implement scrapy + pygea job runner

tests/test_web.py

@@ -6,6 +6,7 @@ from typing import Any, cast
 
 from repub.components import status_badge
 from repub.datastar import RefreshBroker, render_sse_event, render_stream
+from repub.jobs import load_dashboard_view
 from repub.model import (
     Job,
     JobExecution,
@@ -15,6 +16,7 @@ from repub.model import (
     SourcePangea,
     create_source,
 )
+from repub.pages.runs import runs_page
 from repub.web import (
     create_app,
     get_refresh_broker,
@@ -34,6 +36,37 @@ def test_status_badge_uses_green_done_tone() -> None:
     assert "Succeeded" in badge
 
 
+def test_runs_page_renders_completed_execution_end_time_as_relative_hoverable_time() -> (
+    None
+):
+    ended_at = "2026-01-15T10:00:00+00:00"
+    body = str(
+        runs_page(
+            completed_executions=(
+                {
+                    "source": "Completed source",
+                    "slug": "completed-source",
+                    "job_id": 7,
+                    "execution_id": 42,
+                    "ended_at": "2 hours ago",
+                    "ended_at_iso": ended_at,
+                    "status": "Succeeded",
+                    "status_tone": "done",
+                    "stats": "1 requests • 1 items • 1 bytes",
+                    "summary": "Worker exited successfully",
+                    "log_href": "/job/7/execution/42/logs",
+                },
+            )
+        )
+    )
+
+    assert "data-ended-at" in body
+    assert f'data-ended-at="{ended_at}"' in body
+    assert f'datetime="{ended_at}"' in body
+    assert f'title="{ended_at}"' in body
+    assert ">2 hours ago<" in body
+
+
 def test_root_get_serves_datastar_shim() -> None:
     async def run() -> None:
         client = create_app().test_client()
@@ -179,6 +212,40 @@ def test_render_dashboard_shows_dashboard_information_architecture(
     asyncio.run(run())
 
 
+def test_load_dashboard_view_measures_log_artifact_path(
+    monkeypatch, tmp_path: Path
+) -> None:
+    db_path = tmp_path / "dashboard-footprint.db"
+    monkeypatch.setenv("REPUBLISHER_DB_PATH", str(db_path))
+    create_app()
+    out_dir = tmp_path / "out"
+    log_dir = out_dir / "logs"
+    cache_dir = out_dir / "httpcache"
+    log_dir.mkdir(parents=True)
+    cache_dir.mkdir(parents=True)
+    (log_dir / "run.log").write_bytes(b"x" * 1024)
+    (cache_dir / "cache.bin").write_bytes(b"y" * 2048)
+
+    snapshot = load_dashboard_view(log_dir=log_dir)["snapshot"]
+
+    assert cast(dict[str, str], snapshot)["artifact_footprint"] == "3.0 KB"
+
+
+def test_render_dashboard_describes_log_artifact_footprint(
+    monkeypatch, tmp_path: Path
+) -> None:
+    db_path = tmp_path / "dashboard-footprint-copy.db"
+    monkeypatch.setenv("REPUBLISHER_DB_PATH", str(db_path))
+
+    async def run() -> None:
+        app = create_app()
+        body = str(await render_dashboard(app))
+
+        assert "Current artifact size under the output path." in body
+
+    asyncio.run(run())
+
+
 def test_render_sources_shows_table_and_create_link() -> None:
     async def run() -> None:
         body = str(await render_sources())