79,19 @@ def _get_repo_current_branch_or_tag(full_filesystem_repo_path):
     except TypeError:
         # This means that the current ref is not a branch, so possibly a tag
         # Let's try to get the tag
-        current_repo_branch_or_tag = git.Repo(full_filesystem_repo_path).git.describe("--tags", "--exact-match")
-        # Note that git is assymetric -- the tag you told it to check out may not be the one
-        # you get back here (if there are multiple tags associated with the same commit)
+        try:
+            current_repo_branch_or_tag = git.Repo(full_filesystem_repo_path).git.describe("--tags", "--exact-match")
+            # Note that git is asymmetric -- the tag you told it to check out may not be the one
+            # you get back here (if there are multiple tags associated with the same commit)
+        except GitCommandError:
+            # If there is no matching branch or tag checked out, just use the current SHA
+            current_repo_branch_or_tag = git.Repo(full_filesystem_repo_path).commit("HEAD").hexsha
     return current_repo_branch_or_tag, is_branch
 
 
 # TODO: fix the messy arg list here
-def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_path, branches_array, fully_qualified_repo):
-    if verbose:
+def process_repo(pull, check_only, git_ssh, dev_root_path, branches_array, fully_qualified_repo):
+    if opts.o.verbose:
         print(f"Processing repo: {fully_qualified_repo}")
     repo_host, repo_path, repo_branch = host_and_path_for_repo(fully_qualified_repo)
     git_ssh_prefix = f"git@{repo_host}:"
@@ -100,8 +103,8 @@ def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_pa
     (current_repo_branch_or_tag, is_branch) = _get_repo_current_branch_or_tag(
         full_filesystem_repo_path
         ) if is_present else (None, None)
-    if not quiet:
-        present_text = f"already exists active {'branch' if is_branch else 'tag'}: {current_repo_branch_or_tag}" if is_present \
+    if not opts.o.quiet:
+        present_text = f"already exists active {'branch' if is_branch else 'ref'}: {current_repo_branch_or_tag}" if is_present \
             else 'Needs to be fetched'
         print(f"Checking: {full_filesystem_repo_path}: {present_text}")
     # Quick check that it's actually a repo
@@ -111,25 +114,25 @@ def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_pa
             sys.exit(1)
         else:
             if pull:
-                if verbose:
+                if opts.o.verbose:
                     print(f"Running git pull for {full_filesystem_repo_path}")
                 if not check_only:
                     if is_branch:
                         git_repo = git.Repo(full_filesystem_repo_path)
                         origin = git_repo.remotes.origin
-                        origin.pull(progress=None if quiet else GitProgress())
+                        origin.pull(progress=None if opts.o.quiet else GitProgress())
                     else:
-                        print("skipping pull because this repo checked out a tag")
+                        print("skipping pull because this repo is not on a branch")
                 else:
                     print("(git pull skipped)")
     if not is_present:
         # Clone
-        if verbose:
+        if opts.o.verbose:
             print(f'Running git clone for {full_github_repo_path} into {full_filesystem_repo_path}')
-        if not dry_run:
+        if not opts.o.dry_run:
             git.Repo.clone_from(full_github_repo_path,
                                 full_filesystem_repo_path,
-                                progress=None if quiet else GitProgress())
+                                progress=None if opts.o.quiet else GitProgress())
         else:
             print("(git clone skipped)")
     # Checkout the requested branch, if one was specified
@@ -150,13 +153,13 @@ def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_pa
             current_repo_branch_or_tag and (
                 current_repo_branch_or_tag != branch_to_checkout)
                 ):
-            if not quiet:
+            if not opts.o.quiet:
                 print(f"switching to branch {branch_to_checkout} in repo {repo_path}")
             git_repo = git.Repo(full_filesystem_repo_path)
             # git checkout works for both branches and tags
             git_repo.git.checkout(branch_to_checkout)
         else:
-            if verbose:
+            if opts.o.verbose:
                 print(f"repo {repo_path} is already on branch/tag {branch_to_checkout}")
 
 
@@ -182,36 +185,18 @@ def parse_branches(branches_string):
 @click.option('--check-only', is_flag=True, default=False)
 @click.option('--pull', is_flag=True, default=False)
 @click.option("--branches", help="override branches for repositories")
-@click.option('--branches-file', help="checkout branches specified in this file")
 @click.pass_context
-def command(ctx, include, exclude, git_ssh, check_only, pull, branches, branches_file):
+def command(ctx, include, exclude, git_ssh, check_only, pull, branches):
     '''git clone the set of repositories required to build the complete system from source'''
 
-    quiet = ctx.obj.quiet
-    verbose = ctx.obj.verbose
-    dry_run = ctx.obj.dry_run
-    stack = ctx.obj.stack
+    quiet = opts.o.quiet
+    verbose = opts.o.verbose
+    stack = opts.o.stack
 
     branches_array = []
 
-    # TODO: branches file needs to be re-worked in the context of stacks
-    if branches_file:
-        if branches:
-            print("Error: can't specify both --branches and --branches-file")
-            sys.exit(1)
-        else:
-            if verbose:
-                print(f"loading branches from: {branches_file}")
-            with open(branches_file) as branches_file_open:
-                branches_array = branches_file_open.read().splitlines()
-
-    print(f"branches: {branches}")
     if branches:
-        if branches_file:
-            print("Error: can't specify both --branches and --branches-file")
-            sys.exit(1)
-        else:
-            branches_array = parse_branches(branches)
+        branches_array = parse_branches(branches)
 
     if branches_array and verbose:
         print(f"Branches are: {branches_array}")
@@ -239,20 +224,10 @@ def command(ctx, include, exclude, git_ssh, check_only, pull, branches, branches
 
     repos_in_scope = []
     if stack:
-        if stack_is_external(stack):
-            stack_file_path = Path(stack).joinpath(stack_file_name)
-        else:
-            # In order to be compatible with Python 3.8 we need to use this hack to get the path:
-            # See: https://stackoverflow.com/questions/25389095/python-get-path-of-root-project-structure
-            stack_file_path = Path(__file__).absolute().parent.parent.joinpath("data", "stacks", stack, stack_file_name)
-        if not stack_file_path.exists():
-            error_exit(f"stack {stack} does not exist")
-        with stack_file_path:
-            stack_config = yaml.safe_load(open(stack_file_path, "r"))
-            if "repos" not in stack_config or stack_config["repos"] is None:
-                warn_exit(f"stack {stack} does not define any repositories")
-            else:
-                repos_in_scope = stack_config["repos"]
+        stack_config = get_parsed_stack_config(stack)
+        if "repos" not in stack_config or stack_config["repos"] is None:
+            warn_exit(f"stack {stack} does not define any repositories")
+        repos_in_scope = stack_config["repos"]
     else:
         repos_in_scope = all_repos
 
@@ -271,7 +246,6 @@ def command(ctx, include, exclude, git_ssh, check_only, pull, branches, branches
 
     for repo in repos:
         try:
-            process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_path, branches_array, repo)
+            process_repo(pull, check_only, git_ssh, dev_root_path, branches_array, repo)
         except git.exc.GitCommandError as error:
-            print(f"\n******* git command returned error exit status:\n{error}")
-            sys.exit(1)
+            error_exit(f"\n******* git command returned error exit status:\n{error}")

stack_orchestrator/util.py

@@ -20,6 +20,7 @@ import ruamel.yaml
 from pathlib import Path
 from dotenv import dotenv_values
 from typing import Mapping, Set, List
+from stack_orchestrator.constants import stack_file_name, deployment_file_name
 
 
 def include_exclude_check(s, include, exclude):
@@ -33,11 +34,14 @@ def include_exclude_check(s, include, exclude):
         return s not in exclude_list
 
