Skip to content

feat: plumb reasoning_effort through Open Interpreter → LiteLLM#1644

Open
M-J-W1 wants to merge 12 commits intoopeninterpreter:developmentfrom
M-J-W1:reasoning-effort
Open

feat: plumb reasoning_effort through Open Interpreter → LiteLLM#1644
M-J-W1 wants to merge 12 commits intoopeninterpreter:developmentfrom
M-J-W1:reasoning-effort

Conversation

@M-J-W1
Copy link

@M-J-W1 M-J-W1 commented Sep 3, 2025

Adds a reasoning_effort parameter ("minimal" | "low" | "medium" | "high") and passes it through to LiteLLM for reasoning-capable models.

Changed files:

  • interpreter/core/core.py
  • interpreter/core/llm/llm.py

Usage:
interpreter.llm.reasoning_effort = "minimal"

External example: https://github.com/uhsealevelcenter/IDEA/blob/main/app.py?target=https://github.com

Backwards compatibility: default behavior unchanged if not set.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants