From 80ae06a44290fc16114113636b89321319c0cbc5 Mon Sep 17 00:00:00 2001
From: Wietze <wietze.suijker@gmail.com>
Date: Thu, 23 Oct 2025 17:49:38 +0200
Subject: [PATCH 1/2] feat: add comprehensive unit test suite

- Unit tests for all 6 core scripts
- Test fixtures and test infrastructure
- CI integration with pytest

Tests cover:
- augment_stac_item.py - Projection and visualization augmentation
- create_geozarr_item.py - GeoZarr conversion wrapper
- get_conversion_params.py - Collection parameter lookup
- register_stac.py - STAC item creation and registration
---
 .github/workflows/test.yml               |   6 +
 tests/__init__.py                        |   0
 tests/conftest.py                        | 133 +++++++++++++
 tests/integration/__init__.py            |   0
 tests/unit/__init__.py                   |   0
 tests/unit/test_augment_stac_item.py     | 165 ++++++++++++++++
 tests/unit/test_create_geozarr_item.py   | 149 ++++++++++++++
 tests/unit/test_get_conversion_params.py |  68 +++++++
 tests/unit/test_register_stac.py         | 241 +++++++++++++++++++++++
 9 files changed, 762 insertions(+)
 create mode 100644 tests/__init__.py
 create mode 100644 tests/conftest.py
 create mode 100644 tests/integration/__init__.py
 create mode 100644 tests/unit/__init__.py
 create mode 100644 tests/unit/test_augment_stac_item.py
 create mode 100644 tests/unit/test_create_geozarr_item.py
 create mode 100644 tests/unit/test_get_conversion_params.py
 create mode 100644 tests/unit/test_register_stac.py

diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index a1223ce..5d4f38c 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -34,3 +34,9 @@ jobs:
 
     - name: Run pre-commit checks
       run: uv run pre-commit run --all-files
+
+    - name: Run unit tests
+      run: uv run pytest tests/unit -v --tb=short
+
+    - name: Generate coverage report
+      run: uv run pytest tests/unit --cov=scripts --cov-report=term-missing --cov-report=html
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..c967b78
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,133 @@
+"""Pytest configuration and shared fixtures for data-pipeline tests."""
+
+import atexit
+import sys
+import warnings
+
+import pytest
+
+# Suppress noisy async context warnings from zarr/s3fs
+warnings.filterwarnings("ignore", category=ResourceWarning)
+warnings.filterwarnings("ignore", message="coroutine.*was never awaited")
+
+
+# Global stderr filter that stays active even after pytest teardown
+_original_stderr = sys.stderr
+_suppress_traceback = False
+
+
+class _FilteredStderr:
+    def write(self, text):
+        global _suppress_traceback
+
+        # Start suppressing when we see async context errors
+        if any(
+            marker in text
+            for marker in [
+                "Exception ignored",
+                "Traceback (most recent call last)",
+                "ValueError: <Token",
+                "was created in a different Context",
+                "zarr/storage/",
+                "s3fs/core.py",
+                "aiobotocore/context.py",
+            ]
+        ):
+            _suppress_traceback = True
+
+        # Reset suppression on empty lines (between tracebacks)
+        if not text.strip():
+            _suppress_traceback = False
+
+        # Only write if not currently suppressing
+        if not _suppress_traceback:
+            _original_stderr.write(text)
+
+    def flush(self):
+        _original_stderr.flush()
+
+
+def _restore_stderr():
+    """Restore original stderr at exit."""
+    sys.stderr = _original_stderr
+
+
+# Install filter at module load time
+sys.stderr = _FilteredStderr()
+atexit.register(_restore_stderr)
+
+
+@pytest.fixture(autouse=True, scope="function")
+def clear_prometheus_registry():
+    """Clear Prometheus registry before each test to avoid duplicates."""
+    import contextlib
+
+    try:
+        from prometheus_client import REGISTRY
+
+        collectors = list(REGISTRY._collector_to_names.keys())
+        for collector in collectors:
+            with contextlib.suppress(Exception):
+                REGISTRY.unregister(collector)
+    except ImportError:
+        pass
+    yield
+
+
+@pytest.fixture
+def sample_stac_item():
+    """Return a minimal STAC item for testing."""
+    return {
+        "type": "Feature",
+        "stac_version": "1.0.0",
+        "id": "test-item",
+        "properties": {
+            "datetime": "2025-01-01T00:00:00Z",
+            "proj:epsg": 32636,
+        },
+        "geometry": {
+            "type": "Polygon",
+            "coordinates": [
+                [
+                    [600000, 6290220],
+                    [709800, 6290220],
+                    [709800, 6400020],
+                    [600000, 6400020],
+                    [600000, 6290220],
+                ]
+            ],
+        },
+        "links": [],
+        "assets": {
+            "B01": {
+                "href": "s3://bucket/data/B01.tif",
+                "type": "image/tiff; application=geotiff",
+                "roles": ["data"],
+                "proj:epsg": 32636,
+                "proj:shape": [10980, 10980],
+                "proj:transform": [10, 0, 600000, 0, -10, 6400020],
+            }
+        },
+        "collection": "test-collection",
+    }
+
+
+@pytest.fixture
+def stac_item_with_proj_code(sample_stac_item):
+    """Return a STAC item with proj:code (should be removed)."""
+    item = sample_stac_item.copy()
+    item["properties"]["proj:code"] = "EPSG:32636"
+    item["assets"]["B01"]["proj:code"] = "EPSG:32636"
+    return item
+
+
+@pytest.fixture
+def mock_zarr_url():
+    """Return a sample GeoZarr URL."""
+    return "s3://bucket/path/to/dataset.zarr"
+
+
+@pytest.fixture
+def mock_stac_api_url():
+    """Return a mock STAC API URL."""
+    return "https://api.example.com/stac"
diff --git a/tests/integration/__init__.py b/tests/integration/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/unit/__init__.py b/tests/unit/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/unit/test_augment_stac_item.py b/tests/unit/test_augment_stac_item.py
new file mode 100644
index 0000000..840fed8
--- /dev/null
+++ b/tests/unit/test_augment_stac_item.py
@@ -0,0 +1,165 @@
+"""Unit tests for augment_stac_item.py."""
+
+from datetime import UTC, datetime
+from unittest.mock import MagicMock, patch
+
+import pytest
+from pystac import Asset, Item
+
+from scripts.augment_stac_item import add_projection, add_visualization, augment, main
+
+
+@pytest.fixture
+def item():
+    """Create test STAC item."""
+    return Item("test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={})
+
+
+@pytest.fixture
+def mock_httpx_success():
+    """Mock successful httpx requests."""
+    with patch("scripts.augment_stac_item.httpx.Client") as mock_client:
+        mock_ctx = MagicMock()
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_ctx.get.return_value = mock_response
+        mock_ctx.put.return_value = mock_response
+        mock_client.return_value.__enter__.return_value = mock_ctx
+        mock_client.return_value.__exit__.return_value = None
+        yield mock_ctx
+
+
+def test_add_projection_extracts_epsg(item):
+    """Test projection extraction from zarr."""
+    item.add_asset("product", Asset(href="s3://test.zarr", media_type="application/vnd+zarr"))
+
+    mock_store = MagicMock()
+    # The actual code reads spatial_ref dict which contains "spatial_ref" key with EPSG value
+    mock_store.attrs.get.return_value = {"spatial_ref": "32632", "crs_wkt": "PROJCS[...]"}
+
+    with patch("scripts.augment_stac_item.zarr.open", return_value=mock_store):
+        add_projection(item)
+
+    # Projection extension sets proj:code based on EPSG
+    assert (
+        item.properties.get("proj:code") == "EPSG:32632"
+        or item.properties.get("proj:epsg") == 32632
+    )
+    assert "proj:wkt2" in item.properties
+
+
+def test_add_projection_handles_errors(item):
+    """Test add_projection error handling."""
+    item.add_asset("product", Asset(href="s3://test.zarr", media_type="application/vnd+zarr"))
+    with patch("scripts.augment_stac_item.zarr.open", side_effect=Exception):
+        add_projection(item)  # Should not raise
+        assert "proj:epsg" not in item.properties
+
+
+def test_add_projection_no_zarr_assets(item):
+    """Test add_projection with no zarr assets."""
+    add_projection(item)
+    assert "proj:epsg" not in item.properties
+
+
+@pytest.mark.parametrize(
+    "collection,expected_asset",
+    [
+        ("sentinel-2-l2a", "TCI_10m"),
+    ],
+)
+def test_add_visualization(item, collection, expected_asset):
+    """Test visualization links for S1/S2."""
+    add_visualization(item, "https://raster.api", collection)
+
+    links = {link.rel: link for link in item.links}
+    assert all(rel in links for rel in ["viewer", "xyz", "tilejson", "via"])
+
+    # Verify asset in xyz URL
+    assert expected_asset in links["xyz"].href
+
+    # Verify proper URL encoding (/ should be %2F, : should be %3A)
+    assert "%2F" in links["xyz"].href  # Forward slashes are encoded
+    assert "%3A" in links["xyz"].href  # Colons are encoded
+
+    # Verify titles are present
+    assert links["xyz"].title is not None
+    assert links["tilejson"].title is not None
+    assert links["viewer"].title is not None
+
+
+def test_augment_verbose(item):
+    """Test augment with verbose output."""
+    with (
+        patch("scripts.augment_stac_item.add_projection"),
+        patch("scripts.augment_stac_item.add_visualization"),
+        patch("builtins.print") as mock_print,
+    ):
+        augment(item, raster_base="https://api", collection_id="col", verbose=True)
+        mock_print.assert_called_once()
+
+
+def test_main_success(mock_httpx_success):
+    """Test main() success flow."""
+    item_dict = Item(
+        "test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={}
+    ).to_dict()
+    item_dict["collection"] = "test-col"
+    mock_httpx_success.get.return_value.json.return_value = item_dict
+
+    with patch("scripts.augment_stac_item.augment") as mock_aug:
+        mock_aug.return_value = Item.from_dict(item_dict)
+        exit_code = main(
+            ["--stac", "https://stac", "--collection", "test-col", "--item-id", "test"]
+        )
+
+    assert exit_code == 0
+
+
+def test_main_get_failure():
+    """Test main() GET failure."""
+    with patch("scripts.augment_stac_item.httpx.Client") as mock:
+        mock.return_value.__enter__.return_value.get.side_effect = Exception("Failed")
+        exit_code = main(["--stac", "https://stac", "--collection", "col", "--item-id", "test"])
+
+    assert exit_code == 1
+
+
+def test_main_put_failure(mock_httpx_success):
+    """Test main() PUT failure."""
+    item_dict = Item(
+        "test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={}
+    ).to_dict()
+    mock_httpx_success.get.return_value.json.return_value = item_dict
+    mock_httpx_success.put.side_effect = Exception("Failed")
+
+    with patch("scripts.augment_stac_item.augment", return_value=Item.from_dict(item_dict)):
+        exit_code = main(["--stac", "https://stac", "--collection", "col", "--item-id", "test"])
+
+    assert exit_code == 1
+
+
+def test_main_with_bearer_token(mock_httpx_success):
+    """Test main() with bearer token."""
+    item_dict = Item(
+        "test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={}
+    ).to_dict()
+    item_dict["collection"] = "col"
+    mock_httpx_success.get.return_value.json.return_value = item_dict
+
+    with patch("scripts.augment_stac_item.augment", return_value=Item.from_dict(item_dict)):
+        main(
+            [
+                "--stac",
+                "https://stac",
+                "--collection",
+                "col",
+                "--item-id",
+                "test",
+                "--bearer",
+                "token",
+            ]
+        )
+
+    call = mock_httpx_success.get.call_args
+    assert call.kwargs["headers"]["Authorization"] == "Bearer token"
diff --git a/tests/unit/test_create_geozarr_item.py b/tests/unit/test_create_geozarr_item.py
new file mode 100644
index 0000000..5f771f4
--- /dev/null
+++ b/tests/unit/test_create_geozarr_item.py
@@ -0,0 +1,149 @@
+"""Unit tests for create_geozarr_item.py."""
+
+import json
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from scripts.create_geozarr_item import (
+    create_geozarr_item,
+    find_source_zarr_base,
+    main,
+    normalize_asset_href,
+    s3_to_https,
+)
+
+
+@pytest.fixture
+def source_item():
+    """Valid source STAC item with band assets."""
+    return {
+        "type": "Feature",
+        "stac_version": "1.0.0",
+        "id": "test-item",
+        "geometry": {"type": "Polygon", "coordinates": [[[0, 0], [1, 0], [1, 1], [0, 1], [0, 0]]]},
+        "bbox": [0, 0, 1, 1],
+        "properties": {"datetime": "2025-01-01T00:00:00Z"},
+        "collection": "source-col",
+        "links": [],
+        "assets": {
+            "B01": {"href": "s3://source/data.zarr/r10m/b01", "type": "image/tiff"},
+            "B02": {"href": "s3://source/data.zarr/r10m/b02", "type": "image/tiff"},
+            "B08A": {"href": "s3://source/data.zarr/r60m/b08a", "type": "image/tiff"},
+        },
+    }
+
+
+@pytest.fixture
+def mock_httpx_and_validation(source_item):
+    """Mock httpx (validation removed from create_geozarr_item)."""
+    with patch("scripts.create_geozarr_item.httpx.get") as mock_get:
+        mock_get.return_value = MagicMock(json=lambda: source_item)
+        yield mock_get
+
+
+def test_s3_to_https():
+    """Test S3 URL conversion."""
+    assert (
+        s3_to_https("s3://bucket/path/file.zarr", "https://s3.io")
+        == "https://bucket.s3.io/path/file.zarr"
+    )
+    assert s3_to_https("https://already/https", "https://s3.io") == "https://already/https"
+
+
+def test_normalize_asset_href():
+    """Test asset href normalization for r60m bands."""
+    # r60m bands need /0/ inserted
+    assert (
+        normalize_asset_href("s3://bucket/data.zarr/r60m/b08a")
+        == "s3://bucket/data.zarr/r60m/0/b08a"
+    )
+    # Already has /0/
+    assert (
+        normalize_asset_href("s3://bucket/data.zarr/r60m/0/b08a")
+        == "s3://bucket/data.zarr/r60m/0/b08a"
+    )
+    # r10m/r20m don't need changes
+    assert (
+        normalize_asset_href("s3://bucket/data.zarr/r10m/b02") == "s3://bucket/data.zarr/r10m/b02"
+    )
+
+
+def test_find_source_zarr_base():
+    """Test finding Zarr base URL from assets."""
+    item = {
+        "assets": {
+            "B01": {"href": "s3://bucket/data.zarr/r10m/b01"},
+            "B02": {"href": "s3://bucket/data.zarr/r10m/b02"},
+        }
+    }
+    assert find_source_zarr_base(item) == "s3://bucket/data.zarr"
+    assert find_source_zarr_base({"assets": {}}) is None
+
+
+def test_create_geozarr_item_rewrites_assets(tmp_path, mock_httpx_and_validation):
+    """Test that asset hrefs are rewritten to point to GeoZarr output."""
+    output = tmp_path / "item.json"
+
+    create_geozarr_item(
+        "https://stac.api/items/test",
+        "geozarr-col",
+        "s3://bucket/output.zarr",
+        "https://s3.endpoint.io",
+        str(output),
+    )
+
+    item = json.loads(output.read_text())
+    assert item["collection"] == "geozarr-col"
+
+    # Check that band assets were rewritten
+    assert "B01" in item["assets"]
+    assert "B02" in item["assets"]
+    assert "B08A" in item["assets"]
+
+    # r10m bands should be rewritten but not normalized
+    assert item["assets"]["B01"]["href"] == "https://bucket.s3.endpoint.io/output.zarr/r10m/b01"
+    assert item["assets"]["B02"]["href"] == "https://bucket.s3.endpoint.io/output.zarr/r10m/b02"
+
+    # r60m bands should be normalized with /0/ inserted
+    assert item["assets"]["B08A"]["href"] == "https://bucket.s3.endpoint.io/output.zarr/r60m/0/b08a"
+
+
+def test_http_error():
+    """Test HTTP error handling."""
+    with (
+        patch("scripts.create_geozarr_item.httpx.get", side_effect=Exception("Failed")),
+        pytest.raises(Exception, match="Failed"),
+    ):
+        create_geozarr_item(
+            "https://stac/items/test",
+            "col",
+            "s3://bucket/data.zarr",
+            "https://s3",
+            "/tmp/out.json",
+        )
+
+
+def test_main(tmp_path, mock_httpx_and_validation):
+    """Test main() CLI."""
+    output = tmp_path / "item.json"
+
+    with patch(
+        "sys.argv",
+        [
+            "create_geozarr_item.py",
+            "--source-url",
+            "https://stac/items/test",
+            "--collection",
+            "col",
+            "--geozarr-url",
+            "s3://bucket/output.zarr",
+            "--s3-endpoint",
+            "https://s3.io",
+            "--output",
+            str(output),
+        ],
+    ):
+        main()
+
+    assert output.exists()
diff --git a/tests/unit/test_get_conversion_params.py b/tests/unit/test_get_conversion_params.py
new file mode 100644
index 0000000..fe33599
--- /dev/null
+++ b/tests/unit/test_get_conversion_params.py
@@ -0,0 +1,68 @@
+"""Tests for get_conversion_params.py - Collection parameter lookup."""
+
+import json
+
+from scripts.get_conversion_params import get_conversion_params, main
+
+
+class TestGetConversionParams:
+    """Test parameter lookup logic."""
+
+    def test_sentinel_2_exact(self):
+        """Sentinel-2 collection returns S2 config."""
+        params = get_conversion_params("sentinel-2-l2a")
+        assert params["groups"] == "/quality/l2a_quicklook/r10m"
+        assert "--crs-groups" in params["extra_flags"]
+        assert params["spatial_chunk"] == 4096
+        assert params["tile_width"] == 512
+
+    def test_sentinel_2_with_suffix(self):
+        """Sentinel-2 with suffix matches."""
+        params = get_conversion_params("sentinel-2-l2a-dp-test")
+        assert params["groups"] == "/quality/l2a_quicklook/r10m"
+
+    def test_sentinel_1_exact(self):
+        """Sentinel-1 collection returns S1 config."""
+        params = get_conversion_params("sentinel-1-l1-grd")
+        assert params["groups"] == "/measurements"
+        assert "--gcp-group" in params["extra_flags"]
+
+    def test_sentinel_1_with_suffix(self):
+        """Sentinel-1 with suffix matches."""
+        params = get_conversion_params("sentinel-1-l1-grd-dp-production")
+        assert params["groups"] == "/measurements"
+
+    def test_unknown_defaults_to_s2(self):
+        """Unknown collection defaults to Sentinel-2."""
+        params = get_conversion_params("sentinel-3-olci")
+        assert params["groups"] == "/quality/l2a_quicklook/r10m"
+
+    def test_case_insensitive(self):
+        """Collection matching is case-insensitive."""
+        lower = get_conversion_params("sentinel-2-l2a")
+        upper = get_conversion_params("SENTINEL-2-L2A")
+        assert lower == upper
+
+
+class TestCLI:
+    """Test command-line interface."""
+
+    def test_json_output(self, capsys):
+        """JSON format outputs valid JSON."""
+        main(["--collection", "sentinel-2-l2a", "--format", "json"])
+        output = capsys.readouterr().out
+        params = json.loads(output)
+        assert params["groups"] == "/quality/l2a_quicklook/r10m"
+
+    def test_shell_output(self, capsys):
+        """Shell format outputs environment variables."""
+        main(["--collection", "sentinel-1-l1-grd"])
+        output = capsys.readouterr().out
+        assert "ZARR_GROUPS='/measurements'" in output
+        assert "CHUNK=4096" in output
+
+    def test_single_param(self, capsys):
+        """Single parameter extraction."""
