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.
2026-04-08 01:39:28 -07:00
parent ab271ebe10
commit 22d1bda185
9 changed files with 203 additions and 20 deletions
--- a/tests/agent/test_minimax_provider.py
+++ b/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
--- a/tests/hermes_cli/test_runtime_provider_resolution.py
+++ b/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")
--- a/tests/hermes_cli/test_setup_model_selection.py
+++ b/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"]),
    ])