rename cli to plano (#647)

docs/source/guides/includes/config.yaml

@@ -0,0 +1,57 @@
+version: v0.1.0
+
+listeners:
+  ingress_traffic:
+    address: 0.0.0.0
+    port: 10000
+    message_format: openai
+    timeout: 30s
+
+# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
+llm_providers:
+  - access_key: $OPENAI_API_KEY
+    model: openai/gpt-4o
+    default: true
+
+# default system prompt used by all prompt targets
+system_prompt: You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.
+
+prompt_targets:
+  - name: information_extraction
+    default: true
+    description: handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.
+    endpoint:
+      name: app_server
+      path: /agent/summary
+      http_method: POST
+    # Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM
+    auto_llm_dispatch_on_response: true
+    # override system prompt for this prompt target
+    system_prompt: You are a helpful information extraction assistant. Use the information that is provided to you.
+
+  - name: reboot_network_device
+    description: Perform device operations like rebooting a device.
+    endpoint:
+      name: app_server
+      path: /agent/action
+      http_method: POST
+    parameters:
+      - name: device_id
+        type: str
+        description: Identifier of the network device to reboot.
+        required: true
+      - name: confirmation
+        type: bool
+        description: Confirmation flag to proceed with reboot.
+        default: false
+        enum: [true, false]
+
+# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
+endpoints:
+  app_server:
+    # value could be ip address or a hostname with port
+    # this could also be a list of endpoints for load balancing
+    # for example endpoint: [ ip1:port, ip2:port ]
+    endpoint: 127.0.0.1:80
+    # max time to wait for a connection to be established
+    connect_timeout: 0.005s