continuedev / continuedev/continue
continue seems to be ignoring my thinking type in the config
Open
Nobody has claimed this yet.
area:configuration
ide:vscode
kind:bug
os:linux
- Dominant language
- TypeScript
- Stars
- 36k
- Forks
- 5.4k
- PR merge metrics
- No merged PRs in 30d
Description
Before submitting your bug report
- I've tried finding an answer on the Continue docs site
- I'm not able to find an open issue that reports the same bug
- I've seen the troubleshooting guide on the Continue Docs
Relevant environment info
- OS: Linux
- Continue version: 2.0.0
- IDE version: vs code 1.126.0
- Model: Claude opus 4.8
- config:
name: Local Config
version: 1.0.0
schema: v1
models:
- name: Claude Opus 4.8
provider: anthropic
model: claude-opus-4-8
apiKey: # removed for obvious reason
roles:
- chat
- edit
- apply
defaultCompletionOptions:
promptCaching: true
thinking:
type: adaptive
output_config:
effort: high
- name: Remote Chat Code
provider: ollama
model: qwen3-coder-next:latest
apiBase: http://192.168.0.108:11434
roles:
- chat
- edit
- apply
# Global defaults
defaultModel: Claude Opus 4.8
defaultCompletionOptions:
thinking:
type: adaptive
Description
I get this error when trying a simple hello query
{"type":"invalid_request_error","message":"\"thinking.type.enabled\" is not supported for this model. Use \"thinking.type.adaptive\" and \"output_config.effort\" to control thinking behavior."}
To reproduce
No response
Log output
{"type":"invalid_request_error","message":"\"thinking.type.enabled\" is not supported for this model. Use \"thinking.type.adaptive\" and \"output_config.effort\" to control thinking behavior."}
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 error in VS Code 1.126.0 with Continue 2.0.0 and the supplied Claude configuration. Inspect how model-level and global defaultCompletionOptions are processed, especially thinking.type and output_config.effort; done means the request preserves adaptive thinking without sending thinking.type.enabled.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript, vscode
- Domain
- ai, devtools
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100