fix(eval): fix manifests to require live inspection + approval followup

plan-always-readonly: prompt now demands live systemd timer inspection,
not just DB lookup. Added calls_tool: run assertion.
iteration-followup: added 'go ahead' as second followup so the
config_mutation plan gets approved and can execute.
iteration-readonly: replaced nonexistent lxc:prometheus with lxc:dns,
keep it read-only so no approval needed.

evals/iteration-readonly.yaml

@@ -1,13 +1,17 @@
-# P5 eval: two read-only sub-tasks back-to-back. Asserts the session
-# reopens and a second plan generation is created for the follow-up.
+# P5 eval: two read-only sub-tasks back-to-back. The follow-up is also
+# read-only (no approval needed) so the agent can execute immediately after
+# proposing the second plan. Asserts the session reopens and a second plan
+# generation is created.
 - name: iteration-readonly
-  prompt: "When was the last backup to Proton Drive done, and when is the next one?"
+  prompt: "Check the live systemd timer on lxc:rclone — when did the last backup to Proton Drive actually run, and when is the next one scheduled?"
   followups:
-    - "Now check when the last snapshot of the prometheus LXC was taken."
+    - "Now check the uptime of lxc:dns."
   assertions:
     - kind: completes
     - kind: plan_generations
       value: 2
     - kind: proposes_plan
+    - kind: calls_tool
+      value: run
     - kind: max_run_calls
       value: 6