MoonshotAI / MoonshotAI/kimi-code

When use with deepseek-v4-pro and deepseek-v4-flash, its context is still 256K

Open
#1,986 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

What version of Kimi Code is running?

0.28.1

Which open platform/subscription were you using?

3rd party deepseek

Which model were you using?

deepseek-v4 pro and deepseek-v4-flash

What platform is your computer?

No response

What issue are you seeing?

For Deepseek V4 models, their context size is 1M, but in kimi code TUI, it show that those model still total 256K context size.

What steps can reproduce the bug?

Open Kimi with Deepseek V4 model configured.

What is the expected behavior?

Automatically fit the actual context size of selected model, no matter it is provided by Kimi official or from 3rd party.

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

Reproduce the issue by opening Kimi Code TUI with the configured DeepSeek V4 Pro or V4 Flash model, then trace how the selected model's context size is obtained and displayed. Done means the TUI reflects the model's actual 1M context size for both official and third-party configurations.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
cli
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.