[Bug]: per_user_oauth Copilot models in responses mode fail with "requires litellm_credential_name"

Finding: In a LiteLLM proxy reported as v1.106.0 (built from main at 7ff5010674, Docker, models stored in DB), a GitHub Copilot model whose cost-map mode is `responses` (example `github_copilot/gpt-6.1-sol`) reportedly fails on /v1/messages and chat-completion requests when its deployment uses a `per_user_oauth` credential. The proxy returns 400 with the message that per_user_oauth requires litellm_credential_name, even though the deployment sets that field (source: https://github.com/BerriAI/litellm/issues/45883). Reported conditions: the credential `github-copilot` has github_copilot_auth_type set to per_user_oauth, the user connected Copilot through the Admin UI, and a virtual key owned by that user calls the model. The reporter says the same credential works for chat-mode Copilot models and for direct /v1/responses calls, so only the chat-to-Responses bridge path is affected. The reporter also says the error is followed by a model-group failure with no fallback attempted. The reported traceback runs through the Anthropic endpoints, the router's Anthropic messages fallback wrapper, the litellm_responses_transformation handler's acompletion, responses/dispatch aresponses, the Copilot per_user_auth session attach function, and github_copilot_auth_mode. Reporter hypothesis (not maintainer-confirmed): completion() passes github_copilot_auth_type to get_litellm_params but not litellm_credential_name, and get_litellm_params does not keep it either. The bridge would then call aresponses with per_user_oauth and no credential name, which the per-user check rejects. The reporter says the same code is still on main at 906f927b23. Status: no maintainer response, comments, linked fix or release appear in the supplied context, and no workaround is documented. Fix status is unknown. Limitations: this is a single external report; KFA did not reproduce it. The cause is a reporter code-path analysis, not verified. Practical diagnostic hint, only as a match check: if you see this exact error on a responses-mode Copilot model with per_user_oauth while chat-mode models work, you may be hitting the same issue; track the upstream issue for a fix.