Option to disable questions from LLM #6940
Description
What specific problem does this solve?
I'm trying the new GPT OSS in roo and it seems to handle the tools correctly, but with one caveat - the only tool it ever wants to call is question asking. A session will go like this:
Should I implement the fix?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
Should I implement the fix now?
Yes, no more questions.
To me, having this feature at all, defeats the point of an agent. I'm happy to specify plenty of detail in the task description, but I never want it to stop what it's doing to ask for clarification. If I see it going off course I can always interject. OpenAI deep research does the same, it will always think for a minute and then stop to ask dumb clarification questions that are specified in the prompt.
Additional context (optional)
No response
Roo Code Task Links (Optional)
No response
Request checklist
- I've searched existing Issues and Discussions for duplicates
- This describes a specific problem with clear impact and context
Interested in implementing this?
- Yes, I'd like to help implement this feature
Implementation requirements
- I understand this needs approval before implementation begins
How should this be solved? (REQUIRED if contributing, optional otherwise)
No response
How will we know it works? (Acceptance Criteria - REQUIRED if contributing, optional otherwise)
No response
Technical considerations (REQUIRED if contributing, optional otherwise)
No response
Trade-offs and risks (REQUIRED if contributing, optional otherwise)
No response