Provider API: deepseek-v4.1-flash is missing reasoning effort metadata

[leike0813]

Summary

The deepseek-v4.1-flash model exposed by Command Code currently does not provide configurable reasoning effort levels.

The official DeepSeek V4.1 Flash model supports three reasoning effort levels:

• low
• high
• max

So this appears to be an issue with the model metadata in Command Code rather than a limitation of the model itself.

Expected Behavior

deepseek-v4.1-flash should advertise and expose the following reasoning effort options:

• low
• high
• max

Compatible clients/harnesses should then be able to select the desired reasoning effort level.

Actual Behavior

deepseek-v4.1-flash is currently exposed without reasoning effort configuration, so clients treat it as a model that does not support configurable reasoning effort.

Steps to reproduce the issue

None

Command Code Version

1.53.0

Operating System

Linux

Terminal/IDE

No response

Shell

No response

Session file (optional)

No response

Fix prompt (optional)

No response

Additional context

No response

[ahmadawais]

@ahmadbilaldev check. i think it was fixed.