chore!: add double routes for v1/openai/v1 (#3636)

So that users get a warning in 0.3.0 and we remove them in 0.4.0.

Signed-off-by: Sébastien Han <seb@redhat.com>

docs/static/llama-stack-spec.html

@@ -1310,16 +1310,11 @@
             "post": {
                 "responses": {
                     "200": {
-                        "description": "An OpenAIResponseObject.",
+                        "description": "A ListOpenAIResponseObject.",
                         "content": {
                             "application/json": {
                                 "schema": {
-                                    "$ref": "#/components/schemas/OpenAIResponseObject"
+                                    "$ref": "#/components/schemas/ListOpenAIResponseObject"
-                                }
-                            },
-                            "text/event-stream": {
-                                "schema": {
-                                    "$ref": "#/components/schemas/OpenAIResponseObjectStream"
                                 }
                             }
                         }
@@ -1340,14 +1335,14 @@
                 "tags": [
                     "Agents"
                 ],
-                "summary": "Create a new OpenAI response.",
+                "summary": "List all OpenAI responses.",
-                "description": "Create a new OpenAI response.",
+                "description": "List all OpenAI responses.",
                 "parameters": [],
                 "requestBody": {
                     "content": {
                         "application/json": {
                             "schema": {
-                                "$ref": "#/components/schemas/CreateOpenaiResponseRequest"
+                                "$ref": "#/components/schemas/ListOpenaiResponsesRequest"
                             }
                         }
                     },
@@ -8238,6 +8233,33 @@
                 ],
                 "title": "OpenAIResponseObjectStreamResponseWebSearchCallSearching"
             },
+            "ListOpenaiResponsesRequest": {
+                "type": "object",
+                "properties": {
+                    "after": {
+                        "type": "string",
+                        "description": "The ID of the last response to return."
+                    },
+                    "limit": {
+                        "type": "integer",
+                        "description": "The number of responses to return."
+                    },
+                    "model": {
+                        "type": "string",
+                        "description": "The model to filter responses by."
+                    },
+                    "order": {
+                        "type": "string",
+                        "enum": [
+                            "asc",
+                            "desc"
+                        ],
+                        "description": "The order to sort responses by when sorted by created_at ('asc' or 'desc')."
+                    }
+                },
+                "additionalProperties": false,
+                "title": "ListOpenaiResponsesRequest"
+            },
             "OpenAIDeleteResponseObject": {
                 "type": "object",
                 "properties": {

docs/static/llama-stack-spec.yaml

@@ -967,14 +967,11 @@ paths:
     post:
       responses:
         '200':
-          description: An OpenAIResponseObject.
+          description: A ListOpenAIResponseObject.
           content:
             application/json:
               schema:
-                $ref: '#/components/schemas/OpenAIResponseObject'
+                $ref: '#/components/schemas/ListOpenAIResponseObject'
-            text/event-stream:
-              schema:
-                $ref: '#/components/schemas/OpenAIResponseObjectStream'
         '400':
           $ref: '#/components/responses/BadRequest400'
         '429':
@@ -987,14 +984,14 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Agents
-      summary: Create a new OpenAI response.
+      summary: List all OpenAI responses.
-      description: Create a new OpenAI response.
+      description: List all OpenAI responses.
       parameters: []
       requestBody:
         content:
           application/json:
             schema:
-              $ref: '#/components/schemas/CreateOpenaiResponseRequest'
+              $ref: '#/components/schemas/ListOpenaiResponsesRequest'
         required: true
       deprecated: false
   /v1/responses/{response_id}:
@@ -6199,6 +6196,27 @@ components:
         - type
       title: >-
         OpenAIResponseObjectStreamResponseWebSearchCallSearching
+    ListOpenaiResponsesRequest:
+      type: object
+      properties:
+        after:
+          type: string
+          description: The ID of the last response to return.
+        limit:
+          type: integer
+          description: The number of responses to return.
+        model:
+          type: string
+          description: The model to filter responses by.
+        order:
+          type: string
+          enum:
+            - asc
+            - desc
+          description: >-
+            The order to sort responses by when sorted by created_at ('asc' or 'desc').
+      additionalProperties: false
+      title: ListOpenaiResponsesRequest
     OpenAIDeleteResponseObject:
       type: object
       properties:

llama_stack/apis/agents/agents.py

@@ -772,6 +772,12 @@ class Agents(Protocol):
     #
     # Both of these APIs are inherently stateful.
 
+    @webmethod(
+        route="/openai/v1/responses/{response_id}",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(route="/responses/{response_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_openai_response(
         self,
@@ -784,6 +790,7 @@ class Agents(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/responses", method="POST", level=LLAMA_STACK_API_V1)
     async def create_openai_response(
         self,
@@ -809,6 +816,7 @@ class Agents(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_responses(
         self,
@@ -828,10 +836,9 @@ class Agents(Protocol):
         ...
 
