From 22942a9d0c406b33c93d64ed50fc0b3f591ec87f Mon Sep 17 00:00:00 2001 From: Bas Alberts Date: Wed, 17 Jun 2026 09:37:25 -0400 Subject: [PATCH] docs: remove GitHub Models references from README GitHub Models is no longer available to new customers (see https://github.blog/changelog/2026-06-16-github-models-is-no-longer-available-to-new-customers). Update README to point at GitHub Copilot instead of GitHub Models for token entitlement, and change the example AI_API_ENDPOINT from models.github.ai/inference to api.githubcopilot.com. The github-models provider remains functional in capi.py for existing users; this only removes it from documentation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 7842f5b..82da316 100644 --- a/README.md +++ b/README.md @@ -205,7 +205,7 @@ Python >= 3.10 or Docker ## Configuration -Provide a GitHub token for an account that is entitled to use [GitHub Models](https://models.github.ai) via the `AI_API_TOKEN` environment variable. Further configuration is use case dependent, i.e. pending which MCP servers you'd like to use in your taskflows. In a terminal, you can add `AI_API_TOKEN` to the environment like this: +Provide a GitHub token for an account that is entitled to use [GitHub Copilot](https://github.com/features/copilot) via the `AI_API_TOKEN` environment variable. Further configuration is use case dependent, i.e. pending which MCP servers you'd like to use in your taskflows. In a terminal, you can add `AI_API_TOKEN` to the environment like this: ```sh export AI_API_TOKEN= @@ -226,7 +226,7 @@ Example: ```sh # MCP configs CODEQL_DBS_BASE_PATH="/app/my_data/codeql_databases" -AI_API_ENDPOINT="https://models.github.ai/inference" +AI_API_ENDPOINT="https://api.githubcopilot.com" ``` ## Deploying from Source