Merge branch 'main' into responses_object

.github/workflows/pre-commit.yml

@@ -36,6 +36,21 @@ jobs:
             **/requirements*.txt
             .pre-commit-config.yaml
 
+      # npm ci may fail -
+      #   npm error `npm ci` can only install packages when your package.json and package-lock.json or npm-shrinkwrap.json are in sync. Please update your lock file with `npm install` before continuing.
+      #   npm error Invalid: lock file's llama-stack-client@0.2.17 does not satisfy llama-stack-client@0.2.18
+
+      # - name: Set up Node.js
+      #   uses: actions/setup-node@39370e3970a6d050c480ffad4ff0ed4d3fdee5af # v4.1.0
+      #   with:
+      #     node-version: '20'
+      #     cache: 'npm'
+      #     cache-dependency-path: 'llama_stack/ui/'
+
+      # - name: Install npm dependencies
+      #   run: npm ci
+      #   working-directory: llama_stack/ui
+
       - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
         continue-on-error: true
         env:

.pre-commit-config.yaml

@@ -146,20 +146,50 @@ repos:
         pass_filenames: false
         require_serial: true
         files: ^.github/workflows/.*$
-      - id: ui-prettier
+      # ui-prettier and ui-eslint are disabled until we can avoid `npm ci`, which is slow and may fail -
-        name: Format UI code with Prettier
+      #   npm error `npm ci` can only install packages when your package.json and package-lock.json or npm-shrinkwrap.json are in sync. Please update your lock file with `npm install` before continuing.
-        entry: bash -c 'cd llama_stack/ui && npm run format'
+      #   npm error Invalid: lock file's llama-stack-client@0.2.17 does not satisfy llama-stack-client@0.2.18
+      # and until we have infra for installing prettier and next via npm -
+      #   Lint UI code with ESLint.....................................................Failed
+      #   - hook id: ui-eslint
+      #   - exit code: 127
+      #   > ui@0.1.0 lint
+      #   > next lint --fix --quiet
+      #   sh: line 1: next: command not found
+      #
+      # - id: ui-prettier
+      #   name: Format UI code with Prettier
+      #   entry: bash -c 'cd llama_stack/ui && npm ci && npm run format'
+      #   language: system
+      #   files: ^llama_stack/ui/.*\.(ts|tsx)$
+      #   pass_filenames: false
+      #   require_serial: true
+      # - id: ui-eslint
+      #   name: Lint UI code with ESLint
+      #   entry: bash -c 'cd llama_stack/ui && npm run lint -- --fix --quiet'
+      #   language: system
+      #   files: ^llama_stack/ui/.*\.(ts|tsx)$
+      #   pass_filenames: false
+      #   require_serial: true
+
+      - id: check-log-usage
+        name: Ensure 'llama_stack.log' usage for logging
+        entry: bash
         language: system
-        files: ^llama_stack/ui/.*\.(ts|tsx)$
+        types: [python]
-        pass_filenames: false
+        pass_filenames: true
-        require_serial: true
+        args:
-      - id: ui-eslint
+          - -c
-        name: Lint UI code with ESLint
+          - |
-        entry: bash -c 'cd llama_stack/ui && npm run lint -- --fix --quiet'
+            matches=$(grep -EnH '^[^#]*\b(import\s+logging|from\s+logging\b)' "$@" | grep -v -e '#\s*allow-direct-logging' || true)
-        language: system
+            if [ -n "$matches" ]; then
-        files: ^llama_stack/ui/.*\.(ts|tsx)$
+              # GitHub Actions annotation format
-        pass_filenames: false
+              while IFS=: read -r file line_num rest; do
-        require_serial: true
+                echo "::error file=$file,line=$line_num::Do not use 'import logging' or 'from logging import' in $file. Use the custom log instead: from llama_stack.log import get_logger; logger = get_logger(). If direct logging is truly needed, add: # allow-direct-logging"
+              done <<< "$matches"
+              exit 1
+            fi
+            exit 0
 
 ci:
     autofix_commit_msg: 🎨 [pre-commit.ci] Auto format from pre-commit.com hooks

