feat(minimax): add MiniMax provider with tier-aware rate limiting by Societus · Pull Request #84 · repowise-dev/repowise

Societus · 2026-04-14T02:52:04Z

Summary

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

This PR is a straightforward application of the same pattern as #83. Both MiniMax and Z.AI are OpenAI-compatible APIs with subscription tiers and built-in reasoning models. The generic tier framework made this provider almost mechanical to implement -- the only provider-specific code is the model names, the reasoning_split parameter vs Z.AI's thinking toggle, and the tier definitions.

Depends on: #82 (generic tier framework -- merge that first)

Why This Was Inconsequential

MiniMax shares the same architectural profile as Z.AI:

OpenAI-compatible API at https://api.minimax.io/v1
Bearer token auth using the same openai SDK
Reasoning models with a thinking separator parameter
Published subscription tiers with conservative rate limits

The generic framework from #82 eliminated all boilerplate for tier resolution. Adding MiniMax was just: define RATE_LIMIT_TIERS, set the base URL, and pick the reasoning parameter name. Everything else is inherited.

Changes

New: MiniMax Provider (`minimax.py`)

RATE_LIMIT_TIERS with Starter/Plus/Max/Ultra configs from published limits
resolve_rate_limiter() from BaseProvider (zero custom tier code)
reasoning_split=True by default (separates thinking from content)
Retry budget: 5 retries / 30s max wait
Models: MiniMax-M2.7 (default), M2.7-highspeed, M2.5, M2.5-highspeed, M2.1, M2.1-highspeed, M2

Registry (`registry.py`)

Register minimax -> MiniMaxProvider with openai package hint

Rate Limiter (`rate_limiter.py`)

PROVIDER_DEFAULTS["minimax"] = Starter-tier conservative (5 RPM / 25K TPM)

CLI Helpers (`helpers.py`)

MINIMAX_API_KEY, MINIMAX_BASE_URL, MINIMAX_REASONING_SPLIT, MINIMAX_TIER env vars
Auto-detect from MINIMAX_API_KEY
Added to provider validation list

Tests (`test_minimax_provider.py`)

30 tests: constructor, tier resolution (4 tiers + edge cases), generate with mock, stream_chat, reasoning_split, registry integration

Rate Limit Tiers

From published MiniMax docs (5-hour rolling window):

Tier	Requests/5hrs	RPM	TPM
Starter	1,500	5	25,000
Plus	4,500	15	75,000
Max	15,000	50	250,000
Ultra	30,000	100	500,000

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

Ref: https://platform.minimax.io/docs/token-plan/intro

Configuration

export MINIMAX_API_KEY="***"
export MINIMAX_TIER="plus"              # starter | plus | max | ultra
export MINIMAX_BASE_URL="..."           # override default
export MINIMAX_REASONING_SPLIT="true"   # default true

Test Plan

uv run pytest tests/unit/test_providers/test_minimax_provider.py -v
# 30 passed

All 121 provider tests pass with zero regressions.

PR Stack

#	PR	Status
1	#82 -- Generic tier framework	Ready for review
2	#83 -- Z.AI adopts the framework	Depends on #82
3	This PR -- MiniMax provider	Depends on #82

- Add litellm to interactive provider selection menu - Support LITELLM_BASE_URL for local proxy deployments (no API key required) - Auto-add openai/ prefix when using api_base for proper LiteLLM routing - Add dummy API key for local proxies (OpenAI SDK requirement) - Add validation and tests for litellm provider configuration Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

… false positives Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Add first-class support for Z.AI with OpenAI-compatible API. - New ZAIProvider with thinking disabled by default for GLM-5 family - Plan selection: 'coding' (subscription) or 'general' (pay-as-you-go) - Environment variables: ZAI_API_KEY, ZAI_PLAN, ZAI_BASE_URL, ZAI_THINKING - Rate limit defaults and auto-detection in CLI helpers Closes repowise-dev#68

