MoonshotAI / MoonshotAI/kimi-cli

Model API error 400 Validation: Unsupported parameter(s): `prompt_cache_key`

Open
#2,534 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
11.4k
Forks
1.3k
Avg merge
9h 47m
Merged PRs (30d)
2

Description

What version of Kimi Code CLI is running?

0.29.0

Which open platform/subscription were you using?

3rd party API

Which model were you using?

Nvidia nim models

What platform is your computer?

windows

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 cli or web and connect to nvidia endpoints. Tried it with a few models and it is the same

What is the expected behavior?

No response

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

Start by tracing request construction for the CLI and web paths when connecting to Nvidia NIM endpoints, using the reported 0.29.0 behavior as the baseline. Check where prompt_cache_key was introduced and verify that Nvidia requests no longer receive the unsupported parameter while supported models retain their existing behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, 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.