feat: add MiniMax provider support

[octo-patch]

Summary

This PR adds MiniMax as a predefined model provider in DataDesigner, allowing users to generate synthetic data using MiniMax's chat models via the OpenAI-compatible API.

Changes

• Add MiniMax as a predefined provider with endpoint https://api.minimax.io/v1
• Add MINIMAX_API_KEY environment variable support
• Register MiniMax-M2.7 as the default text model
• Register MiniMax-M2.7-highspeed as the reasoning model
• Add unit tests for the new provider and model configurations

Usage

After setting MINIMAX_API_KEY, users can generate datasets using MiniMax:

import data_designer as dd

config = dd.DataDesignerConfig(
    model_configs=[dd.ModelConfig(alias="text", model="MiniMax-M2.7", provider="minimax")],
)

Or using the built-in alias:

import data_designer as dd

dd.DataDesigner(provider="minimax")

API Reference

• Chat (OpenAI Compatible): https://platform.minimax.io/docs/api-reference/text-openai-api

[github-actions]

Thank you for your submission! We ask that you sign our Developer Certificate of Origin before we can accept your contribution. You can sign the DCO by adding a comment below using this text:

---

I have read the DCO document and I hereby sign the DCO.

---

octo-patch seems not to be a GitHub user. You need a GitHub account to be able to sign the DCO. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the DCO Assistant Lite bot.}

[greptile-apps]

Greptile Summary

This PR registers MiniMax as a fourth predefined model provider in DataDesigner, wiring in the endpoint (https://api.minimax.io/v1), MINIMAX_API_KEY env var, and model map entries for two roles (MiniMax-M2.7 as text and MiniMax-M2.7-highspeed as reasoning), all backed by tests.

Confidence Score: 5/5

Safe to merge; both findings are P2 tooling/style gaps with no runtime impact

The core provider registration path (constants, model map, provider list) is correct and tested. The two findings — health-check script omission and shared inference params — do not affect runtime behaviour of the provider, keeping confidence at 5.

scripts/health_checks.py (not in changeset) should be updated to include MINIMAX_PROVIDER_NAME in PROVIDER_API_KEY_ENV_VARS

Important Files Changed

Filename	Overview
packages/data-designer-config/src/data_designer/config/utils/constants.py	Adds MiniMax provider constants and model map entries; identical inference params shared across text and reasoning roles deviates from project pattern
packages/data-designer-config/tests/config/test_default_model_settings.py	Adds correct assertions for 2 new MiniMax model configs and the new MiniMax provider; count-based assertions updated to 14 and 4 respectively

Sequence Diagram

sequenceDiagram
    actor User
    participant DD as DataDesigner
    participant Config as data_designer.config
    participant Engine as data_designer.engine
    participant MiniMax as MiniMax API<br/>(api.minimax.io/v1)

    User->>DD: DataDesigner(provider="minimax")
    DD->>Config: resolve PREDEFINED_PROVIDERS
    Config-->>DD: ModelProvider(endpoint, api_key=MINIMAX_API_KEY)
    DD->>Engine: build column generation DAG
    Engine->>Config: lookup PREDEFINED_PROVIDERS_MODEL_MAP["minimax"][alias]
    Config-->>Engine: {model, inference_parameters}
    Engine->>MiniMax: POST /v1/chat/completions
    MiniMax-->>Engine: completion response
    Engine-->>DD: generated column values
    DD-->>User: DataDesignerResults

Loading

Prompt To Fix All With AI

This is a comment left during a code review.
Path: packages/data-designer-config/src/data_designer/config/utils/constants.py
Line: 372-381

Comment:
**Health-check script not updated for MiniMax**

`scripts/health_checks.py` maintains `PROVIDER_API_KEY_ENV_VARS`, which maps each predefined provider to its API key env var so the script knows which providers to exercise. MiniMax is absent from that dict, so the health-check script will silently skip MiniMax regardless of whether `MINIMAX_API_KEY` is set — meaning `MiniMax-M2.7` and `MiniMax-M2.7-highspeed` are never validated there. Every other provider added to `PREDEFINED_PROVIDERS_MODEL_MAP` has a corresponding entry in that dict.

How can I resolve this? If you propose a fix, please make it concise.

---

This is a comment left during a code review.
Path: packages/data-designer-config/src/data_designer/config/utils/constants.py
Line: 339

Comment:
**Same inference params used for both text and reasoning roles**

`MINIMAX_INFERENCE_PARAMS = {"temperature": 1.0}` is reused for both `MiniMax-M2.7` (text) and `MiniMax-M2.7-highspeed` (reasoning). Every other provider uses a lower temperature for the reasoning role (e.g., `0.35`) and a separate constant. Running a reasoning-aliased model at `temperature=1.0` with no `top_p` bound will produce higher output variance than the project default for structured-generation tasks. Consider splitting into `MINIMAX_TEXT_INFERENCE_PARAMS` and `MINIMAX_REASONING_INFERENCE_PARAMS` to follow the established pattern.

```suggestion
MINIMAX_TEXT_INFERENCE_PARAMS = {"temperature": 1.0}
MINIMAX_REASONING_INFERENCE_PARAMS = {"temperature": 0.35, "top_p": 0.95}
```

How can I resolve this? If you propose a fix, please make it concise.

_{Reviews (1): Last reviewed commit: "feat: add MiniMax provider support" | Re-trigger Greptile}

[greptile-apps]

Health-check script not updated for MiniMax

scripts/health_checks.py maintains PROVIDER_API_KEY_ENV_VARS, which maps each predefined provider to its API key env var so the script knows which providers to exercise. MiniMax is absent from that dict, so the health-check script will silently skip MiniMax regardless of whether MINIMAX_API_KEY is set — meaning MiniMax-M2.7 and MiniMax-M2.7-highspeed are never validated there. Every other provider added to PREDEFINED_PROVIDERS_MODEL_MAP has a corresponding entry in that dict.

Prompt To Fix With AI

This is a comment left during a code review.
Path: packages/data-designer-config/src/data_designer/config/utils/constants.py
Line: 372-381

Comment:
**Health-check script not updated for MiniMax**

`scripts/health_checks.py` maintains `PROVIDER_API_KEY_ENV_VARS`, which maps each predefined provider to its API key env var so the script knows which providers to exercise. MiniMax is absent from that dict, so the health-check script will silently skip MiniMax regardless of whether `MINIMAX_API_KEY` is set — meaning `MiniMax-M2.7` and `MiniMax-M2.7-highspeed` are never validated there. Every other provider added to `PREDEFINED_PROVIDERS_MODEL_MAP` has a corresponding entry in that dict.

How can I resolve this? If you propose a fix, please make it concise.

[github-actions]

Stale PR reminder

This PR has had failing checks for 7 days without activity.

Failing checks: DCOAssistant

Please push an update or leave a comment if you're still working on this.
Otherwise, this PR will be automatically closed in 7 days.

To prevent auto-close, add the keep-open label.