Complete activity-core LLM endpoint handoff (LLM-WP-0006)

Switch the custodian triage default from anthropic/claude-sonnet-4 to
google/gemini-2.5-flash, which advertises structured-output support on
OpenRouter. Tighten the OpenRouter adapter to send strict JSON schema
requests and set provider.require_parameters=true so routing only hits
providers that honor the requested response_format.

Update Kubernetes deploy docs and config for the verified coulombcore
handoff: Containerfile build path, image-pull-policy=Never for smoke
pods, credential-routing notes, and live smoke evidence. Mark
LLM-WP-0006 finished with closure notes from 2026-06-18.

tests/test_profiles.py

@@ -115,6 +115,14 @@ def test_unknown_custodian_profile_fails_without_secret_context():
     assert excinfo.value.context == {"profile": "custodian-missing"}
 
 
+def test_default_custodian_profile_uses_structured_output_capable_model():
+    profiles = default_runtime_profiles()
+    profile = profiles[CUSTODIAN_TRIAGE_BALANCED]
+
+    assert profile.provider == "openrouter"
+    assert profile.model == "google/gemini-2.5-flash"
+
+
 def test_default_profiles_can_be_overridden_from_json_env(monkeypatch):
     monkeypatch.setenv(
         "LLM_CONNECT_PROFILES_JSON",