MoonshotAI / MoonshotAI/kimi-code

Architect/developer and llm quorum strategy

Open
#2,078 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
TypeScript
Stars
7.5k
Forks
1.2k
Avg merge
11h 53m
Merged PRs (30d)
350

Description

What feature would you like to see?

Now we have ability to choose model. It is nice to have to have possibility to choose what model is used for what. For example I speak in main thread with architect model and developer models are used for agent tasks.
More over it is good to have possibility to mix providers.
Also may be it is nice to have some LLM quorum on architect questions: 2 or more different model propose some and final boss (llm model) decide what to do.

Additional information

No response

Contributor guide

Open the contributing guide

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.

Research direction

The issue does not name files, tests, or entry points. Start by locating the existing model-selection configuration and agent-task orchestration, then define whether per-role providers and quorum decisions are both in scope; done should include agreed behavior and acceptance criteria for architect, developer, and final-decision models.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai, cli
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.