Kontrollpflicht der Leitung: Stichproben gegen das Audit (#693)

A lead looks at the runs of the agents it leads - held against the task and
against what the engine stamped, never by asking the agent.

- RunInspector (Core/Inspection): the mechanical check and first profile of
  the inspector foundation (#204). Flags failed runs, tool errors, refusals,
  unfinished calls, tasks answered with bookkeeping alone, and operations the
  agent names but never called in the run (the 2026-09-14 pattern).
- SpotChecks: picks runs per unit (rate, denser for new agents, new models and
  after a failure, daily cap), deterministic by run id; one task per lead.
- Escalation tool: spot_checks, inspect_run, check_done, propose_measure.
  Measures go to a human; nothing is carried out automatically. A security
  suspicion is its own case, not a personnel matter.
- Organisation view: settings per unit, recent checks, measures to decide.

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

src/ClawdDotNet.Manager.Web/wwwroot/app.css

@@ -2637,6 +2637,28 @@ button.org-einheit .org-name {
   gap: 4px;
 }
 
+/* #693: the lead's spot checks and the measures waiting for the human. */
+.org-stichproben h4 {
+  margin: 14px 0 6px;
+  font-size: 13px;
+}
+
+.org-massnahme {
+  border: 1px solid var(--warnung);
+  border-left-width: 4px;
+  padding: 8px 12px;
+  margin-bottom: 8px;
+}
+
+.org-massnahme.sicherheit {
+  border-color: var(--gefahr);
+}
+
+.org-befunde {
+  margin: 0;
+  padding-left: 16px;
+}
+
 tr.org-ausreisser td {
   background: rgba(181, 130, 42, 0.08);
 }