Conversation
6b7250f to
9975689
Compare
db30ec1 to
70aee1c
Compare
|
Can you please just have the Copilot commit in here for easier review? |
|
From talking with one of my colleagues, it sounds like we might want to not get into ownership of all sorts of runners; so maybe it would be better to discuss options in #254? It should be possible to wire this up with the custom executor API for Web Codegen Scorer (WCS). I think we maybe want to have some good docs / examples on this. Feel free to help/play with this |
|
Thanks for the feedback! I'd like to highlight a real-world scenario that I think is quite common: in many enterprises — including the one I work for — developers only have access to GitHub Copilot and do not hold personal API keys. Authentication and license assignment are handled via Microsoft login (Entra ID / Azure AD), and access to the underlying model goes entirely through the Copilot interface. This isn't an edge case — it applies to any company using Microsoft Entra ID with a Copilot license. In that setup, there is no way for a developer to provide an API key, yet they do have full access to a capable model through Copilot. Would it be possible to consider this as a supported configuration? |
f859747 to
15fa7bd
Compare
|
@devversion Any news here? |
Integrate @github/copilot as a new code generation runner. The runner supports multiple models (Claude, Gemini, GPT), configures permissions via .copilot/settings.json, and uses COPILOT.md for instructions. Also add debug logging to BaseCliAgentRunner, controllable via the CLI_RUNNER_DEBUG environment variable, to aid in troubleshooting agent process execution.
e2ff23c to
d14b821
Compare
|
Hello,
@devversion |
|
Thanks for proposing this change and creating this PR. We've discussed this topic with the team internally once again and there are no active plans to support more runners at this point. The WebCodegenScorer provides an ability to create your own "executor" (as mentioned in #253 (comment)), which might be an alternative way of integrating this change for your use-cases. |
Integrate @github/copilot as a new code generation runner. The runner
supports multiple models (Claude, Gemini, GPT), configures permissions
via .copilot/settings.json, and uses COPILOT.md for instructions.
Also, add debug logging to BaseCliAgentRunner, controllable via the
CLI_RUNNER_DEBUG environment variable, to aid in troubleshooting
agent process execution.