Standardize demo configs and CLI templates to v0.3.0

- Update all demo config files to version v0.3.0
- Rename llm_providers → model_providers across all configs
- Modernize listener format from object to array style
  (e.g. listeners: [{type: model, name:, port:}])
- Replace chatbot_ui with AnythingLLM in 6 docker-compose files
- Remove prometheus/grafana services from llm_gateway and
  preference_based_routing docker-compose files
- Add tracing: random_sampling: 100 to configs that lacked it
- Update 3 CLI init templates (coding_agent_routing,
  preference_aware_routing, conversational_state_v1_responses)
- Fix test_init.py assertion for model_providers key

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

cli/planoai/templates/coding_agent_routing.yaml

@@ -1,13 +1,6 @@
-version: v0.1
+version: v0.3.0
 
-listeners:
-  egress_traffic:
-    address: 0.0.0.0
-    port: 12000
-    message_format: openai
-    timeout: 30s
-
-llm_providers:
+model_providers:
   # OpenAI Models
   - model: openai/gpt-5-2025-08-07
     access_key: $OPENAI_API_KEY
@@ -39,5 +32,10 @@ model_aliases:
   arch.claude.code.small.fast:
     target: claude-haiku-4-5
 
+listeners:
+  - type: model
+    name: model_listener
+    port: 12000
+
 tracing:
   random_sampling: 100

cli/planoai/templates/conversational_state_v1_responses.yaml

@@ -1,25 +1,36 @@
-version: v0.1
+version: v0.3.0
 
-listeners:
-  egress_traffic:
-    address: 0.0.0.0
-    port: 12000
-    message_format: openai
-    timeout: 30s
-
-llm_providers:
+agents:
+  - id: assistant
+    url: http://localhost:10510
 
+model_providers:
   # OpenAI Models
   - model: openai/gpt-5-mini-2025-08-07
     access_key: $OPENAI_API_KEY
     default: true
 
-    # Anthropic Models
+  # Anthropic Models
   - model: anthropic/claude-sonnet-4-20250514
     access_key: $ANTHROPIC_API_KEY
 
+listeners:
+  - type: agent
+    name: conversation_service
+    port: 8001
+    router: plano_orchestrator_v1
+    agents:
+      - id: assistant
+        description: |
+          A conversational assistant that maintains context across multi-turn
+          conversations. It can answer follow-up questions, remember previous
+          context, and provide coherent responses in ongoing dialogues.
+
 # State storage configuration for v1/responses API
 # Manages conversation state for multi-turn conversations
 state_storage:
   # Type: memory | postgres
   type: memory
+
+tracing:
+  random_sampling: 100

cli/planoai/templates/preference_aware_routing.yaml

@@ -1,13 +1,6 @@
-version: v0.1.0
+version: v0.3.0
 
-listeners:
-  egress_traffic:
-    address: 0.0.0.0
-    port: 12000
-    message_format: openai
-    timeout: 30s
-
-llm_providers:
+model_providers:
 
   - model: openai/gpt-4o-mini
     access_key: $OPENAI_API_KEY
@@ -25,5 +18,10 @@ llm_providers:
       - name: code generation
         description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
 
+listeners:
+  - type: model
+    name: model_listener
+    port: 12000
+
 tracing:
   random_sampling: 100

cli/test/test_init.py

@@ -26,7 +26,7 @@ def test_init_template_builtin_writes_config(tmp_path, monkeypatch):
     config_path = tmp_path / "config.yaml"
     assert config_path.exists()
     config_text = config_path.read_text(encoding="utf-8")
-    assert "llm_providers:" in config_text
+    assert "model_providers:" in config_text
 
 
 def test_init_refuses_overwrite_without_force(tmp_path, monkeypatch):