Merge remote-tracking branch 'origin/main' into TamiTakamiya/tool-param-definition-update

docs/static/llama-stack-spec.yaml

@@ -132,43 +132,6 @@ paths:
             schema:
               $ref: '#/components/schemas/ChatCompletionRequest'
         required: true
-  /v1/inference/completion:
-    post:
-      responses:
-        '200':
-          description: >-
-            If stream=False, returns a CompletionResponse with the full completion.
-            If stream=True, returns an SSE event stream of CompletionResponseStreamChunk.
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/CompletionResponse'
-            text/event-stream:
-              schema:
-                $ref: '#/components/schemas/CompletionResponseStreamChunk'
-        '400':
-          $ref: '#/components/responses/BadRequest400'
-        '429':
-          $ref: >-
-            #/components/responses/TooManyRequests429
-        '500':
-          $ref: >-
-            #/components/responses/InternalServerError500
-        default:
-          $ref: '#/components/responses/DefaultError'
-      tags:
-        - Inference
-      summary: >-
-        Generate a completion for the given content using the specified model.
-      description: >-
-        Generate a completion for the given content using the specified model.
-      parameters: []
-      requestBody:
-        content:
-          application/json:
-            schema:
-              $ref: '#/components/schemas/CompletionRequest'
-        required: true
   /v1/agents:
     get:
       responses:
@@ -5302,112 +5265,6 @@ components:
       title: ToolCallDelta
       description: >-
         A tool call content delta for streaming responses.
-    CompletionRequest:
-      type: object
-      properties:
-        model_id:
-          type: string
-          description: >-
-            The identifier of the model to use. The model must be registered with
-            Llama Stack and available via the /models endpoint.
-        content:
-          $ref: '#/components/schemas/InterleavedContent'
-          description: >-
-            The content to generate a completion for.
-        sampling_params:
-          $ref: '#/components/schemas/SamplingParams'
-          description: >-
-            (Optional) Parameters to control the sampling strategy.
-        response_format:
-          $ref: '#/components/schemas/ResponseFormat'
-          description: >-
-            (Optional) Grammar specification for guided (structured) decoding.
-        stream:
-          type: boolean
-          description: >-
-            (Optional) If True, generate an SSE event stream of the response. Defaults
-            to False.
-        logprobs:
-          type: object
-          properties:
-            top_k:
-              type: integer
-              default: 0
-              description: >-
-                How many tokens (for each position) to return log probabilities for.
-          additionalProperties: false
-          description: >-
-            (Optional) If specified, log probabilities for each token position will
-            be returned.
-      additionalProperties: false
-      required:
-        - model_id
-        - content
-      title: CompletionRequest
-    CompletionResponse:
-      type: object
-      properties:
-        metrics:
-          type: array
-          items:
-            $ref: '#/components/schemas/MetricInResponse'
-          description: >-
-            (Optional) List of metrics associated with the API response
-        content:
-          type: string
-          description: The generated completion text
-        stop_reason:
-          type: string
-          enum:
-            - end_of_turn
-            - end_of_message
-            - out_of_tokens
-          description: Reason why generation stopped
-        logprobs:
-          type: array
-          items:
-            $ref: '#/components/schemas/TokenLogProbs'
-          description: >-
-            Optional log probabilities for generated tokens
-      additionalProperties: false
-      required:
-        - content
-        - stop_reason
-      title: CompletionResponse
-      description: Response from a completion request.
-    CompletionResponseStreamChunk:
-      type: object
-      properties:
-        metrics:
-          type: array
-          items:
-            $ref: '#/components/schemas/MetricInResponse'
-          description: >-
-            (Optional) List of metrics associated with the API response
-        delta:
-          type: string
-          description: >-
-            New content generated since last chunk. This can be one or more tokens.
-        stop_reason:
-          type: string
-          enum:
-            - end_of_turn
-            - end_of_message
-            - out_of_tokens
-          description: >-
-            Optional reason why generation stopped, if complete
-        logprobs:
-          type: array
-          items:
-            $ref: '#/components/schemas/TokenLogProbs'
-          description: >-
-            Optional log probabilities for generated tokens
-      additionalProperties: false
-      required:
-        - delta
-      title: CompletionResponseStreamChunk
-      description: >-
-        A chunk of a streamed completion response.
     AgentConfig:
       type: object
       properties: