multica_agent_host: merge declared keys into the daemon user's Claude settings (WDWL-22)

The npm-installed Claude Code on spaceship-earth updated itself from the
pinned 2.1.304 to 2.1.308 right after its first login, so every play would
downgrade it and it would update again. New multica_claude_settings is
merged (recursively, not templated, since Claude writes the file too) into
~multica/.claude/settings.json.

provision-agent-host.yml sets DISABLE_AUTOUPDATER=1 and mirrors the model
mix already live on haunted-mansion: model sonnet, subagents haiku,
MAX_THINKING_TOKENS 4000, BASH_MAX_OUTPUT_LENGTH 20000, thinking off.

spaceship-earth: back on 2.1.304 and staying there; second run changed=0.

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

ansible/roles/multica_agent_host/tasks/main.yml

@@ -27,6 +27,13 @@
   ansible.builtin.import_tasks: agent_clis.yml
   tags: [multica, multica_agents]
 
+- name: Claude Code settings
+  ansible.builtin.import_tasks: claude_settings.yml
+  when:
+    - "'claude' in multica_agent_clis"
+    - multica_claude_settings | length > 0
+  tags: [multica, multica_agents, multica_claude_settings]
+
 - name: CLI configuration
   ansible.builtin.import_tasks: config.yml
   tags: [multica, multica_config]