MoonshotAI / MoonshotAI/kimi-code

OpenCodeGo DeepSeek Pro model reports "Invalid max_tokens value"

Open
#509 0 comments 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?

v0.11.0

Which open platform/subscription were you using?

OpenCode Go

Which model were you using?

Deepseek-v4-pro

What platform is your computer?

Linux WSL2

What issue are you seeing?

Error: [provider.api_error] 400 Error from provider (DeepSeek): Invalid max_tokens value, the valid range of max_tokens is [1, 393216]

What steps can reproduce the bug?

Just switch the model and this issue would happen for sure.

What is the expected behavior?

DeepSeek-v4-Pro shall work with OpenCode go plan like it works with official DeepSeek subscription

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 reproducing the failure after switching to the Deepseek-v4-pro model through OpenCode Go, then trace where the request's max_tokens value is assembled. Compare that request with the behavior expected from the official DeepSeek subscription. Done means the model works with OpenCode Go without the provider rejecting max_tokens; no file or test is named in the issue.

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
Quiet
Clarity
Needs clarification
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.