+        main(["--collection", "sentinel-2-l2a", "--param", "groups"])
+        output = capsys.readouterr().out.strip()
+        assert output == "/quality/l2a_quicklook/r10m"
diff --git a/tests/unit/test_register_stac.py b/tests/unit/test_register_stac.py
new file mode 100644
index 0000000..a71e290
--- /dev/null
+++ b/tests/unit/test_register_stac.py
@@ -0,0 +1,241 @@
+"""Unit tests for register_stac.py (simplified implementation)."""
+
+import json
+
+import pytest
+
+from scripts.register_stac import main, register_item
+
+
+@pytest.fixture
+def valid_stac_item():
+    """Minimal valid STAC item for testing."""
+    return {
+        "type": "Feature",
+        "stac_version": "1.0.0",
+        "id": "test-item-123",
+        "geometry": {
+            "type": "Polygon",
+            "coordinates": [[[0, 0], [1, 0], [1, 1], [0, 1], [0, 0]]],
+        },
+        "bbox": [0, 0, 1, 1],
+        "properties": {"datetime": "2025-01-01T00:00:00Z"},
+        "links": [],
+        "assets": {
+            "data": {
+                "href": "s3://bucket/data.zarr",
+                "type": "application/vnd+zarr",
+            }
+        },
+    }
+
+
+def test_register_item_create_new(mocker, valid_stac_item):
+    """Test register_item creates new item when it doesn't exist."""
+    # Mock STAC client
+    mock_client = mocker.Mock()
+    mock_collection = mocker.Mock()
+    mock_collection.get_item.side_effect = Exception("Not found")
+    mock_client.get_collection.return_value = mock_collection
+
+    # Mock StacApiIO session for POST
+    mock_response = mocker.Mock()
+    mock_response.status_code = 201
+    mock_session = mocker.Mock()
+    mock_session.post.return_value = mock_response
+    mock_client._stac_io.session = mock_session
+    mock_client._stac_io.timeout = 30
+
+    # Patch Client class
+    mock_client_class = mocker.patch("pystac_client.Client")
+    mock_client_class.open.return_value = mock_client
+
+    register_item(
+        stac_url="http://stac.example.com",
+        collection_id="test-collection",
+        item_dict=valid_stac_item,
+        mode="create-or-skip",
+    )
+
+    # Verify POST was called
+    mock_session.post.assert_called_once()
+
+
+def test_register_item_skip_existing(mocker, valid_stac_item):
+    """Test register_item skips existing item in create-or-skip mode."""
+    # Mock existing item
+    mock_client = mocker.Mock()
+    mock_collection = mocker.Mock()
+    mock_collection.get_item.return_value = mocker.Mock()  # Item exists
+    mock_client.get_collection.return_value = mock_collection
+    mock_client.add_item = mocker.Mock()
+
+    # Patch Client class - this is production-grade pytest-mock
+    mock_client_class = mocker.patch("pystac_client.Client")
+    mock_client_class.open.return_value = mock_client
+
+    register_item(
+        stac_url="http://stac.example.com",
+        collection_id="test-collection",
+        item_dict=valid_stac_item,
+        mode="create-or-skip",
+    )
+
+    # Verify item was NOT added
+    mock_client.add_item.assert_not_called()
+    # Verify skip metric recorded
+
+
+def test_register_item_upsert_mode(mocker, valid_stac_item):
+    """Test register_item replaces existing item in upsert mode."""
+    # Mock existing item
+    mock_client = mocker.Mock()
+    mock_collection = mocker.Mock()
+    mock_collection.get_item.return_value = mocker.Mock()  # Item exists
+    mock_client.get_collection.return_value = mock_collection
+
+    # Mock StacApiIO session for DELETE and POST
+    mock_delete_response = mocker.Mock()
+    mock_delete_response.status_code = 204
+    mock_post_response = mocker.Mock()
+    mock_post_response.status_code = 201
+    mock_session = mocker.Mock()
+    mock_session.delete.return_value = mock_delete_response
+    mock_session.post.return_value = mock_post_response
+    mock_client._stac_io.session = mock_session
+    mock_client._stac_io.timeout = 30
+
+    # Patch Client class
+    mock_client_class = mocker.patch("pystac_client.Client")
+    mock_client_class.open.return_value = mock_client
+
+    register_item(
+        stac_url="http://stac.example.com",
+        collection_id="test-collection",
+        item_dict=valid_stac_item,
+        mode="upsert",
+    )
+
+    # Verify item was deleted then created via POST
+    mock_session.delete.assert_called_once()
+    mock_session.post.assert_called_once()
+    # Verify replace metric recorded
+
+
+def test_main_reads_item_from_file(mocker, tmp_path, valid_stac_item):
+    """Test main() reads item from JSON file."""
+    # Write test item to file
+    item_file = tmp_path / "item.json"
+    item_file.write_text(json.dumps(valid_stac_item))
+
+    mock_register = mocker.patch("scripts.register_stac.register_item")
+    mocker.patch(
+        "sys.argv",
+        [
+            "register_stac.py",
+            "--stac-api",
+            "http://stac.example.com",
+            "--collection",
+            "test-collection",
+            "--item-json",
+            str(item_file),
+            "--mode",
+            "create-or-skip",
+        ],
+    )
+
+    main()
+
+    # Verify register_item was called with correct args
+    mock_register.assert_called_once()
+    call_args = mock_register.call_args
+    assert call_args[0][0] == "http://stac.example.com"
+    assert call_args[0][1] == "test-collection"
+    assert call_args[0][2] == valid_stac_item
+    assert call_args[0][3] == "create-or-skip"
+
+
+def test_register_item_delete_warning(mocker, valid_stac_item):
+    """Test register_item logs warning on delete failure."""
+    # Mock existing item
+    mock_client = mocker.Mock()
+    mock_collection = mocker.Mock()
+    mock_collection.get_item.return_value = mocker.Mock()
+    mock_client.get_collection.return_value = mock_collection
+
+    # Mock DELETE failure
+    mock_delete_response = mocker.Mock()
+    mock_delete_response.status_code = 404  # Not 200 or 204
+    mock_post_response = mocker.Mock()
+    mock_post_response.status_code = 201
+    mock_session = mocker.Mock()
+    mock_session.delete.return_value = mock_delete_response
+    mock_session.post.return_value = mock_post_response
+    mock_client._stac_io.session = mock_session
+    mock_client._stac_io.timeout = 30
+
+    mock_client_class = mocker.patch("pystac_client.Client")
+    mock_client_class.open.return_value = mock_client
+
+    # Should log warning but still proceed
+    register_item(
+        stac_url="http://stac.example.com",
+        collection_id="test-col",
+        item_dict=valid_stac_item,
+        mode="upsert",
+    )
+
+
+def test_register_item_delete_exception(mocker, valid_stac_item):
+    """Test register_item handles delete exception gracefully."""
+    mock_client = mocker.Mock()
+    mock_collection = mocker.Mock()
+    mock_collection.get_item.return_value = mocker.Mock()
+    mock_client.get_collection.return_value = mock_collection
+
+    # Mock DELETE exception
+    mock_post_response = mocker.Mock()
+    mock_post_response.status_code = 201
+    mock_session = mocker.Mock()
+    mock_session.delete.side_effect = Exception("Network error")
+    mock_session.post.return_value = mock_post_response
+    mock_client._stac_io.session = mock_session
+    mock_client._stac_io.timeout = 30
+
+    mock_client_class = mocker.patch("pystac_client.Client")
+    mock_client_class.open.return_value = mock_client
+
+    # Should log warning but still proceed
+    register_item(
+        stac_url="http://stac.example.com",
+        collection_id="test-col",
+        item_dict=valid_stac_item,
+        mode="replace",
+    )
+
+
+def test_register_item_post_failure(mocker, valid_stac_item):
+    """Test register_item raises on POST failure."""
+    mock_client = mocker.Mock()
+    mock_collection = mocker.Mock()
+    mock_collection.get_item.side_effect = Exception("Not found")
+    mock_client.get_collection.return_value = mock_collection
+
+    # Mock POST failure
+    mock_session = mocker.Mock()
+    mock_session.post.side_effect = Exception("POST failed")
+    mock_client._stac_io.session = mock_session
+    mock_client._stac_io.timeout = 30
+
+    mock_client_class = mocker.patch("pystac_client.Client")
+    mock_client_class.open.return_value = mock_client
+
+    with pytest.raises(Exception, match="POST failed"):
+        register_item(
+            stac_url="http://stac.example.com",
+            collection_id="test-col",
+            item_dict=valid_stac_item,
+            mode="create-or-skip",
+        )
+
+    # Verify failure metric recorded

From f5048c65757d8b39fec196095d3046ceb4787672 Mon Sep 17 00:00:00 2001
From: Wietze <wietze.suijker@gmail.com>
Date: Thu, 23 Oct 2025 16:08:24 +0200
Subject: [PATCH 2/2] feat: multi-mission integration tests and examples

---
 examples/s1_quickstart.py                |  81 ++++++++
 scripts/test_s1_e2e.sh                   | 172 ++++++++++++++++
 tests/integration/test_pipeline_e2e.py   | 148 ++++++++++++++
 tests/unit/test_augment_stac_item.py     | 165 ----------------
 tests/unit/test_convert.py               |  54 +++++
 tests/unit/test_create_geozarr_item.py   | 149 --------------
 tests/unit/test_get_conversion_params.py |  68 -------
 tests/unit/test_register.py              | 230 +++++++++++++++++++++
 tests/unit/test_register_stac.py         | 241 -----------------------
 workflows/examples/payload-s1.json       |   5 +
 10 files changed, 690 insertions(+), 623 deletions(-)
 create mode 100644 examples/s1_quickstart.py
 create mode 100755 scripts/test_s1_e2e.sh
 create mode 100644 tests/integration/test_pipeline_e2e.py
 delete mode 100644 tests/unit/test_augment_stac_item.py
 create mode 100644 tests/unit/test_convert.py
 delete mode 100644 tests/unit/test_create_geozarr_item.py
 delete mode 100644 tests/unit/test_get_conversion_params.py
 create mode 100644 tests/unit/test_register.py
 delete mode 100644 tests/unit/test_register_stac.py
 create mode 100644 workflows/examples/payload-s1.json

diff --git a/examples/s1_quickstart.py b/examples/s1_quickstart.py
new file mode 100644
index 0000000..b3dd09b
--- /dev/null
+++ b/examples/s1_quickstart.py
@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+"""Quick S1 GRD to GeoZarr conversion example.
