MoonshotAI / MoonshotAI/kimi-code
Error with models not supporting prompt cache
Nobody has claimed this yet.
- 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?
0.29.1
Which open platform/subscription were you using?
nvidia nim
Which model were you using?
nemotron, minimax
What platform is your computer?
windows, wsl
What issue are you seeing?
This was working fine until the latest update today. I believe Nvidia NIM doesn't support this but I have been using their models for weeks with kimi code. This week's update broke it somehow. Is there a setting I can use to disable it? Thanks.
Model API error
400 Validation: Unsupported parameter(s): prompt_cache_key
What steps can reproduce the bug?
use 3rd party models without prompt_cache support will error
What is the expected behavior?
No response
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
Start by reproducing the 400 error with the listed NVIDIA NIM models and trace where the CLI adds prompt_cache_key to model API requests. The fix is done when models without prompt-cache support no longer receive the unsupported parameter while compatible models continue to work, with regression coverage for both cases.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- api, cli
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 66/100