diff --git a/.claude/skills/release/SKILL.md b/.claude/skills/release/SKILL.md
index 80510004..ba101bd3 100644
--- a/.claude/skills/release/SKILL.md
+++ b/.claude/skills/release/SKILL.md
@@ -25,4 +25,6 @@ Update the version string in ALL of these files:
Do NOT change version strings in `*.lock` files or `Cargo.lock`.
+After updating all version strings, run `cd cli && uv lock` to update the lock file with the new version.
+
After making changes, show a summary of all files modified and the old → new version.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 25e6f99d..01d5c33f 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -133,13 +133,13 @@ jobs:
load: true
tags: |
${{ env.PLANO_DOCKER_IMAGE }}
- ${{ env.DOCKER_IMAGE }}:0.4.11
+ ${{ env.DOCKER_IMAGE }}:0.4.12
${{ env.DOCKER_IMAGE }}:latest
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Save image as artifact
- run: docker save ${{ env.PLANO_DOCKER_IMAGE }} ${{ env.DOCKER_IMAGE }}:0.4.11 ${{ env.DOCKER_IMAGE }}:latest -o /tmp/plano-image.tar
+ run: docker save ${{ env.PLANO_DOCKER_IMAGE }} ${{ env.DOCKER_IMAGE }}:0.4.12 ${{ env.DOCKER_IMAGE }}:latest -o /tmp/plano-image.tar
- name: Upload image artifact
uses: actions/upload-artifact@v6
diff --git a/.gitignore b/.gitignore
index af706ea4..391c17fa 100644
--- a/.gitignore
+++ b/.gitignore
@@ -152,3 +152,4 @@ apps/*/dist/
.cursor/
.agents
+docs/do/
diff --git a/apps/www/src/components/Hero.tsx b/apps/www/src/components/Hero.tsx
index 7952c68f..fcfe5f01 100644
--- a/apps/www/src/components/Hero.tsx
+++ b/apps/www/src/components/Hero.tsx
@@ -24,7 +24,7 @@ export function Hero() {
>
- v0.4.11
+ v0.4.12
—
diff --git a/build_filter_image.sh b/build_filter_image.sh
index 8e041894..15d3d10e 100644
--- a/build_filter_image.sh
+++ b/build_filter_image.sh
@@ -1 +1 @@
-docker build -f Dockerfile . -t katanemo/plano -t katanemo/plano:0.4.11
+docker build -f Dockerfile . -t katanemo/plano -t katanemo/plano:0.4.12
diff --git a/cli/planoai/__init__.py b/cli/planoai/__init__.py
index b94eadc2..e69352e8 100644
--- a/cli/planoai/__init__.py
+++ b/cli/planoai/__init__.py
@@ -1,3 +1,3 @@
"""Plano CLI - Intelligent Prompt Gateway."""
-__version__ = "0.4.11"
+__version__ = "0.4.12"
diff --git a/cli/planoai/consts.py b/cli/planoai/consts.py
index 145fb640..9c330caa 100644
--- a/cli/planoai/consts.py
+++ b/cli/planoai/consts.py
@@ -5,7 +5,7 @@ PLANO_COLOR = "#969FF4"
SERVICE_NAME_ARCHGW = "plano"
PLANO_DOCKER_NAME = "plano"
-PLANO_DOCKER_IMAGE = os.getenv("PLANO_DOCKER_IMAGE", "katanemo/plano:0.4.11")
+PLANO_DOCKER_IMAGE = os.getenv("PLANO_DOCKER_IMAGE", "katanemo/plano:0.4.12")
DEFAULT_OTEL_TRACING_GRPC_ENDPOINT = "http://localhost:4317"
# Native mode constants
diff --git a/cli/pyproject.toml b/cli/pyproject.toml
index 3f9be272..25cc81a4 100644
--- a/cli/pyproject.toml
+++ b/cli/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "planoai"
-version = "0.4.11"
+version = "0.4.12"
description = "Python-based CLI tool to manage Plano."
authors = [{name = "Katanemo Labs, Inc."}]
readme = "README.md"
diff --git a/cli/uv.lock b/cli/uv.lock
index 9d85bf85..dfca2484 100644
--- a/cli/uv.lock
+++ b/cli/uv.lock
@@ -337,7 +337,7 @@ wheels = [
[[package]]
name = "planoai"
-version = "0.4.9"
+version = "0.4.12"
source = { editable = "." }
dependencies = [
{ name = "click" },
diff --git a/demos/llm_routing/model_routing_service/DEMO.md b/demos/llm_routing/model_routing_service/DEMO.md
new file mode 100644
index 00000000..a64604a8
--- /dev/null
+++ b/demos/llm_routing/model_routing_service/DEMO.md
@@ -0,0 +1,341 @@
+# Plano: Intelligent LLM Routing as Infrastructure
+
+---
+
+## Plano
+
+An AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agent's core logic.
+
+- **One endpoint, many models** — apps call Plano using standard OpenAI/Anthropic APIs; Plano handles provider selection, keys, and failover
+- **Intelligent routing** — a lightweight 1.5B router model classifies user intent and picks the best model per request
+- **Platform governance** — centralize API keys, rate limits, guardrails, and observability without touching app code
+- **Runs anywhere** — single binary, no dependencies; self-host the router for full data privacy
+
+```
+┌───────────┐ ┌─────────────────────────────────┐ ┌──────────────┐
+│ Client │ ──── │ Plano │ ──── │ OpenAI │
+│ (any │ │ │ │ Anthropic │
+│ language)│ │ Arch-Router (1.5B model) │ │ Any Provider│
+└───────────┘ │ analyzes intent → picks model │ └──────────────┘
+ └─────────────────────────────────┘
+```
+
+---
+
+## Live Demo: Routing Decision Service
+
+The `/routing/v1/*` endpoints return **routing decisions without calling the LLM** — perfect for inspecting, testing, and validating routing behavior.
+
+---
+
+### Demo 1 — Code Generation Request
+
+```bash
+curl -s http://localhost:12000/routing/v1/chat/completions \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "gpt-4o-mini",
+ "messages": [
+ {"role": "user", "content": "Write a Python function that implements binary search"}
+ ]
+ }'
+```
+
+**Response:**
+```json
+{
+ "model": "anthropic/claude-sonnet-4-20250514",
+ "route": "code_generation"
+}
+```
+
+Plano recognized the coding intent and routed to Claude.
+
+---
+
+### Demo 2 — Complex Reasoning Request
+
+```bash
+curl -s http://localhost:12000/routing/v1/chat/completions \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "gpt-4o-mini",
+ "messages": [
+ {"role": "user", "content": "Explain the trade-offs between microservices and monolithic architectures"}
+ ]
+ }'
+```
+
+**Response:**
+```json
+{
+ "model": "openai/gpt-4o",
+ "route": "complex_reasoning"
+}
+```
+
+Same endpoint — Plano routed to GPT-4o for reasoning.
+
+---
+
+### Demo 3 — Simple Question (No Match)
+
+```bash
+curl -s http://localhost:12000/routing/v1/chat/completions \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "gpt-4o-mini",
+ "messages": [
+ {"role": "user", "content": "What is the capital of France?"}
+ ]
+ }'
+```
+
+**Response:**
+```json
+{
+ "model": "none",
+ "route": "null"
+}
+```
+
+No preference matched — falls back to the default (cheapest) model.
+
+---
+
+### Demo 4 — Anthropic Messages Format
+
+```bash
+curl -s http://localhost:12000/routing/v1/messages \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "gpt-4o-mini",
+ "max_tokens": 1024,
+ "messages": [
+ {"role": "user", "content": "Create a REST API endpoint in Rust using actix-web that handles user registration"}
+ ]
+ }'
+```
+
+**Response:**
+```json
+{
+ "model": "anthropic/claude-sonnet-4-20250514",
+ "route": "code_generation"
+}
+```
+
+Same routing, Anthropic request format.
