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/playbooks/provision-agent-host.yml

@@ -20,6 +20,17 @@
     # multica_workspaces_root_mount: "/mnt/utilidor"
     multica_agent_clis:
       - claude
+    # Merged into the daemon user's ~/.claude/settings.json. Mirrors the model
+    # mix already live on haunted-mansion (unpinned runs on sonnet, subagents
+    # on haiku), and stops the npm install self-updating past the pin.
+    multica_claude_settings:
+      model: sonnet
+      alwaysThinkingEnabled: false
+      env:
+        DISABLE_AUTOUPDATER: "1"
+        CLAUDE_CODE_SUBAGENT_MODEL: haiku
+        MAX_THINKING_TOKENS: "4000"
+        BASH_MAX_OUTPUT_LENGTH: "20000"
 
     # --- Secret source ----------------------------------------------------
     # This homelab keeps Ansible secrets in ansible-vault encrypted files, so