feat: introduce APIs for retrieving chat completion requests (#2145)

# What does this PR do?
This PR introduces APIs to retrieve past chat completion requests, which
will be used in the LS UI.

Our current `Telemetry` is ill-suited for this purpose as it's untyped
so we'd need to filter by obscure attribute names, making it brittle.

Since these APIs are 'provided by stack' and don't need to be
implemented by inference providers, we introduce a new InferenceProvider
class, containing the existing inference protocol, which is implemented
by inference providers.

The APIs are OpenAI-compliant, with an additional `input_messages`
field.


## Test Plan
This PR just adds the API and marks them provided_by_stack. S
tart stack server -> doesn't crash

docs/_static/llama-stack-spec.yaml

@@ -827,6 +827,35 @@ paths:
           required: true
           schema:
             type: string
+  /v1/openai/v1/chat/completions/{completion_id}:
+    get:
+      responses:
+        '200':
+          description: A OpenAICompletionWithInputMessages.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/OpenAICompletionWithInputMessages'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Inference
+      description: Describe a chat completion by its ID.
+      parameters:
+        - name: completion_id
+          in: path
+          description: ID of the chat completion.
+          required: true
+          schema:
+            type: string
   /v1/datasets/{dataset_id}:
     get:
       responses:
@@ -1795,6 +1824,89 @@ paths:
             schema:
               $ref: '#/components/schemas/RegisterBenchmarkRequest'
         required: true
+  /v1/openai/v1/chat/completions:
+    get:
+      responses:
+        '200':
+          description: A ListOpenAIChatCompletionResponse.
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/ListOpenAIChatCompletionResponse'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Inference
+      description: List all chat completions.
+      parameters:
+        - name: after
+          in: query
+          description: >-
+            The ID of the last chat completion to return.
+          required: false
+          schema:
+            type: string
+        - name: limit
+          in: query
+          description: >-
+            The maximum number of chat completions to return.
+          required: false
+          schema:
+            type: integer
+        - name: model
+          in: query
+          description: The model to filter by.
+          required: false
+          schema:
+            type: string
+        - name: order
+          in: query
+          description: >-
+            The order to sort the chat completions by: "asc" or "desc". Defaults to
+            "desc".
+          required: false
+          schema:
+            $ref: '#/components/schemas/Order'
+    post:
+      responses:
+        '200':
+          description: An OpenAIChatCompletion.
+          content:
+            application/json:
+              schema:
+                oneOf:
+                  - $ref: '#/components/schemas/OpenAIChatCompletion'
+                  - $ref: '#/components/schemas/OpenAIChatCompletionChunk'
+        '400':
+          $ref: '#/components/responses/BadRequest400'
+        '429':
+          $ref: >-
+            #/components/responses/TooManyRequests429
+        '500':
+          $ref: >-
+            #/components/responses/InternalServerError500
+        default:
+          $ref: '#/components/responses/DefaultError'
+      tags:
+        - Inference
+      description: >-
+        Generate an OpenAI-compatible chat completion for the given messages using
+        the specified model.
+      parameters: []
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/OpenaiChatCompletionRequest'
+        required: true
   /v1/datasets:
     get:
       responses:
@@ -2261,39 +2373,6 @@ paths:
             schema:
               $ref: '#/components/schemas/LogEventRequest'
         required: true
-  /v1/openai/v1/chat/completions:
-    post:
-      responses:
-        '200':
-          description: An OpenAIChatCompletion.
-          content:
-            application/json:
-              schema:
-                oneOf:
-                  - $ref: '#/components/schemas/OpenAIChatCompletion'
-                  - $ref: '#/components/schemas/OpenAIChatCompletionChunk'
-        '400':
-          $ref: '#/components/responses/BadRequest400'
-        '429':
-          $ref: >-
-            #/components/responses/TooManyRequests429
-        '500':
-          $ref: >-
-            #/components/responses/InternalServerError500
-        default:
-          $ref: '#/components/responses/DefaultError'
-      tags:
-        - Inference
-      description: >-
-        Generate an OpenAI-compatible chat completion for the given messages using
-        the specified model.
-      parameters: []
-      requestBody:
-        content:
-          application/json:
-            schema:
-              $ref: '#/components/schemas/OpenaiChatCompletionRequest'
-        required: true
   /v1/openai/v1/completions:
     post:
       responses:
@@ -5479,6 +5558,369 @@ components:
         - scoring_functions
         - metadata
       title: Benchmark
+    OpenAIAssistantMessageParam:
+      type: object
+      properties:
+        role:
+          type: string
+          const: assistant
+          default: assistant
+          description: >-
+            Must be "assistant" to identify this as the model's response
+        content:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
+          description: The content of the model's response
+        name:
+          type: string
+          description: >-
+            (Optional) The name of the assistant message participant.
+        tool_calls:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
+          description: >-
+            List of tool calls. Each tool call is an OpenAIChatCompletionToolCall
+            object.
