anomalyco / anomalyco/opencode
[Bug]: deepseek-v4-flash max_tokens too large (384000 > 131072)
Open
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 209k
- Forks
- 27.5k
- Avg merge
- 7h 2m
- Merged PRs (30d)
- 384
Description
Description
When using the deepseek-v4-flash model via OpenCode Go, all requests fail with the following error:400: max_tokens is too large: 384000. This model supports at most 131072 completion tokens.
Plugins
No response
OpenCode version
No response
Steps to reproduce
No response
Screenshot and/or share link
No response
Operating System
No response
Terminal
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
No file, test, or reproduction steps are named. Start by tracing the deepseek-v4-flash provider configuration and request construction, then reproduce the OpenCode Go request and verify that its max_tokens value is accepted by the model, up to 131072.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100