docs/_static/llama-stack-spec.html

@@ -8585,6 +8585,21 @@
                 "title": "OpenAIResponseError",
                 "description": "Error details for failed OpenAI response requests."
             },
+            "OpenAIResponseIncompleteDetails": {
+                "type": "object",
+                "properties": {
+                    "reason": {
+                        "type": "string",
+                        "description": "Reason for the response being incomplete"
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "reason"
+                ],
+                "title": "OpenAIResponseIncompleteDetails",
+                "description": "Incomplete details for OpenAI responses."
+            },
             "OpenAIResponseObject": {
                 "type": "object",
                 "properties": {
@@ -8600,6 +8615,39 @@
                         "type": "string",
                         "description": "Unique identifier for this response"
                     },
+                    "incomplete_details": {
+                        "$ref": "#/components/schemas/OpenAIResponseIncompleteDetails",
+                        "description": "(Optional) Incomplete details if the response is incomplete"
+                    },
+                    "instructions": {
+                        "oneOf": [
+                            {
+                                "type": "string"
+                            },
+                            {
+                                "type": "array",
+                                "items": {
+                                    "type": "string"
+                                }
+                            }
+                        ],
+                        "description": "(Optional) A system (or developer) message inserted into the model's context."
+                    },
+                    "max_output_tokens": {
+                        "type": "integer",
+                        "description": "(Optional) An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens."
+                    },
+                    "max_tool_calls": {
+                        "type": "integer",
+                        "description": "(Optional) The maximum number of total calls to built-in tools that can be processed in a response."
+                    },
+                    "metadata": {
+                        "type": "object",
+                        "additionalProperties": {
+                            "type": "string"
+                        },
+                        "description": "(Optional) Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard."
+                    },
                     "model": {
                         "type": "string",
                         "description": "Model identifier used for generation"
@@ -8626,6 +8674,26 @@
                         "type": "string",
                         "description": "(Optional) ID of the previous response in a conversation"
                     },
+                    "prompt": {
+                        "$ref": "#/components/schemas/OpenAIResponsePrompt",
+                        "description": "(Optional) Reference to a prompt template and its variables."
+                    },
+                    "prompt_cache_key": {
+                        "type": "string",
+                        "description": "(Optional)Used to cache responses for similar requests to optimize your cache hit rates. Replaces the user field."
+                    },
+                    "reasoning": {
+                        "$ref": "#/components/schemas/OpenAIResponseReasoning",
+                        "description": "(Optional) Configuration options for reasoning models."
+                    },
+                    "safety_identifier": {
+                        "type": "string",
+                        "description": "(Optional) A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies."
+                    },
+                    "service_tier": {
+                        "type": "string",
+                        "description": "(Optional) Specifies the processing type used for serving the request."
+                    },
                     "status": {
                         "type": "string",
                         "description": "Current status of the response generation"
@@ -8638,17 +8706,29 @@
                         "$ref": "#/components/schemas/OpenAIResponseText",
                         "description": "Text formatting configuration for the response"
                     },
+                    "tool_choice": {
+                        "$ref": "#/components/schemas/OpenAIResponsesToolChoice"
+                    },
+                    "tools": {
+                        "type": "array",
+                        "items": {
+                            "$ref": "#/components/schemas/OpenAIResponsesTool"
+                        }
+                    },
+                    "top_logprobs": {
+                        "type": "integer"
+                    },
                     "top_p": {
                         "type": "number",
                         "description": "(Optional) Nucleus sampling parameter used for generation"
                     },
-                    "truncation": {
-                        "type": "string",
-                        "description": "(Optional) Truncation strategy applied to the response"
-                    },
                     "user": {
                         "type": "string",
                         "description": "(Optional) User identifier associated with the request"
+                    },
+                    "truncation": {
+                        "type": "string",
+                        "description": "(Optional) Truncation strategy applied to the response"
                     }
                 },
                 "additionalProperties": false,
@@ -8659,11 +8739,10 @@
                     "object",
                     "output",
                     "parallel_tool_calls",
-                    "status",
+                    "status"
-                    "text"
                 ],
                 "title": "OpenAIResponseObject",
-                "description": "Complete OpenAI response object containing generation results and metadata."
+                "description": "Complete OpenAI response object containing generation results and metadata.\nBased on OpenAI Responses API schema: https://github.com/openai/openai-python/blob/34014aedbb8946c03e97e5c8d72e03ad2259cd7c/src/openai/types/responses/response.py#L38"
             },
             "OpenAIResponseOutput": {
                 "oneOf": [
@@ -8821,6 +8900,103 @@
                 "title": "OpenAIResponseOutputMessageMCPListTools",
                 "description": "MCP list tools output message containing available tools from an MCP server."
             },
+            "OpenAIResponsePrompt": {
+                "type": "object",
+                "properties": {
+                    "id": {
+                        "type": "string",
+                        "description": "The unique identifier of the prompt template to use."
+                    },
+                    "variables": {
+                        "type": "object",
+                        "additionalProperties": {
+                            "oneOf": [
+                                {
+                                    "type": "null"
+                                },
+                                {
+                                    "type": "boolean"
+                                },
+                                {
+                                    "type": "number"
+                                },
+                                {
+                                    "type": "string"
+                                },
+                                {
+                                    "type": "array"
+                                },
+                                {
+                                    "type": "object"
+                                }
+                            ]
+                        },
+                        "description": "(Optional) Map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files."
+                    },
+                    "version": {
+                        "type": "string",
+                        "description": "(Optional) Version of the prompt template."
+                    }
+                },
+                "additionalProperties": false,
+                "required": [
+                    "id"
+                ],
+                "title": "OpenAIResponsePrompt",
+                "description": "Reference to a prompt template and its variables."
+            },
+            "OpenAIResponseReasoning": {
+                "type": "object",
+                "properties": {
+                    "effort": {
+                        "type": "string",
+                        "enum": [
+                            "low",
+                            "medium",
+                            "high",
+                            "minimal"
+                        ],
+                        "description": "(Optional) The effort level to use for reasoning."
+                    },
+                    "generate_summary": {
+                        "type": "string",
+                        "description": "Deprecated. Use the generate_summary_text field instead. (Optional) Whether to generate a summary of the reasoning process."
+                    },
+                    "summary": {
+                        "type": "string"
+                    }
+                },
+                "additionalProperties": false,
+                "title": "OpenAIResponseReasoning",
+                "description": "Configuration options for reasoning models."
+            },
+            "OpenAIResponsesTool": {
+                "type": "object",
+                "properties": {
+                    "description": {
+                        "type": "string"
+                    },
+                    "name": {
+                        "type": "string"
+                    },
+                    "parameters": {
+                        "type": "object",
+                        "title": "object",
+                        "description": "The base class of the class hierarchy.\nWhen called, it accepts no arguments and returns a new featureless\ninstance that has no instance attributes and cannot be given any."
+                    },
+                    "type": {
+                        "type": "string",
+                        "const": "function"
+                    }
+                },
+                "additionalProperties": false,
+                "title": "OpenAIResponsesTool"
+            },
+            "OpenAIResponsesToolChoice": {
+                "type": "object",
+                "title": "OpenAIResponsesToolChoice",
+                "description": "Type alias.\nType aliases are created through the type statement::\n\n    type Alias = int\n\nIn this example, Alias and int will be treated equivalently by static\ntype checkers.\n\nAt runtime, Alias is an instance of TypeAliasType. The __name__\nattribute holds the name of the type alias. The value of the type alias\nis stored in the __value__ attribute. It is evaluated lazily, so the\nvalue is computed only if the attribute is accessed.\n\nType aliases can also be generic::\n\n    type ListOrSet[T] = list[T] | set[T]\n\nIn this case, the type parameters of the alias are stored in the\n__type_params__ attribute.\n\nSee PEP 695 for more information."
+            },
             "OpenAIResponseContentPart": {
                 "oneOf": [
                     {
@@ -12744,6 +12920,39 @@
                         "type": "string",
                         "description": "Unique identifier for this response"
                     },
+                    "incomplete_details": {
+                        "$ref": "#/components/schemas/OpenAIResponseIncompleteDetails",
+                        "description": "(Optional) Incomplete details if the response is incomplete"
+                    },
+                    "instructions": {
+                        "oneOf": [
+                            {
+                                "type": "string"
+                            },
+                            {
+                                "type": "array",
+                                "items": {
+                                    "type": "string"
+                                }
+                            }
+                        ],
+                        "description": "(Optional) A system (or developer) message inserted into the model's context."
+                    },
+                    "max_output_tokens": {
+                        "type": "integer",
+                        "description": "(Optional) An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens."
+                    },
+                    "max_tool_calls": {
+                        "type": "integer",
+                        "description": "(Optional) The maximum number of total calls to built-in tools that can be processed in a response."
+                    },
+                    "metadata": {
+                        "type": "object",
+                        "additionalProperties": {
+                            "type": "string"
+                        },
+                        "description": "(Optional) Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard."
+                    },
                     "model": {
                         "type": "string",
                         "description": "Model identifier used for generation"
@@ -12770,6 +12979,26 @@
                         "type": "string",
                         "description": "(Optional) ID of the previous response in a conversation"
                     },
+                    "prompt": {
+                        "$ref": "#/components/schemas/OpenAIResponsePrompt",
+                        "description": "(Optional) Reference to a prompt template and its variables."
+                    },
+                    "prompt_cache_key": {
+                        "type": "string",
+                        "description": "(Optional)Used to cache responses for similar requests to optimize your cache hit rates. Replaces the user field."
+                    },
+                    "reasoning": {
+                        "$ref": "#/components/schemas/OpenAIResponseReasoning",
+                        "description": "(Optional) Configuration options for reasoning models."
+                    },
+                    "safety_identifier": {
+                        "type": "string",
+                        "description": "(Optional) A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies."
+                    },
+                    "service_tier": {
+                        "type": "string",
+                        "description": "(Optional) Specifies the processing type used for serving the request."
+                    },
                     "status": {
                         "type": "string",
                         "description": "Current status of the response generation"
@@ -12782,18 +13011,30 @@
                         "$ref": "#/components/schemas/OpenAIResponseText",
                         "description": "Text formatting configuration for the response"
                     },
+                    "tool_choice": {
+                        "$ref": "#/components/schemas/OpenAIResponsesToolChoice"
+                    },
+                    "tools": {
+                        "type": "array",
+                        "items": {
+                            "$ref": "#/components/schemas/OpenAIResponsesTool"
+                        }
+                    },
+                    "top_logprobs": {
+                        "type": "integer"
+                    },
                     "top_p": {
                         "type": "number",
                         "description": "(Optional) Nucleus sampling parameter used for generation"
                     },
-                    "truncation": {
-                        "type": "string",
-                        "description": "(Optional) Truncation strategy applied to the response"
-                    },
                     "user": {
                         "type": "string",
                         "description": "(Optional) User identifier associated with the request"
                     },
+                    "truncation": {
+                        "type": "string",
+                        "description": "(Optional) Truncation strategy applied to the response"
+                    },
                     "input": {
                         "type": "array",
                         "items": {
@@ -12811,7 +13052,6 @@
                     "output",
                     "parallel_tool_calls",
                     "status",
-                    "text",
                     "input"
                 ],
                 "title": "OpenAIResponseObjectWithInput",

