Merge pull request #607 from tisnik/lcore-650-update-llama-stack-version-in-doc

LCORE-650: update Llama Stack version in documentation and examples

Author: tisnik

README.md

@@ -245,7 +245,7 @@ version = "0.1.0"
 description = "Llama Stack runner"
 authors = []
 dependencies = [
-    "llama-stack==0.2.20",
+    "llama-stack==0.2.21",
     "fastapi>=0.115.12",
     "opentelemetry-sdk>=1.34.0",
     "opentelemetry-exporter-otlp>=1.34.0",

docs/deployment_guide.md

@@ -390,7 +390,7 @@ cp examples/run.yaml /tmp/llama-stack-server
     The output should be in this form:
     ```json
     {
-      "version": "0.2.20"
+      "version": "0.2.21"
     }
     ```
 

docs/getting_started.md

@@ -24,7 +24,7 @@ It is possible to run Lightspeed Core Stack service with Llama Stack "embedded"
 1. Add and install all required dependencies
     ```bash
     uv add \
-    "llama-stack==0.2.20" \
+    "llama-stack==0.2.21" \
     "fastapi>=0.115.12" \
     "opentelemetry-sdk>=1.34.0" \
     "opentelemetry-exporter-otlp>=1.34.0" \
@@ -383,4 +383,4 @@ curl -X POST "http://localhost:8080/v1/query" \
 ```
 
 #### Step 4: Verify connectivity
-After starting the MCP servers and updating `lightspeed-stack.yaml`, test by sending a prompt to the AI agent. LCS evaluates the prompt against available tools’ metadata, selects the appropriate tool, calls the corresponding MCP server, and uses the result to generate more accurate agent response.
+After starting the MCP servers and updating `lightspeed-stack.yaml`, test by sending a prompt to the AI agent. LCS evaluates the prompt against available tools’ metadata, selects the appropriate tool, calls the corresponding MCP server, and uses the result to generate more accurate agent response.

docs/openapi.json

@@ -2153,7 +2153,7 @@
                     "llama_stack_version"
                 ],
                 "title": "InfoResponse",
-                "description": "Model representing a response to an info request.\n\nAttributes:\n    name: Service name.\n    service_version: Service version.\n    llama_stack_version: Llama Stack version.\n\nExample:\n    ```python\n    info_response = InfoResponse(\n        name=\"Lightspeed Stack\",\n        service_version=\"1.0.0\",\n        llama_stack_version=\"0.2.20\",\n    )\n    ```",
+                "description": "Model representing a response to an info request.\n\nAttributes:\n    name: Service name.\n    service_version: Service version.\n    llama_stack_version: Llama Stack version.\n\nExample:\n    ```python\n    info_response = InfoResponse(\n        name=\"Lightspeed Stack\",\n        service_version=\"1.0.0\",\n        llama_stack_version=\"0.2.21\",\n    )\n    ```",
                 "examples": [
                     {
                         "llama_stack_version": "1.0.0",
@@ -3159,4 +3159,4 @@
             }
         }
     }
-}
+}

docs/openapi.md

@@ -1011,7 +1011,7 @@ Example:
     info_response = InfoResponse(
         name="Lightspeed Stack",
         service_version="1.0.0",
-        llama_stack_version="0.2.20",
+        llama_stack_version="0.2.21",
     )
     ```
 

docs/output.md

@@ -1011,7 +1011,7 @@ Example:
     info_response = InfoResponse(
         name="Lightspeed Stack",
         service_version="1.0.0",
-        llama_stack_version="0.2.20",
+        llama_stack_version="0.2.21",
     )
     ```
 

examples/pyproject.llamastack.toml

@@ -4,7 +4,7 @@ version = "0.1.0"
 description = "Default template for PDM package"
 authors = []
 dependencies = [
-    "llama-stack==0.2.20",
+    "llama-stack==0.2.21",
     "fastapi>=0.115.12",
     "opentelemetry-sdk>=1.34.0",
     "opentelemetry-exporter-otlp>=1.34.0",

src/models/responses.py

@@ -164,7 +164,7 @@ class InfoResponse(BaseModel):
         info_response = InfoResponse(
             name="Lightspeed Stack",
             service_version="1.0.0",
-            llama_stack_version="0.2.20",
+            llama_stack_version="0.2.21",
         )
         ```
     """