feat: parallel execution of native tool_use calls#486
Merged
Conversation
Replace sequential for-loop in handle_native_tool_calls() with futures::join_all for concurrent tool execution. When tool count exceeds max_parallel_tools (default 8), uses stream::buffered() to cap concurrency while preserving result ordering. Closes #485
github-actions
bot
added
rust
core
dependencies
config
enhancement
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
handle_native_tool_calls()withfutures::join_allfor concurrent tool executionmax_parallel_tools(default 8), usesstream::buffered()to cap concurrency while preserving result orderingChanges
crates/zeph-core/src/agent/streaming.rs— parallel execution via join_all/bufferedcrates/zeph-core/src/config/types.rs—max_parallel_toolsfield in TimeoutConfigcrates/zeph-core/Cargo.toml— addedfuturesdependencyconfig/default.toml— documented new config keyTest plan
parallel_preserves_result_order— verifies ordering after join_allparallel_faster_than_sequential— concurrent execution faster than sequentialone_failure_does_not_block_others— failure isolationbuffered_preserves_order— bounded concurrency preserves ordercargo clippy --workspace -- -D warningscleanCloses #485