fix(minimax): correct context lengths, model catalog, thinking guard, aux model, and config base_url

Cherry-picked from PR #6046 by kshitijk4poor with dead code stripped.

- Context lengths: 204800 → 1M (M1) / 1048576 (M2.5/M2.7) per official docs
- Model catalog: add M1 family, remove deprecated M2.1 and highspeed variants
- Thinking guard: skip extended thinking for MiniMax (Anthropic-compat endpoint)
- Aux model: MiniMax-M2.7-highspeed → MiniMax-M2.7 (same model, half price)
- Config base_url: honour model.base_url for API-key providers (fixes China users)
- Stripped unused get_minimax_max_output() / _MINIMAX_MAX_OUTPUT (no consumer)

Fixes #5777, #4082, #6039. Closes #3895.

agent/anthropic_adapter.py

@@ -1224,9 +1224,9 @@ def build_anthropic_kwargs(
     # Map reasoning_config to Anthropic's thinking parameter.
     # Claude 4.6 models use adaptive thinking + output_config.effort.
     # Older models use manual thinking with budget_tokens.
-    # Haiku models do NOT support extended thinking at all — skip entirely.
+    # Haiku and MiniMax models do NOT support extended thinking — skip entirely.
     if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" not in model.lower():
             effort = str(reasoning_config.get("effort", "medium")).lower()
             budget = THINKING_BUDGET.get(effort, 8000)
             if _supports_adaptive_thinking(model):

agent/auxiliary_client.py

@@ -99,8 +99,8 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "gemini": "gemini-3-flash-preview",
     "zai": "glm-4.5-flash",
     "kimi-coding": "kimi-k2-turbo-preview",
-    "minimax": "MiniMax-M2.7-highspeed",
-    "minimax-cn": "MiniMax-M2.7-highspeed",
+    "minimax": "MiniMax-M2.7",
+    "minimax-cn": "MiniMax-M2.7",
     "anthropic": "claude-haiku-4-5-20251001",
     "ai-gateway": "google/gemini-3-flash",
     "opencode-zen": "gemini-3-flash",

agent/model_metadata.py

@@ -113,8 +113,15 @@ DEFAULT_CONTEXT_LENGTHS = {
     "llama": 131072,
     # Qwen
     "qwen": 131072,
-    # MiniMax
-    "minimax": 204800,
+    # MiniMax (lowercase — lookup lowercases model names at line 973)
+    "minimax-m1-256k": 1000000,
+    "minimax-m1-128k": 1000000,
+    "minimax-m1-80k": 1000000,
+    "minimax-m1-40k": 1000000,
+    "minimax-m1": 1000000,
+    "minimax-m2.5": 1048576,
+    "minimax-m2.7": 1048576,
+    "minimax": 1048576,
     # GLM
     "glm": 202752,
     # Kimi
@@ -127,7 +134,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek-ai/DeepSeek-V3.2": 65536,
     "moonshotai/Kimi-K2.5": 262144,
     "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 204800,
+    "minimaxai/minimax-m2.5": 1048576,
     "XiaomiMiMo/MiMo-V2-Flash": 32768,
     "mimo-v2-pro": 1048576,
     "mimo-v2-omni": 1048576,

hermes_cli/models.py

@@ -144,18 +144,22 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-0905-preview",
     ],
     "minimax": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
         "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
+        "MiniMax-M2.7",
     ],
     "minimax-cn": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
         "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
+        "MiniMax-M2.7",
     ],
     "anthropic": [
         "claude-opus-4-6",

