fix AiTokenLimiterPlugin appendResponse #6027
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
using english，pls |
Contributor
Author
done |
478320
pushed a commit
to 478320/shenyu
that referenced
this pull request
Jul 17, 2025
* fix: one-time decompression after the flow is finished * chore: code style * feat: save memory by streaming cross-block decompression * chore: code style * chore: del useless imports
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Question:
In the appendResponse method,
Processing ByteBuffer in chunks leads to the first ByteBuffer having a gzip response header, which is correctly decompressed. Subsequent ByteBuffers are intermediate segments in the compressed stream and no longer contain a header. When taken out separately and decompressed using GZIPInputStream, they cannot identify the beginning and will report an error when constructing the stream or reading data. If subsequent chunks fail to decompress, the original compressed bytes will be written to BodyWriter unchanged. What accumulates in BodyWriter is a garbled binary stream rather than decompressed text. This leads to inaccurate token statistics.
Solution:
By decompressing across chunks in a streaming manner, memory consumption is reduced while gzip data is correctly processed and token counts are accurately tallied.