+      additionalProperties: false
+      required:
+        - role
+      title: OpenAIAssistantMessageParam
+      description: >-
+        A message containing the model's (assistant) response in an OpenAI-compatible
+        chat completion request.
+    "OpenAIChatCompletionContentPartImageParam":
+      type: object
+      properties:
+        type:
+          type: string
+          const: image_url
+          default: image_url
+        image_url:
+          $ref: '#/components/schemas/OpenAIImageURL'
+      additionalProperties: false
+      required:
+        - type
+        - image_url
+      title: >-
+        OpenAIChatCompletionContentPartImageParam
+    OpenAIChatCompletionContentPartParam:
+      oneOf:
+        - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
+        - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
+      discriminator:
+        propertyName: type
+        mapping:
+          text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
+          image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
+    OpenAIChatCompletionContentPartTextParam:
+      type: object
+      properties:
+        type:
+          type: string
+          const: text
+          default: text
+        text:
+          type: string
+      additionalProperties: false
+      required:
+        - type
+        - text
+      title: OpenAIChatCompletionContentPartTextParam
+    OpenAIChatCompletionToolCall:
+      type: object
+      properties:
+        index:
+          type: integer
+        id:
+          type: string
+        type:
+          type: string
+          const: function
+          default: function
+        function:
+          $ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
+      additionalProperties: false
+      required:
+        - type
+      title: OpenAIChatCompletionToolCall
+    OpenAIChatCompletionToolCallFunction:
+      type: object
+      properties:
+        name:
+          type: string
+        arguments:
+          type: string
+      additionalProperties: false
+      title: OpenAIChatCompletionToolCallFunction
+    OpenAIChoice:
+      type: object
+      properties:
+        message:
+          $ref: '#/components/schemas/OpenAIMessageParam'
+          description: The message from the model
+        finish_reason:
+          type: string
+          description: The reason the model stopped generating
+        index:
+          type: integer
+          description: The index of the choice
+        logprobs:
+          $ref: '#/components/schemas/OpenAIChoiceLogprobs'
+          description: >-
+            (Optional) The log probabilities for the tokens in the message
+      additionalProperties: false
+      required:
+        - message
+        - finish_reason
+        - index
+      title: OpenAIChoice
+      description: >-
+        A choice from an OpenAI-compatible chat completion response.
+    OpenAIChoiceLogprobs:
+      type: object
+      properties:
+        content:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAITokenLogProb'
+          description: >-
+            (Optional) The log probabilities for the tokens in the message
+        refusal:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAITokenLogProb'
+          description: >-
+            (Optional) The log probabilities for the tokens in the message
+      additionalProperties: false
+      title: OpenAIChoiceLogprobs
+      description: >-
+        The log probabilities for the tokens in the message from an OpenAI-compatible
+        chat completion response.
+    OpenAIDeveloperMessageParam:
+      type: object
+      properties:
+        role:
+          type: string
+          const: developer
+          default: developer
+          description: >-
+            Must be "developer" to identify this as a developer message
+        content:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
+          description: The content of the developer message
+        name:
+          type: string
+          description: >-
+            (Optional) The name of the developer message participant.
+      additionalProperties: false
+      required:
+        - role
+        - content
+      title: OpenAIDeveloperMessageParam
+      description: >-
+        A message from the developer in an OpenAI-compatible chat completion request.
+    OpenAIImageURL:
+      type: object
+      properties:
+        url:
+          type: string
+        detail:
+          type: string
+      additionalProperties: false
+      required:
+        - url
+      title: OpenAIImageURL
+    OpenAIMessageParam:
+      oneOf:
+        - $ref: '#/components/schemas/OpenAIUserMessageParam'
+        - $ref: '#/components/schemas/OpenAISystemMessageParam'
+        - $ref: '#/components/schemas/OpenAIAssistantMessageParam'
+        - $ref: '#/components/schemas/OpenAIToolMessageParam'
+        - $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
+      discriminator:
+        propertyName: role
+        mapping:
+          user: '#/components/schemas/OpenAIUserMessageParam'
+          system: '#/components/schemas/OpenAISystemMessageParam'
+          assistant: '#/components/schemas/OpenAIAssistantMessageParam'
+          tool: '#/components/schemas/OpenAIToolMessageParam'
+          developer: '#/components/schemas/OpenAIDeveloperMessageParam'
+    OpenAISystemMessageParam:
+      type: object
+      properties:
+        role:
+          type: string
+          const: system
+          default: system
+          description: >-
+            Must be "system" to identify this as a system message
+        content:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
+          description: >-
+            The content of the "system prompt". If multiple system messages are provided,
+            they are concatenated. The underlying Llama Stack code may also add other
+            system messages (for example, for formatting tool definitions).
+        name:
+          type: string
+          description: >-
+            (Optional) The name of the system message participant.
+      additionalProperties: false
+      required:
+        - role
+        - content
+      title: OpenAISystemMessageParam
+      description: >-
+        A system message providing instructions or context to the model.
+    OpenAITokenLogProb:
+      type: object
+      properties:
+        token:
+          type: string
+        bytes:
+          type: array
+          items:
+            type: integer
+        logprob:
+          type: number
+        top_logprobs:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAITopLogProb'
+      additionalProperties: false
+      required:
+        - token
+        - logprob
+        - top_logprobs
+      title: OpenAITokenLogProb
+      description: >-
+        The log probability for a token from an OpenAI-compatible chat completion
+        response.
+    OpenAIToolMessageParam:
+      type: object
+      properties:
+        role:
+          type: string
+          const: tool
+          default: tool
+          description: >-
+            Must be "tool" to identify this as a tool response
+        tool_call_id:
+          type: string
+          description: >-
+            Unique identifier for the tool call this response is for
+        content:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
+          description: The response content from the tool
+      additionalProperties: false
+      required:
+        - role
+        - tool_call_id
+        - content
+      title: OpenAIToolMessageParam
+      description: >-
+        A message representing the result of a tool invocation in an OpenAI-compatible
+        chat completion request.
+    OpenAITopLogProb:
+      type: object
+      properties:
+        token:
+          type: string
+        bytes:
+          type: array
+          items:
+            type: integer
+        logprob:
+          type: number
+      additionalProperties: false
+      required:
+        - token
+        - logprob
+      title: OpenAITopLogProb
+      description: >-
+        The top log probability for a token from an OpenAI-compatible chat completion
+        response.
+    OpenAIUserMessageParam:
+      type: object
+      properties:
+        role:
+          type: string
+          const: user
+          default: user
+          description: >-
+            Must be "user" to identify this as a user message
+        content:
+          oneOf:
+            - type: string
+            - type: array
+              items:
+                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
+          description: >-
+            The content of the message, which can include text and other media
+        name:
+          type: string
+          description: >-
+            (Optional) The name of the user message participant.
+      additionalProperties: false
+      required:
+        - role
+        - content
+      title: OpenAIUserMessageParam
+      description: >-
+        A message from the user in an OpenAI-compatible chat completion request.
+    OpenAICompletionWithInputMessages:
+      type: object
+      properties:
+        id:
+          type: string
+          description: The ID of the chat completion
+        choices:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAIChoice'
+          description: List of choices
+        object:
+          type: string
+          const: chat.completion
+          default: chat.completion
+          description: >-
+            The object type, which will be "chat.completion"
+        created:
+          type: integer
+          description: >-
+            The Unix timestamp in seconds when the chat completion was created
+        model:
+          type: string
+          description: >-
+            The model that was used to generate the chat completion
+        input_messages:
+          type: array
+          items:
+            $ref: '#/components/schemas/OpenAIMessageParam'
+      additionalProperties: false
+      required:
+        - id
+        - choices
+        - object
+        - created
+        - model
+        - input_messages
+      title: OpenAICompletionWithInputMessages
     DataSource:
       oneOf:
         - $ref: '#/components/schemas/URIDataSource'
@@ -6497,6 +6939,73 @@ components:
       required:
         - data
       title: ListBenchmarksResponse
+    Order:
+      type: string
+      enum:
+        - asc
+        - desc
+      title: Order
+    ListOpenAIChatCompletionResponse:
+      type: object
+      properties:
+        data:
+          type: array
+          items:
+            type: object
+            properties:
+              id:
+                type: string
+                description: The ID of the chat completion
+              choices:
+                type: array
+                items:
+                  $ref: '#/components/schemas/OpenAIChoice'
+                description: List of choices
+              object:
+                type: string
+                const: chat.completion
+                default: chat.completion
+                description: >-
+                  The object type, which will be "chat.completion"
+              created:
+                type: integer
+                description: >-
+                  The Unix timestamp in seconds when the chat completion was created
+              model:
+                type: string
+                description: >-
+                  The model that was used to generate the chat completion
+              input_messages:
+                type: array
+                items:
+                  $ref: '#/components/schemas/OpenAIMessageParam'
+            additionalProperties: false
+            required:
+              - id
+              - choices
+              - object
+              - created
+              - model
+              - input_messages
+            title: OpenAICompletionWithInputMessages
+        has_more:
+          type: boolean
+        first_id:
+          type: string
+        last_id:
+          type: string
+        object:
+          type: string
+          const: list
+          default: list
+      additionalProperties: false
+      required:
+        - data
+        - has_more
+        - first_id
+        - last_id
+        - object
+      title: ListOpenAIChatCompletionResponse
     ListDatasetsResponse:
       type: object
       properties:
@@ -6835,142 +7344,6 @@ components:
         - event
         - ttl_seconds
       title: LogEventRequest
-    OpenAIAssistantMessageParam:
-      type: object
-      properties:
-        role:
-          type: string
-          const: assistant
-          default: assistant
-          description: >-
-            Must be "assistant" to identify this as the model's response
-        content:
-          oneOf:
-            - type: string
-            - type: array
-              items:
-                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
-          description: The content of the model's response
-        name:
-          type: string
-          description: >-
-            (Optional) The name of the assistant message participant.
-        tool_calls:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
-          description: >-
-            List of tool calls. Each tool call is an OpenAIChatCompletionToolCall
-            object.
-      additionalProperties: false
-      required:
-        - role
-      title: OpenAIAssistantMessageParam
-      description: >-
-        A message containing the model's (assistant) response in an OpenAI-compatible
-        chat completion request.
-    "OpenAIChatCompletionContentPartImageParam":
-      type: object
-      properties:
-        type:
-          type: string
-          const: image_url
-          default: image_url
-        image_url:
-          $ref: '#/components/schemas/OpenAIImageURL'
-      additionalProperties: false
-      required:
-        - type
-        - image_url
-      title: >-
-        OpenAIChatCompletionContentPartImageParam
-    OpenAIChatCompletionContentPartParam:
-      oneOf:
-        - $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
-        - $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
-      discriminator:
-        propertyName: type
-        mapping:
-          text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
-          image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
-    OpenAIChatCompletionContentPartTextParam:
-      type: object
-      properties:
-        type:
-          type: string
-          const: text
-          default: text
-        text:
-          type: string
-      additionalProperties: false
-      required:
-        - type
-        - text
-      title: OpenAIChatCompletionContentPartTextParam
-    OpenAIChatCompletionToolCall:
-      type: object
-      properties:
-        index:
-          type: integer
-        id:
-          type: string
-        type:
-          type: string
-          const: function
-          default: function
-        function:
-          $ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
-      additionalProperties: false
-      required:
-        - type
-      title: OpenAIChatCompletionToolCall
-    OpenAIChatCompletionToolCallFunction:
-      type: object
-      properties:
-        name:
-          type: string
-        arguments:
-          type: string
-      additionalProperties: false
-      title: OpenAIChatCompletionToolCallFunction
-    OpenAIDeveloperMessageParam:
-      type: object
-      properties:
-        role:
-          type: string
-          const: developer
-          default: developer
-          description: >-
-            Must be "developer" to identify this as a developer message
-        content:
-          oneOf:
-            - type: string
-            - type: array
-              items:
-                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
-          description: The content of the developer message
-        name:
-          type: string
-          description: >-
-            (Optional) The name of the developer message participant.
-      additionalProperties: false
-      required:
-        - role
-        - content
-      title: OpenAIDeveloperMessageParam
-      description: >-
-        A message from the developer in an OpenAI-compatible chat completion request.
-    OpenAIImageURL:
-      type: object
-      properties:
-        url:
-          type: string
-        detail:
-          type: string
-      additionalProperties: false
-      required:
-        - url
-      title: OpenAIImageURL
     OpenAIJSONSchema:
       type: object
       properties:
@@ -6994,21 +7367,6 @@ components:
       required:
         - name
       title: OpenAIJSONSchema
-    OpenAIMessageParam:
-      oneOf:
-        - $ref: '#/components/schemas/OpenAIUserMessageParam'
-        - $ref: '#/components/schemas/OpenAISystemMessageParam'
-        - $ref: '#/components/schemas/OpenAIAssistantMessageParam'
-        - $ref: '#/components/schemas/OpenAIToolMessageParam'
-        - $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
-      discriminator:
-        propertyName: role
-        mapping:
-          user: '#/components/schemas/OpenAIUserMessageParam'
-          system: '#/components/schemas/OpenAISystemMessageParam'
-          assistant: '#/components/schemas/OpenAIAssistantMessageParam'
-          tool: '#/components/schemas/OpenAIToolMessageParam'
-          developer: '#/components/schemas/OpenAIDeveloperMessageParam'
     OpenAIResponseFormatJSONObject:
       type: object
       properties:
@@ -7056,93 +7414,6 @@ components:
       required:
         - type
       title: OpenAIResponseFormatText
-    OpenAISystemMessageParam:
-      type: object
-      properties:
-        role:
-          type: string
-          const: system
-          default: system
-          description: >-
-            Must be "system" to identify this as a system message