docs/_static/llama-stack-spec.yaml

@@ -6249,6 +6249,17 @@ components:
       title: OpenAIResponseError
       description: >-
         Error details for failed OpenAI response requests.
+    OpenAIResponseIncompleteDetails:
+      type: object
+      properties:
+        reason:
+          type: string
+          description: Reason for the response being incomplete
+      additionalProperties: false
+      required:
+        - reason
+      title: OpenAIResponseIncompleteDetails
+      description: Incomplete details for OpenAI responses.
     OpenAIResponseObject:
       type: object
       properties:
@@ -6263,6 +6274,36 @@ components:
         id:
           type: string
           description: Unique identifier for this response
+        incomplete_details:
+          $ref: '#/components/schemas/OpenAIResponseIncompleteDetails'
+          description: >-
+            (Optional) Incomplete details if the response is incomplete
+        instructions:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                type: string
+          description: >-
+            (Optional) A system (or developer) message inserted into the model's context.
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) An upper bound for the number of tokens that can be generated
+            for a response, including visible output tokens and reasoning tokens.
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) The maximum number of total calls to built-in tools that can
+            be processed in a response.
+        metadata:
+          type: object
+          additionalProperties:
+            type: string
+          description: >-
+            (Optional) Set of 16 key-value pairs that can be attached to an object.
+            This can be useful for storing additional information about the object
+            in a structured format, and querying for objects via API or the dashboard.
         model:
           type: string
           description: Model identifier used for generation
@@ -6287,6 +6328,28 @@ components:
           type: string
           description: >-
             (Optional) ID of the previous response in a conversation
+        prompt:
+          $ref: '#/components/schemas/OpenAIResponsePrompt'
+          description: >-
+            (Optional) Reference to a prompt template and its variables.
+        prompt_cache_key:
+          type: string
+          description: >-
+            (Optional)Used to cache responses for similar requests to optimize your
+            cache hit rates. Replaces the user field.
+        reasoning:
+          $ref: '#/components/schemas/OpenAIResponseReasoning'
+          description: >-
+            (Optional) Configuration options for reasoning models.
+        safety_identifier:
+          type: string
+          description: >-
+            (Optional) A stable identifier used to help detect users of your application
+            that may be violating OpenAI's usage policies.
+        service_tier:
+          type: string
+          description: >-
+            (Optional) Specifies the processing type used for serving the request.
         status:
           type: string
           description: >-
@@ -6299,18 +6362,26 @@ components:
           $ref: '#/components/schemas/OpenAIResponseText'
           description: >-
             Text formatting configuration for the response
+        tool_choice:
+          $ref: '#/components/schemas/OpenAIResponsesToolChoice'
+        tools:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAIResponsesTool'
+        top_logprobs:
+          type: integer
         top_p:
           type: number
           description: >-
             (Optional) Nucleus sampling parameter used for generation
-        truncation:
-          type: string
-          description: >-
-            (Optional) Truncation strategy applied to the response
         user:
           type: string
           description: >-
             (Optional) User identifier associated with the request
+        truncation:
+          type: string
+          description: >-
+            (Optional) Truncation strategy applied to the response
       additionalProperties: false
       required:
         - created_at
@@ -6320,10 +6391,11 @@ components:
         - output
         - parallel_tool_calls
         - status
-        - text
       title: OpenAIResponseObject
       description: >-
         Complete OpenAI response object containing generation results and metadata.
+
+        Based on OpenAI Responses API schema: https://github.com/openai/openai-python/blob/34014aedbb8946c03e97e5c8d72e03ad2259cd7c/src/openai/types/responses/response.py#L38
     OpenAIResponseOutput:
       oneOf:
         - $ref: '#/components/schemas/OpenAIResponseMessage'
@@ -6441,6 +6513,115 @@ components:
       title: OpenAIResponseOutputMessageMCPListTools
       description: >-
         MCP list tools output message containing available tools from an MCP server.
+    OpenAIResponsePrompt:
+      type: object
+      properties:
+        id:
+          type: string
+          description: >-
+            The unique identifier of the prompt template to use.
+        variables:
+          type: object
+          additionalProperties:
+            oneOf:
+              - type: 'null'
+              - type: boolean
+              - type: number
+              - type: string
+              - type: array
+              - type: object
+          description: >-
+            (Optional) Map of values to substitute in for variables in your prompt.
+            The substitution values can either be strings, or other Response input
+            types like images or files.
+        version:
+          type: string
+          description: >-
+            (Optional) Version of the prompt template.
+      additionalProperties: false
+      required:
+        - id
+      title: OpenAIResponsePrompt
+      description: >-
+        Reference to a prompt template and its variables.
+    OpenAIResponseReasoning:
+      type: object
+      properties:
+        effort:
+          type: string
+          enum:
+            - low
+            - medium
+            - high
+            - minimal
+          description: >-
+            (Optional) The effort level to use for reasoning.
+        generate_summary:
+          type: string
+          description: >-
+            Deprecated. Use the generate_summary_text field instead. (Optional) Whether
+            to generate a summary of the reasoning process.
+        summary:
+          type: string
+      additionalProperties: false
+      title: OpenAIResponseReasoning
+      description: >-
+        Configuration options for reasoning models.
+    OpenAIResponsesTool:
+      type: object
+      properties:
+        description:
+          type: string
+        name:
+          type: string
+        parameters:
+          type: object
+          title: object
+          description: >-
+            The base class of the class hierarchy.
+
+            When called, it accepts no arguments and returns a new featureless
+
+            instance that has no instance attributes and cannot be given any.
+        type:
+          type: string
+          const: function
+      additionalProperties: false
+      title: OpenAIResponsesTool
+    OpenAIResponsesToolChoice:
+      type: object
+      title: OpenAIResponsesToolChoice
+      description: >-
+        Type alias.
+
+        Type aliases are created through the type statement::
+
+            type Alias = int
+
+        In this example, Alias and int will be treated equivalently by static
+
+        type checkers.
+
+
+        At runtime, Alias is an instance of TypeAliasType. The __name__
+
+        attribute holds the name of the type alias. The value of the type alias
+
+        is stored in the __value__ attribute. It is evaluated lazily, so the
+
+        value is computed only if the attribute is accessed.
+
+
+        Type aliases can also be generic::
+
+            type ListOrSet[T] = list[T] | set[T]
+
+        In this case, the type parameters of the alias are stored in the
+
+        __type_params__ attribute.
+
+
+        See PEP 695 for more information.
     OpenAIResponseContentPart:
       oneOf:
         - $ref: '#/components/schemas/OpenAIResponseContentPartOutputText'
@@ -9464,6 +9645,36 @@ components:
         id:
           type: string
           description: Unique identifier for this response
+        incomplete_details:
+          $ref: '#/components/schemas/OpenAIResponseIncompleteDetails'
+          description: >-
+            (Optional) Incomplete details if the response is incomplete
+        instructions:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                type: string
+          description: >-
+            (Optional) A system (or developer) message inserted into the model's context.
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) An upper bound for the number of tokens that can be generated
+            for a response, including visible output tokens and reasoning tokens.
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) The maximum number of total calls to built-in tools that can
+            be processed in a response.
+        metadata:
+          type: object
+          additionalProperties:
+            type: string
+          description: >-
+            (Optional) Set of 16 key-value pairs that can be attached to an object.
+            This can be useful for storing additional information about the object
+            in a structured format, and querying for objects via API or the dashboard.
         model:
           type: string
           description: Model identifier used for generation
@@ -9488,6 +9699,28 @@ components:
           type: string
           description: >-
             (Optional) ID of the previous response in a conversation
+        prompt:
+          $ref: '#/components/schemas/OpenAIResponsePrompt'
+          description: >-
+            (Optional) Reference to a prompt template and its variables.
+        prompt_cache_key:
+          type: string
+          description: >-
+            (Optional)Used to cache responses for similar requests to optimize your
+            cache hit rates. Replaces the user field.
+        reasoning:
+          $ref: '#/components/schemas/OpenAIResponseReasoning'
+          description: >-
+            (Optional) Configuration options for reasoning models.
+        safety_identifier:
+          type: string
+          description: >-
+            (Optional) A stable identifier used to help detect users of your application
+            that may be violating OpenAI's usage policies.
+        service_tier:
+          type: string
+          description: >-
+            (Optional) Specifies the processing type used for serving the request.
         status:
           type: string
           description: >-
@@ -9500,18 +9733,26 @@ components:
           $ref: '#/components/schemas/OpenAIResponseText'
           description: >-
             Text formatting configuration for the response
+        tool_choice:
+          $ref: '#/components/schemas/OpenAIResponsesToolChoice'
+        tools:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAIResponsesTool'
+        top_logprobs:
+          type: integer
         top_p:
           type: number
           description: >-
             (Optional) Nucleus sampling parameter used for generation
-        truncation:
-          type: string
-          description: >-
-            (Optional) Truncation strategy applied to the response
         user:
           type: string
           description: >-
             (Optional) User identifier associated with the request
+        truncation:
+          type: string
+          description: >-
+            (Optional) Truncation strategy applied to the response
         input:
           type: array
           items:
@@ -9527,7 +9768,6 @@ components:
         - output
         - parallel_tool_calls
         - status
-        - text
         - input
       title: OpenAIResponseObjectWithInput
       description: >-

docs/source/distributions/k8s-benchmark/benchmark.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
 #

llama_stack/apis/agents/openai_responses.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Annotated, Any, Literal, Optional
+from typing import Annotated, Any, Literal, Union
 
 from pydantic import BaseModel, Field
 from typing_extensions import TypedDict
@@ -19,9 +19,16 @@ from llama_stack.apis.tools.openai_tool_choice import (
 from llama_stack.apis.vector_io import SearchRankingOptions as FileSearchRankingOptions
 from llama_stack.schema_utils import json_schema_type, register_schema
 
-type OpenAIResponsesToolChoice = (
+type OpenAIResponsesToolChoice = Annotated[
-    ToolChoiceTypes | ToolChoiceAllowed | ToolChoiceFunction | ToolChoiceMcp | ToolChoiceCustom
+    Union[
-)
+        ToolChoiceTypes,
+        ToolChoiceAllowed,
+        ToolChoiceFunction,
+        ToolChoiceMcp,
+        ToolChoiceCustom
+    ],
+    Field(discriminator="type"),
+]
 register_schema(OpenAIResponsesToolChoice, name="OpenAIResponsesToolChoice")
 
 
@@ -420,30 +427,30 @@ class OpenAIResponseObject(BaseModel):
     created_at: int
     error: OpenAIResponseError | None = None
     id: str
-    incomplete_details: Optional[OpenAIResponseIncompleteDetails] = None
+    incomplete_details: OpenAIResponseIncompleteDetails | None = None
-    instructions: Optional[str | list[str]] = None
+    instructions: str | list[str] | None = None
-    max_output_tokens: Optional[int] = None
+    max_output_tokens: int | None = None
-    max_tool_calls: Optional[int] = None 
+    max_tool_calls: int | None = None
-    metadata: Optional[dict[str, str]] = None 
+    metadata: dict[str, str] | None = None
     model: str
     object: Literal["response"] = "response"
     output: list[OpenAIResponseOutput]
     parallel_tool_calls: bool = False
-    previous_response_id: Optional[str] = None 
+    previous_response_id: str | None = None
-    prompt: Optional[OpenAIResponsePrompt] = None 
+    prompt: OpenAIResponsePrompt | None = None
-    prompt_cache_key: Optional[str] = None 
+    prompt_cache_key: str | None = None
-    reasoning: Optional[OpenAIResponseReasoning] = None 
+    reasoning: OpenAIResponseReasoning | None = None
-    safety_identifier: Optional[str] = None 
+    safety_identifier: str | None = None
-    service_tier: Optional[str] = None 
+    service_tier: str | None = None
     status: str
     temperature: float | None = None
-    text: Optional[OpenAIResponseText] = None
+    text: OpenAIResponseText | None = None
-    tool_choice:  Optional[OpenAIResponsesToolChoice] = None 
+    tool_choice: OpenAIResponsesToolChoice | None = None
-    tools: Optional[list[OpenAIResponsesTool]] = None 
+    tools: list[OpenAIResponsesTool] | None = None
-    top_logprobs: Optional[int] = None 
+    top_logprobs: int | None = None
-    top_p: Optional[float] = None
+    top_p: float | None = None
-    user: Optional[str] = None # Deprecated: This field is being replaced by safety_identifier and prompt_cache_key
+    user: str | None = None  # Deprecated: This field is being replaced by safety_identifier and prompt_cache_key
-    truncation: Optional[str] = None
+    truncation: str | None = None
 