+
+Demonstrates end-to-end S1 pipeline:
+1. Fetch S1 item from STAC
+2. Convert to GeoZarr
+3. Register in STAC catalog
+4. Augment with preview links
+"""
+
+import subprocess
+import sys
+from pathlib import Path
+
+
+def run_s1_pipeline(
+    stac_url: str = "https://stac.core.eopf.eodc.eu",
+    item_id: str = "S1C_IW_GRDH_1SDV_20251008T163126_20251008T163151_004473_008DBA_9AB4",
+    output_dir: Path = Path("./s1_output"),
+) -> int:
+    """Run S1 GRD pipeline locally."""
+
+    output_dir.mkdir(exist_ok=True)
+    geozarr_path = output_dir / f"{item_id}_geozarr.zarr"
+
+    print(f"🛰️  Processing S1 item: {item_id}")
+
+    # Step 1: Get source URL
+    print("\n1️⃣  Fetching STAC item...")
+    cmd = [
+        "python",
+        "scripts/get_zarr_url.py",
+        f"{stac_url}/collections/sentinel-1-l1-grd/items/{item_id}",
+    ]
+    result = subprocess.run(cmd, capture_output=True, text=True, check=True)
+    source_url = result.stdout.strip()
+    print(f"   Source: {source_url}")
+
+    # Step 2: Convert to GeoZarr
+    print("\n2️⃣  Converting to GeoZarr...")
+    cmd = [
+        "eopf-geozarr",
+        "convert",
+        source_url,
+        str(geozarr_path),
+        "--groups",
+        "/measurements",
+        "--gcp-group",
+        "/conditions/gcp",
+        "--spatial-chunk",
+        "2048",
+        "--verbose",
+    ]
+    subprocess.run(cmd, check=True)
+    print(f"   ✓ Created: {geozarr_path}")
+
+    # Step 3: Validate
+    print("\n3️⃣  Validating GeoZarr...")
+    cmd = ["eopf-geozarr", "validate", str(geozarr_path)]
+    subprocess.run(cmd, check=True)
+    print("   ✓ Valid GeoZarr")
+
+    print("\n✅ S1 pipeline complete!")
+    print(f"   Output: {geozarr_path}")
+    print("\n   Next steps:")
+    print("   - Upload to S3")
+    print("   - Register in STAC catalog")
+    print("   - View in titiler-eopf")
+
+    return 0
+
+
+if __name__ == "__main__":
+    try:
+        sys.exit(run_s1_pipeline())
+    except subprocess.CalledProcessError as e:
+        print(f"\n❌ Pipeline failed: {e}", file=sys.stderr)
+        sys.exit(1)
+    except KeyboardInterrupt:
+        print("\n⚠️  Interrupted", file=sys.stderr)
+        sys.exit(130)
diff --git a/scripts/test_s1_e2e.sh b/scripts/test_s1_e2e.sh
new file mode 100755
index 0000000..3a53158
--- /dev/null
+++ b/scripts/test_s1_e2e.sh
@@ -0,0 +1,172 @@
+#!/bin/bash
+# Test S1 GRD end-to-end pipeline in devseed-staging namespace
+#
+# This script:
+# 1. Applies the workflow template
+# 2. Publishes an S1 test payload via AMQP
+# 3. Waits for workflow completion
+# 4. Shows logs and verifies STAC item was created
+
+set -euo pipefail
+
+# Set kubeconfig
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(dirname "$SCRIPT_DIR")"
+export KUBECONFIG="${KUBECONFIG:-$PROJECT_ROOT/.work/kubeconfig}"
+
+if [ ! -f "$KUBECONFIG" ]; then
+  echo "❌ Kubeconfig not found at: $KUBECONFIG"
+  echo "Please set KUBECONFIG environment variable or create .work/kubeconfig"
+  exit 1
+fi
+
+NAMESPACE="${NAMESPACE:-devseed-staging}"
+PAYLOAD_FILE="${PAYLOAD_FILE:-workflows/examples/payload-s1.json}"
+TIMEOUT="${TIMEOUT:-600}"  # 10 minutes
+
+echo "=========================================="
+echo "S1 GRD Pipeline E2E Test"
+echo "=========================================="
+echo "Kubeconfig: $KUBECONFIG"
+echo "Namespace: $NAMESPACE"
+echo "Payload: $PAYLOAD_FILE"
+echo "Timeout: ${TIMEOUT}s"
+echo ""
+
+# Step 1: Apply workflow template
+echo "📝 Applying workflow template..."
+kubectl -n "$NAMESPACE" apply -f workflows/template.yaml
+echo "✅ Template applied"
+echo ""
+
+# Step 2: Publish AMQP message
+echo "📤 Publishing test payload..."
+kubectl -n "$NAMESPACE" delete job amqp-publish-once --ignore-not-found=true
+kubectl -n "$NAMESPACE" delete configmap amqp-payload --ignore-not-found=true
+kubectl -n "$NAMESPACE" create configmap amqp-payload --from-file=body.json="$PAYLOAD_FILE"
+kubectl -n "$NAMESPACE" apply -f workflows/amqp-publish-once.yaml
+echo "⏳ Waiting for publish job..."
+kubectl -n "$NAMESPACE" wait --for=condition=complete --timeout=120s job/amqp-publish-once
+echo "✅ Payload published"
+echo ""
+
+# Step 3: Get latest workflow
+echo "🔍 Finding triggered workflow..."
+sleep 3  # Give sensor time to create workflow
+WORKFLOW=$(kubectl -n "$NAMESPACE" get wf --sort-by=.metadata.creationTimestamp -o jsonpath='{.items[-1:].metadata.name}' 2>/dev/null || true)
+if [ -z "$WORKFLOW" ]; then
+  echo "❌ No workflow found!"
+  exit 1
+fi
+echo "✅ Workflow: $WORKFLOW"
+echo ""
+
+# Step 4: Wait for completion
+echo "⏳ Waiting for workflow completion (timeout: ${TIMEOUT}s)..."
+START_TIME=$(date +%s)
+while true; do
+  PHASE=$(kubectl -n "$NAMESPACE" get wf "$WORKFLOW" -o jsonpath='{.status.phase}' 2>/dev/null || echo "Unknown")
+  ELAPSED=$(($(date +%s) - START_TIME))
+
+  echo "  [${ELAPSED}s] Phase: $PHASE"
+
+  case "$PHASE" in
+    Succeeded)
+      echo "✅ Workflow succeeded!"
+      break
+      ;;
+    Failed|Error)
+      echo "❌ Workflow failed!"
+      break
+      ;;
+    Unknown)
+      echo "❌ Workflow disappeared!"
+      exit 1
+      ;;
+  esac
+
+  if [ $ELAPSED -ge $TIMEOUT ]; then
+    echo "⏰ Timeout reached!"
+    break
+  fi
+
+  sleep 5
+done
+echo ""
+
+# Step 5: Show workflow details
+echo "=========================================="
+echo "Workflow Details"
+echo "=========================================="
+kubectl -n "$NAMESPACE" get wf "$WORKFLOW" -o jsonpath='
+Name: {.metadata.name}
+Status: {.status.phase}
+Started: {.status.startedAt}
+Finished: {.status.finishedAt}
+Duration: {.status.estimatedDuration}
+
+Parameters:
+  source_url: {.spec.arguments.parameters[?(@.name=="source_url")].value}
+  item_id: {.spec.arguments.parameters[?(@.name=="item_id")].value}
+  collection: {.spec.arguments.parameters[?(@.name=="register_collection")].value}
+'
+echo ""
+echo ""
+
+# Step 6: Show pod logs
+echo "=========================================="
+echo "Pod Logs"
+echo "=========================================="
+PODS=$(kubectl -n "$NAMESPACE" get pods -l workflows.argoproj.io/workflow="$WORKFLOW" -o name 2>/dev/null || true)
+if [ -z "$PODS" ]; then
+  echo "⚠️  No pods found"
+else
+  for POD in $PODS; do
+    POD_NAME=$(basename "$POD")
+    TEMPLATE=$(kubectl -n "$NAMESPACE" get pod "$POD_NAME" -o jsonpath='{.metadata.labels.workflows\.argoproj\.io/template}' 2>/dev/null || echo "unknown")
+    echo ""
+    echo "--- $POD_NAME ($TEMPLATE) ---"
+    kubectl -n "$NAMESPACE" logs "$POD_NAME" --tail=100 -c main 2>/dev/null || echo "No logs available"
+  done
+fi
+echo ""
+
+# Step 7: Verify STAC item
+echo "=========================================="
+echo "STAC Item Verification"
+echo "=========================================="
+ITEM_ID=$(kubectl -n "$NAMESPACE" get wf "$WORKFLOW" -o jsonpath='{.spec.arguments.parameters[?(@.name=="item_id")].value}')
+COLLECTION=$(kubectl -n "$NAMESPACE" get wf "$WORKFLOW" -o jsonpath='{.spec.arguments.parameters[?(@.name=="register_collection")].value}')
+STAC_URL="https://api.explorer.eopf.copernicus.eu/stac/collections/$COLLECTION/items/$ITEM_ID"
+
+echo "Checking: $STAC_URL"
+ITEM_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "$STAC_URL")
+if [ "$ITEM_STATUS" = "200" ]; then
+  echo "✅ STAC item exists!"
