litellm/cookbook/ai_coding_tool_guides
devin-ai-integration[bot] 2e27a02a9f
feat(chatgpt): forward client subscriptions through the gateway (#41522)
* feat(chatgpt): forward each Codex user's ChatGPT OAuth login through the proxy

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(router): cover _model_group_llm_provider metadata resolution

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(chatgpt): keep the gateway ChatGPT login bound to the authenticator api_base

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(chatgpt): move client credential header selection into the chatgpt provider

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(chatgpt): cover credential recognition and stored account id fallbacks

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat(chatgpt): support per-model chatgpt_auth_file for multiple ChatGPT accounts

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(chatgpt): resolve bare chatgpt_auth_file paths and drop redundant test docstring

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(chatgpt): pass per-model auth file to early provider detection

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(chatgpt): normalize chatgpt_auth_file before caching the authenticator

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(chatgpt): type account selection parameters

* fix(chatgpt): preserve account selection through saved prompts

* fix(chatgpt): allow administrator account configuration through the proxy

* test(chatgpt): construct immutable request parameters

* fix(router): preserve typed deployment credential resolution

* fix(chatgpt): allow admins to probe unsaved account configurations

* fix(chatgpt): retain SDK login headers during provider resolution

* fix(chatgpt): allow admins to probe unsaved account configurations

* fix(chatgpt): normalize subscription health probe input

* fix(chatgpt): normalize health probe input and cover credential destinations

* test(chatgpt): keep destination rejection assertions focused

* feat(proxy): forward client ChatGPT subscriptions on native Codex routes

* docs: lead ChatGPT forwarding with standard model setup

* fix(chatgpt): preserve selected credentials in health provider lookup

* fix(chatgpt): preserve gateway credentials and workspace selection

* refactor(chatgpt): avoid rebinding streaming metadata inputs

* fix(chatgpt): keep account lookup token argument immutable

* fix(chatgpt): scope forwarded credential routing to ChatGPT

* refactor: keep forwarded credential isolation opt-in by provider

---------

Co-authored-by: Moe Khalil <moe@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Urbanonymous <ugutitej@gmail.com>
Co-authored-by: mateo <mateo@berri.ai>
2026-10-26 15:44:05 -07:00
..
claude_code_quickstart fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
chatgpt_subscription_passthrough.md feat(chatgpt): forward client subscriptions through the gateway (#41522) 2026-10-26 15:44:05 -07:00
index.json docs: fix doc title 2026-01-19 14:18:59 -08:00