Add RATE_LIMIT_TIERS class attribute and resolve_rate_limiter() static method to BaseProvider. Any provider with subscription tiers can define RATE_LIMIT_TIERS and pass tier + tiers to resolve_rate_limiter() to get automatic tier-aware rate limiter creation. Precedence: tier > explicit rate_limiter > None. Tier matching is case-insensitive. Invalid tiers raise ValueError. This is a provider-agnostic foundation -- no provider-specific code. Providers adopt it by defining RATE_LIMIT_TIERS and calling resolve_rate_limiter() in their constructor. Ref: repowise-dev#68

Add MiniMax as a built-in provider using the generic tier framework (repowise-dev#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 (repowise-dev#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: repowise-dev#82 (generic tier framework) Ref: repowise-dev#68

swati510

missing zai and minimax in providers/llm/init.py, registry.py docstring got updated, it didnt

swati510 · 2026-04-18T15:29:45Z

-            console.print(f"  [{WARN}]Skipped. Please select another provider.[/]")
-            return interactive_provider_select(console, model_flag, repo_path=repo_path)
+        # Special case: litellm local proxy doesn't need an API key
+        if chosen == "litellm" and os.environ.get("LITELLM_BASE_URL"):


this branch is unreachable — _detect_provider_status (L417-420) already marks litellm as detected when LITELLM_BASE_URL is set, so we never enter the outer if chosen not in detected with this combo.

swati510 · 2026-04-18T15:30:52Z

@@ -268,18 +268,22 @@ def print_phase_header(
    "litellm": "groq/llama-3.1-70b-versatile",
 }


zai and minimax are wired in helpers.py, validate_provider_config, and the registry but not here , they won't show up in the interactive init menu. please add them to _PROVIDER_DEFAULTS, _PROVIDER_ENV, and _PROVIDER_SIGNUP

swati510 · 2026-04-18T15:31:25Z

+    """
+
+    def __init__(
+        self,


since this PR introduces the tier framework on BaseProvider, should zai adopt it too? lite/pro/max have published limits. ok to defer but feels odd to land the framework and only wire minimax

swati510

Looks like this is stacked on #83, so the base.py/registry/zai changes are shared. Assuming #83 lands first this is fine, just calling it out.

Three things:

My earlier note about _PROVIDER_DEFAULTS / _PROVIDER_ENV / _PROVIDER_SIGNUP in cli/ui.py still stands, zai and minimax are invisible in the interactive init menu. Worth fixing here since this PR ships both.
MiniMax rate limits are published as 1500 requests / 5 hours. Our RateLimiter is a 60-second sliding window. Converting to ~5 RPM is a reasonable steady-state approximation but a user who bursts will see spurious 429s locally, and one who paces slowly can technically exceed quota without tripping our limiter. Fine to ship as-is, but leave a comment acknowledging the window mismatch so nobody chases a ghost bug later.
MINIMAX_REASONING_SPLIT is parsed as .lower() == "true" in two different branches of helpers.py. Extract a tiny _env_bool helper and accept the usual truthy values (1/yes/on) since that's what users reach for.

swati510 · 2026-04-18T15:55:54Z

+            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"


Same .lower() == "true" parsing is copy-pasted at line 357 in the auto-detect path. Extract into _env_bool(name, default=False) and reuse. Also accept 1/yes/on, that's what users will type.

@swati510

…ta warning, clean dead branch Apologies for the oversight -- these provider dict entries were mostly in place during development but got lost assembling the PR stack. - Add zai and minimax to _PROVIDER_DEFAULTS, _PROVIDER_ENV, and _PROVIDER_SIGNUP so they appear in interactive init - Extract _env_bool(name, default=False) helper accepting 1/yes/on/true and reuse for MINIMAX_REASONING_SPLIT parsing in both code paths - Add session_request_warn to RateLimitConfig: logs a warning when cumulative session requests exceed a threshold, giving users advance notice before hitting long-window provider quotas (e.g. MiniMax's 1500 req/5hr) - Remove unreachable litellm local-proxy branch (L488): _detect_provider_status already marks litellm as detected when LITELLM_BASE_URL is set, so the guard at L483 makes it unreachable - Add note about MiniMax 1500req/5hr vs our 60s window approximation Addresses review feedback from @swati510 on repowise-dev#84.

