Upgrade MiniMax default model to M3#570
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Promote `MiniMax-M3` as the recommended default while keeping `MiniMax-M2.7` and `MiniMax-M2.7-highspeed` available for users who need the previous generation. Changes: - `.env.example`: default `MINIMAX_MODEL_ID` now `MiniMax-M3` - `00-course-setup/README.md`: M3 listed first as recommended; M2.7 / M2.7-highspeed retained - `14-microsoft-agent-framework/README.md`: sample snippet uses M3 - `14-microsoft-agent-framework/code-samples/hotel_booking_workflow_sample.py`: fallback `model_id` updated to M3 No API URL or non-MiniMax provider configuration is touched. The translated mirrors under `translations/` are regenerated automatically by the existing translation workflow, so they are left alone here. Co-Authored-By: Octopus <liyuan851277048@icloud.com>
Contributor
|
👋 Thanks for contributing @octo-patch! We will review the pull request and get back to you soon. |
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Updates the MiniMax default/model examples across the course to use MiniMax-M3 instead of MiniMax-M2.7.
Changes:
- Changed the MiniMax default
model_idused by the Lesson 14 hotel booking workflow sample. - Updated documentation examples to reference
MiniMax-M3. - Updated
.env.exampleand setup docs to recommendMiniMax-M3and list available MiniMax models.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| 14-microsoft-agent-framework/code-samples/hotel_booking_workflow_sample.py | Switches the MiniMax default model_id to MiniMax-M3 in the runtime sample. |
| 14-microsoft-agent-framework/README.md | Updates the MiniMax usage snippet to use MiniMax-M3. |
| 00-course-setup/README.md | Updates the suggested MINIMAX_MODEL_ID and the “Available models” list to include/recommend MiniMax-M3. |
| .env.example | Updates the example MiniMax model id to MiniMax-M3. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
192
to
196
| chat_client = OpenAIChatClient( | ||
| base_url=os.environ.get("MINIMAX_BASE_URL", "https://api.minimax.io/v1"), | ||
| api_key=minimax_api_key, | ||
| model_id=os.environ.get("MINIMAX_MODEL_ID", "MiniMax-M2.7"), | ||
| model_id=os.environ.get("MINIMAX_MODEL_ID", "MiniMax-M3"), | ||
| ) |
| | `MINIMAX_MODEL_ID` | Model name to use (e.g., `MiniMax-M3`) | | ||
|
|
||
| **Available models**: `MiniMax-M2.7` (recommended), `MiniMax-M2.7-highspeed` (faster responses) | ||
| **Available models**: `MiniMax-M3` (recommended), `MiniMax-M2.7`, `MiniMax-M2.7-highspeed` (faster responses) |
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
Promote
MiniMax-M3as the recommended default for the optionalMiniMaxprovider added in #474, while keepingMiniMax-M2.7andMiniMax-M2.7-highspeedavailable for users who still want the previous generation.Changes
.env.example— defaultMINIMAX_MODEL_IDis nowMiniMax-M3.00-course-setup/README.md— "Available models" listsMiniMax-M3(recommended) first, withMiniMax-M2.7andMiniMax-M2.7-highspeedkept as options; the exampleMINIMAX_MODEL_IDvalue is updated to match.14-microsoft-agent-framework/README.md— the inlineOpenAIChatClient(...)snippet usesmodel_id="MiniMax-M3".14-microsoft-agent-framework/code-samples/hotel_booking_workflow_sample.py— fallbackmodel_idin the MiniMax branch is now"MiniMax-M3".Nothing else is touched:
MINIMAX_BASE_URL(https://api.minimax.io/v1), the Azure / GitHub Models / OpenAI provider blocks, and unrelated lessons are all left as-is. The localized mirrors undertranslations/are regenerated by the existing translation workflow, so they are intentionally not edited by hand here.Test plan
python -c "import ast; ast.parse(open('14-microsoft-agent-framework/code-samples/hotel_booking_workflow_sample.py').read())"— the modified sample still parses.git grep "MINIMAX_MODEL_ID" -- ':!translations'— every non-translated reference now points atMiniMax-M3.MiniMax-M2.7andMiniMax-M2.7-highspeedare still listed for users who want to pin the older generation.