streaming: fix reading the last empty chunk #170
+1
−1
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hello! We built a small, straightforward LLM benchmarking tool in Go that sends a large number of concurrent requests through a single openai client.
Issue:
We noticed that connections were repeatedly being re-created instead of reused. By limiting the client to a single connection per host, we discovered that the connection was hanging because the final chunk in a chunked response
"0\r\n\r\n"
was never read.Returning false at that moment prevents the last chunk from being processed properly, causing the body to not be properly closed. This fix corrects that typo, ensuring the final chunk is consumed and allowing connections to be reused as intended.