feat(example): sandbox-acp-agent — the live composition; RFCs to implemented

The three-entry cordis.yml (dsh-sandbox-local + dsh-bash-sandbox at a
read-only default + dsh-approval) served over ACP: the first live approval
composition. Recorded snapshot scenarios pin the wire end to end —
config-options advertisement, the mode-switching arc as the suite pinned
header (both switches, the prompt-section delta, one changed-by-the-user
notice per knob, a confined write landing under the switched mode), and
both escalation branches over scripted permissionAnswers (a grant runs
confined under workspace-write; a rejection executes nothing and pins the
fail-closed text). The with-key escalation e2e drives a real model +
real runner + the real bridge answerer, world-verified; ci.yml snapshot
lane and e2e.yml install bubblewrap so the confined replays actually
execute.

Both RFCs move to implemented/ (Decision/Consequences form, deferred
phases tracked in their own sections), with every cross-reference flipped.

examples/sandbox-acp-agent/tests/snapshots/escalation-approved/input.json

@@ -0,0 +1,10 @@
+{
+  "steps": [
+    { "op": "initialize" },
+    { "op": "newSession" },
+    { "op": "prompt", "text": "The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop." }
+  ],
+  "permissionAnswers": [
+    { "kind": "allow_once" }
+  ]
+}