+  echo ""
+  curl -s "$STAC_URL" | jq '{
+    id: .id,
+    collection: .collection,
+    geometry: .geometry.type,
+    assets: [.assets | keys[]],
+    links: [.links[] | select(.rel=="xyz" or .rel=="viewer" or .rel=="tilejson") | {rel, href}]
+  }'
+else
+  echo "❌ STAC item not found (HTTP $ITEM_STATUS)"
+fi
+echo ""
+
+echo "=========================================="
+echo "Test Summary"
+echo "=========================================="
+echo "Workflow: $WORKFLOW"
+echo "Status: $PHASE"
+echo "STAC Item: $ITEM_STATUS"
+echo ""
+if [ "$PHASE" = "Succeeded" ] && [ "$ITEM_STATUS" = "200" ]; then
+  echo "🎉 END-TO-END TEST PASSED!"
+  exit 0
+else
+  echo "❌ END-TO-END TEST FAILED"
+  exit 1
+fi
diff --git a/tests/integration/test_pipeline_e2e.py b/tests/integration/test_pipeline_e2e.py
new file mode 100644
index 0000000..1013025
--- /dev/null
+++ b/tests/integration/test_pipeline_e2e.py
@@ -0,0 +1,148 @@
+"""Integration tests for end-to-end pipeline flow.
+
+Tests the full workflow:
+1. Extract metadata from source Zarr
+2. Register GeoZarr to STAC API
+3. Augment item with preview links
+4. Validate final STAC item
+"""
+
+from unittest.mock import Mock, patch
+
+import pytest
+
+
+@pytest.mark.integration
+def test_s3_url_conversion():
+    """Test S3 URL to HTTPS conversion."""
+    from scripts.register import s3_to_https
+
+    # Test S3 URL conversion
+    s3_url = "s3://eopf-bucket/geozarr/S2A_test.zarr"
+    https_url = s3_to_https(s3_url, "https://s3.gra.cloud.ovh.net")
+
+    assert https_url.startswith("https://")
+    assert "eopf-bucket" in https_url
+    assert "s3.gra.cloud.ovh.net" in https_url
+
+    # Test already HTTPS URL (should pass through)
+    https_input = "https://example.com/data.zarr"
+    result = s3_to_https(https_input, "https://s3.example.com")
+    assert result == https_input
+
+
+@pytest.fixture
+def sample_sentinel1_item():
+    """Sentinel-1 GRD test item."""
+    return {
+        "type": "Feature",
+        "stac_version": "1.0.0",
+        "id": "S1A_IW_GRDH_1SDV_20250518T120000",
+        "collection": "sentinel-1-l1-grd",
+        "geometry": {
+            "type": "Polygon",
+            "coordinates": [[[10.0, 50.0], [10.0, 51.0], [12.0, 51.0], [12.0, 50.0], [10.0, 50.0]]],
+        },
+        "properties": {
+            "datetime": "2025-05-18T12:00:00Z",
+            "platform": "sentinel-1a",
+            "instruments": ["c-sar"],
+            "sar:instrument_mode": "IW",
+            "sar:polarizations": ["VV", "VH"],
+        },
+        "assets": {
+            "vh": {
+                "href": "s3://bucket/s1.zarr/S01SIWGRD_20250518_VH/measurements",
+                "type": "application/vnd+zarr",
+                "roles": ["data"],
+            },
+            "vv": {
+                "href": "s3://bucket/s1.zarr/S01SIWGRD_20250518_VV/measurements",
+                "type": "application/vnd+zarr",
+                "roles": ["data"],
+            },
+        },
+        "links": [],
+    }
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize(
+    "collection_id,item_fixture",
+    [
+        ("sentinel-2-l2a", "sample_stac_item"),
+        ("sentinel-1-l1-grd", "sample_sentinel1_item"),
+    ],
+)
+def test_multi_mission_registration(collection_id, item_fixture, request):
+    """Test registration workflow for multiple missions (S1, S2)."""
+    from pystac import Item
+
+    from scripts.register import upsert_item
+
+    item_dict = request.getfixturevalue(item_fixture)
+    item = Item.from_dict(item_dict)
+
+    with patch("pystac_client.Client") as mock_client_class:
+        mock_client = Mock()
+        mock_client.self_href = "https://stac.example.com/stac"
+        mock_response = Mock()
+        mock_response.status_code = 201
+        mock_response.raise_for_status = Mock()
+        mock_client._stac_io.session.post = Mock(return_value=mock_response)
+        mock_client_class.return_value = mock_client
+
+        upsert_item(
+            client=mock_client,
+            collection_id=collection_id,
+            item=item,
+        )
+
+        assert mock_client._stac_io.session.post.called
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize(
+    "mission,expected_has_group,expected_sharding",
+    [
+        ("sentinel-2", "/quality/l2a_quicklook/r10m", True),
+        ("sentinel-1", "/measurements", False),
+    ],
+)
+def test_collection_parameter_dispatch(mission, expected_has_group, expected_sharding):
+    """Test mission-based parameter dispatch from CONFIGS."""
+    from scripts.convert import CONFIGS
+
+    assert mission in CONFIGS, f"Mission {mission} not found in CONFIGS"
+
+    config = CONFIGS[mission]
+
+    # Check that expected group is in the groups list
+    assert expected_has_group in config["groups"]
+
+    # Verify sharding configuration matches mission
+    assert config["enable_sharding"] is expected_sharding
+
+    # S2 should have 4 groups, S1 should have 1
+    if mission == "sentinel-2":
+        assert len(config["groups"]) == 4
+        assert config["spatial_chunk"] == 1024
+        assert config["tile_width"] == 256
+    elif mission == "sentinel-1":
+        assert len(config["groups"]) == 1
+        assert config["spatial_chunk"] == 4096
+        assert config["tile_width"] == 512
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize(
+    "collection_id,item_id,expected_substring",
+    [
+        ("sentinel-2-l2a", "S2B_MSIL2A_20250518_T29RLL", "sentinel-2-l2a"),
+        ("sentinel-1-l1-grd", "S1A_IW_GRDH_1SDV_20250518", "sentinel-1-l1-grd"),
+    ],
+)
+def test_collection_aware_output_paths(collection_id, item_id, expected_substring):
+    """Test that output paths include collection ID for multi-mission organization."""
+    output_path = f"s3://bucket/{collection_id}/{item_id}.zarr"
+    assert expected_substring in output_path
diff --git a/tests/unit/test_augment_stac_item.py b/tests/unit/test_augment_stac_item.py
deleted file mode 100644
index 840fed8..0000000
--- a/tests/unit/test_augment_stac_item.py
+++ /dev/null
@@ -1,165 +0,0 @@
-"""Unit tests for augment_stac_item.py."""
-
-from datetime import UTC, datetime
-from unittest.mock import MagicMock, patch
-
-import pytest
-from pystac import Asset, Item
-
-from scripts.augment_stac_item import add_projection, add_visualization, augment, main
-
-
-@pytest.fixture
-def item():
-    """Create test STAC item."""
-    return Item("test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={})
-
-
-@pytest.fixture
-def mock_httpx_success():
-    """Mock successful httpx requests."""
-    with patch("scripts.augment_stac_item.httpx.Client") as mock_client:
-        mock_ctx = MagicMock()
-        mock_response = MagicMock()
-        mock_response.status_code = 200
-        mock_ctx.get.return_value = mock_response
-        mock_ctx.put.return_value = mock_response
-        mock_client.return_value.__enter__.return_value = mock_ctx
-        mock_client.return_value.__exit__.return_value = None
-        yield mock_ctx
-
-
-def test_add_projection_extracts_epsg(item):
-    """Test projection extraction from zarr."""
-    item.add_asset("product", Asset(href="s3://test.zarr", media_type="application/vnd+zarr"))
-
-    mock_store = MagicMock()
-    # The actual code reads spatial_ref dict which contains "spatial_ref" key with EPSG value
-    mock_store.attrs.get.return_value = {"spatial_ref": "32632", "crs_wkt": "PROJCS[...]"}
-
-    with patch("scripts.augment_stac_item.zarr.open", return_value=mock_store):
-        add_projection(item)
-
-    # Projection extension sets proj:code based on EPSG
-    assert (
-        item.properties.get("proj:code") == "EPSG:32632"
-        or item.properties.get("proj:epsg") == 32632
-    )
-    assert "proj:wkt2" in item.properties
-
-
-def test_add_projection_handles_errors(item):
-    """Test add_projection error handling."""
-    item.add_asset("product", Asset(href="s3://test.zarr", media_type="application/vnd+zarr"))
-    with patch("scripts.augment_stac_item.zarr.open", side_effect=Exception):
-        add_projection(item)  # Should not raise
-        assert "proj:epsg" not in item.properties
-
-
-def test_add_projection_no_zarr_assets(item):
-    """Test add_projection with no zarr assets."""
-    add_projection(item)
-    assert "proj:epsg" not in item.properties
-
-
-@pytest.mark.parametrize(
-    "collection,expected_asset",
-    [
-        ("sentinel-2-l2a", "TCI_10m"),
-    ],
-)
-def test_add_visualization(item, collection, expected_asset):
-    """Test visualization links for S1/S2."""
-    add_visualization(item, "https://raster.api", collection)
-
-    links = {link.rel: link for link in item.links}
-    assert all(rel in links for rel in ["viewer", "xyz", "tilejson", "via"])
-
-    # Verify asset in xyz URL
-    assert expected_asset in links["xyz"].href
-
-    # Verify proper URL encoding (/ should be %2F, : should be %3A)
-    assert "%2F" in links["xyz"].href  # Forward slashes are encoded
-    assert "%3A" in links["xyz"].href  # Colons are encoded
-
-    # Verify titles are present
-    assert links["xyz"].title is not None
-    assert links["tilejson"].title is not None
-    assert links["viewer"].title is not None
-
-
-def test_augment_verbose(item):
-    """Test augment with verbose output."""
-    with (
-        patch("scripts.augment_stac_item.add_projection"),
-        patch("scripts.augment_stac_item.add_visualization"),
-        patch("builtins.print") as mock_print,
-    ):
-        augment(item, raster_base="https://api", collection_id="col", verbose=True)
-        mock_print.assert_called_once()
-
-
-def test_main_success(mock_httpx_success):
-    """Test main() success flow."""
-    item_dict = Item(
-        "test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={}
-    ).to_dict()
-    item_dict["collection"] = "test-col"
-    mock_httpx_success.get.return_value.json.return_value = item_dict
-
-    with patch("scripts.augment_stac_item.augment") as mock_aug:
-        mock_aug.return_value = Item.from_dict(item_dict)
-        exit_code = main(
-            ["--stac", "https://stac", "--collection", "test-col", "--item-id", "test"]
-        )
-
-    assert exit_code == 0
-
-
-def test_main_get_failure():
-    """Test main() GET failure."""
-    with patch("scripts.augment_stac_item.httpx.Client") as mock:
-        mock.return_value.__enter__.return_value.get.side_effect = Exception("Failed")
-        exit_code = main(["--stac", "https://stac", "--collection", "col", "--item-id", "test"])
-
-    assert exit_code == 1
-
-
-def test_main_put_failure(mock_httpx_success):
-    """Test main() PUT failure."""
-    item_dict = Item(
-        "test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={}
-    ).to_dict()
-    mock_httpx_success.get.return_value.json.return_value = item_dict
-    mock_httpx_success.put.side_effect = Exception("Failed")
-
-    with patch("scripts.augment_stac_item.augment", return_value=Item.from_dict(item_dict)):
-        exit_code = main(["--stac", "https://stac", "--collection", "col", "--item-id", "test"])
-
-    assert exit_code == 1
-
-
-def test_main_with_bearer_token(mock_httpx_success):
-    """Test main() with bearer token."""
-    item_dict = Item(
-        "test", geometry=None, bbox=None, datetime=datetime.now(UTC), properties={}
-    ).to_dict()
-    item_dict["collection"] = "col"
-    mock_httpx_success.get.return_value.json.return_value = item_dict
-
-    with patch("scripts.augment_stac_item.augment", return_value=Item.from_dict(item_dict)):
-        main(
-            [
-                "--stac",
-                "https://stac",
-                "--collection",
-                "col",
-                "--item-id",
-                "test",
-                "--bearer",
-                "token",
-            ]
-        )
-
-    call = mock_httpx_success.get.call_args
-    assert call.kwargs["headers"]["Authorization"] == "Bearer token"
diff --git a/tests/unit/test_convert.py b/tests/unit/test_convert.py
new file mode 100644
index 0000000..5c54864
--- /dev/null
+++ b/tests/unit/test_convert.py
@@ -0,0 +1,54 @@
+"""Unit tests for convert.py - GeoZarr conversion configuration."""
+
+from scripts.convert import CONFIGS
+
+
+class TestConversionConfigs:
+    """Test conversion configuration dictionaries."""
+
+    def test_s2_config_has_all_groups(self):
+        """Verify S2 config includes all 4 required groups."""
+        s2 = CONFIGS["sentinel-2"]
+        assert len(s2["groups"]) == 4
+        assert "/measurements/reflectance/r10m" in s2["groups"]
+        assert "/measurements/reflectance/r20m" in s2["groups"]
+        assert "/measurements/reflectance/r60m" in s2["groups"]
+        assert "/quality/l2a_quicklook/r10m" in s2["groups"]
+
+    def test_s2_config_has_crs_groups(self):
+        """Verify S2 config includes CRS groups."""
+        s2 = CONFIGS["sentinel-2"]
+        assert s2["crs_groups"] == ["/conditions/geometry"]
+
+    def test_s2_config_optimized_chunks(self):
+        """Verify S2 config has optimized chunk and tile sizes."""
+        s2 = CONFIGS["sentinel-2"]
+        assert s2["spatial_chunk"] == 1024
+        assert s2["tile_width"] == 256
+        assert s2["enable_sharding"] is True
+
+    def test_s1_config_structure(self):
+        """Verify S1 GRD config structure."""
+        s1 = CONFIGS["sentinel-1"]
+        assert s1["groups"] == ["/measurements"]
+        assert s1["crs_groups"] == ["/conditions/gcp"]
+        assert s1["spatial_chunk"] == 4096
+        assert s1["tile_width"] == 512
+        assert s1["enable_sharding"] is False
+
+    def test_both_missions_present(self):
+        """Verify both mission configs exist."""
+        assert "sentinel-1" in CONFIGS
+        assert "sentinel-2" in CONFIGS
+
+    def test_config_keys_consistent(self):
+        """Verify all configs have consistent keys."""
+        required_keys = {
+            "groups",
+            "crs_groups",
+            "spatial_chunk",
+            "tile_width",
+            "enable_sharding",
+        }
+        for mission, config in CONFIGS.items():
+            assert set(config.keys()) == required_keys, f"{mission} missing required keys"
diff --git a/tests/unit/test_create_geozarr_item.py b/tests/unit/test_create_geozarr_item.py
deleted file mode 100644
index 5f771f4..0000000
--- a/tests/unit/test_create_geozarr_item.py
+++ /dev/null
@@ -1,149 +0,0 @@
-"""Unit tests for create_geozarr_item.py."""
-
-import json
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from scripts.create_geozarr_item import (
-    create_geozarr_item,
-    find_source_zarr_base,
-    main,
-    normalize_asset_href,
-    s3_to_https,
-)
-
-
-@pytest.fixture
-def source_item():
-    """Valid source STAC item with band assets."""
-    return {
-        "type": "Feature",
-        "stac_version": "1.0.0",
-        "id": "test-item",
-        "geometry": {"type": "Polygon", "coordinates": [[[0, 0], [1, 0], [1, 1], [0, 1], [0, 0]]]},
-        "bbox": [0, 0, 1, 1],
-        "properties": {"datetime": "2025-01-01T00:00:00Z"},
-        "collection": "source-col",
-        "links": [],
-        "assets": {
-            "B01": {"href": "s3://source/data.zarr/r10m/b01", "type": "image/tiff"},
-            "B02": {"href": "s3://source/data.zarr/r10m/b02", "type": "image/tiff"},
-            "B08A": {"href": "s3://source/data.zarr/r60m/b08a", "type": "image/tiff"},
-        },
-    }
-
-
-@pytest.fixture
-def mock_httpx_and_validation(source_item):
-    """Mock httpx (validation removed from create_geozarr_item)."""
-    with patch("scripts.create_geozarr_item.httpx.get") as mock_get:
-        mock_get.return_value = MagicMock(json=lambda: source_item)
-        yield mock_get
-
-
-def test_s3_to_https():
-    """Test S3 URL conversion."""
-    assert (
-        s3_to_https("s3://bucket/path/file.zarr", "https://s3.io")
-        == "https://bucket.s3.io/path/file.zarr"
-    )
-    assert s3_to_https("https://already/https", "https://s3.io") == "https://already/https"
-
-
-def test_normalize_asset_href():
-    """Test asset href normalization for r60m bands."""
-    # r60m bands need /0/ inserted
-    assert (
-        normalize_asset_href("s3://bucket/data.zarr/r60m/b08a")
-        == "s3://bucket/data.zarr/r60m/0/b08a"
-    )
-    # Already has /0/
-    assert (
-        normalize_asset_href("s3://bucket/data.zarr/r60m/0/b08a")
-        == "s3://bucket/data.zarr/r60m/0/b08a"
-    )
-    # r10m/r20m don't need changes
-    assert (
-        normalize_asset_href("s3://bucket/data.zarr/r10m/b02") == "s3://bucket/data.zarr/r10m/b02"
-    )
-
-
-def test_find_source_zarr_base():
-    """Test finding Zarr base URL from assets."""
-    item = {
-        "assets": {
-            "B01": {"href": "s3://bucket/data.zarr/r10m/b01"},
-            "B02": {"href": "s3://bucket/data.zarr/r10m/b02"},
-        }
-    }
-    assert find_source_zarr_base(item) == "s3://bucket/data.zarr"
-    assert find_source_zarr_base({"assets": {}}) is None
-
-
-def test_create_geozarr_item_rewrites_assets(tmp_path, mock_httpx_and_validation):
-    """Test that asset hrefs are rewritten to point to GeoZarr output."""
-    output = tmp_path / "item.json"
-
-    create_geozarr_item(
-        "https://stac.api/items/test",
-        "geozarr-col",
-        "s3://bucket/output.zarr",
-        "https://s3.endpoint.io",
-        str(output),
-    )
-
-    item = json.loads(output.read_text())
-    assert item["collection"] == "geozarr-col"
-
-    # Check that band assets were rewritten
-    assert "B01" in item["assets"]
-    assert "B02" in item["assets"]
-    assert "B08A" in item["assets"]
-
-    # r10m bands should be rewritten but not normalized
-    assert item["assets"]["B01"]["href"] == "https://bucket.s3.endpoint.io/output.zarr/r10m/b01"
-    assert item["assets"]["B02"]["href"] == "https://bucket.s3.endpoint.io/output.zarr/r10m/b02"
-
-    # r60m bands should be normalized with /0/ inserted
-    assert item["assets"]["B08A"]["href"] == "https://bucket.s3.endpoint.io/output.zarr/r60m/0/b08a"
-
-
-def test_http_error():
-    """Test HTTP error handling."""
-    with (
-        patch("scripts.create_geozarr_item.httpx.get", side_effect=Exception("Failed")),
-        pytest.raises(Exception, match="Failed"),
-    ):
-        create_geozarr_item(
-            "https://stac/items/test",
-            "col",
-            "s3://bucket/data.zarr",
-            "https://s3",
-            "/tmp/out.json",
-        )
-
-
-def test_main(tmp_path, mock_httpx_and_validation):
-    """Test main() CLI."""
