release: 2.0.0-alpha.9

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.0.0-alpha.8"
+  ".": "2.0.0-alpha.9"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 43
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/togetherai%2Ftogetherai-a1f15d8f8f7326616ea246a73d53bda093da7a9a5e3fe50a9ec6a5a0b958ec63.yml
-openapi_spec_hash: 7a03e5140a9a6668ff42c47ea0d03a07
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/togetherai%2Ftogetherai-bfa7422593036f383fcc5209e8a52705f582be9480f90747f8962a46ed5b1152.yml
+openapi_spec_hash: 400da476d5f86a3493bf6dacfe6826f0
 config_hash: 87a5832ab2ecefe567d22108531232f5

CHANGELOG.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## 2.0.0-alpha.9 (2025-11-27)
+
+Full Changelog: [v2.0.0-alpha.8...v2.0.0-alpha.9](https://github.com/togethercomputer/together-py/compare/v2.0.0-alpha.8...v2.0.0-alpha.9)
+
+### Bug Fixes
+
+* ensure streams are always closed ([db990c7](https://github.com/togethercomputer/together-py/commit/db990c744ebfffcfe48f52dc44b1ca7b47f1f79a))
+
+
+### Chores
+
+* **deps:** mypy 1.18.1 has a regression, pin to 1.17 ([2235b95](https://github.com/togethercomputer/together-py/commit/2235b95d3e8dc11c9edc308e2b4b69b1463d21cb))
+
 ## 2.0.0-alpha.8 (2025-11-26)
 
 Full Changelog: [v2.0.0-alpha.7...v2.0.0-alpha.8](https://github.com/togethercomputer/together-py/compare/v2.0.0-alpha.7...v2.0.0-alpha.8)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "together"
-version = "2.0.0-alpha.8"
+version = "2.0.0-alpha.9"
 description = "The official Python library for the together API"
 dynamic = ["readme"]
 license = "Apache-2.0"
@@ -67,7 +67,7 @@ conflicts = [
 # version pins are in uv.lock
 dev = [
     "pyright==1.1.399",
-    "mypy",
+    "mypy==1.17",
     "respx",
     "pytest",
     "pytest-asyncio",

requirements-dev.lock

@@ -76,7 +76,7 @@ multidict==6.7.0
     # via
     #   aiohttp
     #   yarl
-mypy==1.18.2
+mypy==1.17.0
 mypy-extensions==1.1.0
     # via mypy
 nodeenv==1.9.1
@@ -95,7 +95,7 @@ propcache==0.4.1
     # via
     #   aiohttp
     #   yarl
-pydantic==2.12.4
+pydantic==2.12.5
     # via together
 pydantic-core==2.41.5
     # via pydantic

src/together/_streaming.py

@@ -55,30 +55,31 @@ def __stream__(self) -> Iterator[_T]:
         process_data = self._client._process_response_data
         iterator = self._iter_events()
 
-        for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
-
-            if sse.event is None:
-                data = sse.json()
-                if is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
-
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
-
-                yield process_data(data=data, cast_to=cast_to, response=response)
-
-        # As we might not fully consume the response stream, we need to close it explicitly
-        response.close()
+        try:
+            for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
+
+                if sse.event is None:
+                    data = sse.json()
+                    if is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
+
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
+
+                    yield process_data(data=data, cast_to=cast_to, response=response)
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            response.close()
 
     def __enter__(self) -> Self:
         return self
@@ -137,30 +138,31 @@ async def __stream__(self) -> AsyncIterator[_T]:
         process_data = self._client._process_response_data
         iterator = self._iter_events()
 
-        async for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
-
-            if sse.event is None:
-                data = sse.json()
-                if is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
-
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
-
-                yield process_data(data=data, cast_to=cast_to, response=response)
-
-        # As we might not fully consume the response stream, we need to close it explicitly
-        await response.aclose()
+        try:
+            async for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
+
+                if sse.event is None:
+                    data = sse.json()
+                    if is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
+
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
+
+                    yield process_data(data=data, cast_to=cast_to, response=response)
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            await response.aclose()
 
     async def __aenter__(self) -> Self:
         return self

src/together/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "together"
-__version__ = "2.0.0-alpha.8"  # x-release-please-version
+__version__ = "2.0.0-alpha.9"  # x-release-please-version