 
 @json_schema_type

llama_stack/core/build.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import importlib.resources
-import logging
 import sys
 
 from pydantic import BaseModel
@@ -17,9 +16,10 @@ from llama_stack.core.external import load_external_apis
 from llama_stack.core.utils.exec import run_command
 from llama_stack.core.utils.image_types import LlamaStackImageType
 from llama_stack.distributions.template import DistributionTemplate
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="core")
 
 # These are the dependencies needed by the distribution server.
 # `llama-stack` is automatically installed by the installation script.

llama_stack/core/configure.py

@@ -3,7 +3,6 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-import logging
 import textwrap
 from typing import Any
 
@@ -21,9 +20,10 @@ from llama_stack.core.stack import cast_image_name_to_string, replace_env_vars
 from llama_stack.core.utils.config_dirs import EXTERNAL_PROVIDERS_DIR
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.prompt_for_config import prompt_for_config
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, ProviderSpec
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="core")
 
 
 def configure_single_provider(registry: dict[str, ProviderSpec], provider: Provider) -> Provider:

llama_stack/core/library_client.py

@@ -7,7 +7,7 @@
 import asyncio
 import inspect
 import json
-import logging
+import logging  # allow-direct-logging
 import os
 import sys
 from concurrent.futures import ThreadPoolExecutor
@@ -48,6 +48,7 @@ from llama_stack.core.stack import (
 from llama_stack.core.utils.config import redact_sensitive_fields
 from llama_stack.core.utils.context import preserve_contexts_async_generator
 from llama_stack.core.utils.exec import in_notebook
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.telemetry.tracing import (
     CURRENT_TRACE_CONTEXT,
     end_trace,
@@ -55,7 +56,7 @@ from llama_stack.providers.utils.telemetry.tracing import (
     start_trace,
 )
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="core")
 
 T = TypeVar("T")
 

llama_stack/core/request_headers.py

@@ -6,15 +6,15 @@
 
 import contextvars
 import json
-import logging
 from contextlib import AbstractContextManager
 from typing import Any
 
 from llama_stack.core.datatypes import User
+from llama_stack.log import get_logger
 
 from .utils.dynamic import instantiate_class_type
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="core")
 
 # Context variable for request provider data and auth attributes
 PROVIDER_DATA_VAR = contextvars.ContextVar("provider_data", default=None)

llama_stack/core/server/server.py

@@ -9,7 +9,7 @@ import asyncio
 import functools
 import inspect
 import json
-import logging
+import logging  # allow-direct-logging
 import os
 import ssl
 import sys

llama_stack/core/utils/exec.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
+import importlib
 import os
 import signal
 import subprocess
@@ -12,9 +12,9 @@ import sys
 
 from termcolor import cprint
 
-log = logging.getLogger(__name__)
+from llama_stack.log import get_logger
 
-import importlib
+log = get_logger(name=__name__, category="core")
 
 
 def formulate_run_args(image_type: str, image_name: str) -> list:

llama_stack/core/utils/prompt_for_config.py

@@ -6,7 +6,6 @@
 
 import inspect
 import json
-import logging
 from enum import Enum
 from typing import Annotated, Any, Literal, Union, get_args, get_origin
 
@@ -14,7 +13,9 @@ from pydantic import BaseModel
 from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefinedType
 
-log = logging.getLogger(__name__)
+from llama_stack.log import get_logger
+
+log = get_logger(name=__name__, category="core")
 
 
 def is_list_of_primitives(field_type):

llama_stack/log.py

@@ -4,10 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
+import logging  # allow-direct-logging
 import os
 import re
-from logging.config import dictConfig
+from logging.config import dictConfig  # allow-direct-logging
 
 from rich.console import Console
 from rich.errors import MarkupError

llama_stack/models/llama/llama3/multimodal/encoder_utils.py

@@ -13,14 +13,15 @@
 
 # Copyright (c) Meta Platforms, Inc. and its affiliates.
 import math
-from logging import getLogger
 
 import torch
 import torch.nn.functional as F
 
+from llama_stack.log import get_logger
+
 from .utils import get_negative_inf_value, to_2tuple
 
-logger = getLogger()
+logger = get_logger(name=__name__, category="models::llama")
 
 
 def resize_local_position_embedding(orig_pos_embed, grid_size):

llama_stack/models/llama/llama3/multimodal/image_transform.py

@@ -13,7 +13,6 @@
 
 import math
 from collections import defaultdict
-from logging import getLogger
 from typing import Any
 
 import torch
@@ -21,9 +20,11 @@ import torchvision.transforms as tv
 from PIL import Image
 from torchvision.transforms import functional as F
 
+from llama_stack.log import get_logger
+
 IMAGE_RES = 224
 
-logger = getLogger()
+logger = get_logger(name=__name__, category="models::llama")
 
 
 class VariableSizeImageTransform:

llama_stack/models/llama/llama3/multimodal/model.py

@@ -3,8 +3,6 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-
-import logging
 import math
 from collections.abc import Callable
 from functools import partial
@@ -22,6 +20,8 @@ from PIL import Image as PIL_Image
 from torch import Tensor, nn
 from torch.distributed import _functional_collectives as funcol
 
+from llama_stack.log import get_logger
+
 from ..model import ModelArgs, RMSNorm, apply_rotary_emb, precompute_freqs_cis
 from .encoder_utils import (
     build_encoder_attention_mask,
@@ -34,9 +34,10 @@ from .encoder_utils import (
 from .image_transform import VariableSizeImageTransform
 from .utils import get_negative_inf_value, to_2tuple
 
-logger = logging.getLogger(__name__)
 MP_SCALE = 8
 
+logger = get_logger(name=__name__, category="models")
+
 
 def reduce_from_tensor_model_parallel_region(input_):
     """All-reduce the input tensor across model parallel group."""
@@ -771,7 +772,7 @@ class TilePositionEmbedding(nn.Module):
         if embed is not None:
             # reshape the weights to the correct shape
             nt_old, nt_old, _, w = embed.shape
-            logging.info(f"Resizing tile embedding from {nt_old}x{nt_old} to {self.num_tiles}x{self.num_tiles}")
+            logger.info(f"Resizing tile embedding from {nt_old}x{nt_old} to {self.num_tiles}x{self.num_tiles}")
             embed_new = TilePositionEmbedding._dynamic_resize(embed, self.num_tiles)
             # assign the weights to the module
             state_dict[prefix + "embedding"] = embed_new

llama_stack/models/llama/llama3/tokenizer.py

@@ -4,8 +4,8 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+
 from collections.abc import Collection, Iterator, Sequence, Set
-from logging import getLogger
 from pathlib import Path
 from typing import (
     Literal,
@@ -14,11 +14,9 @@ from typing import (
 
 import tiktoken
 
+from llama_stack.log import get_logger
 from llama_stack.models.llama.tokenizer_utils import load_bpe_file
 
-logger = getLogger(__name__)
-
-
 # The tiktoken tokenizer can handle <=400k chars without
 # pyo3_runtime.PanicException.
 TIKTOKEN_MAX_ENCODE_CHARS = 400_000
@@ -31,6 +29,8 @@ MAX_NO_WHITESPACES_CHARS = 25_000
 
 _INSTANCE = None
 
+logger = get_logger(name=__name__, category="models::llama")
+
 
 class Tokenizer:
     """

llama_stack/models/llama/llama4/quantization/loader.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import os
 from collections.abc import Callable
 
@@ -13,11 +12,13 @@ from fairscale.nn.model_parallel.initialize import get_model_parallel_rank
 from torch import Tensor, nn
 from torch.nn import functional as F
 
+from llama_stack.log import get_logger
+
 from ...datatypes import QuantizationMode
 from ..model import Transformer, TransformerBlock
 from ..moe import MoE
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="models")
 
 
 def swiglu_wrapper_no_reduce(

llama_stack/models/llama/llama4/tokenizer.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 from collections.abc import Collection, Iterator, Sequence, Set
-from logging import getLogger
 from pathlib import Path
 from typing import (
     Literal,
@@ -14,11 +13,9 @@ from typing import (
 
 import tiktoken
 
+from llama_stack.log import get_logger
 from llama_stack.models.llama.tokenizer_utils import load_bpe_file
 
-logger = getLogger(__name__)
-
-
 # The tiktoken tokenizer can handle <=400k chars without
 # pyo3_runtime.PanicException.
 TIKTOKEN_MAX_ENCODE_CHARS = 400_000
@@ -101,6 +98,8 @@ BASIC_SPECIAL_TOKENS = [
     "<|fim_suffix|>",
 ]
 
