feat(api): support WebSocket warmup and preserve cleanup cancellation

.castiron.stats.yml

@@ -1,7 +1,7 @@
 schema_version: 1
-generation_id: 65a0f13e-756e-4f10-b075-12ae5d3d27a9
-openapi_spec_hash: 51b199ef7fd5542bc4910765f9becd60
-openapi_transformed_spec_hash: 73822d924c15a6ed58dcfe8f616bd4be
+generation_id: 287e1fa6-451c-4f5f-9a80-498c77a0bd65
+openapi_spec_hash: 17689beb6a2da96f6cf9e5ac1e758a99
+openapi_transformed_spec_hash: 75a7f7b19910025d8f8f8aa1556d9b69
 config_hash: b707b209c892562880c415693d111ad6
-codegen_sha: 52c5bafacb27ede81a3d66b62b29d946df4ed2cd
-codegen_hash: 536c408e94523f4af5a3ddf0c2f8f0764014bad6b9287cacdb9b8e3eeb60ba7d
+codegen_sha: b79c2ec277007e5a097e73a710864b77338da840
+codegen_hash: 7acc6ff9d93bbfd3be9e38f79d6b509bfd063f80cdd751f997b86e000327b9ae

api_reference/openapi.transformed.yml

@@ -68596,6 +68596,12 @@ components:
               `stream_id` controls routing; `previous_response_id` controls
               conversation lineage, so a new lane can fork from a response created
               on another lane.
+          generate:
+            type: boolean
+            description: |
+              Whether to generate output for this response. Defaults to true when omitted.
+              Set to false to prepare request state without model output; the response
+              ID can be used as previous_response_id on a later turn.
         required:
         - type
       - $ref: '#/components/schemas/CreateResponse'
@@ -111544,6 +111550,12 @@ components:
               `stream_id` controls routing; `previous_response_id` controls
               conversation lineage, so a new lane can fork from a response created
               on another lane.
+          generate:
+            type: boolean
+            description: |
+              Whether to generate output for this response. Defaults to true when omitted.
+              Set to false to prepare request state without model output; the response
+              ID can be used as previous_response_id on a later turn.
         required:
         - type
       - $ref: '#/components/schemas/BetaCreateResponse'

scripts/castiron/generated-files.json

@@ -379,7 +379,7 @@
     },
     "src/openai/resources/beta/responses/responses.py": {
       "mode": "100644",
-      "sha256": "effa8db6d9a676f1f264f0b6acb3252d8dcd5f75db251bfd8b5d45ea49f0f533"
+      "sha256": "c5a3b0cb69c3f990dc2ae76db0d2c5fb2df54b8fc312d330cb33d223d1389d26"
     },
     "src/openai/resources/beta/threads/__init__.py": {
       "mode": "100644",
@@ -559,19 +559,19 @@
     },
     "src/openai/resources/live/forks.py": {
       "mode": "100644",
-      "sha256": "7fe78c144680df54628773683f9dd5b06c5241d0218b4f4c745890ddae225c92"
+      "sha256": "f65742e893b6af599b97156ed30e80629364a4cf74fa76593c26b845c4fd6a1b"
     },
     "src/openai/resources/live/live.py": {
       "mode": "100644",
-      "sha256": "86be3e074d011a750fa52a4d216a7e87ee5c8e82f6ccec00102c03a539199882"
+      "sha256": "4f9a3128d0a4d56f14c74c80a1d6bb8ee76fdb8096699f6573bc6c4ed434b9d6"
     },
     "src/openai/resources/live/sessions.py": {
       "mode": "100644",
       "sha256": "9ba2d59d9c7498c96ac2e7e48660c91468e0eeb5df881e77f123ee37985c3dfd"
     },
     "src/openai/resources/live/sideband.py": {
       "mode": "100644",
-      "sha256": "d19149c042afcd8c8efca3d7794092acc1c2f76a4bcb4f6f620547314a78e59b"
+      "sha256": "57b9f15595dc68614203c5c0fa4c92f309e27a90f927a0cf8e46542cfa3eb79b"
     },
     "src/openai/resources/models.py": {
       "mode": "100644",
@@ -599,7 +599,7 @@
     },
     "src/openai/resources/realtime/realtime.py": {
       "mode": "100644",
-      "sha256": "9cb69e1f54c6e21d9111ddfb59a2a4de18466a1a86487fc65a0e17224b72475e"
+      "sha256": "57a32212a3d102145e054727e00c979b616b38d85a2802761dd2f6c2848a0db1"
     },
     "src/openai/resources/realtime/translations/__init__.py": {
       "mode": "100644",
@@ -611,7 +611,7 @@
     },
     "src/openai/resources/realtime/translations/translations.py": {
       "mode": "100644",
-      "sha256": "4a6f072cea78d5afab3fe1c995b939ff8c79f449665346c729abb5c516c53f21"
+      "sha256": "dd26ca4fe27aa6b23b9d0add6e5aa41d10379ee3c6fa8c22293a26da867ca90e"
     },
     "src/openai/resources/responses/__init__.py": {
       "mode": "100644",
@@ -631,7 +631,7 @@
     },
     "src/openai/resources/responses/responses.py": {
       "mode": "100644",
-      "sha256": "f844db6ec37b49de883ab2c507570b94c29e8c2609ee93cf45c0aec19fd671d3"
+      "sha256": "86130a834c60c1b7df85118cbc918e84d0a23c122099f1f4e931c1a39b35abfa"
     },
     "src/openai/resources/safety/__init__.py": {
       "mode": "100644",
@@ -3087,11 +3087,11 @@
     },
     "src/openai/types/beta/beta_responses_client_event.py": {
       "mode": "100644",
-      "sha256": "939052a456df5a661ed334033a9151c18ed63dfba6c520fd92a7572d50efc091"
+      "sha256": "977d2d22d8468005d9dcf27c5e9c7e5c6430bb9dacd5258369022f1513431d3d"
     },
     "src/openai/types/beta/beta_responses_client_event_param.py": {
       "mode": "100644",
-      "sha256": "ba2e2d06061761345308086b4b1d2ce39f86db631c46db825c5bbc7f62f63ccb"
+      "sha256": "0ad4be42df7202197e66ed97ae6fbfbdcad2aeb4e92328064630497d18fb457c"
     },
     "src/openai/types/beta/beta_responses_server_event.py": {
       "mode": "100644",
@@ -6735,11 +6735,11 @@
     },
     "src/openai/types/responses/responses_client_event.py": {
       "mode": "100644",
-      "sha256": "77d64183c9c69abfd4300c8094fbd3bc9c3a89743b9efa83a5264bd3dc165961"
+      "sha256": "3993eec234392a96646408fb959860a86b2711ac53dc7e8ae1338c43ca6383b4"
     },
     "src/openai/types/responses/responses_client_event_param.py": {
       "mode": "100644",
-      "sha256": "95444697e02d702e9f568da381903d251b3d5c649de9c5d26662a1782431647b"
+      "sha256": "20cbab38d02cfd2506ad2104d09e2b3bfb0d2b0d8a55adec13882f3a15c9db2d"
     },
     "src/openai/types/responses/responses_server_event.py": {
       "mode": "100644",

src/openai/resources/beta/responses/responses.py

@@ -5278,7 +5278,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -5696,7 +5696,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -5715,6 +5715,7 @@ def create(
         context_management: Optional[Iterable[beta_responses_client_event_param.ResponseCreateContextManagement]]
         | Omit = omit,
         conversation: Optional[beta_responses_client_event_param.ResponseCreateConversation] | Omit = omit,
+        generate: bool | Omit = omit,
         include: Optional[List[BetaResponseIncludable]] | Omit = omit,
         input: Union[str, BetaResponseInputParam] | Omit = omit,
         instructions: Optional[str] | Omit = omit,
@@ -5881,6 +5882,7 @@ def create(
                         "background": background,
                         "context_management": context_management,
                         "conversation": conversation,
+                        "generate": generate,
                         "include": include,
                         "input": input,
                         "instructions": instructions,
@@ -5973,6 +5975,7 @@ async def create(
         context_management: Optional[Iterable[beta_responses_client_event_param.ResponseCreateContextManagement]]
         | Omit = omit,
         conversation: Optional[beta_responses_client_event_param.ResponseCreateConversation] | Omit = omit,
+        generate: bool | Omit = omit,
         include: Optional[List[BetaResponseIncludable]] | Omit = omit,
         input: Union[str, BetaResponseInputParam] | Omit = omit,
         instructions: Optional[str] | Omit = omit,
@@ -6139,6 +6142,7 @@ async def create(
                         "background": background,
                         "context_management": context_management,
                         "conversation": conversation,
+                        "generate": generate,
                         "include": include,
                         "input": input,
                         "instructions": instructions,

