feat(actions): added YAML linting action using yamlfmt, and linted existing YAML files

.github/workflows/yamlfmt-lint.yml

@@ -0,0 +1,19 @@
+name: yamlfmt-lint
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    container:
+      image: ghcr.io/google/yamlfmt:0.21.0
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Run yamlfmt lint
+        run: yamlfmt -lint .

.pre-commit-config.yaml

@@ -1,36 +1,36 @@
 repos:
-- repo: https://github.com/astral-sh/ruff-pre-commit
-  # Ruff version.
-  rev: v0.14.2
-  hooks:
-    # Run the linter and fix issues.
-    - id: ruff-check
-      args: [ --fix ]
-      files: ^ena-submission/
-    # Run lint but only fix auto-fixable issues.
-    - id: ruff-check
-      args: [ --fix-only ]
-      files: ^preprocessing/nextclade/
-    # Run the formatter.
-    - id: ruff-format
-      files: ^ena-submission/|^preprocessing/nextclade/
-- repo: local
-  hooks:
-    - id: prettier-values-schema
-      name: prettier (values.schema.json)
-      entry: npx prettier@3.6.2 --write
-      language: system
-      files: ^kubernetes/loculus/values\.schema\.json$
-    - id: helm-lint
-      name: helm lint
-      entry: bash
-      args:
-        - -c
-        - |
-          set -euo pipefail
-          helm lint kubernetes/loculus -f kubernetes/loculus/values.yaml
-          helm lint kubernetes/loculus -f kubernetes/loculus/values.yaml -f kubernetes/loculus/values_e2e_and_dev.yaml
-          helm lint kubernetes/loculus -f kubernetes/loculus/values.yaml -f kubernetes/loculus/values_preview_server.yaml
-      language: system
-      pass_filenames: false
-      files: ^kubernetes/loculus/
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.14.2
+    hooks:
+      # Run the linter and fix issues.
+      - id: ruff-check
+        args: [--fix]
+        files: ^ena-submission/
+      # Run lint but only fix auto-fixable issues.
+      - id: ruff-check
+        args: [--fix-only]
+        files: ^preprocessing/nextclade/
+      # Run the formatter.
+      - id: ruff-format
+        files: ^ena-submission/|^preprocessing/nextclade/
+  - repo: local
+    hooks:
+      - id: prettier-values-schema
+        name: prettier (values.schema.json)
+        entry: npx prettier@3.6.2 --write
+        language: system
+        files: ^kubernetes/loculus/values\.schema\.json$
+      - id: helm-lint
+        name: helm lint
+        entry: bash
+        args:
+          - -c
+          - |
+            set -euo pipefail
+            helm lint kubernetes/loculus -f kubernetes/loculus/values.yaml
+            helm lint kubernetes/loculus -f kubernetes/loculus/values.yaml -f kubernetes/loculus/values_e2e_and_dev.yaml
+            helm lint kubernetes/loculus -f kubernetes/loculus/values.yaml -f kubernetes/loculus/values_preview_server.yaml
+        language: system
+        pass_filenames: false
+        files: ^kubernetes/loculus/

.yamlfmt.yaml

@@ -2,6 +2,9 @@
 formatter:
   type: basic
   drop_merge_tag: true
+  trim_trailing_whitespace: true
+  retain_line_breaks_single: true
 gitignore_excludes: true
 exclude:
   - kubernetes/loculus/templates
+  - .github

ena-submission/environment.yml

@@ -5,7 +5,7 @@ channels:
   - nodefaults
 dependencies:
   # Core Python dependencies
-  - python=3.12.9  # Pinned to 3.12.x series, check for patch updates within 3.12
+  - python=3.12.9 # Pinned to 3.12.x series, check for patch updates within 3.12
   - pip=25.2
   - uv=0.9.5
   # Extra dependencies

ena-submission/test/test_config.yaml

@@ -19,7 +19,7 @@ enaOrganisms:
     scientific_name: Orthonairovirus haemorrhagiae
     taxon_id: 3052518
     organismName: "Crimean-Congo Hemorrhagic Fever Virus"
-    segments: 
+    segments:
       - L
       - M
       - S
@@ -92,7 +92,7 @@ enaOrganisms:
     scientific_name: West Nile virus
     taxon_id: 11082
     organismName: "West Nile Virus"
-    segments: 
+    segments:
       - main
     externalMetadata:
       - externalMetadataUpdater: ena
@@ -133,4 +133,4 @@ enaOrganisms:
         type: int
       - externalMetadataUpdater: ena
         name: sraRunAccession
-        type: string
+        type: string

ingest/config/defaults.yaml

@@ -62,16 +62,16 @@ ncbi_mappings:
     - ncbiHostCommonName
     - ncbiPurposeOfSampling
     - ncbiHostSex
-group_name: insdc_ingest_group  # Used only to set the group name, never read
+group_name: insdc_ingest_group # Used only to set the group name, never read
 username: insdc_ingest_user
 password: insdc_ingest_user
 keycloak_client_id: backend-client
 subsample_fraction: 1.0
-approve_timeout_min: "25" # Cronjobs run every 30min, make approve stop before it is forced to stop by argocd 
+approve_timeout_min: "25" # Cronjobs run every 30min, make approve stop before it is forced to stop by argocd
 db_username: postgres
 db_password: unsecure
 db_url: "jdbc:postgresql://127.0.0.1:5432/loculus"
-batch_chunk_size: 10000  # Batch size for submitting sequences to Loculus backend
+batch_chunk_size: 10000 # Batch size for submitting sequences to Loculus backend
 nextclade_dataset_server: https://data.clades.nextstrain.org/v3
 time_between_approve_requests_seconds: 60
 backend_request_timeout_seconds: 600

ingest/environment.yml

@@ -5,7 +5,7 @@ channels:
   - nodefaults
 dependencies:
   # Core Python dependencies
-  - python=3.12.9  # Pinned to 3.12.x series, check for patch updates within 3.12
+  - python=3.12.9 # Pinned to 3.12.x series, check for patch updates within 3.12
   # Extra dependencies
   - biopython=1.85
   - click=8.3.0

kubernetes/loculus/values.yaml

@@ -1391,8 +1391,8 @@ defaultOrganismConfig: &defaultOrganismConfig
         segments:
           - name: main
             references:
-            - name: singleReference
-              genes: []
+              - name: singleReference
+                genes: []
         nextclade_dataset_server: https://data.clades.nextstrain.org/v3
   ingest: &ingest
     image: ghcr.io/loculus-project/ingest
@@ -1424,9 +1424,9 @@ defaultOrganisms:
           segments:
             - name: main
               references:
-              - name: singleReference
-                nextclade_dataset_name: nextstrain/ebola/sudan
-                genes: [NP, VP35, VP40, GP, sGP, ssGP, VP30, VP24, L]
+                - name: singleReference
+                  nextclade_dataset_name: nextstrain/ebola/sudan
+                  genes: [NP, VP35, VP40, GP, sGP, ssGP, VP30, VP24, L]
           nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/ebola/data_output
           taxon_id: 186540
           scientific_name: "Sudan ebolavirus"
@@ -1539,9 +1539,9 @@ defaultOrganisms:
           segments:
             - name: main
               references:
-              - name: singleReference
-                nextclade_dataset_name: nextstrain/wnv/all-lineages
-                genes: [capsid, prM, env, NS1, NS2A, NS2B, NS3, NS4A, 2K, NS4B, NS5]
+                - name: singleReference
+                  nextclade_dataset_name: nextstrain/wnv/all-lineages
+                  genes: [capsid, prM, env, NS1, NS2A, NS2B, NS3, NS4A, 2K, NS4B, NS5]
           nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/wnv/data_output
           taxon_id: 11082
           scientific_name: "West Nile virus"
@@ -1638,7 +1638,7 @@ defaultOrganisms:
           required: true
           type: string
           lineageSystem: pangoLineage
-          options: 
+          options:
             - name: A
             - name: A.1
             - name: A.1.1
@@ -1750,7 +1750,7 @@ defaultOrganisms:
           required: true
           type: string
           lineageSystem: alternativeLineage
-          options: 
+          options:
             - name: A
             - name: A.1
             - name: A.1.1
@@ -1806,8 +1806,8 @@ defaultOrganisms:
           segments:
             - name: main
               references:
-              - name: singleReference
-                genes: []
+                - name: singleReference
+                  genes: []
     referenceGenomes:
       - name: main
         references:
@@ -1880,19 +1880,19 @@ defaultOrganisms:
           segments:
             - name: L
               references:
-              - nextclade_dataset_name: community/pathoplexus/cchfv/L
-                name: singleReference
-                genes: [RdRp]
+                - nextclade_dataset_name: community/pathoplexus/cchfv/L
+                  name: singleReference
+                  genes: [RdRp]
             - name: M
               references:
-              - nextclade_dataset_name: community/pathoplexus/cchfv/M
-                name: singleReference
-                genes: [GPC]
+                - nextclade_dataset_name: community/pathoplexus/cchfv/M
+                  name: singleReference
+                  genes: [GPC]
             - name: S
               references:
-              - nextclade_dataset_name: community/pathoplexus/cchfv/S
-                name: singleReference
-                genes: [NP]
+                - nextclade_dataset_name: community/pathoplexus/cchfv/S
+                  name: singleReference
+                  genes: [NP]
     ingest:
       <<: *ingest
       configFile:
@@ -2017,32 +2017,32 @@ defaultOrganisms:
           segments:
             - name: L
               references:
-              - nextclade_dataset_name: cchfv/L
-                name: singleReference
-                genes: [RdRp]
+                - nextclade_dataset_name: cchfv/L
+                  name: singleReference
+                  genes: [RdRp]
             - name: M
               references:
-              - nextclade_dataset_name: cchfv/M-MH396653
-                name: MH396653
-                genes: [GPC]
-              - nextclade_dataset_name: cchfv/M-OR047158
-                name: OR047158
-                genes: [GPC]
+                - nextclade_dataset_name: cchfv/M-MH396653
+                  name: MH396653
+                  genes: [GPC]
+                - nextclade_dataset_name: cchfv/M-OR047158
+                  name: OR047158
+                  genes: [GPC]
             - name: S
               references:
-              - nextclade_dataset_name: cchfv/S-1and6
-                name: 1and6
-                genes: [NP]
-              - nextclade_dataset_name: cchfv/S-2to5
-                name: 2to5
-                genes: [NP]
+                - nextclade_dataset_name: cchfv/S-1and6
+                  name: 1and6
+                  genes: [NP]
+                - nextclade_dataset_name: cchfv/S-2to5
+                  name: 2to5
+                  genes: [NP]
     ingest:
       <<: *ingest
       configFile:
         taxon_id: 3052518
         segment_identification:
           method: "align"
-          nextclade_dataset_name: community/pathoplexus/cchfv  #TODO: allow multiple ref in ingest grouping algo
+          nextclade_dataset_name: community/pathoplexus/cchfv #TODO: allow multiple ref in ingest grouping algo
     enaDeposition:
       singleReference:
         configFile:
@@ -2191,23 +2191,23 @@ defaultOrganisms:
           segments:
             - name: main
               references:
-              - name: CV-A16
-                nextclade_dataset_name: enpen/enterovirus/cv-a16
-                accepted_dataset_matches: ["community/hodcroftlab/enterovirus/cva16", "community/hodcroftlab/enterovirus/enterovirus/linked/CV-A16"]
-                genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
-              - name: CV-A10
-                nextclade_dataset_name: enpen/enterovirus/cv-a10
-                accepted_dataset_matches: ["community/hodcroftlab/enterovirus/enterovirus/linked/CV-A10"]
-                genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
-              - name: EV-A71
-                nextclade_dataset_name: enpen/enterovirus/ev-a71
-                accepted_dataset_matches: ["community/hodcroftlab/enterovirus/enterovirus/linked/EV-A71"]
-                genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
-              - name: EV-D68
-                accepted_dataset_matches: ["community/hodcroftlab/enterovirus/enterovirus/linked/EV-D68"]
-                genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
-                nextclade_dataset_name: enpen/enterovirus/ev-d68
-                nextclade_dataset_server: https://data.clades.nextstrain.org/v3
+                - name: CV-A16
+                  nextclade_dataset_name: enpen/enterovirus/cv-a16
+                  accepted_dataset_matches: ["community/hodcroftlab/enterovirus/cva16", "community/hodcroftlab/enterovirus/enterovirus/linked/CV-A16"]
+                  genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
+                - name: CV-A10
+                  nextclade_dataset_name: enpen/enterovirus/cv-a10
+                  accepted_dataset_matches: ["community/hodcroftlab/enterovirus/enterovirus/linked/CV-A10"]
+                  genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
+                - name: EV-A71
+                  nextclade_dataset_name: enpen/enterovirus/ev-a71
+                  accepted_dataset_matches: ["community/hodcroftlab/enterovirus/enterovirus/linked/EV-A71"]
+                  genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
+                - name: EV-D68
+                  accepted_dataset_matches: ["community/hodcroftlab/enterovirus/enterovirus/linked/EV-D68"]
+                  genes: ["VP4", "VP2", "VP3", "VP1", "2A", "2B", "2C", "3A", "3B", "3C", "3D"]
+                  nextclade_dataset_name: enpen/enterovirus/ev-d68
+                  nextclade_dataset_server: https://data.clades.nextstrain.org/v3
           nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/evs-datasets/data_output
     ingest:
       <<: *ingest
@@ -2445,7 +2445,7 @@ enforceHTTPS: true
 registrationTermsMessage: >
   You must agree to the <a href="http://main.loculus.org/terms">terms of use</a>.
 
-enaDeposition: 
+enaDeposition:
   submitToEnaProduction: false
   enaDbName: Loculus
   enaUniqueSuffix: Loculus

kubernetes/loculus/values_e2e_and_dev.yaml

@@ -14,4 +14,4 @@ auth:
   verifyEmail: false
 host: localhost:3000
 siloImport:
-  pollIntervalSeconds: 5
+  pollIntervalSeconds: 5

kubernetes/loculus/values_preview_server.yaml

@@ -140,4 +140,4 @@ defaultResources:
     cpu: "20m"
   limits:
     memory: "1Gi"
-    cpu: "20m"
+    cpu: "20m"