💻 Chore: Add .github dir and dev tooling dot files

.github/workflows/ci.yml

@@ -0,0 +1,218 @@
+name: CI
+
+on:
+  push:
+    branches: [main, chore/configure-dev-tools]
+  pull_request:
+    branches: [main]
+
+jobs:
+  code-quality:
+    name: Code Quality Checks
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Install dependencies
+        run: |
+          uv sync --all-extras --dev
+
+      - name: Check code formatting with Black
+        run: |
+          uv run black --check gfmstudio/ tests/
+
+      - name: Lint with Ruff
+        run: |
+          uv run ruff check gfmstudio/ tests/
+
+      - name: Type checking with mypy (if configured)
+        run: |
+          uv run mypy gfmstudio/ || echo "mypy not configured, skipping"
+        continue-on-error: true
+
+  security:
+    name: Security Scanning
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Install dependencies
+        run: |
+          uv sync --all-extras --dev
+
+      - name: Run Bandit security checks
+        run: |
+          uv run bandit -r gfmstudio/ -f json -o bandit-report.json || true
+          uv run bandit -r gfmstudio/
+        continue-on-error: true
+
+      - name: Check for security vulnerabilities with pip-audit
+        run: |
+          uv pip install pip-audit
+          uv run pip-audit || echo "Vulnerabilities found, please review"
+        continue-on-error: true
+
+  test:
+    name: Run Tests
+    runs-on: ubuntu-latest
+
+    services:
+      postgres:
+        image: postgres:15
+        env:
+          POSTGRES_USER: test_user
+          POSTGRES_PASSWORD: test_password
+          POSTGRES_DB: test_db
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+      redis:
+        image: redis:7
+        ports:
+          - 6379:6379
+        options: >-
+          --health-cmd "redis-cli ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Install dependencies
+        run: |
+          uv sync --all-extras --dev
+
+      - name: Run pytest with coverage
+        env:
+          DATABASE_URI: postgresql+pg8000://test_user:test_password@localhost:5432/gfmstudio
+          AUTH_DATABASE_URI: postgresql+pg8000://test_user:test_password@localhost:5432/geostudio_auth
+          TEST_DATABASE_URI: postgresql+pg8000://test_user:test_password@localhost:5432/gfmstudio_test
+          # Caching Authentication Requests and Background Tasks
+          REDIS_URL: redis://localhost:6379
+          # COS INSTANCE and Buckets
+          OBJECT_STORAGE_KEY_ID: ...
+          OBJECT_STORAGE_SEC_KEY: ...
+          OBJECT_STORAGE_ENDPOINT: ...
+          OBJECT_STORAGE_REGION: 'us-south'
+          # COS Buckets
+          DATA_PVC: geoft-files-pvc
+          TUNES_FILES_BUCKET: geoft-service
+          DATASET_FILES_BUCKET: geoft-service-datasets
+          # FineTuning
+          TUNE_BASEDIR: /tmp/geoft-tunefiles/
+          DATA_MOUNT: /data
+          FILES_MOUNT: /geotunes/
+          FILES_PVC: geoft-files-pvc
+          CELERY_TASKS_ENABLED: True
+          # Inferencing
+          PIPELINES_V2_INFERENCE_ROOT_FOLDER: /tmp/inference_testing
+
+        run: |
+          uv run pytest tests/ \
+            --cov=gfmstudio \
+            --cov-report=xml \
+            --cov-report=html \
+            --cov-report=term-missing \
+            --junitxml=pytest-report.xml \
+            -v
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          file: ./coverage.xml
+          flags: unittests
+          name: codecov-umbrella
+          fail_ci_if_error: false
+        continue-on-error: true
+
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-results
+          path: |
+            pytest-report.xml
+            htmlcov/
+          retention-days: 30
+
+  docker-build:
+    name: Docker Build Test
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: false
+          tags: geospatial-studio-core:test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  dependency-review:
+    name: Dependency Review
+    runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request'
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Dependency Review
+        uses: actions/dependency-review-action@v4
+        with:
+          fail-on-severity: moderate
+
+  all-checks-passed:
+    name: All Checks Passed
+    runs-on: ubuntu-latest
+    needs: [code-quality, security, test, docker-build]
+    if: always()
+    steps:
+      - name: Check if all jobs passed
+        run: |
+          if [[ "${{ needs.code-quality.result }}" != "success" ]] || \
+             [[ "${{ needs.security.result }}" != "success" ]] || \
+             [[ "${{ needs.test.result }}" != "success" ]] || \
+             [[ "${{ needs.docker-build.result }}" != "success" ]]; then
+            echo "One or more checks failed"
+            exit 1
+          fi
+          echo "All checks passed successfully!"

gfmstudio/amo/api.py

@@ -93,11 +93,13 @@ async def onboard_inference_model(
             OnboardingStatus.PRESIGNED_URL_FAILED,
         ]
     ):
+        msg = (
+            f"model_id: {item.model_id} already in use."
+            "You can only reuse a model_id for successfully offboarded models and models that fail onboarding."
+        )
         raise HTTPException(
             status_code=422,
-            detail={
-                "message": f"model_id: {item.model_id} already in use. You can only reuse a model_id for successfully offboarded models and models that fail onboarding."
-            },
+            detail={"message": msg},
         )
     else:
         amo_task_manager.set_task_status(

gfmstudio/common/db/session.py

@@ -7,5 +7,6 @@
 
 from ...config import settings
 
+print(f"================= {settings.DATABASE_URI}")
 engine = create_engine(str(settings.DATABASE_URI), pool_size=30, max_overflow=10)
 SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)

gfmstudio/data_advisor/helper_functions.py

@@ -384,7 +384,8 @@ def find_data_bbox(connector: DataConnector, payload: DataAdvisorRequestSchema):
                     response["unique_dates"] = []
                     response.pop("available_data")
                     response["message"] = (
-                        f"The modalities {collections_with_no_data} do not have any data for the selected dates. Try the Bef_Days: {before_mydatetimes} or Aft_Days: {after_mydatetimes}"
+                        f"The modalities {collections_with_no_data} do not have any data for the selected dates. "
+                        f"Try the Bef_Days: {before_mydatetimes} or Aft_Days: {after_mydatetimes}"
                     )
                 results.append(response)
             return {"results": results}

gfmstudio/fine_tuning/core/schema.py

@@ -312,7 +312,9 @@ class LossFunction(BaseModel):
     type : Optional[str]
         The type of loss function to be used. Defaults to "CrossEntropyLoss".
     avg_non_ignore : bool
-        If True, the loss is averaged only over non-ignored targets, where the labels are present. Ignored targets (e.g., missing labels) are excluded from the averaging. Defaults to True.
+        If True, the loss is averaged only over non-ignored targets,
+        where the labels are present. Ignored targets (e.g., missing labels)
+        are excluded from the averaging. Defaults to True.
 
     Examples
     --------
@@ -328,7 +330,10 @@ class LossFunction(BaseModel):
     )
     avg_non_ignore: bool = Field(
         default=True,
-        description="The loss is only averaged over non-ignored targets (ignored targets are usually where labels are missing in the dataset) if this is True",
+        description=(
+            "The loss is only averaged over non-ignored targets "
+            "(ignored targets are usually where labels are missing in the dataset) if this is True"
+        ),
     )
 
 
@@ -339,7 +344,8 @@ class AuxLossFunction(LossFunction):
     Attributes
     ----------
     loss_weight : Optional[float]
-        The weight to apply to the auxiliary loss. This controls the contribution of this loss to the total loss. Defaults to 0.2.
+        The weight to apply to the auxiliary loss.
+        This controls the contribution of this loss to the total loss. Defaults to 0.2.
 
     Examples
     --------
@@ -543,9 +549,13 @@ class DataLoading(BaseModel):
     --------
     Create a DataLoading object:
 
-    >>> custom_data_loading = DataLoading(batch_size=16, workers_per_gpu=4, random_flip=1, bands=['RED', 'GREEN', 'BLUE'], tuning_bands=['GREEN', 'BLUE'])
+    >>> custom_data_loading = DataLoading(
+            batch_size=16, workers_per_gpu=4, random_flip=1,
+            bands=['RED', 'GREEN', 'BLUE'], tuning_bands=['GREEN', 'BLUE'])
     >>> print(custom_data_loading)
-    DataLoading(batch_size=16, bands=['RED', 'GREEN', 'BLUE'], workers_per_gpu=4, random_flip=1, tuning_bands=['GREEN', 'BLUE'])
+    DataLoading(
+        batch_size=16, bands=['RED', 'GREEN', 'BLUE'],
+        workers_per_gpu=4, random_flip=1, tuning_bands=['GREEN', 'BLUE'])
     """
 
     batch_size: Optional[int] = None
@@ -787,22 +797,27 @@ class BaseModelNecks(BaseModel):
 
 class AuxiliaryHead(DecodeHead):
     """
-    Auxiliary head used in a neural network model, extending the main decode head, and including an auxiliary loss function.
+    Auxiliary head used in a neural network model, extending the main decode head,
+    and including an auxiliary loss function.
 