+logger = get_logger(name=__name__, category="models::llama")
+
 
 class Tokenizer:
     """

llama_stack/models/llama/quantize_impls.py

@@ -6,9 +6,10 @@
 
 # type: ignore
 import collections
-import logging
 
-log = logging.getLogger(__name__)
+from llama_stack.log import get_logger
+
+log = get_logger(name=__name__, category="llama")
 
 try:
     import fbgemm_gpu.experimental.gen_ai  # noqa: F401

llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import uuid
 from collections.abc import AsyncGenerator
 from datetime import UTC, datetime
@@ -42,6 +41,7 @@ from llama_stack.apis.safety import Safety
 from llama_stack.apis.tools import ToolGroups, ToolRuntime
 from llama_stack.apis.vector_io import VectorIO
 from llama_stack.core.datatypes import AccessRule
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
 from llama_stack.providers.utils.pagination import paginate_records
 from llama_stack.providers.utils.responses.responses_store import ResponsesStore
@@ -51,7 +51,7 @@ from .config import MetaReferenceAgentsImplConfig
 from .persistence import AgentInfo
 from .responses.openai_responses import OpenAIResponsesImpl
 
-logger = logging.getLogger()
+logger = get_logger(name=__name__, category="agents")
 
 
 class MetaReferenceAgentsImpl(Agents):

llama_stack/providers/inline/agents/meta_reference/persistence.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import json
-import logging
 import uuid
 from datetime import UTC, datetime
 
@@ -15,9 +14,10 @@ from llama_stack.core.access_control.access_control import AccessDeniedError, is
 from llama_stack.core.access_control.datatypes import AccessRule
 from llama_stack.core.datatypes import User
 from llama_stack.core.request_headers import get_authenticated_user
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import KVStore
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="agents")
 
 
 class AgentSessionInfo(Session):

llama_stack/providers/inline/agents/meta_reference/safety.py

@@ -5,13 +5,13 @@
 # the root directory of this source tree.
 
 import asyncio
-import logging
 
 from llama_stack.apis.inference import Message
 from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.telemetry import tracing
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="agents")
 
 
 class SafetyException(Exception):  # noqa: N818

llama_stack/providers/inline/inference/meta_reference/parallel_utils.py

@@ -12,7 +12,6 @@
 
 import copy
 import json
-import logging
 import multiprocessing
 import os
 import tempfile
@@ -32,13 +31,14 @@ from fairscale.nn.model_parallel.initialize import (
 from pydantic import BaseModel, Field
 from torch.distributed.launcher.api import LaunchConfig, elastic_launch
 
+from llama_stack.log import get_logger
 from llama_stack.models.llama.datatypes import GenerationResult
 from llama_stack.providers.utils.inference.prompt_adapter import (
     ChatCompletionRequestWithRawContent,
     CompletionRequestWithRawContent,
 )
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="inference")
 
 
 class ProcessingMessageName(str, Enum):

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 from collections.abc import AsyncGenerator
 
 from llama_stack.apis.inference import (
@@ -21,6 +20,7 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.apis.models import ModelType
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.embedding_mixin import (
     SentenceTransformerEmbeddingMixin,
@@ -32,7 +32,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
 
 from .config import SentenceTransformersInferenceConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="inference")
 
 
 class SentenceTransformersInferenceImpl(

llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device.py

@@ -6,7 +6,6 @@
 
 import gc
 import json
-import logging
 import multiprocessing
 from pathlib import Path
 from typing import Any
@@ -28,6 +27,7 @@ from llama_stack.apis.post_training import (
     LoraFinetuningConfig,
     TrainingConfig,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device
 
 from ..config import HuggingFacePostTrainingConfig
@@ -44,7 +44,7 @@ from ..utils import (
     split_dataset,
 )
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="post_training")
 
 
 class HFFinetuningSingleDevice:

llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device_dpo.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import gc
-import logging
 import multiprocessing
 from pathlib import Path
 from typing import Any
@@ -24,6 +23,7 @@ from llama_stack.apis.post_training import (
     DPOAlignmentConfig,
     TrainingConfig,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device
 
 from ..config import HuggingFacePostTrainingConfig
@@ -40,7 +40,7 @@ from ..utils import (
     split_dataset,
 )
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="post_training")
 
 
 class HFDPOAlignmentSingleDevice:

llama_stack/providers/inline/post_training/huggingface/utils.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import os
 import signal
 import sys
@@ -19,10 +18,11 @@ from transformers import AutoConfig, AutoModelForCausalLM
 
 from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.post_training import Checkpoint, TrainingConfig
+from llama_stack.log import get_logger
 
 from .config import HuggingFacePostTrainingConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="post_training")
 
 
 def setup_environment():

llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import os
 import time
 from datetime import UTC, datetime
@@ -19,6 +18,7 @@ from torch.utils.data import DataLoader, DistributedSampler
 from torchtune import modules, training
 from torchtune import utils as torchtune_utils
 from torchtune.data import padded_collate_sft
+from torchtune.models.llama3._tokenizer import Llama3Tokenizer
 from torchtune.modules.loss import CEWithChunkedOutputLoss
 from torchtune.modules.peft import (
     get_adapter_params,
@@ -45,6 +45,7 @@ from llama_stack.apis.post_training import (
 )
 from llama_stack.core.utils.config_dirs import DEFAULT_CHECKPOINT_DIR
 from llama_stack.core.utils.model_utils import model_local_dir
+from llama_stack.log import get_logger
 from llama_stack.models.llama.sku_list import resolve_model
 from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device
 from llama_stack.providers.inline.post_training.torchtune.common import utils
@@ -56,9 +57,7 @@ from llama_stack.providers.inline.post_training.torchtune.config import (
 )
 from llama_stack.providers.inline.post_training.torchtune.datasets.sft import SFTDataset
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="post_training")
-
-from torchtune.models.llama3._tokenizer import Llama3Tokenizer
 
 
 class LoraFinetuningSingleDevice:

llama_stack/providers/inline/safety/code_scanner/code_scanner.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import uuid
 from typing import TYPE_CHECKING, Any
 
@@ -20,13 +19,14 @@ from llama_stack.apis.safety import (
 )
 from llama_stack.apis.safety.safety import ModerationObject, ModerationObjectResults
 from llama_stack.apis.shields import Shield
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )
 
 from .config import CodeScannerConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="safety")
 
 ALLOWED_CODE_SCANNER_MODEL_IDS = [
     "code-scanner",

llama_stack/providers/inline/safety/llama_guard/llama_guard.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import re
 import uuid
 from string import Template
@@ -21,6 +20,7 @@ from llama_stack.apis.safety import (
 from llama_stack.apis.safety.safety import ModerationObject, ModerationObjectResults
 from llama_stack.apis.shields import Shield
 from llama_stack.core.datatypes import Api
+from llama_stack.log import get_logger
 from llama_stack.models.llama.datatypes import Role
 from llama_stack.models.llama.sku_types import CoreModelId
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
@@ -132,6 +132,8 @@ Provide your safety assessment for ONLY THE LAST $agent_type message in the abov
 
 PROMPT_TEMPLATE = Template(f"{PROMPT_TASK}{SAFETY_CATEGORIES}{PROMPT_CONVERSATION}{PROMPT_INSTRUCTIONS}")
 
+logger = get_logger(name=__name__, category="safety")
+
 
 class LlamaGuardSafetyImpl(Safety, ShieldsProtocolPrivate):
     def __init__(self, config: LlamaGuardConfig, deps) -> None:
@@ -407,7 +409,7 @@ class LlamaGuardShield:
             unsafe_code_list = [code.strip() for code in unsafe_code.split(",")]
             invalid_codes = [code for code in unsafe_code_list if code not in SAFETY_CODE_TO_CATEGORIES_MAP]
             if invalid_codes:
-                logging.warning(f"Invalid safety codes returned: {invalid_codes}")
+                logger.warning(f"Invalid safety codes returned: {invalid_codes}")
                 # just returning safe object, as we don't know what the invalid codes can map to
                 return ModerationObject(
                     id=f"modr-{uuid.uuid4()}",

llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 from typing import Any
 
 import torch
@@ -21,6 +20,7 @@ from llama_stack.apis.safety import (
 from llama_stack.apis.safety.safety import ModerationObject
 from llama_stack.apis.shields import Shield
 from llama_stack.core.utils.model_utils import model_local_dir
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
@@ -28,7 +28,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import PromptGuardConfig, PromptGuardType
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="safety")
 
 PROMPT_GUARD_MODEL = "Prompt-Guard-86M"
 

llama_stack/providers/inline/scoring/basic/utils/ifeval_utils.py

@@ -7,7 +7,6 @@
 import collections
 import functools
 import json
-import logging
 import random
 import re
 import string
@@ -20,7 +19,9 @@ import nltk
 from pythainlp.tokenize import sent_tokenize as sent_tokenize_thai
 from pythainlp.tokenize import word_tokenize as word_tokenize_thai
 
-logger = logging.getLogger()
+from llama_stack.log import get_logger
+
+logger = get_logger(name=__name__, category="scoring")
 
 WORD_LIST = [
     "western",

llama_stack/providers/inline/telemetry/meta_reference/telemetry.py

@@ -4,13 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import threading
 from typing import Any
 
 from opentelemetry import metrics, trace
-
-logger = logging.getLogger(__name__)
 from opentelemetry.exporter.otlp.proto.http.metric_exporter import OTLPMetricExporter
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
 from opentelemetry.sdk.metrics import MeterProvider
@@ -40,6 +37,7 @@ from llama_stack.apis.telemetry import (
     UnstructuredLogEvent,
 )
 from llama_stack.core.datatypes import Api
+from llama_stack.log import get_logger
 from llama_stack.providers.inline.telemetry.meta_reference.console_span_processor import (
     ConsoleSpanProcessor,
 )
@@ -61,6 +59,8 @@ _GLOBAL_STORAGE: dict[str, dict[str | int, Any]] = {
 _global_lock = threading.Lock()
 _TRACER_PROVIDER = None
 
+logger = get_logger(name=__name__, category="telemetry")
+
 
 def is_tracing_enabled(tracer):
     with tracer.start_as_current_span("check_tracing") as span:

llama_stack/providers/inline/tool_runtime/rag/memory.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import asyncio
-import logging
 import secrets
 import string
 from typing import Any
@@ -32,6 +31,7 @@ from llama_stack.apis.tools import (
     ToolRuntime,
 )
 from llama_stack.apis.vector_io import QueryChunksResponse, VectorIO
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate
 from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str
 from llama_stack.providers.utils.memory.vector_store import (
@@ -42,7 +42,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 from .config import RagToolRuntimeConfig
 from .context_retriever import generate_rag_query
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="tool_runtime")
 
 
 def make_random_string(length: int = 8):

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -8,7 +8,6 @@ import asyncio
 import base64
 import io
 import json
-import logging
 from typing import Any
 
 import faiss
@@ -24,6 +23,7 @@ from llama_stack.apis.vector_io import (
     QueryChunksResponse,
     VectorIO,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import (
     HealthResponse,
     HealthStatus,
@@ -40,7 +40,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import FaissVectorIOConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="vector_io")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:{VERSION}::"

llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import asyncio
-import logging
 import re
 import sqlite3
 import struct
@@ -24,6 +23,7 @@ from llama_stack.apis.vector_io import (
     QueryChunksResponse,
     VectorIO,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import VectorDBsProtocolPrivate
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.kvstore.api import KVStore
@@ -36,7 +36,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     VectorDBWithIndex,
 )
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="vector_io")
 
 # Specifying search mode is dependent on the VectorIO provider.
 VECTOR_SEARCH = "vector"

llama_stack/providers/remote/inference/llama_openai_compat/llama.py

@@ -3,15 +3,14 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-import logging
+from llama_stack.log import get_logger
-
 from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
 from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .models import MODEL_ENTRIES
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="inference")
 
 
 class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):

llama_stack/providers/remote/inference/nvidia/NVIDIA.md

@@ -77,6 +77,10 @@ print(f"Response: {response.completion_message.content}")
 ```
 
 ### Create Embeddings
+> Note on OpenAI embeddings compatibility
+>
+> NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. The NVIDIA Inference Adapter automatically sets `input_type="query"` when using the OpenAI-compatible embeddings endpoint for NVIDIA. For passage embeddings, use the `embeddings` API with `task_type="document"`.
+
 ```python
 response = client.inference.embeddings(
     model_id="nvidia/llama-3.2-nv-embedqa-1b-v2",

llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -4,11 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import warnings
 from collections.abc import AsyncIterator
 
-from openai import APIConnectionError, BadRequestError
+from openai import NOT_GIVEN, APIConnectionError, BadRequestError
 
 from llama_stack.apis.common.content_types import (
     InterleavedContent,
@@ -27,12 +26,16 @@ from llama_stack.apis.inference import (
     Inference,
     LogProbConfig,
     Message,
+    OpenAIEmbeddingData,
+    OpenAIEmbeddingsResponse,
+    OpenAIEmbeddingUsage,
     ResponseFormat,
     SamplingParams,
     TextTruncation,
     ToolChoice,
     ToolConfig,
 )
+from llama_stack.log import get_logger
 from llama_stack.models.llama.datatypes import ToolDefinition, ToolPromptFormat
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,
@@ -54,7 +57,7 @@ from .openai_utils import (
 )
 from .utils import _is_nvidia_hosted
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="inference")
 
 
 class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
@@ -210,6 +213,57 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
         #
         return EmbeddingsResponse(embeddings=[embedding.embedding for embedding in response.data])
 
+    async def openai_embeddings(
+        self,
+        model: str,
+        input: str | list[str],
+        encoding_format: str | None = "float",
+        dimensions: int | None = None,
+        user: str | None = None,
+    ) -> OpenAIEmbeddingsResponse:
+        """
+        OpenAI-compatible embeddings for NVIDIA NIM.
+
+        Note: NVIDIA NIM asymmetric embedding models require an "input_type" field not present in the standard OpenAI embeddings API.
+        We default this to "query" to ensure requests succeed when using the
+        OpenAI-compatible endpoint. For passage embeddings, use the embeddings API with
+        `task_type='document'`.
+        """
+        extra_body: dict[str, object] = {"input_type": "query"}
+        logger.warning(
+            "NVIDIA OpenAI-compatible embeddings: defaulting to input_type='query'. "
+            "For passage embeddings, use the embeddings API with task_type='document'."
+        )
+
+        response = await self.client.embeddings.create(
+            model=await self._get_provider_model_id(model),
+            input=input,
+            encoding_format=encoding_format if encoding_format is not None else NOT_GIVEN,
+            dimensions=dimensions if dimensions is not None else NOT_GIVEN,
+            user=user if user is not None else NOT_GIVEN,
+            extra_body=extra_body,
+        )
+
+        data = []
+        for i, embedding_data in enumerate(response.data):
+            data.append(
+                OpenAIEmbeddingData(
+                    embedding=embedding_data.embedding,
+                    index=i,
+                )
+            )
+
+        usage = OpenAIEmbeddingUsage(
+            prompt_tokens=response.usage.prompt_tokens,
+            total_tokens=response.usage.total_tokens,
+        )
+
+        return OpenAIEmbeddingsResponse(
+            data=data,
+            model=response.model,
+            usage=usage,
+        )
+
     async def chat_completion(
         self,
         model_id: str,

llama_stack/providers/remote/inference/nvidia/utils.py

@@ -4,13 +4,13 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
-
 import httpx
 
+from llama_stack.log import get_logger
+
 from . import NVIDIAConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="inference")
 
 
 def _is_nvidia_hosted(config: NVIDIAConfig) -> bool:

llama_stack/providers/remote/inference/openai/openai.py

@@ -4,15 +4,14 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
+from llama_stack.log import get_logger
-
 from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import OpenAIConfig
 from .models import MODEL_ENTRIES
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="inference")
 
 
 #

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 
-import logging
 from collections.abc import AsyncGenerator
 
 from huggingface_hub import AsyncInferenceClient, HfApi
@@ -34,6 +33,7 @@ from llama_stack.apis.inference import (
     ToolPromptFormat,
 )
 from llama_stack.apis.models import Model
+from llama_stack.log import get_logger
 from llama_stack.models.llama.sku_list import all_registered_models
 from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import (
@@ -58,7 +58,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="inference")
 
 
 def build_hf_repo_model_entries():

llama_stack/providers/remote/post_training/nvidia/utils.py

@@ -4,18 +4,18 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import warnings
 from typing import Any
 
 from pydantic import BaseModel
 
 from llama_stack.apis.post_training import TrainingConfig
+from llama_stack.log import get_logger
 from llama_stack.providers.remote.post_training.nvidia.config import SFTLoRADefaultConfig
 
 from .config import NvidiaPostTrainingConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="integration")
 
 
 def warn_unsupported_params(config_dict: Any, supported_keys: set[str], config_name: str) -> None:

llama_stack/providers/remote/safety/bedrock/bedrock.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import json
-import logging
 from typing import Any
 
 from llama_stack.apis.inference import Message
@@ -16,12 +15,13 @@ from llama_stack.apis.safety import (
     ViolationLevel,
 )
 from llama_stack.apis.shields import Shield
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.bedrock.client import create_bedrock_client
 
 from .config import BedrockSafetyConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="safety")
 
 
 class BedrockSafetyAdapter(Safety, ShieldsProtocolPrivate):

llama_stack/providers/remote/safety/nvidia/nvidia.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 from typing import Any
 
 import requests
@@ -12,12 +11,13 @@ import requests
 from llama_stack.apis.inference import Message
 from llama_stack.apis.safety import RunShieldResponse, Safety, SafetyViolation, ViolationLevel
 from llama_stack.apis.shields import Shield
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict_new
 
 from .config import NVIDIASafetyConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="safety")
 
 
 class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):

llama_stack/providers/remote/safety/sambanova/sambanova.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import json
-import logging
 from typing import Any
 
 import litellm
@@ -20,12 +19,13 @@ from llama_stack.apis.safety import (
 )
 from llama_stack.apis.shields import Shield
 from llama_stack.core.request_headers import NeedsRequestProviderData
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict_new
 
 from .config import SambaNovaSafetyConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="safety")
 
 CANNED_RESPONSE_TEXT = "I can't answer that. Can I help with something else?"
 

llama_stack/providers/remote/vector_io/chroma/chroma.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 import asyncio
 import json
-import logging
 from typing import Any
 from urllib.parse import urlparse
 
@@ -20,6 +19,7 @@ from llama_stack.apis.vector_io import (
     QueryChunksResponse,
     VectorIO,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig
 from llama_stack.providers.utils.kvstore import kvstore_impl
@@ -33,7 +33,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import ChromaVectorIOConfig as RemoteChromaVectorIOConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="vector_io")
 
 ChromaClientType = chromadb.api.AsyncClientAPI | chromadb.api.ClientAPI
 

llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import asyncio
-import logging
 import os
 from typing import Any
 
@@ -21,6 +20,7 @@ from llama_stack.apis.vector_io import (
     QueryChunksResponse,
     VectorIO,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import VectorDBsProtocolPrivate
 from llama_stack.providers.inline.vector_io.milvus import MilvusVectorIOConfig as InlineMilvusVectorIOConfig
 from llama_stack.providers.utils.kvstore import kvstore_impl
@@ -36,7 +36,7 @@ from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collecti
 
 from .config import MilvusVectorIOConfig as RemoteMilvusVectorIOConfig
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="vector_io")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:milvus:{VERSION}::"
@@ -413,15 +413,6 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
         index = await self._get_and_cache_vector_db_index(vector_db_id)
         if not index:
             raise VectorStoreNotFoundError(vector_db_id)
-
-        if params and params.get("mode") == "keyword":
-            # Check if this is inline Milvus (Milvus-Lite)
-            if hasattr(self.config, "db_path"):
-                raise NotImplementedError(
-                    "Keyword search is not supported in Milvus-Lite. "
-                    "Please use a remote Milvus server for keyword search functionality."
-                )
-
         return await index.query_chunks(query, params)
 
     async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:

llama_stack/providers/remote/vector_io/pgvector/pgvector.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 from typing import Any
 
 import psycopg2
@@ -22,6 +21,7 @@ from llama_stack.apis.vector_io import (
     QueryChunksResponse,
     VectorIO,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.kvstore.api import KVStore
@@ -34,7 +34,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import PGVectorVectorIOConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="vector_io")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:pgvector:{VERSION}::"

llama_stack/providers/remote/vector_io/qdrant/qdrant.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import asyncio
-import logging
 import uuid
 from typing import Any
 
@@ -24,6 +23,7 @@ from llama_stack.apis.vector_io import (
     VectorStoreChunkingStrategy,
     VectorStoreFileObject,
 )
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
 from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
@@ -36,7 +36,7 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="vector_io")
 CHUNK_ID_KEY = "_chunk_id"
 
 # KV store prefixes for vector databases

llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import json
-import logging
 from typing import Any
 
 import weaviate
@@ -19,6 +18,7 @@ from llama_stack.apis.files.files import Files
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO
 from llama_stack.core.request_headers import NeedsRequestProviderData
+from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.utils.kvstore import kvstore_impl
 from llama_stack.providers.utils.kvstore.api import KVStore
@@ -34,7 +34,7 @@ from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collecti
 
 from .config import WeaviateVectorIOConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="vector_io")
 
 VERSION = "v3"
 VECTOR_DBS_PREFIX = f"vector_dbs:weaviate:{VERSION}::"

llama_stack/providers/utils/inference/embedding_mixin.py

@@ -5,10 +5,11 @@
 # the root directory of this source tree.
 
 import base64
-import logging
 import struct
 from typing import TYPE_CHECKING
 
+from llama_stack.log import get_logger
+
 if TYPE_CHECKING:
     from sentence_transformers import SentenceTransformer
 
@@ -27,7 +28,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import interleaved_con
 EMBEDDING_MODELS = {}
 
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="inference")
 
 
 class SentenceTransformerEmbeddingMixin:

llama_stack/providers/utils/inference/openai_compat.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 import base64
 import json
-import logging
 import struct
 import time
 import uuid
@@ -122,6 +121,7 @@ from llama_stack.apis.inference import (
 from llama_stack.apis.inference import (
     OpenAIChoice as OpenAIChatCompletionChoice,
 )
+from llama_stack.log import get_logger
 from llama_stack.models.llama.datatypes import (
     BuiltinTool,
     StopReason,
@@ -134,7 +134,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     decode_assistant_message,
 )
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="inference")
 
 
 class OpenAICompatCompletionChoiceDelta(BaseModel):

llama_stack/providers/utils/kvstore/mongodb/mongodb.py

@@ -4,16 +4,16 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 from datetime import datetime
 
 from pymongo import AsyncMongoClient
 
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import KVStore
 
 from ..config import MongoDBKVStoreConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="kvstore")
 
 
 class MongoDBKVStoreImpl(KVStore):

llama_stack/providers/utils/kvstore/postgres/postgres.py

@@ -4,16 +4,17 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 from datetime import datetime
 
 import psycopg2
 from psycopg2.extras import DictCursor
 
+from llama_stack.log import get_logger
+
 from ..api import KVStore
 from ..config import PostgresKVStoreConfig
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="kvstore")
 
 
 class PostgresKVStoreImpl(KVStore):

llama_stack/providers/utils/memory/openai_vector_store_mixin.py

@@ -44,7 +44,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     make_overlapped_chunks,
 )
 
-logger = get_logger(__name__, category="vector_io")
+logger = get_logger(name=__name__, category="memory")
 
 # Constants for OpenAI vector stores
 CHUNK_MULTIPLIER = 5

llama_stack/providers/utils/memory/vector_store.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 import base64
 import io
-import logging
 import re
 import time
 from abc import ABC, abstractmethod
@@ -26,6 +25,7 @@ from llama_stack.apis.common.content_types import (
 from llama_stack.apis.tools import RAGDocument
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
+from llama_stack.log import get_logger
 from llama_stack.models.llama.llama3.tokenizer import Tokenizer
 from llama_stack.providers.datatypes import Api
 from llama_stack.providers.utils.inference.prompt_adapter import (
@@ -33,7 +33,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 )
 from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="memory")
 
 
 class ChunkForDeletion(BaseModel):

llama_stack/providers/utils/telemetry/tracing.py

@@ -6,7 +6,7 @@
 
 import asyncio
 import contextvars
-import logging
+import logging  # allow-direct-logging
 import queue
 import random
 import sys

llama_stack/ui/package.json

@@ -23,7 +23,7 @@
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "framer-motion": "^11.18.2",
-    "llama-stack-client": "^0.2.17",
+    "llama-stack-client": "^0.2.18",
     "lucide-react": "^0.510.0",
     "next": "15.3.3",
     "next-auth": "^4.24.11",

pyproject.toml

@@ -7,7 +7,7 @@ required-version = ">=0.7.0"
 
 [project]
 name = "llama_stack"
-version = "0.2.17"
+version = "0.2.18"
 authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
 description = "Llama Stack"
 readme = "README.md"
@@ -31,7 +31,7 @@ dependencies = [
     "huggingface-hub>=0.34.0,<1.0",
     "jinja2>=3.1.6",
     "jsonschema",
-    "llama-stack-client>=0.2.17",
+    "llama-stack-client>=0.2.18",
     "llama-api-client>=0.1.2",
     "openai>=1.99.6,<1.100.0",
     "prompt-toolkit",
@@ -56,7 +56,7 @@ dependencies = [
 ui = [
     "streamlit",
     "pandas",
-    "llama-stack-client>=0.2.17",
+    "llama-stack-client>=0.2.18",
     "streamlit-option-menu",
 ]
 
@@ -93,6 +93,7 @@ unit = [
     "blobfile",
     "faiss-cpu",
     "pymilvus>=2.5.12",
+    "milvus-lite>=2.5.0",
     "litellm",
     "together",
     "coverage",
@@ -118,6 +119,7 @@ test = [
     "sqlalchemy[asyncio]>=2.0.41",
     "requests",
     "pymilvus>=2.5.12",
+    "milvus-lite>=2.5.0",
     "weaviate-client>=4.16.4",
 ]
 docs = [

tests/integration/post_training/test_post_training.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import sys
 import time
 import uuid
@@ -19,10 +18,10 @@ from llama_stack.apis.post_training import (
     LoraFinetuningConfig,
     TrainingConfig,
 )
+from llama_stack.log import get_logger
 
 # Configure logging
-logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s", force=True)
+logger = get_logger(name=__name__, category="post_training")
-logger = logging.getLogger(__name__)
 
 
 skip_because_resource_intensive = pytest.mark.skip(

tests/integration/vector_io/test_openai_vector_stores.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import time
 from io import BytesIO
 
@@ -14,8 +13,9 @@ from openai import BadRequestError as OpenAIBadRequestError
 
 from llama_stack.apis.vector_io import Chunk
 from llama_stack.core.library_client import LlamaStackAsLibraryClient
+from llama_stack.log import get_logger
 
-logger = logging.getLogger(__name__)
+logger = get_logger(name=__name__, category="vector_io")
 
 
 def skip_if_provider_doesnt_support_openai_vector_stores(client_with_models):
@@ -56,6 +56,7 @@ def skip_if_provider_doesnt_support_openai_vector_stores_search(client_with_mode
         "keyword": [
             "inline::sqlite-vec",
             "remote::milvus",
+            "inline::milvus",
         ],
         "hybrid": [
             "inline::sqlite-vec",

tests/unit/providers/agents/meta_reference/test_response_conversion_utils.py

@@ -45,7 +45,6 @@ from llama_stack.providers.inline.agents.meta_reference.responses.utils import (
 
 
 class TestConvertChatChoiceToResponseMessage:
-    @pytest.mark.asyncio
     async def test_convert_string_content(self):
         choice = OpenAIChoice(
             message=OpenAIAssistantMessageParam(content="Test message"),
@@ -61,7 +60,6 @@ class TestConvertChatChoiceToResponseMessage:
         assert isinstance(result.content[0], OpenAIResponseOutputMessageContentOutputText)
         assert result.content[0].text == "Test message"
 
-    @pytest.mark.asyncio
     async def test_convert_text_param_content(self):
         choice = OpenAIChoice(
             message=OpenAIAssistantMessageParam(
@@ -78,12 +76,10 @@ class TestConvertChatChoiceToResponseMessage:
 
 
 class TestConvertResponseContentToChatContent:
-    @pytest.mark.asyncio
     async def test_convert_string_content(self):
         result = await convert_response_content_to_chat_content("Simple string")
         assert result == "Simple string"
 
-    @pytest.mark.asyncio
     async def test_convert_text_content_parts(self):
         content = [
             OpenAIResponseInputMessageContentText(text="First part"),
@@ -98,7 +94,6 @@ class TestConvertResponseContentToChatContent:
         assert isinstance(result[1], OpenAIChatCompletionContentPartTextParam)
         assert result[1].text == "Second part"
 
-    @pytest.mark.asyncio
     async def test_convert_image_content(self):
         content = [OpenAIResponseInputMessageContentImage(image_url="https://example.com/image.jpg", detail="high")]
 
@@ -111,7 +106,6 @@ class TestConvertResponseContentToChatContent:
 
 
 class TestConvertResponseInputToChatMessages:
-    @pytest.mark.asyncio
     async def test_convert_string_input(self):
         result = await convert_response_input_to_chat_messages("User message")
 
@@ -119,7 +113,6 @@ class TestConvertResponseInputToChatMessages:
         assert isinstance(result[0], OpenAIUserMessageParam)
         assert result[0].content == "User message"
 
-    @pytest.mark.asyncio
     async def test_convert_function_tool_call_output(self):
         input_items = [
             OpenAIResponseInputFunctionToolCallOutput(
@@ -135,7 +128,6 @@ class TestConvertResponseInputToChatMessages:
         assert result[0].content == "Tool output"
         assert result[0].tool_call_id == "call_123"
 
-    @pytest.mark.asyncio
     async def test_convert_function_tool_call(self):
         input_items = [
             OpenAIResponseOutputMessageFunctionToolCall(
@@ -154,7 +146,6 @@ class TestConvertResponseInputToChatMessages:
         assert result[0].tool_calls[0].function.name == "test_function"
         assert result[0].tool_calls[0].function.arguments == '{"param": "value"}'
 
-    @pytest.mark.asyncio
     async def test_convert_response_message(self):
         input_items = [
             OpenAIResponseMessage(
@@ -173,7 +164,6 @@ class TestConvertResponseInputToChatMessages:
 
 
 class TestConvertResponseTextToChatResponseFormat:
-    @pytest.mark.asyncio
     async def test_convert_text_format(self):
         text = OpenAIResponseText(format=OpenAIResponseTextFormat(type="text"))
         result = await convert_response_text_to_chat_response_format(text)
@@ -181,14 +171,12 @@ class TestConvertResponseTextToChatResponseFormat:
         assert isinstance(result, OpenAIResponseFormatText)
         assert result.type == "text"
 
-    @pytest.mark.asyncio
     async def test_convert_json_object_format(self):
         text = OpenAIResponseText(format={"type": "json_object"})
         result = await convert_response_text_to_chat_response_format(text)
 
         assert isinstance(result, OpenAIResponseFormatJSONObject)
 
-    @pytest.mark.asyncio
     async def test_convert_json_schema_format(self):
         schema_def = {"type": "object", "properties": {"test": {"type": "string"}}}
         text = OpenAIResponseText(
@@ -204,7 +192,6 @@ class TestConvertResponseTextToChatResponseFormat:
         assert result.json_schema["name"] == "test_schema"
         assert result.json_schema["schema"] == schema_def
 
-    @pytest.mark.asyncio
     async def test_default_text_format(self):
         text = OpenAIResponseText()
         result = await convert_response_text_to_chat_response_format(text)
@@ -214,27 +201,22 @@ class TestConvertResponseTextToChatResponseFormat:
 
 
 class TestGetMessageTypeByRole:
-    @pytest.mark.asyncio
     async def test_user_role(self):
         result = await get_message_type_by_role("user")
         assert result == OpenAIUserMessageParam
 
-    @pytest.mark.asyncio
     async def test_system_role(self):
         result = await get_message_type_by_role("system")
         assert result == OpenAISystemMessageParam
 
-    @pytest.mark.asyncio
     async def test_assistant_role(self):
         result = await get_message_type_by_role("assistant")
         assert result == OpenAIAssistantMessageParam
 
-    @pytest.mark.asyncio
     async def test_developer_role(self):
         result = await get_message_type_by_role("developer")
         assert result == OpenAIDeveloperMessageParam
 
-    @pytest.mark.asyncio
     async def test_unknown_role(self):
         result = await get_message_type_by_role("unknown")
         assert result is None

tests/unit/providers/inference/test_remote_vllm.py

@@ -6,7 +6,7 @@
 
 import asyncio
 import json
-import logging
+import logging  # allow-direct-logging
 import threading
 import time
 from http.server import BaseHTTPRequestHandler, HTTPServer

uv.lock

@@ -1719,7 +1719,7 @@ wheels = [
 
 [[package]]
 name = "llama-stack"
-version = "0.2.17"
+version = "0.2.18"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },
@@ -1809,6 +1809,7 @@ test = [
     { name = "chardet" },
     { name = "datasets" },
     { name = "mcp" },
+    { name = "milvus-lite" },
     { name = "openai" },
     { name = "pymilvus" },
     { name = "pypdf" },
@@ -1831,6 +1832,7 @@ unit = [
     { name = "faiss-cpu" },
     { name = "litellm" },
     { name = "mcp" },
+    { name = "milvus-lite" },
     { name = "ollama" },
     { name = "openai" },
     { name = "pymilvus" },
@@ -1854,8 +1856,8 @@ requires-dist = [
     { name = "jinja2", specifier = ">=3.1.6" },
     { name = "jsonschema" },
     { name = "llama-api-client", specifier = ">=0.1.2" },
-    { name = "llama-stack-client", specifier = ">=0.2.17" },
+    { name = "llama-stack-client", specifier = ">=0.2.18" },
-    { name = "llama-stack-client", marker = "extra == 'ui'", specifier = ">=0.2.17" },
+    { name = "llama-stack-client", marker = "extra == 'ui'", specifier = ">=0.2.18" },
     { name = "openai", specifier = ">=1.99.6,<1.100.0" },
     { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" },
     { name = "opentelemetry-sdk", specifier = ">=1.30.0" },
@@ -1925,6 +1927,7 @@ test = [
     { name = "chardet" },
     { name = "datasets" },
     { name = "mcp" },
+    { name = "milvus-lite", specifier = ">=2.5.0" },
     { name = "openai" },
     { name = "pymilvus", specifier = ">=2.5.12" },
     { name = "pypdf" },
@@ -1946,6 +1949,7 @@ unit = [
     { name = "faiss-cpu" },
     { name = "litellm" },
     { name = "mcp" },
+    { name = "milvus-lite", specifier = ">=2.5.0" },
     { name = "ollama" },
     { name = "openai" },
     { name = "pymilvus", specifier = ">=2.5.12" },
@@ -1959,7 +1963,7 @@ unit = [
 
 [[package]]
 name = "llama-stack-client"
-version = "0.2.17"
+version = "0.2.18"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
@@ -1978,9 +1982,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c5/2a/bb2949d6a5c494d21da0c185d426e25eaa8016f8287b689249afc6c96fb5/llama_stack_client-0.2.17.tar.gz", hash = "sha256:1fe2070133c6356761e394fa346045e9b6b567d4c63157b9bc6be89b9a6e7a41", size = 257636, upload-time = "2025-08-05T01:42:55.911Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/69/da/5e5a745495f8a2b8ef24fc4d01fe9031aa2277c36447cb22192ec8c8cc1e/llama_stack_client-0.2.18.tar.gz", hash = "sha256:860c885c9e549445178ac55cc9422e6e2a91215ac7aff5aaccfb42f3ce07e79e", size = 277284, upload-time = "2025-08-19T22:12:09.106Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/81/fc/5eccc86b83c5ced3a3bca071d250a86ccafa4ff17546cf781deb7758ab74/llama_stack_client-0.2.17-py3-none-any.whl", hash = "sha256:336c32f8688700ff64717b8109f405dc87a990fbe310c2027ac9ed6d39d67d16", size = 350329, upload-time = "2025-08-05T01:42:54.381Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/e4/e97f8fdd8a07aa1efc7f7e37b5657d84357b664bf70dd1885a437edc0699/llama_stack_client-0.2.18-py3-none-any.whl", hash = "sha256:90f827d5476f7fc15fd993f1863af6a6e72bd064646bf6a99435eb43a1327f70", size = 367586, upload-time = "2025-08-19T22:12:07.899Z" },
 ]
 
 [[package]]