hermes_cli/runtime_provider.py

@@ -163,6 +163,16 @@ def _resolve_runtime_from_pool_entry(
         api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
     else:
         configured_provider = str(model_cfg.get("provider") or "").strip().lower()
+        # Honour model.base_url from config.yaml when the configured provider
+        # matches this provider — same pattern as the Anthropic branch above.
+        # Only override when the pool entry has no explicit base_url (i.e. it
+        # fell back to the hardcoded default).  Env var overrides win (#6039).
+        pconfig = PROVIDER_REGISTRY.get(provider)
+        pool_url_is_default = pconfig and base_url.rstrip("/") == pconfig.inference_base_url.rstrip("/")
+        if configured_provider == provider and pool_url_is_default:
+            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
+            if cfg_base_url:
+                base_url = cfg_base_url
         configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
         if configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
             api_mode = configured_mode
@@ -724,7 +734,15 @@ def resolve_runtime_provider(
     pconfig = PROVIDER_REGISTRY.get(provider)
     if pconfig and pconfig.auth_type == "api_key":
         creds = resolve_api_key_provider_credentials(provider)
-        base_url = creds.get("base_url", "").rstrip("/")
+        # Honour model.base_url from config.yaml when the configured provider
+        # matches this provider — mirrors the Anthropic path above.  Without
+        # this, users who set model.base_url to e.g. api.minimaxi.com/anthropic
+        # (China endpoint) still get the hardcoded api.minimax.io default (#6039).
+        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
+        cfg_base_url = ""
+        if cfg_provider == provider:
+            cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
+        base_url = cfg_base_url or creds.get("base_url", "").rstrip("/")
         api_mode = "chat_completions"
         if provider == "copilot":
             api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))

hermes_cli/setup.py

@@ -105,8 +105,8 @@ _DEFAULT_PROVIDER_MODELS = {
     ],
     "zai": ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"],
     "kimi-coding": ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
-    "minimax": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
-    "minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
+    "minimax": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
+    "minimax-cn": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
     "ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
     "kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
     "opencode-zen": ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash", "glm-5", "kimi-k2.5", "minimax-m2.7"],

tests/agent/test_minimax_provider.py

@@ -0,0 +1,105 @@
+"""Tests for MiniMax provider hardening — context lengths, thinking guard, catalog."""
+
+
+class TestMinimaxContextLengths:
+    """Verify per-model context length entries for MiniMax models."""
+
+    def test_m1_variants_have_1m_context(self):
+        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
+        # Keys are lowercase because the lookup lowercases model names
+        for model in ("minimax-m1", "minimax-m1-40k", "minimax-m1-80k",
+                       "minimax-m1-128k", "minimax-m1-256k"):
+            assert model in DEFAULT_CONTEXT_LENGTHS, f"{model} missing from context lengths"
+            assert DEFAULT_CONTEXT_LENGTHS[model] == 1_000_000, f"{model} expected 1M"
+
+    def test_m2_variants_have_1m_context(self):
+        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
+        # Keys are lowercase because the lookup lowercases model names
+        for model in ("minimax-m2.5", "minimax-m2.7"):
+            assert model in DEFAULT_CONTEXT_LENGTHS, f"{model} missing from context lengths"
+            assert DEFAULT_CONTEXT_LENGTHS[model] == 1_048_576, f"{model} expected 1048576"
+
+    def test_minimax_prefix_fallback(self):
+        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
+        # The generic "minimax" prefix entry should be 1M for unknown models
+        assert DEFAULT_CONTEXT_LENGTHS["minimax"] == 1_048_576
+
+
+
+class TestMinimaxThinkingGuard:
+    """Verify that build_anthropic_kwargs does NOT add thinking params for MiniMax models."""
+
+    def test_no_thinking_for_minimax_m27(self):
+        from agent.anthropic_adapter import build_anthropic_kwargs
+        kwargs = build_anthropic_kwargs(
+            model="MiniMax-M2.7",
+            messages=[{"role": "user", "content": "hello"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "medium"},
+        )
+        assert "thinking" not in kwargs
+        assert "output_config" not in kwargs
+
+    def test_no_thinking_for_minimax_m1(self):
+        from agent.anthropic_adapter import build_anthropic_kwargs
+        kwargs = build_anthropic_kwargs(
+            model="MiniMax-M1-128k",
+            messages=[{"role": "user", "content": "hello"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "high"},
+        )
+        assert "thinking" not in kwargs
+
+    def test_thinking_still_works_for_claude(self):
+        from agent.anthropic_adapter import build_anthropic_kwargs
+        kwargs = build_anthropic_kwargs(
+            model="claude-sonnet-4-20250514",
+            messages=[{"role": "user", "content": "hello"}],
+            tools=None,
+            max_tokens=4096,
+            reasoning_config={"enabled": True, "effort": "medium"},
+        )
+        assert "thinking" in kwargs
+
+
+class TestMinimaxAuxModel:
+    """Verify auxiliary model is standard (not highspeed)."""
+
+    def test_minimax_aux_is_standard(self):
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+        assert _API_KEY_PROVIDER_AUX_MODELS["minimax"] == "MiniMax-M2.7"
+        assert _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"] == "MiniMax-M2.7"
+
+    def test_minimax_aux_not_highspeed(self):
+        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
+        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax"]
+        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"]
+
+
+class TestMinimaxModelCatalog:
+    """Verify the model catalog includes M1 family and excludes deprecated models."""
+
+    def test_catalog_includes_m1_family(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        for provider in ("minimax", "minimax-cn"):
+            models = _PROVIDER_MODELS[provider]
+            assert "MiniMax-M1" in models
+            assert "MiniMax-M1-40k" in models
+            assert "MiniMax-M1-80k" in models
+            assert "MiniMax-M1-128k" in models
+            assert "MiniMax-M1-256k" in models
+
+    def test_catalog_excludes_deprecated(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        for provider in ("minimax", "minimax-cn"):
+            models = _PROVIDER_MODELS[provider]
+            assert "MiniMax-M2.1" not in models
+
+    def test_catalog_excludes_highspeed(self):
+        from hermes_cli.models import _PROVIDER_MODELS
+        for provider in ("minimax", "minimax-cn"):
+            models = _PROVIDER_MODELS[provider]
+            assert "MiniMax-M2.7-highspeed" not in models
+            assert "MiniMax-M2.5-highspeed" not in models

