History

open_ai: Enable parallel tool calling for models that support it (#52203)

## Context We seemed to have disabled it in #28056, because our agent did not support parallel tool calls at the time. ## Self-Review Checklist <!-- Check before requesting review: --> - [x] I've reviewed my own diff for quality, security, and reliability - [x] Unsafe blocks (if any) have justifying comments - [x] The content is consistent with the [UI/UX checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist) - [x] Tests cover the new/changed behavior - [x] Performance impact has been considered and is acceptable Release Notes: - N/A or Added/Fixed/Improved ...

Bennet Bo Fenner committed 7 months ago

Commit 256135e1 parent 45ca6511 file · +1 −2Browse files

Unified · Split

crates/language_models/src/provider/open_ai.rs+1−2
@@ -514,8 +514,7 @@ pub fn into_open_ai( · 513 unmodified lines
514514 temperature: request.temperature.or(Some(1.0)),
515515 max_completion_tokens: max_output_tokens,
516516 parallel_tool_calls: if supports_parallel_tool_calls && !request.tools.is_empty() {
517− // Disable parallel tool calls, as the Agent currently expects a maximum of one per turn.
518− Some(false)
517+ Some(supports_parallel_tool_calls)
519518 } else {
520519 None
521520 },