Compare commits

...
Author SHA1 Message Date
9qeklajc 5a3774a414 consolidate streaming 2026-06-20 11:33:52 +02:00
2 changed files with 105 additions and 6 deletions
+33 -6
View File
@@ -766,7 +766,9 @@ class BaseUpstreamProvider:
except Exception:
pass
def _process_event(raw_event: bytes) -> Iterator[bytes]:
def _process_event(
raw_event: bytes, final: bool = False
) -> Iterator[bytes]:
"""Process one complete SSE event block (lines up to a blank line).
Handles arbitrary upstream framing across every supported
@@ -872,6 +874,12 @@ class BaseUpstreamProvider:
return
yield prefix + b"data: " + json.dumps(obj).encode() + b"\n\n"
else:
if final:
# Final flush of a truncated tail: the upstream closed
# mid-event, so ``data`` is incomplete JSON. Emitting it
# as a ``data:`` frame would hand the client invalid
# JSON (the "unexpected token" parse error). Drop it.
return
# Non-JSON data payload (partial fragment already reassembled
# by buffering, or a provider control string). Re-prefix each
# line so multi-line ``data`` stays valid SSE framing - a bare
@@ -890,7 +898,13 @@ class BaseUpstreamProvider:
# boundary-independent for every provider.
buffer = b""
async for chunk in response.aiter_bytes():
buffer += chunk.replace(b"\r\n", b"\n")
# Normalize the *joined* buffer, not each chunk in
# isolation: a CRLF event delimiter can straddle two
# ``aiter_bytes`` chunks (``...\r`` then ``\n...``). A
# per-chunk replace would leave a stray ``\r`` and the
# ``\n\n`` split would miss the delimiter, merging two
# events into one frame and breaking SSE clients.
buffer = (buffer + chunk).replace(b"\r\n", b"\n")
while b"\n\n" in buffer:
raw_event, buffer = buffer.split(b"\n\n", 1)
for out in _process_event(raw_event):
@@ -898,7 +912,7 @@ class BaseUpstreamProvider:
# Flush any trailing event that lacked a final blank line.
if buffer.strip():
for out in _process_event(buffer):
for out in _process_event(buffer, final=True):
yield out
async with create_session() as session:
@@ -1204,7 +1218,9 @@ class BaseUpstreamProvider:
except Exception:
pass
def _process_event(raw_event: bytes) -> Iterator[bytes]:
def _process_event(
raw_event: bytes, final: bool = False
) -> Iterator[bytes]:
"""Process one complete SSE event block for the Responses API.
Buffers full events (delimited by a blank line) so parsing is
@@ -1274,6 +1290,11 @@ class BaseUpstreamProvider:
yield prefix + b"data: " + json.dumps(obj).encode() + b"\n\n"
else:
if final:
# Final flush of a truncated tail: upstream closed
# mid-event, so ``data`` is incomplete JSON. Dropping it
# avoids handing the client an invalid ``data:`` frame.
return
# Re-prefix each line so multi-line ``data`` stays valid SSE
# framing for the client.
body = b"".join(
@@ -1286,14 +1307,20 @@ class BaseUpstreamProvider:
# delimiter so parsing is independent of byte boundaries.
buffer = b""
async for chunk in response.aiter_bytes():
buffer += chunk.replace(b"\r\n", b"\n")
# Normalize the *joined* buffer, not each chunk in
# isolation: a CRLF event delimiter can straddle two
# ``aiter_bytes`` chunks (``...\r`` then ``\n...``). A
# per-chunk replace would leave a stray ``\r`` and the
# ``\n\n`` split would miss the delimiter, merging two
# events into one frame and breaking SSE clients.
buffer = (buffer + chunk).replace(b"\r\n", b"\n")
while b"\n\n" in buffer:
raw_event, buffer = buffer.split(b"\n\n", 1)
for out in _process_event(raw_event):
yield out
if buffer.strip():
for out in _process_event(buffer):
for out in _process_event(buffer, final=True):
yield out
# Always emit a cost-bearing data chunk
@@ -337,3 +337,75 @@ async def test_multiline_non_json_data_each_line_prefixed() -> None:
continue
assert line.startswith(b"data: "), f"bare line leaked to client: {line!r}"
assert b"data: line one" in blob and b"data: line two" in blob
@pytest.mark.asyncio
async def test_crlf_delimiter_split_across_chunk_boundary() -> None:
"""CRLF event delimiter straddling two TCP reads must not merge events.
Regression: a per-chunk ``replace(b"\\r\\n", b"\\n")`` left a stray ``\\r``
when a ``\\r\\n`` of the ``\\r\\n\\r\\n`` delimiter landed at the very end of
one ``aiter_bytes`` chunk and the matching ``\\n`` opened the next. The
``\\n\\n`` split then missed the boundary, glued two events into one frame
with two ``data:`` lines, and the client's ``JSON.parse`` threw on the
concatenated payload (the "unexpected token"/"Extra data" crash).
"""
e1 = b'data: {"id":"x","choices":[{"delta":{"content":"a"}}]}'
e2 = b'data: {"id":"x","choices":[{"delta":{"content":"b"}}]}'
chunks = [
e1 + b"\r\n\r", # delimiter cut mid-CRLF
b"\n" + e2 + b"\r\n\r\n",
b"data: [DONE]\r\n\r\n",
]
out = await _drive(chunks)
# Client-accurate check: a real SSE client concatenates all ``data:`` lines
# *within one event* (events are ``\n\n``-delimited) before parsing. A
# merged frame would surface here as two objects glued into one payload,
# which ``_assert_clean`` (per-line) would miss.
blob = b"".join(out)
contents: list[str] = []
for event in blob.split(b"\n\n"):
datas = [
ln[len(b"data: ") :]
for ln in event.split(b"\n")
if ln.startswith(b"data: ")
]
if not datas:
continue
payload = b"".join(datas)
if payload.strip() == b"[DONE]":
continue
obj = json.loads(payload) # raises if two events were merged into one
for c in obj.get("choices", []):
if "delta" in c:
contents.append(c["delta"]["content"])
assert contents == ["a", "b"]
@pytest.mark.asyncio
async def test_truncated_json_tail_on_connection_close() -> None:
"""A stream that drops mid-event must not emit the partial JSON downstream.
Regression: the end-of-stream flush ran ``_process_event`` on the leftover
buffer unconditionally. When the upstream connection closed mid-event the
leftover was incomplete JSON, which fell through to the raw-forward path and
handed the client a ``data: {partial`` frame -> ``Unterminated string`` parse
error. The truncated tail must be dropped instead.
"""
chunks = [
b'data: {"id":"x","choices":[{"delta":{"content":"ok"}}]}\n\n',
b'data: {"id":"x","choices":[{"delta":{"con', # connection dies here
]
out = await _drive(chunks)
objs = _assert_clean(out) # raises if the partial tail leaked as a data frame
contents = [
c["delta"]["content"]
for o in objs
for c in o.get("choices", [])
if "delta" in c
]
# The one complete chunk is delivered; the truncated fragment is dropped
# entirely (no second delta), and _assert_clean above guarantees nothing
# non-JSON ever reached the client.
assert contents == ["ok"]