feat(docker): readable names, CPU in cores and memory in bytes, failures listed with since-times (#5209)

#5209 "Docker views: readable names, CPU/memory in cores and bytes, failures
listed with since-time" (milestone 477 "UI problems first").

- A swarm task reads as its service and slot ("codex_db · 1", or the node
  for a global service), with the raw name in the title: Docker page, host
  panel, busiest widget, container detail.
- CPU reads in cores (Docker's 100% = one core), toned by its share of the
  host's CPUs from the agent's per-core series. Memory reads in bytes, against
  a limit only when one is really set (Docker reports host RAM otherwise).
- Exit 137/143 without an OOM kill is a stop, not a failure: no
  exited_nonzero, no crash-loop death, no "failed (24h)", dim exit code.
- "Failed (24h)" is a list (Docker page #failures, linked from the widget
  and the tile): plain containers by their deaths, swarm services by Swarm's
  failed tasks; a second manager's copy of a task death counts once.
- Failing swarm services lead Needs attention; services sort problems first
  with since-times on the page, the widget and the Swarm page; nodes that
  are down or drained sort first.
- Busiest widget orders by a 5-minute CPU average so the list holds still.
- Host panel: a table, problems first with what is wrong and since when;
  replaced swarm tasks hidden and counted.
- Container detail: node hostname, I/O labelled "since start", Restarts
  hidden for swarm tasks with a note on where task failures are.
- Widget names: "Docker — Services & failures", "Docker — Busiest containers".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/plugins/docker/test_docker_page.py

@@ -43,22 +43,24 @@ def test_stale_is_older_than_the_agents_window():
 async def test_a_crash_loop_comes_first_and_a_stale_row_says_so(app):
     loop = _c("api", status="restarting", exit_code=1, restart_count=7)
     old = _c("cache", scraped_at=NOW - timedelta(minutes=30), cpu_pct=95.0)
-    attention = [{"container": loop, "problems": ["restarting", "crash_looping"], "replaced": False,
+    attention = [{"container": loop, "label": "api", "problems": ["restarting", "crash_looping"], "replaced": False,
                   "since": datetime.now(timezone.utc) - timedelta(minutes=8), "stale": False}]
     groups = [{"host": None, "host_id": "h1", "host_name": "nas", "running": 1, "stopped": 1, "grouped": False,
                "subgroups": [{"label": None, "containers": [
-                   {"container": loop, "ports": [], "uptime": None, "stale": False},
-                   {"container": old, "ports": [], "uptime": "2h", "stale": True}]}]}]
+                   {"container": loop, "ports": [], "uptime": None, "stale": False,
+                    "usage": svc.usage(loop, 1, None), "exit_failed": True},
+                   {"container": old, "ports": [], "uptime": "2h", "stale": True,
+                    "usage": svc.usage(old, 1, None), "exit_failed": False}]}]}]
     async with app.test_request_context("/plugins/docker/rows"):
         page = await render_plugin_template(
             app, "docker", "docker/rows.html", attention=attention, says=svc.PROBLEM_SAYS, severity=svc.PROBLEM_SEVERITY,
             unhealthy=0, restarting=1, stale=1, host_groups=groups, swarm_services=[],
-            running=1, stopped=1, total=2)
+            running=1, stopped=1, docker_hosts=1, failures=[], failing_services=[])
     page = re.sub(r">\s+<", "><", " ".join(page.split()))
 
     card = page[page.index("Needs attention"):page.index("</section>")]
     assert '<span class="badge badge-crit">Restarting</span>' in card
-    assert 'href="/plugins/docker/container/h1/api">api</a>' in card
+    assert 'href="/plugins/docker/container/h1/api" title="api">api</a>' in card
     assert "is restarting and keeps dying · exit 1 · since <time" in card and ">8m ago</time>" in card
     assert "cache" not in card
     assert page.index("Needs attention") < page.index("<table")
@@ -66,7 +68,9 @@ async def test_a_crash_loop_comes_first_and_a_stale_row_says_so(app):
     assert '<span class="stat-tile-label">Restarting</span><span class="stat-tile-value">1</span>' in page
     assert '<span class="stat-tile-label">Stale</span><span class="stat-tile-value">1</span>' in page
     assert 'class="badge badge-warn" title="Last report' in page          # the stale row
-    assert '<span class="tone-crit">95.0%</span>' in page                  # CPU through Settings → Thresholds
+    # CPU in cores, toned by its share of the host's CPUs through Settings → Thresholds.
+    assert ('<span class="tone-crit" title="Docker counts CPU per core: 95% of one core, '
+            '95.0% of this host\'s 1 core">0.95 cores</span>') in page
     assert "history" not in page.lower() and "<svg" not in page            # no sparklines on the overview
     assert not hex_colours(page), hex_colours(page)
 
