Merge origin/main into musa/chatgpt-subscription

demos/llm_routing/claude_code_router/pretty_model_resolution.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Pretty-print Plano MODEL_RESOLUTION lines from docker logs
-# - hides Arch-Router
+# - hides Plano-Orchestrator
 # - prints timestamp
 # - colors MODEL_RESOLUTION red
 # - colors req_model cyan
@@ -9,7 +9,7 @@
 
 docker logs -f plano 2>&1 \
 | awk '
-/MODEL_RESOLUTION:/ && $0 !~ /Arch-Router/ {
+/MODEL_RESOLUTION:/ && $0 !~ /Plano-Orchestrator/ {
   # extract timestamp between first [ and ]
   ts=""
   if (match($0, /\[[0-9-]+ [0-9:.]+\]/)) {

demos/llm_routing/codex_router/pretty_model_resolution.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Pretty-print Plano MODEL_RESOLUTION lines from docker logs
-# - hides Arch-Router
+# - hides Plano-Orchestrator
 # - prints timestamp
 # - colors MODEL_RESOLUTION red
 # - colors req_model cyan
@@ -9,7 +9,7 @@
 
 docker logs -f plano 2>&1 \
 | awk '
-/MODEL_RESOLUTION:/ && $0 !~ /Arch-Router/ {
+/MODEL_RESOLUTION:/ && $0 !~ /Plano-Orchestrator/ {
   # extract timestamp between first [ and ]
   ts=""
   if (match($0, /\[[0-9-]+ [0-9:.]+\]/)) {

demos/llm_routing/model_routing_service/README.md

@@ -6,7 +6,7 @@ Plano is an AI-native proxy and data plane for agentic apps — with built-in or
 ┌───────────┐      ┌─────────────────────────────────┐      ┌──────────────┐
 │  Client   │ ───► │  Plano                          │ ───► │  OpenAI      │
 │  (any     │      │                                 │      │  Anthropic   │
-│  language)│      │  Arch-Router (1.5B model)       │      │  Any Provider│
+│  language)│      │  Plano-Orchestrator              │      │  Any Provider│
 └───────────┘      │  analyzes intent → picks model  │      └──────────────┘
                    └─────────────────────────────────┘
 ```
@@ -39,17 +39,17 @@ routing_preferences:
 
 When a request arrives, Plano:
 
-1. Sends the conversation + route descriptions to Arch-Router for intent classification
+1. Sends the conversation + route descriptions to Plano-Orchestrator for intent classification
 2. Looks up the matched route and returns its candidate models
 3. Returns an ordered list — client uses `models[0]`, falls back to `models[1]` on 429/5xx
 
 ```
 1. Request arrives          → "Write binary search in Python"
-2. Arch-Router classifies   → route: "code_generation"
+2. Plano-Orchestrator classifies → route: "code_generation"
 3. Response                 → models: ["anthropic/claude-sonnet-4-20250514", "openai/gpt-4o"]
 ```
 
-No match? Arch-Router returns `null` route → client falls back to the model in the original request.
+No match? Plano-Orchestrator returns an empty route → client falls back to the model in the original request.
 
 The `/routing/v1/*` endpoints return the routing decision **without** forwarding to the LLM — useful for testing routing behavior before going to production.
 
@@ -163,9 +163,9 @@ routing:
 
 Without the `X-Model-Affinity` header, routing runs fresh every time (no breaking change).
 
-## Kubernetes Deployment (Self-hosted Arch-Router on GPU)
+## Kubernetes Deployment (Self-hosted Plano-Orchestrator on GPU)
 
-To run Arch-Router in-cluster using vLLM instead of the default hosted endpoint:
+To run Plano-Orchestrator in-cluster using vLLM instead of the default hosted endpoint:
 
 **0. Check your GPU node labels and taints**
 
@@ -176,10 +176,10 @@ kubectl get node <gpu-node-name> -o jsonpath='{.spec.taints}'
 
 GPU nodes commonly have a `nvidia.com/gpu:NoSchedule` taint — `vllm-deployment.yaml` includes a matching toleration. If you have multiple GPU node pools and need to pin to a specific one, uncomment and set the `nodeSelector` in `vllm-deployment.yaml` using the label for your cloud provider.
 
-**1. Deploy Arch-Router and Plano:**
+**1. Deploy Plano-Orchestrator and Plano:**
 
 ```bash
-# arch-router deployment
+# plano-orchestrator deployment
 kubectl apply -f vllm-deployment.yaml
 
 # plano deployment
@@ -197,8 +197,8 @@ kubectl apply -f plano-deployment.yaml
 **3. Wait for both pods to be ready:**
 
 ```bash
-# Arch-Router downloads the model (~1 min) then vLLM loads it (~2 min)
-kubectl get pods -l app=arch-router -w
+# Plano-Orchestrator downloads the model (~1 min) then vLLM loads it (~2 min)
+kubectl get pods -l app=plano-orchestrator -w
 kubectl rollout status deployment/plano
 ```
 
@@ -209,10 +209,10 @@ kubectl port-forward svc/plano 12000:12000
 ./demo.sh
 ```
 
-To confirm requests are hitting your in-cluster Arch-Router (not just health checks):
+To confirm requests are hitting your in-cluster Plano-Orchestrator (not just health checks):
 
 ```bash
-kubectl logs -l app=arch-router -f --tail=0
+kubectl logs -l app=plano-orchestrator -f --tail=0
 # Look for POST /v1/chat/completions entries
 ```
 

demos/llm_routing/model_routing_service/config_k8s.yaml

@@ -1,7 +1,7 @@
 version: v0.3.0
 
 overrides:
-  llm_routing_model: plano/Arch-Router
+  llm_routing_model: plano/Plano-Orchestrator
 
 listeners:
   - type: model
@@ -10,8 +10,8 @@ listeners:
 
 model_providers:
 
-  - model: plano/Arch-Router
-    base_url: http://arch-router:10000
+  - model: plano/Plano-Orchestrator
+    base_url: http://plano-orchestrator:10000
 
   - model: openai/gpt-4o-mini
     access_key: $OPENAI_API_KEY

demos/llm_routing/model_routing_service/vllm-deployment.yaml

@@ -1,18 +1,18 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: arch-router
+  name: plano-orchestrator
   labels:
-    app: arch-router
+    app: plano-orchestrator
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app: arch-router
+      app: plano-orchestrator
   template:
     metadata:
       labels:
-        app: arch-router
+        app: plano-orchestrator
     spec:
       tolerations:
         - key: nvidia.com/gpu
@@ -53,7 +53,7 @@ spec:
             - "--tokenizer"
             - "katanemo/Arch-Router-1.5B"
             - "--served-model-name"
-            - "Arch-Router"
+            - "Plano-Orchestrator"
             - "--gpu-memory-utilization"
             - "0.3"
             - "--tensor-parallel-size"
@@ -94,10 +94,10 @@ spec:
 apiVersion: v1
 kind: Service
 metadata:
-  name: arch-router
+  name: plano-orchestrator
 spec:
   selector:
-    app: arch-router
+    app: plano-orchestrator
   ports:
     - name: http
       port: 10000

demos/llm_routing/openclaw_routing/config.yaml

@@ -1,7 +1,7 @@
 version: v0.1.0
 
 overrides:
-  llm_routing_model: Arch-Router
+  llm_routing_model: Plano-Orchestrator
 
 listeners:
   egress_traffic:

demos/llm_routing/preference_based_routing/README.md

@@ -3,7 +3,7 @@ This demo shows how you can use user preferences to route user prompts to approp
 
 ## How to start the demo
 
-Make sure you have Plano CLI installed (`pip install planoai==0.4.18` or `uv tool install planoai==0.4.18`).
+Make sure you have Plano CLI installed (`pip install planoai==0.4.20` or `uv tool install planoai==0.4.20`).
 
 ```bash
 cd demos/llm_routing/preference_based_routing
@@ -32,9 +32,9 @@ planoai up config.yaml
 
 3. Test with curl or open AnythingLLM http://localhost:3001/
 
-## Running with local Arch-Router (via Ollama)
+## Running with local routing model (via Ollama)
 
-By default, Plano uses a hosted Arch-Router endpoint. To self-host Arch-Router locally using Ollama:
+By default, Plano uses a hosted Plano-Orchestrator endpoint. To self-host a routing model locally using Ollama:
 
 1. Install [Ollama](https://ollama.ai) and pull the model:
 ```bash

demos/llm_routing/preference_based_routing/test_router_endpoint.rest

@@ -22,11 +22,11 @@ Content-Type: application/json
 
 ### get model list from arch-function
 GET https://archfc.katanemo.dev/v1/models HTTP/1.1
-model: Arch-Router
+model: Plano-Orchestrator
 
-### get model list from Arch-Router (notice model header)
+### get model list from Plano-Orchestrator (notice model header)
 GET https://archfc.katanemo.dev/v1/models HTTP/1.1
-model: Arch-Router
+model: Plano-Orchestrator
 
 
 ### test try code generating