-        content:
-          oneOf:
-            - type: string
-            - type: array
-              items:
-                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
-          description: >-
-            The content of the "system prompt". If multiple system messages are provided,
-            they are concatenated. The underlying Llama Stack code may also add other
-            system messages (for example, for formatting tool definitions).
-        name:
-          type: string
-          description: >-
-            (Optional) The name of the system message participant.
-      additionalProperties: false
-      required:
-        - role
-        - content
-      title: OpenAISystemMessageParam
-      description: >-
-        A system message providing instructions or context to the model.
-    OpenAIToolMessageParam:
-      type: object
-      properties:
-        role:
-          type: string
-          const: tool
-          default: tool
-          description: >-
-            Must be "tool" to identify this as a tool response
-        tool_call_id:
-          type: string
-          description: >-
-            Unique identifier for the tool call this response is for
-        content:
-          oneOf:
-            - type: string
-            - type: array
-              items:
-                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
-          description: The response content from the tool
-      additionalProperties: false
-      required:
-        - role
-        - tool_call_id
-        - content
-      title: OpenAIToolMessageParam
-      description: >-
-        A message representing the result of a tool invocation in an OpenAI-compatible
-        chat completion request.
-    OpenAIUserMessageParam:
-      type: object
-      properties:
-        role:
-          type: string
-          const: user
-          default: user
-          description: >-
-            Must be "user" to identify this as a user message
-        content:
-          oneOf:
-            - type: string
-            - type: array
-              items:
-                $ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
-          description: >-
-            The content of the message, which can include text and other media
-        name:
-          type: string
-          description: >-
-            (Optional) The name of the user message participant.
-      additionalProperties: false
-      required:
-        - role
-        - content
-      title: OpenAIUserMessageParam
-      description: >-
-        A message from the user in an OpenAI-compatible chat completion request.
     OpenaiChatCompletionRequest:
       type: object
       properties:
@@ -7356,30 +7627,6 @@ components:
       title: OpenAIChatCompletionChunk
       description: >-
         Chunk from a streaming response to an OpenAI-compatible chat completion request.
-    OpenAIChoice:
-      type: object
-      properties:
-        message:
-          $ref: '#/components/schemas/OpenAIMessageParam'
-          description: The message from the model
-        finish_reason:
-          type: string
-          description: The reason the model stopped generating
-        index:
-          type: integer
-          description: The index of the choice
-        logprobs:
-          $ref: '#/components/schemas/OpenAIChoiceLogprobs'
-          description: >-
-            (Optional) The log probabilities for the tokens in the message
-      additionalProperties: false
-      required:
-        - message
-        - finish_reason
-        - index
-      title: OpenAIChoice
-      description: >-
-        A choice from an OpenAI-compatible chat completion response.
     OpenAIChoiceDelta:
       type: object
       properties:
@@ -7401,26 +7648,6 @@ components:
       title: OpenAIChoiceDelta
       description: >-
         A delta from an OpenAI-compatible chat completion streaming response.
-    OpenAIChoiceLogprobs:
-      type: object
-      properties:
-        content:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAITokenLogProb'
-          description: >-
-            (Optional) The log probabilities for the tokens in the message
-        refusal:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAITokenLogProb'
-          description: >-
-            (Optional) The log probabilities for the tokens in the message
-      additionalProperties: false
-      title: OpenAIChoiceLogprobs
-      description: >-
-        The log probabilities for the tokens in the message from an OpenAI-compatible
-        chat completion response.
     OpenAIChunkChoice:
       type: object
       properties:
@@ -7445,49 +7672,6 @@ components:
       title: OpenAIChunkChoice
       description: >-
         A chunk choice from an OpenAI-compatible chat completion streaming response.
-    OpenAITokenLogProb:
-      type: object
-      properties:
-        token:
-          type: string
-        bytes:
-          type: array
-          items:
-            type: integer
-        logprob:
-          type: number
-        top_logprobs:
-          type: array
-          items:
-            $ref: '#/components/schemas/OpenAITopLogProb'
-      additionalProperties: false
-      required:
-        - token
-        - logprob
-        - top_logprobs
-      title: OpenAITokenLogProb
-      description: >-
-        The log probability for a token from an OpenAI-compatible chat completion
-        response.
-    OpenAITopLogProb:
-      type: object
-      properties:
-        token:
-          type: string
-        bytes:
-          type: array
-          items:
-            type: integer
-        logprob:
-          type: number
-      additionalProperties: false
-      required:
-        - token
-        - logprob
-      title: OpenAITopLogProb
-      description: >-
-        The top log probability for a token from an OpenAI-compatible chat completion
-        response.
     OpenaiCompletionRequest:
       type: object
       properties:

