MoonshotAI / MoonshotAI/kimi-code
Architect/developer and llm quorum strategy
Nobody has claimed this yet.
- 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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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