release 0.4.25 (#969)

* add teh system role into messages array

* ci: trigger workflows

* dont normalize for anthropic

---------

Co-authored-by: Spherrrical <malikmusa1323@gmail.com>

.github/workflows/ci.yml

@@ -117,7 +117,7 @@ jobs:
       # repo means find_repo_root() returns None, the local-build short-
       # circuit is skipped, and the CLI tries to download from a GitHub
       # release that does not yet exist for the in-flight version on
-      # release-bump PRs (e.g. 0.4.24 before publish-binaries has run).
+      # release-bump PRs (e.g. 0.4.25 before publish-binaries has run).
       - name: Seed ~/.plano cache for zero-config test
         run: |
           VERSION=$(sed -nE 's/^__version__ = "(.*)"$/\1/p' cli/planoai/__init__.py)
@@ -183,13 +183,13 @@ jobs:
           load: true
           tags: |
             ${{ env.PLANO_DOCKER_IMAGE }}
-            ${{ env.DOCKER_IMAGE }}:0.4.24
+            ${{ env.DOCKER_IMAGE }}:0.4.25
             ${{ 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 }}:0.4.24 ${{ env.DOCKER_IMAGE }}:latest -o /tmp/plano-image.tar
+        run: docker save ${{ env.PLANO_DOCKER_IMAGE }} ${{ env.DOCKER_IMAGE }}:0.4.25 ${{ env.DOCKER_IMAGE }}:latest -o /tmp/plano-image.tar
 
       - name: Upload image artifact
         uses: actions/upload-artifact@v6

apps/www/src/components/Hero.tsx

@@ -24,7 +24,7 @@ export function Hero() {
             >
               <div className="inline-flex flex-wrap items-center gap-1.5 sm:gap-2 px-3 sm:px-4 py-1 rounded-full bg-[rgba(185,191,255,0.4)] border border-[var(--secondary)] shadow backdrop-blur hover:bg-[rgba(185,191,255,0.6)] transition-colors cursor-pointer">
                 <span className="text-xs sm:text-sm font-medium text-black/65">
-                  v0.4.24
+                  v0.4.25
                 </span>
                 <span className="text-xs sm:text-sm font-medium text-black ">
                   —

build_filter_image.sh

@@ -1 +1 @@
-docker build  -f Dockerfile . -t katanemo/plano -t katanemo/plano:0.4.24
+docker build  -f Dockerfile . -t katanemo/plano -t katanemo/plano:0.4.25

cli/planoai/__init__.py

@@ -1,3 +1,3 @@
 """Plano CLI - Intelligent Prompt Gateway."""
 
-__version__ = "0.4.24"
+__version__ = "0.4.25"

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:0.4.24")
+PLANO_DOCKER_IMAGE = os.getenv("PLANO_DOCKER_IMAGE", "katanemo/plano:0.4.25")
 DEFAULT_OTEL_TRACING_GRPC_ENDPOINT = "http://localhost:4317"
 
 # Native mode constants

cli/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "planoai"
-version = "0.4.24"
+version = "0.4.25"
 description = "Python-based CLI tool to manage Plano."
 authors = [{name = "Katanemo Labs, Inc."}]
 readme = "README.md"

cli/uv.lock

@@ -337,7 +337,7 @@ wheels = [
 
 [[package]]
 name = "planoai"
-version = "0.4.24"
+version = "0.4.25"
 source = { editable = "." }
 dependencies = [
     { name = "click" },

crates/hermesllm/src/apis/anthropic.rs

@@ -128,6 +128,7 @@ pub struct MessagesRequest {
 pub enum MessagesRole {
     User,
     Assistant,
+    System,
 }
 
 /// Cache control types for content blocks
@@ -632,6 +633,7 @@ impl MessagesRole {
         match self {
             MessagesRole::User => "user",
             MessagesRole::Assistant => "assistant",
+            MessagesRole::System => "system",
         }
     }
 }

crates/hermesllm/src/transforms/request/from_anthropic.rs

@@ -223,6 +223,7 @@ impl From<MessagesRole> for Role {
         match val {
             MessagesRole::User => Role::User,
             MessagesRole::Assistant => Role::Assistant,
+            MessagesRole::System => Role::System,
         }
     }
 }
@@ -340,6 +341,11 @@ impl TryFrom<MessagesMessage> for BedrockMessage {
         let role = match message.role {
             MessagesRole::User => ConversationRole::User,
             MessagesRole::Assistant => ConversationRole::Assistant,
+            MessagesRole::System => {
+                return Err(TransformError::UnsupportedConversion(
+                    "System messages must be set via the system prompt, not messages".to_string(),
+                ));
+            }
         };
 
         let mut content_blocks = Vec::new();

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==0.4.24` or `uv tool install planoai==0.4.24`).
+Make sure you have Plano CLI installed (`pip install planoai==0.4.25` or `uv tool install planoai==0.4.25`).
 
 ```bash
 cd demos/llm_routing/preference_based_routing

docs/source/conf.py

@@ -17,7 +17,7 @@ from sphinxawesome_theme.postprocess import Icons
 project = "Plano Docs"
 copyright = "2026, Katanemo Labs, a DigitalOcean Company"
 author = "Katanemo Labs, Inc"
-release = " v0.4.24"
+release = " v0.4.25"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

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==0.4.24
+   $ uv tool install planoai==0.4.25
 
 **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==0.4.24
+   $ pip install planoai==0.4.25
 
 
 .. _llm_routing_quickstart:

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:0.4.24
+       image: katanemo/plano:0.4.25
        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:0.4.24
+             image: katanemo/plano:0.4.25
              ports:
                - containerPort: 12000  # LLM gateway (chat completions, model routing)
                  name: llm-gateway