@@ -75,7 +79,8 @@ async def test_a_healthy_board_has_no_attention_card(app):
     async with app.test_request_context("/plugins/docker/rows"):
         page = await render_plugin_template(
             app, "docker", "docker/rows.html", attention=[], says=svc.PROBLEM_SAYS, severity=svc.PROBLEM_SEVERITY,
-            unhealthy=0, restarting=0, stale=0, host_groups=[], swarm_services=[], running=0, stopped=0, total=0)
+            unhealthy=0, restarting=0, stale=0, host_groups=[], swarm_services=[], running=0, stopped=0,
+            docker_hosts=0, failures=[], failing_services=[])
     assert "Needs attention</h2>" not in page and "No containers reported yet" in page
 
 
@@ -89,7 +94,7 @@ async def test_a_host_whose_docker_stopped_answering_says_so(app):
         page = await render_plugin_template(
             app, "docker", "docker/rows.html", docker_down=down, attention=[], says=svc.PROBLEM_SAYS,
             severity=svc.PROBLEM_SEVERITY, unhealthy=0, restarting=0, stale=0, host_groups=[],
-            swarm_services=[], running=0, stopped=0, total=0)
+            swarm_services=[], running=0, stopped=0, docker_hosts=0, failures=[], failing_services=[])
     page = re.sub(r">\s+<", "><", " ".join(page.split()))
     card = page[page.index("Docker not answering"):page.index("</section>")]
     assert '<span class="badge badge-warn">No Docker</span><a href="/hosts/h1">nas</a>' in card
@@ -102,5 +107,35 @@ async def test_no_card_while_every_docker_answers(app):
         page = await render_plugin_template(
             app, "docker", "docker/rows.html", docker_down=[], attention=[], says=svc.PROBLEM_SAYS,
             severity=svc.PROBLEM_SEVERITY, unhealthy=0, restarting=0, stale=0, host_groups=[],
-            swarm_services=[], running=0, stopped=0, total=0)
+            swarm_services=[], running=0, stopped=0, docker_hosts=0, failures=[], failing_services=[])
     assert "Docker not answering" not in page
+
+
+async def test_a_failing_service_leads_and_the_failures_are_listed(app):
+    now = datetime.now(timezone.utc)
+    sick = {"name": "codex_db", "mode": "replicated", "running": 0, "desired": 1, "state": "down",
+            "crash_looping": True, "failures_1h": 7, "failures_24h": 9, "tasks_known": True,
+            "trouble_since": now - timedelta(minutes=20), "replicas": [], "previous_tasks": 7,
+            "last_error": {"state": "failed", "error": "task: non-zero exit (1)", "exit_code": 1,
+                           "node": "nas", "at": None}}
+    failures = [{"kind": "service", "name": "codex_db", "host_id": None, "host": "nas", "count": 9,
+                 "at": now - timedelta(minutes=2), "detail": "task: non-zero exit (1)"},
+                {"kind": "container", "name": "backup", "host_id": "h1", "host": "nas", "count": 1,
+                 "at": now - timedelta(hours=3), "detail": "exit 2"}]
+    async with app.test_request_context("/plugins/docker/rows"):
+        page = await render_plugin_template(
+            app, "docker", "docker/rows.html", docker_down=[], attention=[], says=svc.PROBLEM_SAYS,
+            severity=svc.PROBLEM_SEVERITY, unhealthy=0, restarting=0, stale=0, host_groups=[],
+            swarm_services=[sick], services_healthy=0, failing_services=[sick], failures=failures,
+            running=0, stopped=0, docker_hosts=1)
+    page = re.sub(r">\s+<", "><", " ".join(page.split()))
+    card = page[page.index("Needs attention"):page.index("</section>")]
+    assert '<span class="badge badge-crit">Crash-looping</span><a href="/plugins/docker/swarm">codex_db</a>' in card
+    assert "0 of 1 running · 7 tasks failed in the last hour · last task failed: task: non-zero exit (1)" in card
+    assert "since <time" in card
+    assert '<span class="stat-tile-label">Swarm services</span><span class="stat-tile-value">0/1</span>' in page
+    listed = page[page.index('id="failures"'):]
+    listed = listed[:listed.index("</section>")]
+    assert listed.index("codex_db") < listed.index("backup")              # newest first
+    assert "9 failures · last: task: non-zero exit (1) · nas" in listed
+    assert 'href="/plugins/docker/container/h1/backup">backup</a>' in listed