 
-def get_stack_file_path(stack):
-    # In order to be compatible with Python 3.8 we need to use this hack to get the path:
-    # See: https://stackoverflow.com/questions/25389095/python-get-path-of-root-project-structure
-    stack_file_path = Path(__file__).absolute().parent.joinpath("data", "stacks", stack, "stack.yml")
-    return stack_file_path
+def get_stack_path(stack):
+    if stack_is_external(stack):
+        stack_path = Path(stack)
+    else:
+        # In order to be compatible with Python 3.8 we need to use this hack to get the path:
+        # See: https://stackoverflow.com/questions/25389095/python-get-path-of-root-project-structure
+        stack_path = Path(__file__).absolute().parent.joinpath("data", "stacks", stack)
+    return stack_path
 
 
 def get_dev_root_path(ctx):
@@ -52,21 +56,14 @@ def get_dev_root_path(ctx):
 
 # Caller can pass either the name of a stack, or a path to a stack file
 def get_parsed_stack_config(stack):
-    stack_file_path = stack if isinstance(stack, os.PathLike) else get_stack_file_path(stack)
-    try:
-        with stack_file_path:
-            stack_config = get_yaml().load(open(stack_file_path, "r"))
-            return stack_config
-    except FileNotFoundError as error:
-        # We try here to generate a useful diagnostic error
-        # First check if the stack directory is present
-        stack_directory = stack_file_path.parent
-        if os.path.exists(stack_directory):
-            print(f"Error: stack.yml file is missing from stack: {stack}")
-        else:
-            print(f"Error: stack: {stack} does not exist")
-        print(f"Exiting, error: {error}")
-        sys.exit(1)
+    stack_file_path = get_stack_path(stack).joinpath(stack_file_name)
+    if stack_file_path.exists():
+        return get_yaml().load(open(stack_file_path, "r"))
+    # We try here to generate a useful diagnostic error
+    # First check if the stack directory is present
+    if stack_file_path.parent.exists():
+        error_exit(f"stack.yml file is missing from stack: {stack}")
+    error_exit(f"stack {stack} does not exist")
 
 
 def get_pod_list(parsed_stack):
@@ -87,17 +84,45 @@ def get_plugin_code_paths(stack) -> List[Path]:
     result: Set[Path] = set()
     for pod in pods:
         if type(pod) is str:
-            result.add(get_stack_file_path(stack).parent)
+            result.add(get_stack_path(stack))
         else:
             pod_root_dir = os.path.join(get_dev_root_path(None), pod["repository"].split("/")[-1], pod["path"])
             result.add(Path(os.path.join(pod_root_dir, "stack")))
     return list(result)
 
 
-def get_pod_file_path(parsed_stack, pod_name: str):
+# # Find a config directory, looking first in any external stack
+# and if not found there, internally
+def resolve_config_dir(stack, config_dir_name: str):
+    if stack_is_external(stack):
+        # First try looking in the external stack for the compose file
+        config_base = Path(stack).parent.parent.joinpath("config")
+        proposed_dir = config_base.joinpath(config_dir_name)
+        if proposed_dir.exists():
+            return proposed_dir
+        # If we don't find it fall through to the internal case
+    config_base = get_internal_config_dir()
+    return config_base.joinpath(config_dir_name)
+
+
+# Find a compose file, looking first in any external stack
+# and if not found there, internally
+def resolve_compose_file(stack, pod_name: str):
+    if stack_is_external(stack):
+        # First try looking in the external stack for the compose file
+        compose_base = Path(stack).parent.parent.joinpath("compose")
+        proposed_file = compose_base.joinpath(f"docker-compose-{pod_name}.yml")
+        if proposed_file.exists():
+            return proposed_file
+        # If we don't find it fall through to the internal case
+    compose_base = get_internal_compose_file_dir()
+    return compose_base.joinpath(f"docker-compose-{pod_name}.yml")
+
+
+def get_pod_file_path(stack, parsed_stack, pod_name: str):
     pods = parsed_stack["pods"]
     if type(pods[0]) is str:
-        result = os.path.join(get_compose_file_dir(), f"docker-compose-{pod_name}.yml")
+        result = resolve_compose_file(stack, pod_name)
     else:
         for pod in pods:
             if pod["name"] == pod_name:
@@ -131,7 +156,7 @@ def pod_has_scripts(parsed_stack, pod_name: str):
     return result
 