RaghavChamadiya · 2026-04-26T10:39:34Z

This is currently stacked on #83 and re-includes all of #83's framework code verbatim. Once #83 lands, please rebase so this PR shrinks to just the MiniMax-specific delta (provider, env vars, registry entry, tests). It will be much easier to review at that point.

While you're rebasing, please also pick up the four items below so we can close everything out in one shot:

Missing exports. zai and minimax aren't added to packages/core/src/repowise/core/providers/llm/__init__.py, so they're invisible to consumers importing from the package root.
Interactive init menu. _PROVIDER_DEFAULTS, _PROVIDER_ENV, and _PROVIDER_SIGNUP in packages/cli/src/repowise/cli/ui.py don't list either provider, so neither shows up in the interactive provider picker. Worth adding both here since this PR ships them.
Rate-limit window mismatch. MiniMax publishes 1500 req / 5 hr, but our RateLimiter is a 60-second sliding window. Converting to ~5 RPM is a reasonable steady-state approximation but a user who bursts will see spurious 429s locally and one who paces slowly can technically exceed quota without tripping the limiter. Fine to ship as-is, just leave a code comment in minimax.py acknowledging the window mismatch so nobody chases a ghost bug later.
MINIMAX_REASONING_SPLIT is parsed as .lower() == "true" in two different branches of helpers.py. Extract a tiny _env_bool helper and accept the usual truthy values (1, yes, on, true) since that's what users reach for.

Once #83 is merged and this is rebased + the four items above are addressed, this is ready to land.

vinit13792 and others added 5 commits April 13, 2026 12:29

fix(litellm): add inline comment for sk-dummy to avoid secret scanner…

27f6770

… false positives Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Societus requested review from RaghavChamadiya and swati510 as code owners April 14, 2026 02:52

This was referenced Apr 14, 2026

Feature: Add Z.AI (Zhipu AI) provider support #68

Open

feat: add generic tier-aware rate limiting framework #82

Closed

feat(zai): adopt tier framework for plan-aware rate limiting #83

Open

swati510 reviewed Apr 18, 2026

View reviewed changes

swati510 mentioned this pull request Apr 18, 2026

feat: add MiniMax provider support #58

Closed

2 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(minimax): add MiniMax provider with tier-aware rate limiting#84

feat(minimax): add MiniMax provider with tier-aware rate limiting#84
Societus wants to merge 6 commits intorepowise-dev:mainfrom
Societus:feat/minimax-provider

Societus commented Apr 14, 2026

Uh oh!

swati510 left a comment

Uh oh!

swati510 Apr 18, 2026

Uh oh!

swati510 Apr 18, 2026

Uh oh!

swati510 Apr 18, 2026

Uh oh!

swati510 left a comment

Uh oh!

swati510 Apr 18, 2026

Uh oh!

RaghavChamadiya commented Apr 26, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

		@@ -268,18 +268,22 @@ def print_phase_header(
		"litellm": "groq/llama-3.1-70b-versatile",
		}

Conversation

Societus commented Apr 14, 2026

Summary

Why This Was Inconsequential

Changes

New: MiniMax Provider (minimax.py)

Registry (registry.py)

Rate Limiter (rate_limiter.py)

CLI Helpers (helpers.py)

Tests (test_minimax_provider.py)

Rate Limit Tiers

Configuration

Test Plan

PR Stack

Related

Uh oh!

swati510 left a comment

Choose a reason for hiding this comment

Uh oh!

swati510 Apr 18, 2026

Choose a reason for hiding this comment

Uh oh!

swati510 Apr 18, 2026

Choose a reason for hiding this comment

Uh oh!

swati510 Apr 18, 2026

Choose a reason for hiding this comment

Uh oh!

swati510 left a comment

Choose a reason for hiding this comment

Uh oh!

swati510 Apr 18, 2026

Choose a reason for hiding this comment

Uh oh!

RaghavChamadiya commented Apr 26, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

New: MiniMax Provider (`minimax.py`)

Registry (`registry.py`)

Rate Limiter (`rate_limiter.py`)

CLI Helpers (`helpers.py`)

Tests (`test_minimax_provider.py`)