     Attributes
     ----------
     channels : Optional[int]
-        Number of channels at each block of the auxiliary head, except the final one. Inherited from `DecodeHead`. Defaults to 32.
+        Number of channels at each block of the auxiliary head, except the final one. Inherited from `DecodeHead`.
+        Defaults to 32.
     num_convs : Optional[int]
-        Number of convolutional blocks in the auxiliary head, excluding the final block. Inherited from `DecodeHead`. Defaults to 1.
+        Number of convolutional blocks in the auxiliary head, excluding the final block. Inherited from `DecodeHead`.
+        Defaults to 1.
     loss_decode : Optional[AuxLossFunction]
-        Defines the auxiliary loss function used for training. Defaults to an `AuxLossFunction` object with a loss weight of 0.2.
+        Defines the auxiliary loss function used for training.
+        Defaults to an `AuxLossFunction` object with a loss weight of 0.2.
 
     Examples
     --------
     Create a `AuxiliaryHead` object:
 
-    >>> custom_aux_head = AuxiliaryHead(channels=64, num_convs=2, loss_decode=AuxLossFunction(type='DiceLoss', loss_weight=0.3))
+    >>> custom_aux_head = AuxiliaryHead(
+            channels=64, num_convs=2, loss_decode=AuxLossFunction(type='DiceLoss', loss_weight=0.3))
     >>> print(custom_aux_head)
     AuxiliaryHead(
         channels=64,
@@ -866,17 +881,21 @@ class TemplateUserDefinedParams(BaseModel):
     dataset_id : Optional[str]
         The dataset id. Defaults to None.
     data : Optional[DataLoading]
-        Parameters for configuring data loading, including batch size and number of workers. Defaults to a DataLoading object.
+        Parameters for configuring data loading, including batch size and number of workers.
+        Defaults to a DataLoading object.
     runner : Optional[Runner]
-        Defines training parameters such as the number of epochs and early stopping criteria. Defaults to a Runner object.
+        Defines training parameters such as the number of epochs and early stopping criteria.
+        Defaults to a Runner object.
     optimizer : Optional[Optimizer]
-        The optimizer configuration, including type (e.g., Adam) and learning rate settings. Defaults to an Optimizer object.
+        The optimizer configuration, including type (e.g., Adam) and learning rate settings.
+        Defaults to an Optimizer object.
     lr_config : Optional[LRPolicy]
         Learning rate policy configuration, including warmup settings. Defaults to None.
     evaluation : Optional[Evaluation]
         Parameters for model evaluation, such as validation frequency and metric. Defaults to an Evaluation object.
     model : Optional[Model]
-        The model configuration, including whether to freeze the backbone and the definition of the decode and auxiliary heads. Defaults to a Model object.
+        The model configuration, including whether to freeze the backbone and the
+        definition of the decode and auxiliary heads. Defaults to a Model object.
     backbone_model_id : Optional[str]
         Base model id. Defaults to None.
 
@@ -901,7 +920,9 @@ class TemplateUserDefinedParams(BaseModel):
         optimizer=Optimizer(type='SGD', lr='0.01', weight_decay=None),
         lr_config=None,
         evaluation=Evaluation(interval=5, metric='accuracy'),
-        model=Model(frozen_backbone=True, decode_head=DecodeHead(channels=32, num_convs=1, loss_decode=LossFunction(type='CrossEntropyLoss', avg_non_ignore=True)), auxiliary_head=None),
+        model=Model(frozen_backbone=True, decode_head=DecodeHead(
+            channels=32, num_convs=1, loss_decode=LossFunction(
+                type='CrossEntropyLoss', avg_non_ignore=True)), auxiliary_head=None),
         backbone_model_id=None
     )
     """
@@ -1027,7 +1048,10 @@ class TuneTemplateParameters(
     )
     mlflow_tags: Optional[dict] = Field(
         default=dict,
-        description="Mlflow tags to uniquely match an experiment with unique identifiers e.g user email address, name ...",
+        description=(
+            "Mlflow tags to uniquely match an experiment with unique"
+            "identifiers e.g user email address, name ..."
+        ),
     )
 
     # Fields `num_layers` from the BaseModels