Release 0.11.0

.github/dependabot.yml

@@ -0,0 +1,19 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "dev"
+
+  - package-ecosystem: "npm"
+    directory: "/frontend"
+    schedule:
+      interval: "weekly"
+    target-branch: "dev"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "dev"

.github/workflows/black.yml

@@ -6,6 +6,10 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
-      - uses: psf/black@stable
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install ruff
+      - run: ruff check .
+      - run: ruff format --check .

.github/workflows/claude-code-review.yml

@@ -1,30 +1,22 @@
 name: Claude Code Review
 
 on:
-  pull_request:
-    types: [opened, ready_for_review]
-    # Optional: Only run on specific file changes
-    # paths:
-    #   - "src/**/*.ts"
-    #   - "src/**/*.tsx"
-    #   - "src/**/*.js"
-    #   - "src/**/*.jsx"
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: 'PR number to review'
+        required: true
+        type: number
 
 jobs:
   claude-review:
-    # Optional: Filter by PR author
-    # if: |
-    #   github.event.pull_request.user.login == 'external-contributor' ||
-    #   github.event.pull_request.user.login == 'new-developer' ||
-    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
-
     runs-on: ubuntu-latest
     permissions:
       contents: read
       pull-requests: read
       issues: read
       id-token: write
-    
+
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -36,43 +28,12 @@ jobs:
         uses: anthropics/claude-code-action@beta
         with:
           claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
-
-          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
-          # model: "claude-opus-4-20250514"
-
-          # Direct prompt for automated review (no @claude mention needed)
           direct_prompt: |
-            Please review this pull request and provide feedback on:
+            Please review pull request #${{ inputs.pr_number }} and provide feedback on:
             - Code quality and best practices
             - Potential bugs or issues
             - Performance considerations
             - Security concerns
             - Test coverage
-
-            Be constructive and helpful in your feedback.
-
-          # Optional: Use sticky comments to make Claude reuse the same comment on subsequent pushes to the same PR
-          # use_sticky_comment: true
-
-          # Optional: Customize review based on file types
-          # direct_prompt: |
-          #   Review this PR focusing on:
-          #   - For TypeScript files: Type safety and proper interface usage
-          #   - For API endpoints: Security, input validation, and error handling
-          #   - For React components: Performance, accessibility, and best practices
-          #   - For tests: Coverage, edge cases, and test quality
-
-          # Optional: Different prompts for different authors
-          # direct_prompt: |
-          #   ${{ github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR' && 
-          #   'Welcome! Please review this PR from a first-time contributor. Be encouraging and provide detailed explanations for any suggestions.' ||
-          #   'Please provide a thorough code review focusing on our coding standards and best practices.' }}
-
-          # Optional: Add specific tools for running tests or linting
-          # allowed_tools: "Bash(npm run test),Bash(npm run lint),Bash(npm run typecheck)"
-
-          # Optional: Skip review for certain conditions
-          # if: |
-          #   !contains(github.event.pull_request.title, '[skip-review]') &&
-          #   !contains(github.event.pull_request.title, '[WIP]')
 
+            Be constructive and helpful in your feedback.

.github/workflows/deploy_store.yml

@@ -15,44 +15,41 @@ jobs:
     steps:
     - name: Checkout
       uses: actions/checkout@v5
-      with:
-        ref: dev
 
     - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@v1
+      uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
         aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
         aws-region: us-east-1
 
     - name: Login to Amazon ECR
       id: login-ecr
-      uses: aws-actions/amazon-ecr-login@v1
+      uses: aws-actions/amazon-ecr-login@v2
 
     - name: Build, tag, and push image to Amazon ECR
       id: build-image
       env:
         ECR_REGISTRY: ${{ steps.login-ecr.outputs.registry }}
-        ECR_REPOSITORY: seqcolapi-store
+        ECR_REPOSITORY: seqcolapi
         IMAGE_TAG: ${{ github.sha }}
       run: |
-        cd deployment/seqcolapi-store/
-        docker build -t $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG -f Dockerfile .
+        docker build -t $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG -f deployment/seqcolapi-store/Dockerfile .
         docker push $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG
-        echo "::set-output name=image::$ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG"
+        echo "image=$ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG" >> $GITHUB_OUTPUT
 
     - name: Fill in the new image ID in the Amazon ECS task definition
       id: task-def
-      uses: aws-actions/amazon-ecs-render-task-definition@v1
+      uses: aws-actions/amazon-ecs-render-task-definition@v1.6.2
       with:
         task-definition: deployment/seqcolapi-store/task_def.json
-        container-name: seqcolapi-store
+        container-name: seqcolapi
         image: ${{ steps.build-image.outputs.image }}
 
     - name: Deploy Amazon ECS task definition
-      uses: aws-actions/amazon-ecs-deploy-task-definition@v1
+      uses: aws-actions/amazon-ecs-deploy-task-definition@v2
       with:
         task-definition: ${{ steps.task-def.outputs.task-definition }}
-        service: seqcolapi-store-service
+        service: seqcolapi-service
         cluster: yeti
         wait-for-service-stability: true

.github/workflows/python-publish.yml

@@ -1,4 +1,4 @@
-# This workflows will upload a Python Package using Twine when a release is created
+# This workflow uploads a Python Package using trusted publishing when a release is created
 # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
 
 name: Upload Python Package
@@ -23,10 +23,9 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools wheel twine
-    - name: Build and publish
+        pip install build
+    - name: Build package
       run: |
-        python setup.py sdist bdist_wheel
+        python -m build
     - name: Publish package distributions to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
-

.github/workflows/run-pytest.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.10", "3.13"]
+        python-version: ["3.10", "3.14"]
         os: [ubuntu-latest]
 
     steps:
@@ -20,13 +20,10 @@ jobs:
       with:
         python-version: ${{ matrix.python-version }}
 
-    - name: Install test dependencies
-      run: if [ -f requirements/requirements-test.txt ]; then pip install -r requirements/requirements-test.txt; fi
-
-    - name: Install package
+    - name: Install package with test extras
       env:
         PYO3_USE_ABI3_FORWARD_COMPATIBILITY: 1
-      run: python -m pip install .
+      run: python -m pip install ".[test]"
 
     - name: Run pytest tests
-      run: pytest -x -vv --cov=./ --cov-report=xml
+      run: pytest -x -vv --cov=./ --cov-report=xml

README.md

@@ -43,9 +43,48 @@ This starts the test database, runs tests, and cleans up automatically.
 
 ## Development and deployment: Backend
 
-### Easy-peasy way
+### Store-backed (no database)
 
-In a moment I'll show you how to do these steps individually, but if you're in a hurry, the easy way get a development API running for testing is to just use my very simple shell script like this (no data persistence, just loads demo data):
+The store-backed seqcolapi uses a RefgetStore (local files) instead of PostgreSQL. This is the simplest way to run the API:
+
+#### Quick start
+
+```console
+bash deployment/store_demo_up.sh
+```
+
+This will:
+- Build a local RefgetStore from test FASTA files
+- Run the store-backed seqcolapi with uvicorn
+- Block the terminal until you press Ctrl+C, which cleans up
+
+No Docker or database required.
+
+#### Step-by-step
+
+1. Build a store from FASTA files:
+
+```console
+python data_loaders/demo_build_store.py test_fasta /tmp/refget_demo_store
+```
+
+2. Start the store-backed API:
+
+```console
+REFGET_STORE_PATH=/tmp/refget_demo_store uvicorn seqcolapi.main:store_app --reload --port 8100
+```
+
+#### Remote store
+
+To run against a remote (S3) store:
+
+```console
+REFGET_STORE_URL=https://example.com/store uvicorn seqcolapi.main:store_app --port 8100
+```
+
+### DB-backed (PostgreSQL)
+
+If you need a database-backed instance (e.g., for mutable data, advanced queries), use the DB-backed workflow. In a moment I'll show you how to do these steps individually, but if you're in a hurry, the easy way to get a development API running for testing is to just use my very simple shell script like this (no data persistence, just loads demo data):
 
 ```console
 bash deployment/demo_up.sh
@@ -58,7 +97,7 @@ This will:
 - load up the demo data
 - block the terminal until you press Ctrl+C, which will shut down all services.
 
-### Step-by-step process
+### Step-by-step process (DB-backed)
 
 Alternatively, if you want to run each step separately to see what's really going on, start here.
 

data_loaders/demo_build_store.py

@@ -38,7 +38,14 @@ def main():
     store = RefgetStore.on_disk(store_path)
 
     for fasta in fasta_files:
-        store.add_sequence_collection_from_fasta(fasta)
+        result = store.add_sequence_collection_from_fasta(fasta)
+        # Register the filename (without extension) as a collection alias
+        basename = os.path.basename(fasta)
+        name = basename.split(".")[0]  # strip .fa, .fasta, .fa.gz, etc.
+        meta = result[0] if isinstance(result, tuple) else result
+        if meta:
+            store.add_collection_alias("fasta_filename", name, meta.digest)
+            print(f"  {name} → {meta.digest}")
 
     print(f"Done. Store at: {store_path}")
     print(f"Stats: {store.stats()}")

data_loaders/demo_remote_store.py

@@ -39,7 +39,7 @@ def main():
     print(f"\n1. Loading remote store from:\n   {REMOTE_URL}")
     print(f"   Cache directory: {CACHE_DIR}\n")
 
-    store = RefgetStore.load_remote(cache_path=str(CACHE_DIR), remote_url=REMOTE_URL)
+    store = RefgetStore.open_remote(cache_path=str(CACHE_DIR), remote_url=REMOTE_URL)
 
     print(f"   Loaded! {len(store)} sequences available (metadata only)")
 
@@ -51,17 +51,16 @@ def main():
 
     # 3. List sequences (first 5)
     print(f"\n3. Listing sequences (first 5 of {len(store)}):")
-    records = store.sequence_records()
-    for i, rec in enumerate(records[:5]):
-        m = rec.metadata
+    records = store.list_sequences()
+    for i, m in enumerate(records[:5]):
         print(f"   {i+1}. {m.name[:50]}...")
         print(f"      sha512t24u: {m.sha512t24u}")
         print(f"      length: {m.length:,} bp")
 
     # 4. Fetch a sequence by ID (downloads sequence data on first access)
     seq_digest = "du4GiRD_OcmdmCn_RmImyb71YZ4XoCdk"
     print(f"\n4. Get sequence record by ID (fetches from remote):")
-    record = store.get_sequence_by_id(seq_digest)
+    record = store.get_sequence(seq_digest)
     if record:
         print(f"   Name: {record.metadata.name}")
         print(f"   Length: {record.metadata.length:,} bp")
@@ -107,7 +106,7 @@ def main():
     print(f"   Collection: {EXAMPLE_COLLECTION}")
     print(f"   Sequence: {EXAMPLE_SEQ_NAME[:50]}...")
 
-    record = store.get_sequence_by_collection_and_name(EXAMPLE_COLLECTION, EXAMPLE_SEQ_NAME)
+    record = store.get_sequence_by_name(EXAMPLE_COLLECTION, EXAMPLE_SEQ_NAME)
     if record:
         print(f"   Found! Length: {record.metadata.length:,} bp")
         print(f"   Digest: {record.metadata.sha512t24u}")
@@ -149,9 +148,9 @@ def main():
     print(f"\nCache directory: {CACHE_DIR}")
     print(f"Temp files: {temp_dir}")
     print("\nKey features demonstrated:")
-    print("  - load_remote(): Load store from URL, fetch sequences on-demand")
-    print("  - get_sequence_by_id(): Lookup by SHA-512/24u or MD5 digest")
-    print("  - get_sequence_by_collection_and_name(): Lookup by sequence name")
+    print("  - open_remote(): Load store from URL, fetch sequences on-demand")
+    print("  - get_sequence(): Lookup by SHA-512/24u or MD5 digest")
+    print("  - get_sequence_by_name(): Lookup by collection digest + sequence name")
     print("  - substrings_from_regions(): Batch retrieval from BED file")
     print("  - export_fasta_by_digests(): Export sequences by digest")
     print("  - export_fasta_from_regions(): Export BED regions to FASTA")

data_loaders/load_demo_seqcols.py

@@ -19,7 +19,7 @@
 DEMO_FASTA = json.load(open("test_fasta/test_fasta_digests.json"))
 
 # Storage locations from environment (if set, will upload; otherwise use demo defaults with skip_upload)
-ENV_STORAGE = json.loads(os.environ.get("FASTA_STORAGE_LOCATIONS", "[]"))
+ENV_STORAGE = json.loads(os.environ.get("FASTA_STORAGE_LOCATIONS") or "[]")
 if ENV_STORAGE:
     DEMO_STORAGE = ENV_STORAGE
     SKIP_UPLOAD = False

data_loaders/ref-genome-analysis/.gitignore

@@ -0,0 +1,3 @@
+__pycache__/
+*.pyc
+*.log