feat: add MiniMax as LLM provider

[octo-patch]

Summary

Add MiniMax AI as a first-class LLM provider for Enterprise Deep Research, alongside existing OpenAI, Anthropic, Groq, Google Vertex AI, and SambaNova backends.

Changes

Backend (llm_clients.py)

• New MiniMaxClient class with OpenAI-compatible streaming via https://api.minimax.io/v1
• Temperature clamping to (0.0, 1.0] as required by MiniMax API
• <think>...</think> tag stripping for reasoning model responses
• MODEL_CONFIGS entry with MiniMax-M2.7 (1M context) and MiniMax-M2.7-highspeed models
• get_llm_client() and get_async_llm_client() factory support

Configuration (src/configuration.py)

• MINIMAX added to LLMProvider enum
• Default model mapping (MiniMax-M2.7) in llm_model property

Frontend (InitialScreen.js)

• MiniMax-M2.7 option in model selection dropdown

Docs & Config

• .env.sample: MINIMAX_API_KEY variable and provider config
• README.md: MiniMax in supported models table and API key docs

Tests (tests/test_minimax_provider.py)

• 25 unit tests covering MODEL_CONFIGS, MiniMaxClient, temperature clamping, think-tag stripping, LLMProvider enum, factory functions, Configuration class
• 3 integration tests (skipped without API key)

Test Plan

• All 25 unit tests pass
• All 3 integration tests pass with live MiniMax API
• Verify frontend model dropdown shows MiniMax-M2.7 option
• Run existing test suite to confirm no regressions

[salesforce-cla]

Thanks for the contribution! Unfortunately we can't verify the commit author(s): PR Bot <p***@m***.com>. One possible solution is to add that email to your GitHub account. Alternatively you can change your commits to another email and force push the change. After getting your commits associated with your GitHub account, sign the Salesforce Inc. Contributor License Agreement and this Pull Request will be revalidated.