feat(minimax): add MiniMax provider with tier-aware rate limiting

Add MiniMax as a built-in provider using the generic tier framework (#82).

MiniMax is an OpenAI-compatible API provider with the M2.x model family
(M2.7, M2.5, M2.1, M2) and published token plan rate tiers.

Changes:
- New MiniMaxProvider with RATE_LIMIT_TIERS (starter/plus/max/ultra)
  derived from published 5-hour rolling window limits
- Uses resolve_rate_limiter() from BaseProvider for tier resolution
- reasoning_split=True by default to separate thinking from content
- Bumped retry budget: 5 retries / 30s max for load-shedding tolerance
- Registered in provider registry with openai package dependency hint
- Conservative PROVIDER_DEFAULTS (Starter-tier: 5 RPM / 25K TPM)
- CLI env vars: MINIMAX_API_KEY, MINIMAX_BASE_URL,
  MINIMAX_REASONING_SPLIT, MINIMAX_TIER
- 30 unit tests (constructor, tiers, generate, stream_chat, registry)

Rate limit tiers (from https://platform.minimax.io/docs/token-plan/intro):
  Starter:  1,500 req/5hrs  ->  5 RPM /  25K TPM
  Plus:     4,500 req/5hrs  -> 15 RPM /  75K TPM
  Max:     15,000 req/5hrs  -> 50 RPM / 250K TPM
  Ultra:   30,000 req/5hrs  -> 100 RPM / 500K TPM

Highspeed variants (e.g., MiniMax-M2.7-highspeed) share the same rate
limits as their base plan -- the difference is faster inference, not quota.

This provider is structurally identical to Z.AI (#83) and was trivial
to implement because both use the generic tier framework. The framework
eliminated all per-provider boilerplate for tier resolution.

Depends on: #82 (generic tier framework)
Ref: #68

Author: Societus

packages/cli/src/repowise/cli/helpers.py

@@ -278,6 +278,16 @@ def resolve_provider(
                 kwargs["base_url"] = os.environ["ZAI_BASE_URL"]
             if os.environ.get("ZAI_THINKING"):
                 kwargs["thinking"] = os.environ["ZAI_THINKING"]
+        elif provider_name == "minimax":
+            # MiniMax: API key, base URL, reasoning_split, and tier
+            if os.environ.get("MINIMAX_API_KEY"):
+                kwargs["api_key"] = os.environ["MINIMAX_API_KEY"]
+            if os.environ.get("MINIMAX_BASE_URL"):
+                kwargs["base_url"] = os.environ["MINIMAX_BASE_URL"]
+            if os.environ.get("MINIMAX_REASONING_SPLIT"):
+                kwargs["reasoning_split"] = os.environ["MINIMAX_REASONING_SPLIT"].lower() == "true"
+            if os.environ.get("MINIMAX_TIER"):
+                kwargs["tier"] = os.environ["MINIMAX_TIER"]
 
         return get_provider(provider_name, **kwargs)
 
@@ -336,11 +346,23 @@ def resolve_provider(
         if os.environ.get("ZAI_THINKING"):
             kwargs["thinking"] = os.environ["ZAI_THINKING"]
         return get_provider("zai", **kwargs)
+    # MiniMax: check for API key
+    if os.environ.get("MINIMAX_API_KEY") and os.environ["MINIMAX_API_KEY"].strip():
+        kwargs = {"api_key": os.environ["MINIMAX_API_KEY"]}
+        if model:
+            kwargs["model"] = model
+        if os.environ.get("MINIMAX_BASE_URL"):
+            kwargs["base_url"] = os.environ["MINIMAX_BASE_URL"]
+        if os.environ.get("MINIMAX_REASONING_SPLIT"):
+            kwargs["reasoning_split"] = os.environ["MINIMAX_REASONING_SPLIT"].lower() == "true"
+        if os.environ.get("MINIMAX_TIER"):
+            kwargs["tier"] = os.environ["MINIMAX_TIER"]
+        return get_provider("minimax", **kwargs)
 
     raise click.ClickException(
         "No provider configured. Use --provider, set REPOWISE_PROVIDER, "
         "or set ANTHROPIC_API_KEY / OPENAI_API_KEY / OLLAMA_BASE_URL / GEMINI_API_KEY / "
-        "LITELLM_API_KEY / LITELLM_BASE_URL / ZAI_API_KEY."
+        "LITELLM_API_KEY / LITELLM_BASE_URL / ZAI_API_KEY / MINIMAX_API_KEY."
     )
 
 
@@ -381,6 +403,7 @@ def _is_env_var_exists(var_name: str) -> bool:
             "LITELLM_BASE_URL",
         ],  # Either one (API key for cloud, base URL for local)
         "zai": ["ZAI_API_KEY"],
+        "minimax": ["MINIMAX_API_KEY"],
     }
 
     if provider_name: