feature: add MiniMax provider and ChatGPT 5.4 xhigh support#2499
Closed
jaivial wants to merge 4 commits into
Closed
feature: add MiniMax provider and ChatGPT 5.4 xhigh support#2499jaivial wants to merge 4 commits into
jaivial wants to merge 4 commits into
Conversation
- Add MINIMAX provider ID constant - Add MiniMax provider config with Anthropic-compatible endpoint - Add minimax_preflight.sh for API testing - Support MiniMax-M2.5, M2.5-highspeed, M2.1, M2.1-highspeed models
ssddOnTop
reviewed
Mar 8, 2026
| @@ -0,0 +1,131 @@ | |||
| #!/usr/bin/env bash | |||
Contributor
There was a problem hiding this comment.
We don't need this file
Comment on lines
+27
to
+44
| "auth_methods": ["api_key"] | ||
| }, | ||
| { | ||
| "id": "minimax", | ||
| "api_key_vars": "MINIMAX_API_KEY", | ||
| "url_param_vars": [], | ||
| "response_type": "Anthropic", | ||
| "url": "https://api.minimax.io/anthropic/v1/messages", | ||
| "models": [ | ||
| { | ||
| "oauth_device": { | ||
| "auth_url": "https://github.com/login/device/code", | ||
| "token_url": "https://github.com/login/oauth/access_token", | ||
| "client_id": "Iv1.b507a08c87ecfe98", | ||
| "scopes": ["read:user"], | ||
| "use_pkce": false, | ||
| "token_refresh_url": "https://api.github.com/copilot_internal/v2/token", | ||
| "custom_headers": { | ||
| "User-Agent": "GitHubCopilotChat/0.26.7", | ||
| "Accept": "application/json", | ||
| "editor-version": "vscode/1.99.3", | ||
| "editor-plugin-version": "copilot-chat/0.26.7" | ||
| } | ||
| } | ||
| "id": "MiniMax-M2", | ||
| "name": "MiniMax M2", | ||
| "description": "MiniMax M2 agentic model with advanced reasoning", | ||
| "context_length": 204800, | ||
| "tools_supported": true, | ||
| "supports_parallel_tool_calls": true, | ||
| "supports_reasoning": true, | ||
| "input_modalities": ["text"] |
Contributor
There was a problem hiding this comment.
Critical: GitHub Copilot OAuth authentication removed
The GitHub Copilot provider's OAuth device flow configuration has been completely deleted and replaced with just ["api_key"]. This change:
- Removes the entire
oauth_deviceauthentication method including auth URLs, client ID, scopes, and custom headers - Was not mentioned in the PR description (which only discusses adding MiniMax support)
- Will break authentication for all users relying on GitHub Copilot's OAuth device flow
Fix: Restore the GitHub Copilot OAuth configuration. The intended change should only add the MiniMax provider block after the GitHub Copilot provider, not modify it:
"auth_methods": [
{
"oauth_device": {
"auth_url": "https://github.com/login/device/code",
"token_url": "https://github.com/login/oauth/access_token",
"client_id": "Iv1.b507a08c87ecfe98",
"scopes": ["read:user"],
"use_pkce": false,
"token_refresh_url": "https://api.github.com/copilot_internal/v2/token",
"custom_headers": {
"User-Agent": "GitHubCopilotChat/0.26.7",
"Accept": "application/json",
"editor-version": "vscode/1.99.3",
"editor-plugin-version": "copilot-chat/0.26.7"
}
}
}
]
Suggested change
| "auth_methods": ["api_key"] | |
| }, | |
| { | |
| "id": "minimax", | |
| "api_key_vars": "MINIMAX_API_KEY", | |
| "url_param_vars": [], | |
| "response_type": "Anthropic", | |
| "url": "https://api.minimax.io/anthropic/v1/messages", | |
| "models": [ | |
| { | |
| "oauth_device": { | |
| "auth_url": "https://github.com/login/device/code", | |
| "token_url": "https://github.com/login/oauth/access_token", | |
| "client_id": "Iv1.b507a08c87ecfe98", | |
| "scopes": ["read:user"], | |
| "use_pkce": false, | |
| "token_refresh_url": "https://api.github.com/copilot_internal/v2/token", | |
| "custom_headers": { | |
| "User-Agent": "GitHubCopilotChat/0.26.7", | |
| "Accept": "application/json", | |
| "editor-version": "vscode/1.99.3", | |
| "editor-plugin-version": "copilot-chat/0.26.7" | |
| } | |
| } | |
| "id": "MiniMax-M2", | |
| "name": "MiniMax M2", | |
| "description": "MiniMax M2 agentic model with advanced reasoning", | |
| "context_length": 204800, | |
| "tools_supported": true, | |
| "supports_parallel_tool_calls": true, | |
| "supports_reasoning": true, | |
| "input_modalities": ["text"] | |
| "auth_methods": [ | |
| { | |
| "oauth_device": { | |
| "auth_url": "https://github.com/login/device/code", | |
| "token_url": "https://github.com/login/oauth/access_token", | |
| "client_id": "Iv1.b507a08c87ecfe98", | |
| "scopes": ["read:user"], | |
| "use_pkce": false, | |
| "token_refresh_url": "https://api.github.com/copilot_internal/v2/token", | |
| "custom_headers": { | |
| "User-Agent": "GitHubCopilotChat/0.26.7", | |
| "Accept": "application/json", | |
| "editor-version": "vscode/1.99.3", | |
| "editor-plugin-version": "copilot-chat/0.26.7" | |
| } | |
| } | |
| } | |
| ] | |
| }, | |
| { | |
| "id": "minimax", | |
| "api_key_vars": "MINIMAX_API_KEY", | |
| "url_param_vars": [], | |
| "response_type": "Anthropic", | |
| "url": "https://api.minimax.io/anthropic/v1/messages", | |
| "models": [ | |
| { | |
| "id": "MiniMax-M2", | |
| "name": "MiniMax M2", | |
| "description": "MiniMax M2 agentic model with advanced reasoning", | |
| "context_length": 204800, | |
| "tools_supported": true, | |
| "supports_parallel_tool_calls": true, | |
| "supports_reasoning": true, | |
| "input_modalities": ["text"] |
Spotted by Graphite
Is this helpful? React 👍 or 👎 to let us know.
| "url": "https://api.githubcopilot.com/chat/completions", | ||
| "models": "https://api.githubcopilot.com/models", | ||
| "auth_methods": [ | ||
| "auth_methods": ["api_key"] |
Contributor
There was a problem hiding this comment.
this is wrong githubcopilot should not change in adding another provider
Contributor
|
Closing this in favor of #2557 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add MiniMax provider support and extend GPT-5.4 reasoning support with the new
chatgpt-5.4-xhighmodel andxhigheffort handling.Context
This branch already introduced MiniMax provider support, and this follow-up also adds compatibility for the new ChatGPT 5.4 highest-effort reasoning tier. Upstream meanwhile updated GPT-5.4 model metadata and Codex verbosity handling, so this branch now rebases cleanly on top of those changes and preserves the new
xhigheffort semantics.Changes
chatgpt-5.4-xhighto the OpenAI model catalogEffortenum and conversation persistence withxhighxhighthrough OpenAI-compatible request transformation and Responses API conversionxhighreasoning effort in the Codex transformer instead of downgrading itKey Implementation Details
MiniMax remains registered through the built-in provider list and provider catalog configuration. The new reasoning level is represented as
Effort::Xhigh, serialized as lowercasexhigh, persisted in conversation records, and translated toasync-openaiviaReasoningEffort::Xhigh. In the Codex request transformer, explicitxhighis preserved while other effort values still normalize toHighandsummarycontinues to normalize toAuto.Use Cases
chatgpt-5.4-xhighmodel idreasoning.effort: xhighfor maximum reasoning intensityTesting
Links