fix: paginate official land-use workspace lookup

backend/tests/test_sprint188_official_landuse_timeseries.py

@@ -141,6 +141,41 @@ def test_official_landuse_metadata_keeps_modern_series_separate(tmp_path: Path)
     assert "historical-landuse" not in module.series_key(theme, "mol")
 
 
+def test_official_landuse_operator_paginates_within_api_limit() -> None:
+    module = load_provisioner()
+
+    class Response:
+        ok = True
+        status_code = 200
+        text = ""
+
+        def __init__(self, payload):
+            self.payload = payload
+
+        def json(self):
+            return {"data": self.payload}
+
+    class Session:
+        def __init__(self) -> None:
+            self.calls = []
+
+        def get(self, url, *, params, timeout):
+            self.calls.append((url, params, timeout))
+            offset = params["offset"]
+            page_items = [{"id": index} for index in range(offset, min(offset + 200, 405))]
+            return Response({"items": page_items, "total": 405, "limit": 200, "offset": offset})
+
+    session = Session()
+    items = module.list_paginated_items(session, "http://backend/api/v1/projects", timeout=30)
+
+    assert len(items) == 405
+    assert [call[1] for call in session.calls] == [
+        {"limit": 200, "offset": 0},
+        {"limit": 200, "offset": 200},
+        {"limit": 200, "offset": 400},
+    ]
+
+
 def test_official_landuse_operator_is_packaged_and_readiness_checked() -> None:
     readiness = (ROOT / "scripts/run_readiness_check.sh").read_text(encoding="utf-8")
     dockerfile = (ROOT / "deploy/unraid/Dockerfile.all-in-one").read_text(encoding="utf-8")

docs/CODEX_EXECUTION_LOG.md

@@ -7837,9 +7837,10 @@ Source validation:
 - Every raster cell touching the municipality is considered before exact vector clipping. The 916 NoData edge cells in each WCS subset were explicitly excluded and recorded rather than assigned a class.
 
 Validation:
-- New focused backend suite passed 4 tests.
-- Frontend TypeScript typecheck passed after temporal-series selection wiring.
-- Full readiness and live Tower/PostGIS/browser validation remain the final steps of this pass.
+- The first live import was rejected before any upload because the operator requested 500 datasets while the canonical API limit is 200. The operator now follows every 200-item page and a focused pagination regression test covers 405 records.
+- New focused backend suite passed 5 tests.
+- Full readiness passed 533 backend tests, one Alembic head, frontend TypeScript typecheck/build and all repository smoke gates.
+- Tower rebuilt successfully and passed PostGIS 3.6, migration, container health and browser-proxy validation; live data provisioning remains the final step of this pass.
 
 Next:
 - Deploy and provision all five modern snapshots on Tower, then verify current forest selection, both temporal series and a drawn rectangle in the internal browser.

scripts/provision_official_landuse_timeseries.py

@@ -585,23 +585,47 @@ def response_data(response: requests.Response) -> Any:
     return payload["data"]
 
 
+def list_paginated_items(session: requests.Session, url: str, *, timeout: int) -> list[dict[str, Any]]:
+    items: list[dict[str, Any]] = []
+    offset = 0
+    total: int | None = None
+    while total is None or offset < total:
+        page = response_data(session.get(url, params={"limit": 200, "offset": offset}, timeout=timeout))
+        page_items = page.get("items") if isinstance(page, dict) else None
+        if not isinstance(page_items, list):
+            raise RuntimeError(f"GeoIntel list response for {url} has no items array")
+        if total is None:
+            total = int(page.get("total", len(page_items)))
+        items.extend(page_items)
+        if not page_items:
+            break
+        offset += len(page_items)
+    if total is not None and len(items) != total:
+        raise RuntimeError(f"GeoIntel list response for {url} returned {len(items)} of {total} items")
+    return items
+
+
 def locate_workspace(session: requests.Session, base_url: str, args: argparse.Namespace):
-    projects = response_data(session.get(f"{base_url}/api/v1/projects", params={"limit": 200}, timeout=args.import_timeout))
-    project = next((item for item in projects.get("items") or [] if item.get("name") == args.project_name), None)
+    projects = list_paginated_items(session, f"{base_url}/api/v1/projects", timeout=args.import_timeout)
+    project = next((item for item in projects if item.get("name") == args.project_name), None)
     if not project:
         raise RuntimeError(f"Project {args.project_name!r} is missing")
     project_id = str(project["id"])
-    areas = response_data(
-        session.get(f"{base_url}/api/v1/projects/{project_id}/areas", params={"limit": 200}, timeout=args.import_timeout)
+    areas = list_paginated_items(
+        session,
+        f"{base_url}/api/v1/projects/{project_id}/areas",
+        timeout=args.import_timeout,
     )
     area_fragment = args.area_name.strip().casefold()
-    matches = [item for item in areas.get("items") or [] if area_fragment in str(item.get("name") or "").casefold()]
+    matches = [item for item in areas if area_fragment in str(item.get("name") or "").casefold()]
     if len(matches) != 1:
         raise RuntimeError(f"Expected one Area matching {args.area_name!r}, received {len(matches)}")
-    datasets = response_data(
-        session.get(f"{base_url}/api/v1/projects/{project_id}/datasets", params={"limit": 500}, timeout=args.import_timeout)
+    datasets = list_paginated_items(
+        session,
+        f"{base_url}/api/v1/projects/{project_id}/datasets",
+        timeout=args.import_timeout,
     )
-    return project_id, str(matches[0]["id"]), list(datasets.get("items") or [])
+    return project_id, str(matches[0]["id"]), datasets
 
 
 def build_source_metadata(args: argparse.Namespace, snapshot: PreparedSnapshot) -> dict[str, Any]: