rename arch provider to plano, use llm_routing_model and agent_orchestration_model

2026-05-18 13:45:15 +02:00 · 2026-03-13 13:27:58 -07:00 · 2026-03-13 13:27:58 -07:00 · 6f8bf96d38
commit 6f8bf96d38
parent 680dee60a0
16 changed files with 37 additions and 50 deletions
--- a/cli/planoai/config_generator.py
+++ b/cli/planoai/config_generator.py
@ -13,7 +13,6 @@ SUPPORTED_PROVIDERS_WITH_BASE_URL = [
    "ollama",
    "qwen",
    "amazon_bedrock",
-    "arch",
    "plano",
 ]

@ -373,7 +372,7 @@ def validate_and_render_schema():
    model_name_set = {mp.get("model") for mp in updated_model_providers}

    # Auto-add arch-router provider if routing preferences exist and no provider matches the router model
-    router_model = overrides_config.get("router_model", "Arch-Router")
+    router_model = overrides_config.get("llm_routing_model", "Arch-Router")
    # Strip provider prefix for comparison since config processing strips prefixes from model names
    router_model_id = (
        router_model.split("/", 1)[1] if "/" in router_model else router_model
@ -382,7 +381,7 @@ def validate_and_render_schema():
        updated_model_providers.append(
            {
                "name": "arch-router",
-                "provider_interface": "arch",
+                "provider_interface": "plano",
                "model": router_model_id,
                "internal": True,
            }
@ -393,7 +392,7 @@ def validate_and_render_schema():
        updated_model_providers.append(
            {
                "name": "arch-function",
-                "provider_interface": "arch",
+                "provider_interface": "plano",
                "model": "Arch-Function",
                "internal": True,
            }
@ -401,7 +400,7 @@ def validate_and_render_schema():

    # Auto-add plano-orchestrator provider if no provider matches the orchestrator model
    orchestrator_model = overrides_config.get(
-        "orchestrator_model", "Plano-Orchestrator"
+        "agent_orchestration_model", "Plano-Orchestrator"
    )
    orchestrator_model_id = (
        orchestrator_model.split("/", 1)[1]
@ -411,8 +410,8 @@ def validate_and_render_schema():
    if orchestrator_model_id not in model_name_set:
        updated_model_providers.append(
            {
-                "name": "plano-orchestrator",
-                "provider_interface": "arch",
+                "name": "plano/orchestrator",
+                "provider_interface": "plano",
                "model": orchestrator_model_id,
                "internal": True,
            }
--- a/config/envoy.template.yaml
+++ b/config/envoy.template.yaml
@ -594,13 +594,13 @@ static_resources:

  clusters:

-    - name: arch
+    - name: plano
      connect_timeout: {{ upstream_connect_timeout | default('5s') }}
      type: LOGICAL_DNS
      dns_lookup_family: V4_ONLY
      lb_policy: ROUND_ROBIN
      load_assignment:
-        cluster_name: arch
+        cluster_name: plano
        endpoints:
          - lb_endpoints:
              - endpoint:
--- a/config/plano_config_schema.yaml
+++ b/config/plano_config_schema.yaml
@ -173,7 +173,6 @@ properties:
        provider_interface:
          type: string
          enum:
-            - arch
            - plano
            - claude
            - deepseek
@ -221,7 +220,6 @@ properties:
        provider_interface:
          type: string
          enum:
-            - arch
            - plano
            - claude
            - deepseek
@ -273,10 +271,10 @@ properties:
      upstream_tls_ca_path:
        type: string
        description: "Path to the trusted CA bundle for upstream TLS verification. Default is '/etc/ssl/certs/ca-certificates.crt'."
-      router_model:
+      llm_routing_model:
        type: string
        description: "Model name for the LLM router (e.g., 'Arch-Router'). Must match a model in model_providers."
-      orchestrator_model:
+      agent_orchestration_model:
        type: string
        description: "Model name for the agent orchestrator (e.g., 'Plano-Orchestrator'). Must match a model in model_providers."
  system_prompt:
--- a/crates/brightstaff/src/main.rs
+++ b/crates/brightstaff/src/main.rs
@ -94,7 +94,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {

    // Strip provider prefix (e.g. "arch/") to get the model ID used in upstream requests
    let routing_model_name: String = overrides
-        .router_model
+        .llm_routing_model
        .as_deref()
        .map(|m| m.split_once('/').map(|(_, id)| id).unwrap_or(m))
        .unwrap_or(DEFAULT_ROUTING_MODEL_NAME)
@ -116,7 +116,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {

    // Strip provider prefix (e.g. "arch/") to get the model ID used in upstream requests
    let orchestrator_model_name: String = overrides
-        .orchestrator_model
+        .agent_orchestration_model
        .as_deref()
        .map(|m| m.split_once('/').map(|(_, id)| id).unwrap_or(m))
        .unwrap_or(DEFAULT_ORCHESTRATOR_MODEL_NAME)
--- a/crates/brightstaff/src/router/plano_orchestrator.rs
+++ b/crates/brightstaff/src/router/plano_orchestrator.rs
@ -81,12 +81,12 @@ impl OrchestratorService {
        debug!(
            model = %self.orchestrator_model.get_model_name(),
            endpoint = %self.orchestrator_url,
-            "sending request to arch-orchestrator"
+            "sending request to plano-orchestrator"
        );

        debug!(
            body = %serde_json::to_string(&orchestrator_request).unwrap(),
-            "arch orchestrator request"
+            "plano orchestrator request"
        );

        let mut orchestration_request_headers = header::HeaderMap::new();
--- a/crates/common/src/configuration.rs
+++ b/crates/common/src/configuration.rs
@ -77,8 +77,8 @@ pub struct Overrides {
    pub prompt_target_intent_matching_threshold: Option<f64>,
    pub optimize_context_window: Option<bool>,
    pub use_agent_orchestrator: Option<bool>,
-    pub router_model: Option<String>,
-    pub orchestrator_model: Option<String>,
+    pub llm_routing_model: Option<String>,
+    pub agent_orchestration_model: Option<String>,
 }

 #[derive(Debug, Clone, Serialize, Deserialize, Default)]
@ -202,8 +202,6 @@ pub struct EmbeddingProviver {

 #[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, Hash)]
 pub enum LlmProviderType {
-    #[serde(rename = "arch")]
-    Arch,
    #[serde(rename = "anthropic")]
    Anthropic,
    #[serde(rename = "deepseek")]
@ -239,7 +237,6 @@ pub enum LlmProviderType {
 impl Display for LlmProviderType {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        match self {
-            LlmProviderType::Arch => write!(f, "arch"),
            LlmProviderType::Anthropic => write!(f, "anthropic"),
            LlmProviderType::Deepseek => write!(f, "deepseek"),
            LlmProviderType::Groq => write!(f, "groq"),
@ -263,15 +260,7 @@ impl LlmProviderType {
    /// Get the ProviderId for this LlmProviderType
    /// Used with the new function-based hermesllm API
    pub fn to_provider_id(&self) -> hermesllm::ProviderId {
-        // Plano provider uses the same interface as Arch
-        let provider_str = match self {
-            LlmProviderType::Plano => "arch",
-            other => {
-                return hermesllm::ProviderId::try_from(other.to_string().as_str())
-                    .expect("LlmProviderType should always map to a valid ProviderId")
-            }
-        };
-        hermesllm::ProviderId::try_from(provider_str)
+        hermesllm::ProviderId::try_from(self.to_string().as_str())
            .expect("LlmProviderType should always map to a valid ProviderId")
    }
 }
@ -597,14 +586,14 @@ mod test {
            },
            LlmProvider {
                name: "arch-router".to_string(),
-                provider_interface: LlmProviderType::Arch,
+                provider_interface: LlmProviderType::Plano,
                model: Some("Arch-Router".to_string()),
                internal: Some(true),
                ..Default::default()
            },
            LlmProvider {
                name: "plano-orchestrator".to_string(),
-                provider_interface: LlmProviderType::Arch,
+                provider_interface: LlmProviderType::Plano,
                model: Some("Plano-Orchestrator".to_string()),
                internal: Some(true),
                ..Default::default()
--- a/crates/common/src/consts.rs
+++ b/crates/common/src/consts.rs
@ -33,4 +33,4 @@ pub const OTEL_COLLECTOR_HTTP: &str = "opentelemetry_collector_http";
 pub const LLM_ROUTE_HEADER: &str = "x-arch-llm-route";
 pub const ENVOY_RETRY_HEADER: &str = "x-envoy-max-retries";
 pub const BRIGHT_STAFF_SERVICE_NAME: &str = "brightstaff";
-pub const ARCH_FC_CLUSTER: &str = "arch";
+pub const PLANO_FC_CLUSTER: &str = "plano";
--- a/crates/hermesllm/src/lib.rs
+++ b/crates/hermesllm/src/lib.rs
@ -35,7 +35,7 @@ mod tests {
            ProviderId::Mistral
        );
        assert_eq!(ProviderId::try_from("groq").unwrap(), ProviderId::Groq);
-        assert_eq!(ProviderId::try_from("arch").unwrap(), ProviderId::Arch);
+        assert_eq!(ProviderId::try_from("plano").unwrap(), ProviderId::Plano);

        // Test aliases
        assert_eq!(ProviderId::try_from("google").unwrap(), ProviderId::Gemini);
--- a/crates/hermesllm/src/providers/id.rs
+++ b/crates/hermesllm/src/providers/id.rs
@ -34,7 +34,7 @@ pub enum ProviderId {
    Gemini,
    Anthropic,
    GitHub,
-    Arch,
+    Plano,
    AzureOpenAI,
    XAI,
    TogetherAI,
@ -58,7 +58,7 @@ impl TryFrom<&str> for ProviderId {
            "google" => Ok(ProviderId::Gemini), // alias
            "anthropic" => Ok(ProviderId::Anthropic),
            "github" => Ok(ProviderId::GitHub),
-            "arch" => Ok(ProviderId::Arch),
+            "plano" => Ok(ProviderId::Plano),
            "azure_openai" => Ok(ProviderId::AzureOpenAI),
            "xai" => Ok(ProviderId::XAI),
            "together_ai" => Ok(ProviderId::TogetherAI),
@ -135,7 +135,7 @@ impl ProviderId {
                | ProviderId::Groq
                | ProviderId::Mistral
                | ProviderId::Deepseek
-                | ProviderId::Arch
+                | ProviderId::Plano
                | ProviderId::Gemini
                | ProviderId::GitHub
                | ProviderId::AzureOpenAI
@ -153,7 +153,7 @@ impl ProviderId {
                | ProviderId::Groq
                | ProviderId::Mistral
                | ProviderId::Deepseek
-                | ProviderId::Arch
+                | ProviderId::Plano
                | ProviderId::Gemini
                | ProviderId::GitHub
                | ProviderId::AzureOpenAI
@ -219,7 +219,7 @@ impl Display for ProviderId {
            ProviderId::Gemini => write!(f, "Gemini"),
            ProviderId::Anthropic => write!(f, "Anthropic"),
            ProviderId::GitHub => write!(f, "GitHub"),
-            ProviderId::Arch => write!(f, "Arch"),
+            ProviderId::Plano => write!(f, "Plano"),
            ProviderId::AzureOpenAI => write!(f, "azure_openai"),
            ProviderId::XAI => write!(f, "xai"),
            ProviderId::TogetherAI => write!(f, "together_ai"),
--- a/crates/llm_gateway/src/stream_context.rs
+++ b/crates/llm_gateway/src/stream_context.rs
@ -873,7 +873,7 @@ impl HttpContext for StreamContext {
                // ensure that the provider has an endpoint if the access key is missing else return a bad request
                if self.llm_provider.as_ref().unwrap().endpoint.is_none()
                    && self.llm_provider.as_ref().unwrap().provider_interface
-                        != LlmProviderType::Arch
+                        != LlmProviderType::Plano
                {
                    self.send_server_error(error, Some(StatusCode::BAD_REQUEST));
                }
--- a/demos/agent_orchestration/travel_agents/config_local_orchestrator.yaml
+++ b/demos/agent_orchestration/travel_agents/config_local_orchestrator.yaml
@ -1,7 +1,7 @@
 version: v0.3.0

 overrides:
-  orchestrator_model: plano/katanemo/Plano-Orchestrator-4B
+  agent_orchestration_model: plano/katanemo/Plano-Orchestrator-4B

 agents:
  - id: weather_agent
--- a/demos/llm_routing/openclaw_routing/config.yaml
+++ b/demos/llm_routing/openclaw_routing/config.yaml
@ -1,7 +1,7 @@
 version: v0.1.0

 overrides:
-  router_model: Arch-Router
+  llm_routing_model: Arch-Router

 listeners:
  egress_traffic:
--- a/demos/llm_routing/preference_based_routing/plano_config_local.yaml
+++ b/demos/llm_routing/preference_based_routing/plano_config_local.yaml
@ -1,7 +1,7 @@
 version: v0.3.0

 overrides:
-  router_model: plano/hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M
+  llm_routing_model: plano/hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M

 listeners:
  - type: model
--- a/docs/source/guides/llm_router.rst
+++ b/docs/source/guides/llm_router.rst
@ -254,7 +254,7 @@ Using Ollama (recommended for local development)
   .. code-block:: yaml

       overrides:
-         router_model: plano/hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M
+         llm_routing_model: plano/hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M

       model_providers:
         - model: plano/hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M
@ -323,7 +323,7 @@ vLLM provides higher throughput and GPU optimizations suitable for production de
   .. code-block:: yaml

       overrides:
-         router_model: plano/Arch-Router
+         llm_routing_model: plano/Arch-Router

       model_providers:
         - model: plano/Arch-Router
--- a/docs/source/guides/orchestration.rst
+++ b/docs/source/guides/orchestration.rst
@ -404,10 +404,11 @@ Using vLLM
   .. code-block:: yaml

       overrides:
-         orchestrator_model: plano/katanemo/Plano-Orchestrator-4B
+         agent_orchestration_model: plano/katanemo/Plano-Orchestrator-4B

       model_providers:
-         - model: plano/katanemo/Plano-Orchestrator-4B
+         - model: katanemo/Plano-Orchestrator-4B
+           provider_interface: plano
           base_url: http://<your-server-ip>:8000

 5. **Verify the server is running**
--- a/docs/source/resources/includes/plano_config_full_reference_rendered.yaml
+++ b/docs/source/resources/includes/plano_config_full_reference_rendered.yaml
@ -107,11 +107,11 @@ model_providers:
 - internal: true
  model: Arch-Function
  name: arch-function
-  provider_interface: arch
+  provider_interface: plano
 - internal: true
  model: Plano-Orchestrator
  name: plano-orchestrator
-  provider_interface: arch
+  provider_interface: plano
 prompt_targets:
 - description: Get current weather at a location.
  endpoint: