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-followup.yaml

@@ -1,11 +1,13 @@
 # P5 eval: iteration. A read-only task completes; the follow-up asks the
-# agent to act on what it found (a config_mutation). Asserts the session
+# agent to act on what it found (a config_mutation). The second followup
+# is the approval ("go ahead") so the plan can execute. Asserts the session
 # reopens, a second plan generation is created, and the agent completes
-# both sub-tasks without duplicate-complete.
+# both sub-tasks.
 - name: iteration-followup
-  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? Inspect the actual service state, don't just read the DB."
   followups:
     - "The repos folder failed last time. Reset the failed service and re-run the backup."
+    - "go ahead"
   assertions:
     - kind: completes
     - kind: plan_generations
@@ -13,4 +15,4 @@
     - kind: proposes_plan
     - kind: writes_back
     - kind: max_run_calls
-      value: 6
+      value: 8