Allow to choose which models falls into the Efficiency/Balance/Intelligence selectors
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 35/100
Research direction
No files, tests, or entry points are identified in the issue. Start by locating the Efficiency, Balance, and Intelligence Auto-mode configuration in the GitHub Copilot app, then determine how enterprise policy and app settings handle model pools. Done means users can choose models for each pool without losing the ability to select those models individually.
Written by the indexing model from the issue text.
Description
Feature summary
No response
What problem are you trying to solve?
It would be nice to have the possibility to choose which models are in the pools of the new Efficiency / Balance / Intelligence "Auto" mode.
Sometimes the model picks aren't completly good for the tasks and you then spend AI tokens on something that would run for a while or that is, in the end, not usable at all.
Proposed solution
Having a specific configuration, either with Enterprise policy or in the github copilot app, to choose the models that are in each pools.
Workflow impact
It would allow to define which models you want to work with on each level of complexity.
This way you're not disapointed with the outputs because the model choose by default isn't the one that you would've choosed (you could disable the model on the enterprise but then you lose the capacity to still use it if you need as a single model pick).
Installation context
No response
Additional context
No response
- Dominant language
- No language data
- Stars
- 2.1k
- Forks
- 157
- PR merge metrics
- No merged PRs in 30d
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.
More from github/app
-
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 64/100
Similar issues
-
ai-observability bug team/ai-observability
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
dair-ai/Prompt-Engineering-Guide#810 · 1 comment ·
-
[addtool] DeepZero Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
gwen001/offsectools_www#2055 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
UKGovernmentBEIS/inspect_evals#2503 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
google-gemma/gemma-skills#13 ·