MoonshotAI / MoonshotAI/kimi-code
LSP support
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?
Support for LSPs (Language Server Protocol) to give the agent additional context when making decisions — e.g. go-to-definition, find references, diagnostics, and document symbols. This would let the agent navigate and reason about the codebase more precisely without having to read every file in full, reducing token usage and improving accuracy on large/typed codebases.
Example in a similar tool crush: https://github.com/charmbracelet/crush?tab=readme-ov-file#lsps
Additional information
Related request on the kimi-cli repo: https://github.com/MoonshotAI/kimi-cli/issues/36
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 names no repository files, tests, or entry points. Start by reviewing the agent context and code-navigation architecture, then compare the referenced Crush LSP example and define the supported LSP operations and integration boundary. Done means the agent can use the agreed LSP capabilities for more precise code navigation and diagnostics.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli, devtools
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100