 
-def get_compose_file_dir():
+def get_internal_compose_file_dir():
     # TODO: refactor to use common code with deploy command
     # See: https://stackoverflow.com/questions/25389095/python-get-path-of-root-project-structure
     data_dir = Path(__file__).absolute().parent.joinpath("data")
@@ -139,7 +164,7 @@ def get_compose_file_dir():
     return source_compose_dir
 
 
-def get_config_file_dir():
+def get_internal_config_dir():
     # TODO: refactor to use common code with deploy command
     data_dir = Path(__file__).absolute().parent.joinpath("data")
     source_config_dir = data_dir.joinpath("config")
@@ -171,6 +196,10 @@ def stack_is_external(stack: str):
     return Path(stack).exists() if stack is not None else False
 
 
+def stack_is_in_deployment(stack: Path):
+    return stack.joinpath(deployment_file_name).exists()
+
+
 def get_yaml():
     # See: https://stackoverflow.com/a/45701840/1701505
     yaml = ruamel.yaml.YAML()

stack_orchestrator/version.py

@@ -14,7 +14,7 @@
 # along with this program.  If not, see <http:#www.gnu.org/licenses/>.
 
 import click
-import importlib.resources
+from importlib import resources, metadata
 
 
 @click.command()
@@ -24,8 +24,11 @@ def command(ctx):
 
     # See: https://stackoverflow.com/a/20885799/1701505
     from stack_orchestrator import data
-    with importlib.resources.open_text(data, "build_tag.txt") as version_file:
-        # TODO: code better version that skips comment lines
-        version_string = version_file.read().splitlines()[1]
+    if resources.is_resource(data, "build_tag.txt"):
+        with resources.open_text(data, "build_tag.txt") as version_file:
+            # TODO: code better version that skips comment lines
+            version_string = version_file.read().splitlines()[1]
+    else:
+        version_string = metadata.version("laconic-stack-orchestrator") + "-unknown"
 
-    print(f"Version: {version_string}")
+    print(version_string)