tests/hermes_cli/test_runtime_provider_resolution.py

@@ -808,6 +808,55 @@ def test_minimax_explicit_api_mode_respected(monkeypatch):
     assert resolved["api_mode"] == "chat_completions"
 
 
+def test_minimax_config_base_url_overrides_hardcoded_default(monkeypatch):
+    """model.base_url in config.yaml should override the hardcoded default (#6039)."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "minimax")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {
+        "provider": "minimax",
+        "base_url": "https://api.minimaxi.com/anthropic",
+    })
+    monkeypatch.setenv("MINIMAX_API_KEY", "test-minimax-key")
+    monkeypatch.delenv("MINIMAX_BASE_URL", raising=False)
+
+    resolved = rp.resolve_runtime_provider(requested="minimax")
+
+    assert resolved["provider"] == "minimax"
+    assert resolved["base_url"] == "https://api.minimaxi.com/anthropic"
+    assert resolved["api_mode"] == "anthropic_messages"
+
+
+def test_minimax_env_base_url_still_wins_over_config(monkeypatch):
+    """MINIMAX_BASE_URL env var should take priority over config.yaml model.base_url."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "minimax")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {
+        "provider": "minimax",
+        "base_url": "https://api.minimaxi.com/anthropic",
+    })
+    monkeypatch.setenv("MINIMAX_API_KEY", "test-minimax-key")
+    monkeypatch.setenv("MINIMAX_BASE_URL", "https://custom.example.com/v1")
+
+    resolved = rp.resolve_runtime_provider(requested="minimax")
+
+    # Env var wins because resolve_api_key_provider_credentials prefers it
+    assert resolved["base_url"] == "https://custom.example.com/v1"
+
+
+def test_minimax_config_base_url_ignored_for_different_provider(monkeypatch):
+    """model.base_url should NOT be used when model.provider doesn't match."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "minimax")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {
+        "provider": "openrouter",
+        "base_url": "https://some-other-endpoint.com/v1",
+    })
+    monkeypatch.setenv("MINIMAX_API_KEY", "test-minimax-key")
+    monkeypatch.delenv("MINIMAX_BASE_URL", raising=False)
+
+    resolved = rp.resolve_runtime_provider(requested="minimax")
+
+    # Should use the default, NOT the config base_url from a different provider
+    assert resolved["base_url"] == "https://api.minimax.io/anthropic"
+
+
 def test_alibaba_default_coding_intl_endpoint_uses_chat_completions(monkeypatch):
     """Alibaba default coding-intl /v1 URL should use chat_completions mode."""
     monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "alibaba")

tests/hermes_cli/test_setup_model_selection.py

@@ -34,8 +34,8 @@ class TestSetupProviderModelSelection:
     @pytest.mark.parametrize("provider_id,expected_defaults", [
         ("zai", ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"]),
         ("kimi-coding", ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"]),
-        ("minimax", ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"]),
-        ("minimax-cn", ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"]),
+        ("minimax", ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"]),
+        ("minimax-cn", ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"]),
         ("opencode-zen", ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash"]),
         ("opencode-go", ["glm-5", "kimi-k2.5", "minimax-m2.5", "minimax-m2.7"]),
     ])