+
+---
+
+### Demo 5 — OpenAI Responses API Format
+
+```bash
+curl -s http://localhost:12000/routing/v1/responses \
+ -H "Content-Type: application/json" \
+ -d '{
+ "model": "gpt-4o-mini",
+ "input": "Build a React component that renders a sortable data table"
+ }'
+```
+
+**Response:**
+```json
+{
+ "model": "anthropic/claude-sonnet-4-20250514",
+ "route": "code_generation"
+}
+```
+
+Same routing engine, works with the OpenAI Responses API format too.
+
+---
+
+## How Did That Work?
+
+10 lines of YAML. No code.
+
+```yaml
+model_providers:
+
+ - model: openai/gpt-4o-mini
+ default: true # fallback for unmatched requests
+
+ - model: openai/gpt-4o
+ routing_preferences:
+ - name: complex_reasoning
+ description: complex reasoning tasks, multi-step analysis
+
+ - model: anthropic/claude-sonnet-4-20250514
+ routing_preferences:
+ - name: code_generation
+ description: generating new code, writing functions
+```
+
+That's the entire routing configuration.
+
+---
+
+## Under the Hood: How Routing Preferences Work
+
+### Writing Good Preferences
+
+Each `routing_preference` has two fields:
+
+| Field | Purpose | Example |
+|---|---|---|
+| `name` | Route identifier (returned in responses) | `code_generation` |
+| `description` | Natural language — tells the router **when** to pick this model | `generating new code, writing functions, or creating boilerplate` |
+
+The `description` is the key lever. Write it like you're explaining to a colleague when to use this model:
+
+```yaml
+# Good — specific, descriptive
+routing_preferences:
+ - name: code_generation
+ description: generating new code snippets, writing functions, creating boilerplate, or refactoring existing code
+
+# Too vague — overlaps with everything
+routing_preferences:
+ - name: code
+ description: anything related to code
+```
+
+Tips:
+- **Be specific** — "multi-step mathematical proofs and formal logic" beats "hard questions"
+- **Describe the task, not the model** — focus on what the user is asking for
+- **Avoid overlap** — if two preferences match the same request, the router has to guess
+- **One model can have multiple preferences** — good at both code and math? List both
+
+---
+
+### How Arch-Router Uses Them
+
+When a request arrives, Plano constructs a prompt for the 1.5B Arch-Router model:
+
+```xml
+You are a helpful assistant designed to find the best suited route.
+
+
+[
+ {"name": "complex_reasoning", "description": "complex reasoning tasks, multi-step analysis"},
+ {"name": "code_generation", "description": "generating new code, writing functions"}
+]
+
+
+
+[{"role": "user", "content": "Write a Python function that implements binary search"}]
+
+
+Your task is to decide which route best suits the user intent...
+```
+
+The router classifies the intent and responds:
+```json
+{"route": "code_generation"}
+```
+
+Plano maps `code_generation` back to the model that owns it → `anthropic/claude-sonnet-4-20250514`.
+
+---
+
+### The Full Flow
+
+```
+1. Request arrives → "Write binary search in Python"
+2. Preferences serialized → [{"name":"code_generation", ...}, {"name":"complex_reasoning", ...}]
+3. Arch-Router classifies → {"route": "code_generation"}
+4. Route → Model lookup → code_generation → anthropic/claude-sonnet-4-20250514
+5. Request forwarded → Claude generates the response
+```
+
+No match? Arch-Router returns `{"route": "other"}` → Plano falls back to the default model.
+
+---
+
+### What Powers the Routing
+
+**Arch-Router** — a purpose-built 1.5B parameter model for intent classification.
+
+- Runs locally (Ollama) or hosted — no data leaves your network
+- Sub-100ms routing decisions
+- Handles multi-turn conversations (automatically truncates to fit context)
+- Based on preference-aligned routing research
+
+---
+
+## Multi-Format Support
+
+Same routing engine, any API format:
+
+| Endpoint | Format |
+|---|---|
+| `/routing/v1/chat/completions` | OpenAI Chat Completions |
+| `/routing/v1/messages` | Anthropic Messages |
+| `/routing/v1/responses` | OpenAI Responses API |
+
+---
+
+## Inline Routing Policy
+
+Clients can override routing at request time — no config change needed:
+
+```json
+{
+ "model": "gpt-4o-mini",
+ "messages": [{"role": "user", "content": "Write quicksort in Go"}],
+ "routing_policy": [
+ {
+ "model": "openai/gpt-4o",
+ "routing_preferences": [
+ {"name": "coding", "description": "code generation and debugging"}
+ ]
+ },
+ {
+ "model": "openai/gpt-4o-mini",
+ "routing_preferences": [
+ {"name": "general", "description": "simple questions and conversation"}
+ ]
+ }
+ ]
+}
+```
+
+Platform sets defaults. Teams override when needed.
+
+---
+
+## Beyond Routing
+
+Plano is a full AI data plane:
+
+- **Guardrails** — prompt/response filtering, PII detection
+- **Observability** — OpenTelemetry tracing, per-request metrics
+- **Rate Limiting** — token-aware rate limiting per model
+- **Multi-Provider** — OpenAI, Anthropic, Azure, Gemini, Groq, DeepSeek, Ollama, and more
+- **Model Aliases** — `arch.fast.v1` → `gpt-4o-mini` (swap providers without client changes)
+
+---
+
+## Key Takeaways
+
+1. **No SDK required** — standard API, any language, any framework
+2. **Semantic routing** — plain English preferences, not hand-coded rules
+3. **Self-hosted router** — 1.5B model runs locally, no data leaves the network
+4. **Inspect before you route** — decision-only endpoints for testing and CI/CD
+5. **Platform governance** — centralized keys, aliases, and routing policies
+
+---
+
+## Try It
+
+```bash
+pip install planoai
+export OPENAI_API_KEY=...
+export ANTHROPIC_API_KEY=...
+plano up -f config.yaml
+bash demo.sh
+```
+
+**GitHub:** github.com/katanemo/plano
diff --git a/docs/source/conf.py b/docs/source/conf.py
index ec476136..e554329f 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -17,7 +17,7 @@ from sphinxawesome_theme.postprocess import Icons
project = "Plano Docs"
copyright = "2025, Katanemo Labs, Inc"
author = "Katanemo Labs, Inc"
-release = " v0.4.11"
+release = " v0.4.12"
# -- General configuration ---------------------------------------------------
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
diff --git a/docs/source/get_started/quickstart.rst b/docs/source/get_started/quickstart.rst
index 279fde2d..9d51d1c4 100644
--- a/docs/source/get_started/quickstart.rst
+++ b/docs/source/get_started/quickstart.rst
@@ -43,7 +43,7 @@ Plano's CLI allows you to manage and interact with the Plano efficiently. To ins
.. code-block:: console
- $ uv tool install planoai==0.4.11
+ $ uv tool install planoai==0.4.12
**Option 2: Install with pip (Traditional)**
@@ -51,7 +51,7 @@ Plano's CLI allows you to manage and interact with the Plano efficiently. To ins
$ python -m venv venv
$ source venv/bin/activate # On Windows, use: venv\Scripts\activate
- $ pip install planoai==0.4.11
+ $ pip install planoai==0.4.12
.. _llm_routing_quickstart:
diff --git a/docs/source/resources/deployment.rst b/docs/source/resources/deployment.rst
index 7b8b0554..2689384e 100644
--- a/docs/source/resources/deployment.rst
+++ b/docs/source/resources/deployment.rst
@@ -65,7 +65,7 @@ Create a ``docker-compose.yml`` file with the following configuration:
# docker-compose.yml
services:
plano:
- image: katanemo/plano:0.4.11
+ image: katanemo/plano:0.4.12
container_name: plano
ports:
- "10000:10000" # ingress (client -> plano)
@@ -153,7 +153,7 @@ Create a ``plano-deployment.yaml``:
spec:
containers:
- name: plano
- image: katanemo/plano:0.4.11
+ image: katanemo/plano:0.4.12
ports:
- containerPort: 12000 # LLM gateway (chat completions, model routing)
name: llm-gateway