Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

mistralai: expose reasoning_effort on the LLM

Open Beginner friendly
  • Is something wrong?
#8,283 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

@muzman123 is already working on this.

Since Oct 30, 2026.

  • #8285 by @muzman123 — open

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
66/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Active
Tech stack
python
Domain
ai, backend

Research direction

Start by reading the Mistral plugin's mistralai.LLM implementation and the code that builds completion_args, then check the SDK's CompletionArgs type for supported values. Add a keyword argument with a default that preserves current behavior and pass it through to completion_args; done means callers can set the supported reasoning effort and existing calls retain their behavior. The issue offers to provide tests but does not name a test file.

Written by the indexing model from the issue text.

Description

enhancement
Feature Type

Would make my life easier

Feature Description

mistralai.LLM sends no reasoning_effort, and there is no way to set it. The plugin uses the Conversations API which accepts reasoning_effort inside completion_args, but the plugin only builds completion_args from max_tokens, temperature, top_p, presence_penalty, frequency_penalty, random_seed and tool_choice.

Two consequences:

  1. Reasoning can't be tuned for voice. Mistral's docs list mistral-small-2603, mistral-medium-3-5 and mistral-large-4-0 as supporting reasoning_effort (all three are in ChatModels), and describe reasoning as using "extra compute time to generate more tokens". The OpenAI plugin exposes reasoning_effort and defaults reasoning models to "none" or "minimal"; Mistral has no equivalent.
  2. The recommended replacement isn't reachable. Mistral deprecated magistral-small-latest and magistral-medium-latest and recommends reasoning_effort on mistral-small-latest or mistral-medium-3-5 instead.
Proposal

A single keyword argument on mistralai.LLM with a default that keeps today's behaviour

Workarounds / Alternatives
  • extra_kwargs on chat(): needs a custom llm_node and gets overwritten when temperature or other option is set
  • Magistral models: deprecated by Mistral.
  • Patching the plugin: has to be redone on every upgrade.
Additional Context
Dominant language
Python
Stars
14.6k
Forks
3.9k
Avg merge
2d 5h
Merged PRs (30d)
232

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from livekit/agents

All issues in livekit/agents

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.