tests/external-stack/run-test.sh

@@ -0,0 +1,185 @@
+#!/usr/bin/env bash
+set -e
+if [ -n "$CERC_SCRIPT_DEBUG" ]; then
+  set -x
+fi
+# Dump environment variables for debugging
+echo "Environment variables:"
+env
+
+if [ "$1" == "from-path" ]; then
+    TEST_TARGET_SO="laconic-so"
+else
+    TEST_TARGET_SO=$( ls -t1 ./package/laconic-so* | head -1 )
+fi
+
+delete_cluster_exit () {
+    $TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes
+    exit 1
+}
+
+# Test basic stack-orchestrator deploy
+echo "Running stack-orchestrator external stack deploy test"
+# Set a non-default repo dir
+export CERC_REPO_BASE_DIR=~/stack-orchestrator-test/repo-base-dir
+echo "Testing this package: $TEST_TARGET_SO"
+echo "Test version command"
+reported_version_string=$( $TEST_TARGET_SO version )
+echo "Version reported is: ${reported_version_string}"
+echo "Cloning repositories into: $CERC_REPO_BASE_DIR"
+rm -rf $CERC_REPO_BASE_DIR
+mkdir -p $CERC_REPO_BASE_DIR
+# Clone the external test stack
+$TEST_TARGET_SO fetch-stack git.vdb.to/cerc-io/test-external-stack
+stack_name="$CERC_REPO_BASE_DIR/test-external-stack/stack-orchestrator/stacks/test-external-stack"
+TEST_TARGET_SO_STACK="$TEST_TARGET_SO --stack ${stack_name}"
+# Test bringing the test container up and down
+# with and without volume removal
+$TEST_TARGET_SO_STACK setup-repositories
+$TEST_TARGET_SO_STACK build-containers
+# Test deploy command execution
+$TEST_TARGET_SO_STACK deploy setup $CERC_REPO_BASE_DIR
+# Check that we now have the expected output directory
+container_output_dir=$CERC_REPO_BASE_DIR/container-output-dir
+if [ ! -d "$container_output_dir" ]; then
+    echo "deploy setup test: output directory not present"
+    echo "deploy setup test: FAILED"
+    exit 1
+fi
+if [ ! -f "$container_output_dir/output-file" ]; then
+    echo "deploy setup test: output file not present"
+    echo "deploy setup test: FAILED"
+    exit 1
+fi
+output_file_content=$(<$container_output_dir/output-file)
+if [ ! "$output_file_content" == "output-data"  ]; then
+    echo "deploy setup test: output file contents not correct"
+    echo "deploy setup test: FAILED"
+    exit 1
+fi
+# Check that we now have the expected output file
+$TEST_TARGET_SO_STACK deploy up
+# Test deploy port command
+deploy_port_output=$( $TEST_TARGET_SO_STACK deploy port test 80 )
+if [[ "$deploy_port_output" =~ ^0.0.0.0:[1-9][0-9]* ]]; then
+    echo "Deploy port test: passed"
+else
+    echo "Deploy port test: FAILED"
+    exit 1
+fi
+$TEST_TARGET_SO_STACK deploy down
+# The next time we bring the container up the volume will be old (from the previous run above)
+$TEST_TARGET_SO_STACK deploy up
+log_output_1=$( $TEST_TARGET_SO_STACK deploy logs )
+if [[ "$log_output_1" == *"filesystem is old"* ]]; then
+    echo "Retain volumes test: passed"
+else
+    echo "Retain volumes test: FAILED"
+    exit 1
+fi
+$TEST_TARGET_SO_STACK deploy down --delete-volumes
+# Now when we bring the container up the volume will be new again
+$TEST_TARGET_SO_STACK deploy up
+log_output_2=$( $TEST_TARGET_SO_STACK deploy logs )
+if [[ "$log_output_2" == *"filesystem is fresh"* ]]; then
+    echo "Delete volumes test: passed"
+else
+    echo "Delete volumes test: FAILED"
+    exit 1
+fi
+$TEST_TARGET_SO_STACK deploy down --delete-volumes
+# Basic test of creating a deployment
+test_deployment_dir=$CERC_REPO_BASE_DIR/test-deployment-dir
+test_deployment_spec=$CERC_REPO_BASE_DIR/test-deployment-spec.yml
+$TEST_TARGET_SO_STACK deploy init --output $test_deployment_spec --config CERC_TEST_PARAM_1=PASSED,CERC_TEST_PARAM_3=FAST
+# Check the file now exists
+if [ ! -f "$test_deployment_spec" ]; then
+    echo "deploy init test: spec file not present"
+    echo "deploy init test: FAILED"
+    exit 1
+fi
+echo "deploy init test: passed"
+$TEST_TARGET_SO_STACK deploy create --spec-file $test_deployment_spec --deployment-dir $test_deployment_dir
+# Check the deployment dir exists
+if [ ! -d "$test_deployment_dir" ]; then
+    echo "deploy create test: deployment directory not present"
+    echo "deploy create test: FAILED"
+    exit 1
+fi
+echo "deploy create test: passed"
+# Check the file writted by the create command in the stack now exists
+if [ ! -f "$test_deployment_dir/create-file" ]; then
+    echo "deploy create test: create output file not present"
+    echo "deploy create test: FAILED"
+    exit 1
+fi
+# And has the right content
+create_file_content=$(<$test_deployment_dir/create-file)
+if [ ! "$create_file_content" == "create-command-output-data"  ]; then
+    echo "deploy create test: create output file contents not correct"
+    echo "deploy create test: FAILED"
+    exit 1
+fi
+
+# Add a config file to be picked up by the ConfigMap before starting.
+echo "dbfc7a4d-44a7-416d-b5f3-29842cc47650" > $test_deployment_dir/data/test-config/test_config
+
+echo "deploy create output file test: passed"
+# Try to start the deployment
+$TEST_TARGET_SO deployment --dir $test_deployment_dir start
+# Check logs command works
+log_output_3=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_3" == *"filesystem is fresh"* ]]; then
+    echo "deployment logs test: passed"
+else
+    echo "deployment logs test: FAILED"
+    exit 1
+fi
+# Check the config variable CERC_TEST_PARAM_1 was passed correctly
+if [[ "$log_output_3" == *"Test-param-1: PASSED"* ]]; then
+    echo "deployment config test: passed"
+else
+    echo "deployment config test: FAILED"
+    exit 1
+fi
+# Check the config variable CERC_TEST_PARAM_2 was passed correctly from the compose file
+if [[ "$log_output_3" == *"Test-param-2: CERC_TEST_PARAM_2_VALUE"* ]]; then
+    echo "deployment compose config test: passed"
+else
+    echo "deployment compose config test: FAILED"
+    exit 1
+fi
+# Check the config variable CERC_TEST_PARAM_3 was passed correctly
+if [[ "$log_output_3" == *"Test-param-3: FAST"* ]]; then
+    echo "deployment config test: passed"
+else
+    echo "deployment config test: FAILED"
+    exit 1
+fi
+
+# Check that the ConfigMap is mounted and contains the expected content.
+log_output_4=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_4" == *"/config/test_config:"* ]] && [[ "$log_output_4" == *"dbfc7a4d-44a7-416d-b5f3-29842cc47650"* ]]; then
+    echo "deployment ConfigMap test: passed"
+else
+    echo "deployment ConfigMap test: FAILED"
+    delete_cluster_exit
+fi
+
+# Stop then start again and check the volume was preserved
+$TEST_TARGET_SO deployment --dir $test_deployment_dir stop
+# Sleep a bit just in case
+# sleep for longer to check if that's why the subsequent create cluster fails
+sleep 20
+$TEST_TARGET_SO deployment --dir $test_deployment_dir start
+log_output_5=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_5" == *"filesystem is old"* ]]; then
+    echo "Retain volumes test: passed"
+else
+    echo "Retain volumes test: FAILED"
+    delete_cluster_exit
+fi
+
+# Stop and clean up
+$TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes
+echo "Test passed"

tests/fixturenet-laconicd/run-cli-test.sh

@@ -22,16 +22,16 @@ echo "$(date +"%Y-%m-%d %T"): Stack started"
 # Verify that the fixturenet is up and running
 $TEST_TARGET_SO --stack fixturenet-laconicd deploy --cluster laconicd ps
 
+# Wait for the laconid endpoint to come up
+echo "Waiting for the RPC endpoint to come up"
+docker exec laconicd-laconicd-1 sh -c "curl --retry 20 --retry-delay 3 --retry-connrefused http://127.0.0.1:9473/api"
+
 # Get the fixturenet account address
 laconicd_account_address=$(docker exec laconicd-laconicd-1 laconicd keys list | awk '/- address:/ {print $3}')
 
 # Copy over config
 docker exec laconicd-cli-1 cp config.yml laconic-registry-cli/
 
-# Wait for the laconid endpoint to come up
-echo "Waiting for the RPC endpoint to come up"
-docker exec laconicd-laconicd-1 sh -c "curl --retry 20 --retry-delay 3 --retry-connrefused http://127.0.0.1:9473/api"
-
 # Run the tests
 echo "Running the tests"
 docker exec -e TEST_ACCOUNT=$laconicd_account_address laconicd-cli-1 sh -c 'cd laconic-registry-cli && yarn && yarn test'