src/openai/resources/live/forks.py

@@ -533,7 +533,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -959,7 +959,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 

src/openai/resources/live/live.py

@@ -746,7 +746,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -1164,7 +1164,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 

src/openai/resources/live/sideband.py

@@ -545,7 +545,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -980,7 +980,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 

src/openai/resources/realtime/realtime.py

@@ -756,7 +756,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -1213,7 +1213,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 

src/openai/resources/realtime/translations/translations.py

@@ -617,7 +617,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -1041,7 +1041,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 

src/openai/resources/responses/responses.py

@@ -4467,7 +4467,7 @@ async def __aexit__(
         if self.__connection is not None:
             try:
                 await self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -4886,7 +4886,7 @@ def __exit__(
         if self.__connection is not None:
             try:
                 self.__connection.close()
-            except BaseException:
+            except Exception:
                 if exc is None:
                     raise
 
@@ -4939,6 +4939,7 @@ def create(
         context_management: Optional[Iterable[responses_client_event_param.ResponseCreateContextManagement]]
         | Omit = omit,
         conversation: Optional[responses_client_event_param.ResponseCreateConversation] | Omit = omit,
+        generate: bool | Omit = omit,
         include: Optional[List[ResponseIncludable]] | Omit = omit,
         input: Union[str, ResponseInputParam] | Omit = omit,
         instructions: Optional[str] | Omit = omit,
@@ -4989,6 +4990,7 @@ def create(
                         "background": background,
                         "context_management": context_management,
                         "conversation": conversation,
+                        "generate": generate,
                         "include": include,
                         "input": input,
                         "instructions": instructions,
@@ -5074,6 +5076,7 @@ async def create(
         context_management: Optional[Iterable[responses_client_event_param.ResponseCreateContextManagement]]
         | Omit = omit,
         conversation: Optional[responses_client_event_param.ResponseCreateConversation] | Omit = omit,
+        generate: bool | Omit = omit,
         include: Optional[List[ResponseIncludable]] | Omit = omit,
         input: Union[str, ResponseInputParam] | Omit = omit,
         instructions: Optional[str] | Omit = omit,
@@ -5124,6 +5127,7 @@ async def create(
                         "background": background,
                         "context_management": context_management,
                         "conversation": conversation,
+                        "generate": generate,
                         "include": include,
                         "input": input,
                         "instructions": instructions,

src/openai/types/beta/beta_responses_client_event.py

@@ -281,6 +281,14 @@ class ResponseCreate(BaseModel):
     to this conversation after this response completes.
     """
 
+    generate: Optional[bool] = None
+    """Whether to generate output for this response.
+
+    Defaults to true when omitted. Set to false to prepare request state without
+    model output; the response ID can be used as previous_response_id on a later
+    turn.
+    """
+
     include: Optional[List[BetaResponseIncludable]] = None
     """Specify additional output data to include in the model response.
 

src/openai/types/beta/beta_responses_client_event_param.py

@@ -281,6 +281,14 @@ class ResponseCreate(TypedDict, total=False):
     to this conversation after this response completes.
     """
 
+    generate: bool
+    """Whether to generate output for this response.
+
+    Defaults to true when omitted. Set to false to prepare request state without
+    model output; the response ID can be used as previous_response_id on a later
+    turn.
+    """
+
     include: Optional[List[BetaResponseIncludable]]
     """Specify additional output data to include in the model response.
 

src/openai/types/responses/responses_client_event.py

@@ -222,6 +222,14 @@ class ResponseCreate(BaseModel):
     to this conversation after this response completes.
     """
 
+    generate: Optional[bool] = None
+    """Whether to generate output for this response.
+
+    Defaults to true when omitted. Set to false to prepare request state without
+    model output; the response ID can be used as previous_response_id on a later
+    turn.
+    """
+
     include: Optional[List[ResponseIncludable]] = None
     """Specify additional output data to include in the model response.
 

src/openai/types/responses/responses_client_event_param.py

@@ -222,6 +222,14 @@ class ResponseCreate(TypedDict, total=False):
     to this conversation after this response completes.
     """
 
+    generate: bool
+    """Whether to generate output for this response.
+
+    Defaults to true when omitted. Set to false to prepare request state without
+    model output; the response ID can be used as previous_response_id on a later
+    turn.
+    """
+
     include: Optional[List[ResponseIncludable]]
     """Specify additional output data to include in the model response.