docs/openapi_generator/pyopenapi/generator.py

@@ -759,7 +759,7 @@ class Generator:
         )
 
         return Operation(
-            tags=[op.defining_class.__name__],
+            tags=[getattr(op.defining_class, "API_NAMESPACE", op.defining_class.__name__)],
             summary=None,
             # summary=doc_string.short_description,
             description=description,
@@ -805,6 +805,8 @@ class Generator:
         operation_tags: List[Tag] = []
         for cls in endpoint_classes:
             doc_string = parse_type(cls)
+            if hasattr(cls, "API_NAMESPACE") and cls.API_NAMESPACE != cls.__name__:
+                continue
             operation_tags.append(
                 Tag(
                     name=cls.__name__,

llama_stack/apis/inference/inference.py

@@ -820,15 +820,32 @@ class BatchChatCompletionResponse(BaseModel):
     batch: list[ChatCompletionResponse]
 
 
+class OpenAICompletionWithInputMessages(OpenAIChatCompletion):
+    input_messages: list[OpenAIMessageParam]
+
+
+@json_schema_type
+class ListOpenAIChatCompletionResponse(BaseModel):
+    data: list[OpenAICompletionWithInputMessages]
+    has_more: bool
+    first_id: str
+    last_id: str
+    object: Literal["list"] = "list"
+
+
+class Order(Enum):
+    asc = "asc"
+    desc = "desc"
+
+
 @runtime_checkable
 @trace_protocol
-class Inference(Protocol):
+class InferenceProvider(Protocol):
-    """Llama Stack Inference API for generating completions, chat completions, and embeddings.
-
-    This API provides the raw interface to the underlying models. Two kinds of models are supported:
-    - LLM models: these models generate "raw" and "chat" (conversational) completions.
-    - Embedding models: these models generate embeddings to be used for semantic search.
     """
+    This protocol defines the interface that should be implemented by all inference providers.
+    """
+
+    API_NAMESPACE: str = "Inference"
 
     model_store: ModelStore | None = None
 
@@ -1062,3 +1079,39 @@ class Inference(Protocol):
         :returns: An OpenAIChatCompletion.
         """
         ...
+
+
+class Inference(InferenceProvider):
+    """Llama Stack Inference API for generating completions, chat completions, and embeddings.
+
+    This API provides the raw interface to the underlying models. Two kinds of models are supported:
+    - LLM models: these models generate "raw" and "chat" (conversational) completions.
+    - Embedding models: these models generate embeddings to be used for semantic search.
+    """
+
+    @webmethod(route="/openai/v1/chat/completions", method="GET")
+    async def list_chat_completions(
+        self,
+        after: str | None = None,
+        limit: int | None = 20,
+        model: str | None = None,
+        order: Order | None = Order.desc,
+    ) -> ListOpenAIChatCompletionResponse:
+        """List all chat completions.
+
+        :param after: The ID of the last chat completion to return.
+        :param limit: The maximum number of chat completions to return.
+        :param model: The model to filter by.
+        :param order: The order to sort the chat completions by: "asc" or "desc". Defaults to "desc".
+        :returns: A ListOpenAIChatCompletionResponse.
+        """
+        raise NotImplementedError("List chat completions is not implemented")
+
+    @webmethod(route="/openai/v1/chat/completions/{completion_id}", method="GET")
+    async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
+        """Describe a chat completion by its ID.
+
+        :param completion_id: ID of the chat completion.
+        :returns: A OpenAICompletionWithInputMessages.
+        """
+        raise NotImplementedError("Get chat completion is not implemented")

llama_stack/distribution/resolver.py

@@ -13,7 +13,7 @@ from llama_stack.apis.datasetio import DatasetIO
 from llama_stack.apis.datasets import Datasets
 from llama_stack.apis.eval import Eval
 from llama_stack.apis.files import Files
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import Inference, InferenceProvider
 from llama_stack.apis.inspect import Inspect
 from llama_stack.apis.models import Models
 from llama_stack.apis.post_training import PostTraining
@@ -83,6 +83,13 @@ def api_protocol_map() -> dict[Api, Any]:
     }
 
 
+def api_protocol_map_for_compliance_check() -> dict[Api, Any]:
+    return {
+        **api_protocol_map(),
+        Api.inference: InferenceProvider,
+    }
+
+
 def additional_protocols_map() -> dict[Api, Any]:
     return {
         Api.inference: (ModelsProtocolPrivate, Models, Api.models),
@@ -302,9 +309,6 @@ async def instantiate_provider(
     inner_impls: dict[str, Any],
     dist_registry: DistributionRegistry,
 ):
-    protocols = api_protocol_map()
-    additional_protocols = additional_protocols_map()
-
     provider_spec = provider.spec
     if not hasattr(provider_spec, "module"):
         raise AttributeError(f"ProviderSpec of type {type(provider_spec)} does not have a 'module' attribute")
@@ -342,6 +346,8 @@ async def instantiate_provider(
     impl.__provider_spec__ = provider_spec
     impl.__provider_config__ = config
 
+    protocols = api_protocol_map_for_compliance_check()
+    additional_protocols = additional_protocols_map()
     # TODO: check compliance for special tool groups
     # the impl should be for Api.tool_runtime, the name should be the special tool group, the protocol should be the special tool group protocol
     check_protocol_compliance(impl, protocols[provider_spec.api])

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

@@ -28,7 +28,7 @@ from llama_stack.apis.inference import (
     CompletionRequest,
     CompletionResponse,
     CompletionResponseStreamChunk,
-    Inference,
+    InferenceProvider,
     InterleavedContent,
     LogProbConfig,
     Message,
@@ -86,7 +86,7 @@ class MetaReferenceInferenceImpl(
     OpenAICompletionToLlamaStackMixin,
     OpenAIChatCompletionToLlamaStackMixin,
     SentenceTransformerEmbeddingMixin,
-    Inference,
+    InferenceProvider,
     ModelsProtocolPrivate,
 ):
     def __init__(self, config: MetaReferenceInferenceConfig) -> None:

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

@@ -9,7 +9,7 @@ from collections.abc import AsyncGenerator
 
 from llama_stack.apis.inference import (
     CompletionResponse,
-    Inference,
+    InferenceProvider,
     InterleavedContent,
     LogProbConfig,
     Message,
@@ -38,7 +38,7 @@ class SentenceTransformersInferenceImpl(
     OpenAIChatCompletionToLlamaStackMixin,
     OpenAICompletionToLlamaStackMixin,
     SentenceTransformerEmbeddingMixin,
-    Inference,
+    InferenceProvider,
     ModelsProtocolPrivate,
 ):
     def __init__(self, config: SentenceTransformersInferenceConfig) -> None:

llama_stack/providers/remote/inference/cerebras_openai_compat/__init__.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import InferenceProvider
 
 from .config import CerebrasCompatConfig
 
 
-async def get_adapter_impl(config: CerebrasCompatConfig, _deps) -> Inference:
+async def get_adapter_impl(config: CerebrasCompatConfig, _deps) -> InferenceProvider:
     # import dynamically so the import is used only when it is needed
     from .cerebras import CerebrasCompatInferenceAdapter
 

llama_stack/providers/remote/inference/fireworks_openai_compat/__init__.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import InferenceProvider
 
 from .config import FireworksCompatConfig
 
 
-async def get_adapter_impl(config: FireworksCompatConfig, _deps) -> Inference:
+async def get_adapter_impl(config: FireworksCompatConfig, _deps) -> InferenceProvider:
     # import dynamically so the import is used only when it is needed
     from .fireworks import FireworksCompatInferenceAdapter
 

llama_stack/providers/remote/inference/groq_openai_compat/__init__.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import InferenceProvider
 
 from .config import GroqCompatConfig
 
 
-async def get_adapter_impl(config: GroqCompatConfig, _deps) -> Inference:
+async def get_adapter_impl(config: GroqCompatConfig, _deps) -> InferenceProvider:
     # import dynamically so the import is used only when it is needed
     from .groq import GroqCompatInferenceAdapter
 

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

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import InferenceProvider
 
 from .config import LlamaCompatConfig
 
 
-async def get_adapter_impl(config: LlamaCompatConfig, _deps) -> Inference:
+async def get_adapter_impl(config: LlamaCompatConfig, _deps) -> InferenceProvider:
     # import dynamically so the import is used only when it is needed
     from .llama import LlamaCompatInferenceAdapter
 

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -28,7 +28,7 @@ from llama_stack.apis.inference import (
     EmbeddingsResponse,
     EmbeddingTaskType,
     GrammarResponseFormat,
-    Inference,
+    InferenceProvider,
     JsonSchemaResponseFormat,
     LogProbConfig,
     Message,
@@ -82,7 +82,7 @@ logger = get_logger(name=__name__, category="inference")
 
 
 class OllamaInferenceAdapter(
-    Inference,
+    InferenceProvider,
     ModelsProtocolPrivate,
 ):
     def __init__(self, url: str) -> None:

llama_stack/providers/remote/inference/sambanova_openai_compat/__init__.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import InferenceProvider
 
 from .config import SambaNovaCompatConfig
 
 
-async def get_adapter_impl(config: SambaNovaCompatConfig, _deps) -> Inference:
+async def get_adapter_impl(config: SambaNovaCompatConfig, _deps) -> InferenceProvider:
     # import dynamically so the import is used only when it is needed
     from .sambanova import SambaNovaCompatInferenceAdapter
 

llama_stack/providers/remote/inference/together_openai_compat/__init__.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.inference import InferenceProvider
 
 from .config import TogetherCompatConfig
 
 
-async def get_adapter_impl(config: TogetherCompatConfig, _deps) -> Inference:
+async def get_adapter_impl(config: TogetherCompatConfig, _deps) -> InferenceProvider:
     # import dynamically so the import is used only when it is needed
     from .together import TogetherCompatInferenceAdapter
 

llama_stack/providers/utils/inference/litellm_openai_mixin.py

@@ -19,7 +19,7 @@ from llama_stack.apis.inference import (
     ChatCompletionResponseStreamChunk,
     EmbeddingsResponse,
     EmbeddingTaskType,
-    Inference,
+    InferenceProvider,
     JsonSchemaResponseFormat,
     LogProbConfig,
     Message,
@@ -59,7 +59,7 @@ logger = get_logger(name=__name__, category="inference")
 
 class LiteLLMOpenAIMixin(
     ModelRegistryHelper,
-    Inference,
+    InferenceProvider,
     NeedsRequestProviderData,
 ):
     # TODO: avoid exposing the litellm specific model names to the user.