Skip to content

Add max_parallel_tool_calls to .act() API #102

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ncoghlan merged 1 commit into from
Jun 26, 2025
Merged

Add max_parallel_tool_calls to .act() API #102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "lmstudio"
version = "1.3.3.dev0"
version = "1.4.0.dev0"
description = "LM Studio Python SDK"
authors = [
{name = "LM Studio", email = "team@lmstudio.ai"},
Expand Down
2 changes: 1 addition & 1 deletion src/lmstudio/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
"""LM Studio Python SDK."""

__version__ = "1.3.3.dev0"
__version__ = "1.4.0.dev0"


# In addition to publishing the main SDK client API,
Expand Down
3 changes: 2 additions & 1 deletion src/lmstudio/sync_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1281,6 +1281,7 @@ def act(
tools: Iterable[ToolDefinition],
*,
max_prediction_rounds: int | None = None,
max_parallel_tool_calls: int | None = 1,
config: LlmPredictionConfig | LlmPredictionConfigDict | None = None,
preset: str | None = None,
on_message: Callable[[AssistantResponse | ToolResultMessage], Any]
Expand Down Expand Up @@ -1351,7 +1352,7 @@ def _wrapped_on_prompt_processing_progress(progress: float) -> None:
on_prompt_processing_for_endpoint = _wrapped_on_prompt_processing_progress
# Request predictions until no more tool call requests are received in response
# (or the maximum number of prediction rounds is reached)
with ThreadPoolExecutor() as pool:
with ThreadPoolExecutor(max_parallel_tool_calls) as pool:
for round_index in round_counter:
self._logger.debug(
"Starting .act() prediction round", round_index=round_index
Expand Down