fix(client): correct logic for line decoding in streaming (#433)

src/anthropic/_streaming.py

@@ -23,7 +23,7 @@ class Stream(Generic[_T]):
 
     response: httpx.Response
 
-    _decoder: SSEDecoder | SSEBytesDecoder
+    _decoder: SSEBytesDecoder
 
     def __init__(
         self,
@@ -46,10 +46,7 @@ def __iter__(self) -> Iterator[_T]:
             yield item
 
     def _iter_events(self) -> Iterator[ServerSentEvent]:
-        if isinstance(self._decoder, SSEBytesDecoder):
-            yield from self._decoder.iter_bytes(self.response.iter_bytes())
-        else:
-            yield from self._decoder.iter(self.response.iter_lines())
+        yield from self._decoder.iter_bytes(self.response.iter_bytes())
 
     def __stream__(self) -> Iterator[_T]:
         cast_to = cast(Any, self._cast_to)
@@ -145,12 +142,8 @@ async def __aiter__(self) -> AsyncIterator[_T]:
             yield item
 
     async def _iter_events(self) -> AsyncIterator[ServerSentEvent]:
-        if isinstance(self._decoder, SSEBytesDecoder):
-            async for sse in self._decoder.aiter_bytes(self.response.aiter_bytes()):
-                yield sse
-        else:
-            async for sse in self._decoder.aiter(self.response.aiter_lines()):
-                yield sse
+        async for sse in self._decoder.aiter_bytes(self.response.aiter_bytes()):
+            yield sse
 
     async def __stream__(self) -> AsyncIterator[_T]:
         cast_to = cast(Any, self._cast_to)
@@ -271,21 +264,49 @@ def __init__(self) -> None:
         self._last_event_id = None
         self._retry = None
 
-    def iter(self, iterator: Iterator[str]) -> Iterator[ServerSentEvent]:
-        """Given an iterator that yields lines, iterate over it & yield every event encountered"""
-        for line in iterator:
-            line = line.rstrip("\n")
-            sse = self.decode(line)
-            if sse is not None:
-                yield sse
-
-    async def aiter(self, iterator: AsyncIterator[str]) -> AsyncIterator[ServerSentEvent]:
-        """Given an async iterator that yields lines, iterate over it & yield every event encountered"""
-        async for line in iterator:
-            line = line.rstrip("\n")
-            sse = self.decode(line)
-            if sse is not None:
-                yield sse
+    def iter_bytes(self, iterator: Iterator[bytes]) -> Iterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        for chunk in self._iter_chunks(iterator):
+            # Split before decoding so splitlines() only uses \r and \n
+            for raw_line in chunk.splitlines():
+                line = raw_line.decode("utf-8")
+                sse = self.decode(line)
+                if sse:
+                    yield sse
+
+    def _iter_chunks(self, iterator: Iterator[bytes]) -> Iterator[bytes]:
+        """Given an iterator that yields raw binary data, iterate over it and yield individual SSE chunks"""
+        data = b""
+        for chunk in iterator:
+            for line in chunk.splitlines(keepends=True):
+                data += line
+                if data.endswith((b"\r\r", b"\n\n", b"\r\n\r\n")):
+                    yield data
+                    data = b""
+        if data:
+            yield data
+
+    async def aiter_bytes(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        async for chunk in self._aiter_chunks(iterator):
+            # Split before decoding so splitlines() only uses \r and \n
+            for raw_line in chunk.splitlines():
+                line = raw_line.decode("utf-8")
+                sse = self.decode(line)
+                if sse:
+                    yield sse
+
+    async def _aiter_chunks(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[bytes]:
+        """Given an iterator that yields raw binary data, iterate over it and yield individual SSE chunks"""
+        data = b""
+        async for chunk in iterator:
+            for line in chunk.splitlines(keepends=True):
+                data += line
+                if data.endswith((b"\r\r", b"\n\n", b"\r\n\r\n")):
+                    yield data
+                    data = b""
+        if data:
+            yield data
 
     def decode(self, line: str) -> ServerSentEvent | None:
         # See: https://html.spec.whatwg.org/multipage/server-sent-events.html#event-stream-interpretation  # noqa: E501