Response compression: compress API response before returning to agent#7
Merged
Conversation
New compress_response_body() function: - Deserializes the API JSON response - Runs compress_assistant_text() on each choice's message content - Code-block-aware: prose sections compressed, code blocks verbatim - Accepts any positive savings (no minimum threshold) - Returns modified body + chars saved in x-reliaty-response-saved header Also fixed compress_prose_inline threshold: accepts any 10+ char savings (was requiring 85% of original threshold). Verified: fires on real LLM responses (~2% savings on reasoning output).
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Compresses the assistant message content in API responses before returning to the agent. Each response's reasoning blocks get compressed by the code-block-aware compressor, saving 2-10% on wire size per turn. Compounds across turns as the compressed responses are reused in conversation history.