     @webmethod(
-        route="/responses/{response_id}/input_items",
+        route="/openai/v1/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
-        method="GET",
-        level=LLAMA_STACK_API_V1,
     )
+    @webmethod(route="/responses/{response_id}/input_items", method="GET", level=LLAMA_STACK_API_V1)
     async def list_openai_response_input_items(
         self,
         response_id: str,
@@ -853,6 +860,7 @@ class Agents(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/responses/{response_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def delete_openai_response(self, response_id: str) -> OpenAIDeleteResponseObject:
         """Delete an OpenAI response by its ID.

llama_stack/apis/batches/batches.py

@@ -43,6 +43,7 @@ class Batches(Protocol):
     Note: This API is currently under active development and may undergo changes.
     """
 
+    @webmethod(route="/openai/v1/batches", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches", method="POST", level=LLAMA_STACK_API_V1)
     async def create_batch(
         self,
@@ -63,6 +64,7 @@ class Batches(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches/{batch_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def retrieve_batch(self, batch_id: str) -> BatchObject:
         """Retrieve information about a specific batch.
@@ -72,6 +74,7 @@ class Batches(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches/{batch_id}/cancel", method="POST", level=LLAMA_STACK_API_V1)
     async def cancel_batch(self, batch_id: str) -> BatchObject:
         """Cancel a batch that is in progress.
@@ -81,6 +84,7 @@ class Batches(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/batches", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/batches", method="GET", level=LLAMA_STACK_API_V1)
     async def list_batches(
         self,

llama_stack/apis/files/files.py

@@ -105,6 +105,7 @@ class OpenAIFileDeleteResponse(BaseModel):
 @trace_protocol
 class Files(Protocol):
     # OpenAI Files API Endpoints
+    @webmethod(route="/openai/v1/files", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_upload_file(
         self,
@@ -127,6 +128,7 @@ class Files(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/files", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_files(
         self,
@@ -146,6 +148,7 @@ class Files(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file(
         self,
@@ -159,6 +162,7 @@ class Files(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_file(
         self,
@@ -172,6 +176,7 @@ class Files(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/files/{file_id}/content", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_file_content(
         self,

llama_stack/apis/inference/inference.py

@@ -1066,6 +1066,7 @@ class InferenceProvider(Protocol):
         raise NotImplementedError("Reranking is not implemented")
         return  # this is so mypy's safe-super rule will consider the method concrete
 
+    @webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_completion(
         self,
@@ -1117,6 +1118,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_chat_completion(
         self,
@@ -1173,6 +1175,7 @@ class InferenceProvider(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/embeddings", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_embeddings(
         self,
@@ -1202,6 +1205,7 @@ class Inference(InferenceProvider):
     - Embedding models: these models generate embeddings to be used for semantic search.
     """
 
+    @webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
     async def list_chat_completions(
         self,
@@ -1220,6 +1224,9 @@ class Inference(InferenceProvider):
         """
         raise NotImplementedError("List chat completions is not implemented")
 
+    @webmethod(
+        route="/openai/v1/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
+    )
     @webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
         """Describe a chat completion by its ID.

llama_stack/apis/models/models.py

@@ -111,6 +111,14 @@ class Models(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/models", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
+    async def openai_list_models(self) -> OpenAIListModelsResponse:
+        """List models using the OpenAI API.
+
+        :returns: A OpenAIListModelsResponse.
+        """
+        ...
+
     @webmethod(route="/models/{model_id:path}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_model(
         self,

llama_stack/apis/safety/safety.py

@@ -114,6 +114,7 @@ class Safety(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/moderations", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/moderations", method="POST", level=LLAMA_STACK_API_V1)
     async def run_moderation(self, input: str | list[str], model: str) -> ModerationObject:
         """Classifies if text and/or image inputs are potentially harmful.

llama_stack/apis/vector_io/vector_io.py

@@ -512,6 +512,7 @@ class VectorIO(Protocol):
         ...
 
     # OpenAI Vector Stores API endpoints
+    @webmethod(route="/openai/v1/vector_stores", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
     async def openai_create_vector_store(
         self,
@@ -538,6 +539,7 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(route="/openai/v1/vector_stores", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_list_vector_stores(
         self,
@@ -556,6 +558,9 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
+    )
     @webmethod(route="/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def openai_retrieve_vector_store(
         self,
@@ -568,6 +573,9 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1, deprecated=True
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}",
         method="POST",
@@ -590,6 +598,9 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}",
         method="DELETE",
@@ -606,6 +617,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/search",
+        method="POST",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/search",
         method="POST",
@@ -638,6 +655,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/files",
+        method="POST",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files",
         method="POST",
@@ -660,6 +683,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/files",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files",
         method="GET",
@@ -686,6 +715,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}",
         method="GET",
@@ -704,6 +739,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}/content",
         method="GET",
@@ -722,6 +763,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
+        method="POST",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}",
         method="POST",
@@ -742,6 +789,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}",
+        method="DELETE",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/files/{file_id}",
         method="DELETE",
@@ -765,6 +818,12 @@ class VectorIO(Protocol):
         method="POST",
         level=LLAMA_STACK_API_V1,
     )
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/file_batches",
+        method="POST",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     async def openai_create_vector_store_file_batch(
         self,
         vector_store_id: str,
@@ -787,6 +846,12 @@ class VectorIO(Protocol):
         method="GET",
         level=LLAMA_STACK_API_V1,
     )
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     async def openai_retrieve_vector_store_file_batch(
         self,
         batch_id: str,
@@ -800,6 +865,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
+        method="GET",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/files",
         method="GET",
@@ -828,6 +899,12 @@ class VectorIO(Protocol):
         """
         ...
 
+    @webmethod(
+        route="/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
+        method="POST",
+        level=LLAMA_STACK_API_V1,
+        deprecated=True,
+    )
     @webmethod(
         route="/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel",
         method="POST",