-    output = tmp_path / "item.json"
-
-    with patch(
-        "sys.argv",
-        [
-            "create_geozarr_item.py",
-            "--source-url",
-            "https://stac/items/test",
-            "--collection",
-            "col",
-            "--geozarr-url",
-            "s3://bucket/output.zarr",
-            "--s3-endpoint",
-            "https://s3.io",
-            "--output",
-            str(output),
-        ],
-    ):
-        main()
-
-    assert output.exists()
diff --git a/tests/unit/test_get_conversion_params.py b/tests/unit/test_get_conversion_params.py
deleted file mode 100644
index fe33599..0000000
--- a/tests/unit/test_get_conversion_params.py
+++ /dev/null
@@ -1,68 +0,0 @@
-"""Tests for get_conversion_params.py - Collection parameter lookup."""
-
-import json
-
-from scripts.get_conversion_params import get_conversion_params, main
-
-
-class TestGetConversionParams:
-    """Test parameter lookup logic."""
-
-    def test_sentinel_2_exact(self):
-        """Sentinel-2 collection returns S2 config."""
-        params = get_conversion_params("sentinel-2-l2a")
-        assert params["groups"] == "/quality/l2a_quicklook/r10m"
-        assert "--crs-groups" in params["extra_flags"]
-        assert params["spatial_chunk"] == 4096
-        assert params["tile_width"] == 512
-
-    def test_sentinel_2_with_suffix(self):
-        """Sentinel-2 with suffix matches."""
-        params = get_conversion_params("sentinel-2-l2a-dp-test")
-        assert params["groups"] == "/quality/l2a_quicklook/r10m"
-
-    def test_sentinel_1_exact(self):
-        """Sentinel-1 collection returns S1 config."""
-        params = get_conversion_params("sentinel-1-l1-grd")
-        assert params["groups"] == "/measurements"
-        assert "--gcp-group" in params["extra_flags"]
-
-    def test_sentinel_1_with_suffix(self):
-        """Sentinel-1 with suffix matches."""
-        params = get_conversion_params("sentinel-1-l1-grd-dp-production")
-        assert params["groups"] == "/measurements"
-
-    def test_unknown_defaults_to_s2(self):
-        """Unknown collection defaults to Sentinel-2."""
-        params = get_conversion_params("sentinel-3-olci")
-        assert params["groups"] == "/quality/l2a_quicklook/r10m"
-
-    def test_case_insensitive(self):
-        """Collection matching is case-insensitive."""
-        lower = get_conversion_params("sentinel-2-l2a")
-        upper = get_conversion_params("SENTINEL-2-L2A")
-        assert lower == upper
-
-
-class TestCLI:
-    """Test command-line interface."""
-
-    def test_json_output(self, capsys):
-        """JSON format outputs valid JSON."""
-        main(["--collection", "sentinel-2-l2a", "--format", "json"])
-        output = capsys.readouterr().out
-        params = json.loads(output)
-        assert params["groups"] == "/quality/l2a_quicklook/r10m"
-
-    def test_shell_output(self, capsys):
-        """Shell format outputs environment variables."""
-        main(["--collection", "sentinel-1-l1-grd"])
-        output = capsys.readouterr().out
-        assert "ZARR_GROUPS='/measurements'" in output
-        assert "CHUNK=4096" in output
-
-    def test_single_param(self, capsys):
-        """Single parameter extraction."""
-        main(["--collection", "sentinel-2-l2a", "--param", "groups"])
-        output = capsys.readouterr().out.strip()
-        assert output == "/quality/l2a_quicklook/r10m"
diff --git a/tests/unit/test_register.py b/tests/unit/test_register.py
new file mode 100644
index 0000000..ecbe229
--- /dev/null
+++ b/tests/unit/test_register.py
@@ -0,0 +1,230 @@
+"""Unit tests for register.py - STAC registration and augmentation."""
+
+from unittest.mock import MagicMock, patch
+
+from pystac import Asset, Item
+from pystac.extensions.projection import ProjectionExtension
+
+from scripts.register import (
+    add_projection_from_zarr,
+    add_visualization_links,
+    rewrite_asset_hrefs,
+    s3_to_https,
+)
+
+
+class TestS3URLConversion:
+    """Test S3 URL to HTTPS conversion."""
+
+    def test_s3_to_https_conversion(self):
+        """Test basic S3 to HTTPS conversion."""
+        result = s3_to_https("s3://bucket/path/file.zarr", "https://s3.example.com")
+        assert result == "https://bucket.s3.example.com/path/file.zarr"
+
+    def test_s3_to_https_with_trailing_slash(self):
+        """Test S3 conversion with trailing slash in endpoint."""
+        result = s3_to_https("s3://bucket/file.zarr", "https://s3.example.com/")
+        assert result == "https://bucket.s3.example.com/file.zarr"
+
+    def test_s3_to_https_already_https(self):
+        """Test that HTTPS URLs are returned unchanged."""
+        https_url = "https://example.com/data.zarr"
+        result = s3_to_https(https_url, "https://s3.example.com")
+        assert result == https_url
+
+
+class TestAssetRewriting:
+    """Test asset href rewriting."""
+
+    def test_rewrite_asset_hrefs(self):
+        """Test asset href rewriting from old to new base."""
+        item = Item(
+            id="test",
+            geometry=None,
+            bbox=None,
+            datetime="2025-01-01T00:00:00Z",
+            properties={},
+        )
+        item.add_asset(
+            "data",
+            Asset(
+                href="s3://old-bucket/old.zarr/path/data",
+                media_type="application/vnd+zarr",
+            ),
+        )
+
+        rewrite_asset_hrefs(
+            item,
+            old_base="s3://old-bucket/old.zarr",
+            new_base="s3://new-bucket/new.zarr",
+            s3_endpoint="https://s3.example.com",
+        )
+
+        # Should rewrite to HTTPS URL with new base
+        new_href = item.assets["data"].href
+        assert new_href.startswith("https://new-bucket.s3.example.com")
+        assert "new.zarr" in new_href
+
+
+class TestProjectionExtension:
+    """Test projection extension from zarr."""
+
+    @patch("scripts.register.zarr.open")
+    def test_add_projection_from_zarr_with_spatial_ref(self, mock_zarr_open):
+        """Test adding projection extension when spatial_ref exists."""
+        # Mock zarr store with spatial_ref
+        mock_store = MagicMock()
+        mock_store.attrs = {
+            "spatial_ref": {
+                "spatial_ref": "32633",  # EPSG code
+                "crs_wkt": "PROJCS[...]",
+            }
+        }
+        mock_zarr_open.return_value = mock_store
+
+        item = Item(
+            id="test",
+            geometry=None,
+            bbox=None,
+            datetime="2025-01-01T00:00:00Z",
+            properties={},
+        )
+        item.add_asset(
+            "data",
+            Asset(
+                href="https://example.com/data.zarr",
+                media_type="application/vnd+zarr",
+            ),
+        )
+
+        add_projection_from_zarr(item)
+
+        # Should have projection extension
+        proj = ProjectionExtension.ext(item)
+        assert proj.epsg == 32633
+        assert proj.wkt2 is not None
+
+    @patch("scripts.register.zarr.open")
+    def test_add_projection_no_spatial_ref(self, mock_zarr_open):
+        """Test that function handles missing spatial_ref gracefully."""
+        # Mock zarr store without spatial_ref
+        mock_store = MagicMock()
+        mock_store.attrs = {}
+        mock_zarr_open.return_value = mock_store
+
+        item = Item(
+            id="test",
+            geometry=None,
+            bbox=None,
+            datetime="2025-01-01T00:00:00Z",
+            properties={},
+        )
+        item.add_asset(
+            "data",
+            Asset(
+                href="https://example.com/data.zarr",
+                media_type="application/vnd+zarr",
+            ),
+        )
+
+        # Should not raise an exception
+        add_projection_from_zarr(item)
+
+        # Should not have projection extension
+        assert "proj:epsg" not in item.properties
+
+
+class TestVisualizationLinks:
+    """Test visualization link generation."""
+
+    def test_add_visualization_links_s2(self):
+        """Test S2 True Color visualization links."""
+        item = Item(
+            id="S2A_MSIL2A_20250518_test",
+            geometry=None,
+            bbox=None,
+            datetime="2025-05-18T00:00:00Z",
+            properties={},
+        )
+        item.add_asset(
+            "TCI_10m",
+            Asset(
+                href="https://example.com/data.zarr/quality/l2a_quicklook/r10m",
+                media_type="application/vnd+zarr",
+            ),
+        )
+
+        add_visualization_links(
+            item,
+            raster_base="https://api.example.com/raster",
+            collection_id="sentinel-2-l2a",
+        )
+
+        # Should have viewer link
+        viewer_links = [link for link in item.links if link.rel == "viewer"]
+        assert len(viewer_links) == 1
+        assert "viewer" in viewer_links[0].href
+
+        # Should have XYZ tile link
+        xyz_links = [link for link in item.links if link.rel == "xyz"]
+        assert len(xyz_links) == 1
+        assert "tiles" in xyz_links[0].href
+
+        # Should have TileJSON link
+        tilejson_links = [link for link in item.links if link.rel == "tilejson"]
+        assert len(tilejson_links) == 1
+        assert "tilejson.json" in tilejson_links[0].href
+
+    def test_add_visualization_links_s1(self):
+        """Test S1 VH visualization links."""
+        item = Item(
+            id="S1A_IW_GRDH_test",
+            geometry=None,
+            bbox=None,
+            datetime="2025-05-18T00:00:00Z",
+            properties={},
+        )
+        item.add_asset(
+            "vh",
+            Asset(
+                href="https://example.com/data.zarr/measurements/vh",
+                media_type="application/vnd+zarr",
+            ),
+        )
+
+        add_visualization_links(
+            item,
+            raster_base="https://api.example.com/raster",
+            collection_id="sentinel-1-l1-grd",
+        )
+
+        # Should have viewer link
+        viewer_links = [link for link in item.links if link.rel == "viewer"]
+        assert len(viewer_links) == 1
+
+        # Should have XYZ tile link for VH
+        xyz_links = [link for link in item.links if link.rel == "xyz"]
+        assert len(xyz_links) == 1
+        assert "VH" in xyz_links[0].title or "vh" in xyz_links[0].href.lower()
+
+    def test_add_eopf_explorer_link(self):
+        """Test EOPF Explorer via link is added."""
