engine: handle LLM tool call responses #95

Closed
opened 2026-07-05 14:26:27 +00:00 by the.auditor · 0 comments
Owner

When the LLM responds with function/tool calls (tool_use), _extract_content in llm.py would return str(None)"None" string since content is null in tool_use responses.

The engine should handle tool call execution in a future iteration — execute the tool, send the result back to the LLM, and return the final text response.

From PR #93 review suggestion.

When the LLM responds with function/tool calls (tool_use), `_extract_content` in `llm.py` would return `str(None)` → `"None"` string since `content` is null in tool_use responses. The engine should handle tool call execution in a future iteration — execute the tool, send the result back to the LLM, and return the final text response. _From PR #93 review suggestion._
fuzzy closed this issue 2026-07-05 17:40:44 +00:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
thwap/kronai#95
No description provided.