Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

fix(proxy/streaming): tolerate malformed content in _response_to_sse (#2481)

Abhay Singh77b26c093cfb
diff --git a/headroom/proxy/handlers/streaming.py b/headroom/proxy/handlers/streaming.py
index b3fc68547..3b864f9dd 100644
--- a/headroom/proxy/handlers/streaming.py
+++ b/headroom/proxy/handlers/streaming.py
@@ -565,8 +565,17 @@ class StreamingMixin:
}
events.append(f"event: message_start\ndata: {json.dumps(msg_start)}\n\n".encode())
- # Content blocks
- for idx, block in enumerate(response.get("content", [])):
+ # Content blocks. `content` is provider/reconstruction-controlled, so a
+ # present-but-null value or a non-list would crash `enumerate`, and a
+ # non-dict element would crash `block.get(...)`. Guard both, matching the
+ # sibling `_record_ccr_feedback_from_response` below. This is reached from
+ # a call site (anthropic.py buffered CCR path) that only catches
+ # ValueError, so an unguarded TypeError/AttributeError would 500 the
+ # streamed request.
+ content = response.get("content")
+ for idx, block in enumerate(content if isinstance(content, list) else []):
+ if not isinstance(block, dict):
+ continue
# content_block_start
if block.get("type") == "text":
block_start = {
@@ -680,10 +689,13 @@ class StreamingMixin:
msg_delta_payload["stop_reason"] = response["stop_reason"]
if "stop_details" in response:
msg_delta_payload["stop_details"] = response["stop_details"]
+ usage = response.get("usage")
+ if not isinstance(usage, dict):
+ usage = {}
msg_delta = {
"type": "message_delta",
"delta": msg_delta_payload,
- "usage": {"output_tokens": response.get("usage", {}).get("output_tokens", 0)},
+ "usage": {"output_tokens": usage.get("output_tokens", 0)},
}
events.append(f"event: message_delta\ndata: {json.dumps(msg_delta)}\n\n".encode())
diff --git a/tests/test_sse_thinking_blocks.py b/tests/test_sse_thinking_blocks.py
index 0b32881f8..236b43c23 100644
--- a/tests/test_sse_thinking_blocks.py
+++ b/tests/test_sse_thinking_blocks.py
@@ -324,6 +324,40 @@ def test_response_to_sse_emits_unknown_content_block_verbatim() -> None:
assert not any(ev["type"] == "content_block_delta" for ev in events)
+def test_response_to_sse_tolerates_malformed_content_and_usage() -> None:
+ # `_response_to_sse` runs on provider/reconstruction-controlled JSON and is
+ # reached from a call site (anthropic.py buffered CCR path) that only catches
+ # ValueError, so a present-but-null `content`/`usage` or a non-dict block must
+ # not raise a TypeError/AttributeError that would 500 the streamed request.
+ # The sibling `_record_ccr_feedback_from_response` guards `content` the same
+ # way. Each of these once crashed the unguarded loop.
+ parser = _Parser()
+
+ for response in (
+ {"content": None, "usage": {"output_tokens": 5}},
+ {"content": "not-a-list"},
+ {"content": [None, {"type": "text", "text": "hi"}]},
+ {"content": [], "usage": None},
+ ):
+ sse_text = b"".join(parser._response_to_sse(response, "anthropic")).decode("utf-8")
+ # Always a well-formed envelope, regardless of the malformed body.
+ assert "event: message_start" in sse_text
+ assert "event: message_stop" in sse_text
+
+ # The one valid block alongside a null element is still rendered.
+ sse_text = b"".join(
+ parser._response_to_sse({"content": [None, {"type": "text", "text": "hi"}]}, "anthropic")
+ ).decode("utf-8")
+ events = _sse_events(sse_text)
+ text_deltas = [
+ ev
+ for ev in events
+ if ev["type"] == "content_block_delta" and ev["delta"].get("type") == "text_delta"
+ ]
+ assert len(text_deltas) == 1
+ assert text_deltas[0]["delta"]["text"] == "hi"
+
+
def test_response_to_sse_emits_server_tool_use_without_delta() -> None:
parser = _Parser()
server_tool_use = {