+        item = Item(
+            id="test-item",
+            geometry=None,
+            bbox=None,
+            datetime="2025-01-01T00:00:00Z",
+            properties={},
+        )
+
+        add_visualization_links(
+            item,
+            raster_base="https://api.example.com/raster",
+            collection_id="sentinel-2-l2a",
+        )
+
+        # Should have via link to EOPF Explorer
+        via_links = [link for link in item.links if link.rel == "via"]
+        assert len(via_links) == 1
+        assert "explorer.eopf.copernicus.eu" in via_links[0].href
+        assert "EOPF Explorer" in via_links[0].title
diff --git a/tests/unit/test_register_stac.py b/tests/unit/test_register_stac.py
deleted file mode 100644
index a71e290..0000000
--- a/tests/unit/test_register_stac.py
+++ /dev/null
@@ -1,241 +0,0 @@
-"""Unit tests for register_stac.py (simplified implementation)."""
-
-import json
-
-import pytest
-
-from scripts.register_stac import main, register_item
-
-
-@pytest.fixture
-def valid_stac_item():
-    """Minimal valid STAC item for testing."""
-    return {
-        "type": "Feature",
-        "stac_version": "1.0.0",
-        "id": "test-item-123",
-        "geometry": {
-            "type": "Polygon",
-            "coordinates": [[[0, 0], [1, 0], [1, 1], [0, 1], [0, 0]]],
-        },
-        "bbox": [0, 0, 1, 1],
-        "properties": {"datetime": "2025-01-01T00:00:00Z"},
-        "links": [],
-        "assets": {
-            "data": {
-                "href": "s3://bucket/data.zarr",
-                "type": "application/vnd+zarr",
-            }
-        },
-    }
-
-
-def test_register_item_create_new(mocker, valid_stac_item):
-    """Test register_item creates new item when it doesn't exist."""
-    # Mock STAC client
-    mock_client = mocker.Mock()
-    mock_collection = mocker.Mock()
-    mock_collection.get_item.side_effect = Exception("Not found")
-    mock_client.get_collection.return_value = mock_collection
-
-    # Mock StacApiIO session for POST
-    mock_response = mocker.Mock()
-    mock_response.status_code = 201
-    mock_session = mocker.Mock()
-    mock_session.post.return_value = mock_response
-    mock_client._stac_io.session = mock_session
-    mock_client._stac_io.timeout = 30
-
-    # Patch Client class
-    mock_client_class = mocker.patch("pystac_client.Client")
-    mock_client_class.open.return_value = mock_client
-
-    register_item(
-        stac_url="http://stac.example.com",
-        collection_id="test-collection",
-        item_dict=valid_stac_item,
-        mode="create-or-skip",
-    )
-
-    # Verify POST was called
-    mock_session.post.assert_called_once()
-
-
-def test_register_item_skip_existing(mocker, valid_stac_item):
-    """Test register_item skips existing item in create-or-skip mode."""
-    # Mock existing item
-    mock_client = mocker.Mock()
-    mock_collection = mocker.Mock()
-    mock_collection.get_item.return_value = mocker.Mock()  # Item exists
-    mock_client.get_collection.return_value = mock_collection
-    mock_client.add_item = mocker.Mock()
-
-    # Patch Client class - this is production-grade pytest-mock
-    mock_client_class = mocker.patch("pystac_client.Client")
-    mock_client_class.open.return_value = mock_client
-
-    register_item(
-        stac_url="http://stac.example.com",
-        collection_id="test-collection",
-        item_dict=valid_stac_item,
-        mode="create-or-skip",
-    )
-
-    # Verify item was NOT added
-    mock_client.add_item.assert_not_called()
-    # Verify skip metric recorded
-
-
-def test_register_item_upsert_mode(mocker, valid_stac_item):
-    """Test register_item replaces existing item in upsert mode."""
-    # Mock existing item
-    mock_client = mocker.Mock()
-    mock_collection = mocker.Mock()
-    mock_collection.get_item.return_value = mocker.Mock()  # Item exists
-    mock_client.get_collection.return_value = mock_collection
-
-    # Mock StacApiIO session for DELETE and POST
-    mock_delete_response = mocker.Mock()
-    mock_delete_response.status_code = 204
-    mock_post_response = mocker.Mock()
-    mock_post_response.status_code = 201
-    mock_session = mocker.Mock()
-    mock_session.delete.return_value = mock_delete_response
-    mock_session.post.return_value = mock_post_response
-    mock_client._stac_io.session = mock_session
-    mock_client._stac_io.timeout = 30
-
-    # Patch Client class
-    mock_client_class = mocker.patch("pystac_client.Client")
-    mock_client_class.open.return_value = mock_client
-
-    register_item(
-        stac_url="http://stac.example.com",
-        collection_id="test-collection",
-        item_dict=valid_stac_item,
-        mode="upsert",
-    )
-
-    # Verify item was deleted then created via POST
-    mock_session.delete.assert_called_once()
-    mock_session.post.assert_called_once()
-    # Verify replace metric recorded
-
-
-def test_main_reads_item_from_file(mocker, tmp_path, valid_stac_item):
-    """Test main() reads item from JSON file."""
-    # Write test item to file
-    item_file = tmp_path / "item.json"
-    item_file.write_text(json.dumps(valid_stac_item))
-
-    mock_register = mocker.patch("scripts.register_stac.register_item")
-    mocker.patch(
-        "sys.argv",
-        [
-            "register_stac.py",
-            "--stac-api",
-            "http://stac.example.com",
-            "--collection",
-            "test-collection",
-            "--item-json",
-            str(item_file),
-            "--mode",
-            "create-or-skip",
-        ],
-    )
-
-    main()
-
-    # Verify register_item was called with correct args
-    mock_register.assert_called_once()
-    call_args = mock_register.call_args
-    assert call_args[0][0] == "http://stac.example.com"
-    assert call_args[0][1] == "test-collection"
-    assert call_args[0][2] == valid_stac_item
-    assert call_args[0][3] == "create-or-skip"
-
-
-def test_register_item_delete_warning(mocker, valid_stac_item):
-    """Test register_item logs warning on delete failure."""
-    # Mock existing item
-    mock_client = mocker.Mock()
-    mock_collection = mocker.Mock()
-    mock_collection.get_item.return_value = mocker.Mock()
-    mock_client.get_collection.return_value = mock_collection
-
-    # Mock DELETE failure
-    mock_delete_response = mocker.Mock()
-    mock_delete_response.status_code = 404  # Not 200 or 204
-    mock_post_response = mocker.Mock()
-    mock_post_response.status_code = 201
-    mock_session = mocker.Mock()
-    mock_session.delete.return_value = mock_delete_response
-    mock_session.post.return_value = mock_post_response
-    mock_client._stac_io.session = mock_session
-    mock_client._stac_io.timeout = 30
-
-    mock_client_class = mocker.patch("pystac_client.Client")
-    mock_client_class.open.return_value = mock_client
-
-    # Should log warning but still proceed
-    register_item(
-        stac_url="http://stac.example.com",
-        collection_id="test-col",
-        item_dict=valid_stac_item,
-        mode="upsert",
-    )
-
-
-def test_register_item_delete_exception(mocker, valid_stac_item):
-    """Test register_item handles delete exception gracefully."""
-    mock_client = mocker.Mock()
-    mock_collection = mocker.Mock()
-    mock_collection.get_item.return_value = mocker.Mock()
-    mock_client.get_collection.return_value = mock_collection
-
-    # Mock DELETE exception
-    mock_post_response = mocker.Mock()
-    mock_post_response.status_code = 201
-    mock_session = mocker.Mock()
-    mock_session.delete.side_effect = Exception("Network error")
-    mock_session.post.return_value = mock_post_response
-    mock_client._stac_io.session = mock_session
-    mock_client._stac_io.timeout = 30
-
-    mock_client_class = mocker.patch("pystac_client.Client")
-    mock_client_class.open.return_value = mock_client
-
-    # Should log warning but still proceed
-    register_item(
-        stac_url="http://stac.example.com",
-        collection_id="test-col",
-        item_dict=valid_stac_item,
-        mode="replace",
-    )
-
-
-def test_register_item_post_failure(mocker, valid_stac_item):
-    """Test register_item raises on POST failure."""
-    mock_client = mocker.Mock()
-    mock_collection = mocker.Mock()
-    mock_collection.get_item.side_effect = Exception("Not found")
-    mock_client.get_collection.return_value = mock_collection
-
-    # Mock POST failure
-    mock_session = mocker.Mock()
-    mock_session.post.side_effect = Exception("POST failed")
-    mock_client._stac_io.session = mock_session
-    mock_client._stac_io.timeout = 30
-
-    mock_client_class = mocker.patch("pystac_client.Client")
-    mock_client_class.open.return_value = mock_client
-
-    with pytest.raises(Exception, match="POST failed"):
-        register_item(
-            stac_url="http://stac.example.com",
-            collection_id="test-col",
-            item_dict=valid_stac_item,
-            mode="create-or-skip",
-        )
-
-    # Verify failure metric recorded
diff --git a/workflows/examples/payload-s1.json b/workflows/examples/payload-s1.json
new file mode 100644
index 0000000..9e6752e
--- /dev/null
+++ b/workflows/examples/payload-s1.json
@@ -0,0 +1,5 @@
+{
+    "source_url": "https://stac.core.eopf.eodc.eu/collections/sentinel-1-l1-grd/items/S1C_IW_GRDH_1SDV_20251008T163126_20251008T163151_004473_008DBA_9AB4",
+    "item_id": "S1C_IW_GRDH_20251008_test",
+    "collection": "sentinel-1-l1-grd-dp-test"
+}