fix: alibaba provider default endpoint and model list (#3484)

- Change default inference_base_url from dashscope-intl Anthropic-compat
  endpoint to coding-intl OpenAI-compat /v1 endpoint. The old Anthropic
  endpoint 404'd when used with the OpenAI SDK (which appends
  /chat/completions to a /apps/anthropic base URL).

- Update curated model list: remove models unavailable on coding-intl
  (qwen3-max, qwen-plus-latest, qwen3.5-flash, qwen-vl-max), add
  third-party models available on the platform (glm-5, glm-4.7,
  kimi-k2.5, MiniMax-M2.5).

- URL-based api_mode auto-detection still works: overriding
  DASHSCOPE_BASE_URL to an /apps/anthropic endpoint automatically
  switches to anthropic_messages mode.

- Update provider description and env var descriptions to reflect the
  coding-intl multi-provider platform.

- Update tests to match new default URL and test the anthropic override
  path instead.

hermes_cli/auth.py

@@ -160,7 +160,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         id="alibaba",
         name="Alibaba Cloud (DashScope)",
         auth_type="api_key",
-        inference_base_url="https://dashscope-intl.aliyuncs.com/apps/anthropic",
+        inference_base_url="https://coding-intl.dashscope.aliyuncs.com/v1",
         api_key_env_vars=("DASHSCOPE_API_KEY",),
         base_url_env_var="DASHSCOPE_BASE_URL",
     ),

hermes_cli/config.py

@@ -547,14 +547,14 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
     },
     "DASHSCOPE_API_KEY": {
-        "description": "Alibaba Cloud DashScope API key for Qwen models",
+        "description": "Alibaba Cloud DashScope API key (Qwen + multi-provider models)",
         "prompt": "DashScope API Key",
         "url": "https://modelstudio.console.alibabacloud.com/",
         "password": True,
         "category": "provider",
     },
     "DASHSCOPE_BASE_URL": {
-        "description": "Custom DashScope base URL (default: international endpoint)",
+        "description": "Custom DashScope base URL (default: coding-intl OpenAI-compat endpoint)",
         "prompt": "DashScope Base URL",
         "url": "",
         "password": False,

hermes_cli/main.py

@@ -821,7 +821,7 @@ def cmd_model(args):
         ("opencode-zen", "OpenCode Zen (35+ curated models, pay-as-you-go)"),
         ("opencode-go", "OpenCode Go (open models, $10/month subscription)"),
         ("ai-gateway", "AI Gateway (Vercel — 200+ models, pay-per-use)"),
-        ("alibaba", "Alibaba Cloud / DashScope (Qwen models, Anthropic-compatible)"),
+        ("alibaba", "Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
         ("huggingface", "Hugging Face Inference Providers (20+ open models)"),
     ]
 

hermes_cli/models.py

@@ -208,14 +208,20 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "google/gemini-3-pro-preview",
         "google/gemini-3-flash-preview",
     ],
+    # Alibaba DashScope Coding platform (coding-intl) — default endpoint.
+    # Supports Qwen models + third-party providers (GLM, Kimi, MiniMax).
+    # Users with classic DashScope keys should override DASHSCOPE_BASE_URL
+    # to https://dashscope-intl.aliyuncs.com/compatible-mode/v1 (OpenAI-compat)
+    # or https://dashscope-intl.aliyuncs.com/apps/anthropic (Anthropic-compat).
     "alibaba": [
         "qwen3.5-plus",
-        "qwen3-max",
         "qwen3-coder-plus",
         "qwen3-coder-next",
-        "qwen-plus-latest",
+        # Third-party models available on coding-intl
-        "qwen3.5-flash",
+        "glm-5",
-        "qwen-vl-max",
+        "glm-4.7",
+        "kimi-k2.5",
+        "MiniMax-M2.5",
     ],
     # Curated HF model list — only agentic models that map to OpenRouter defaults.
     "huggingface": [

tests/test_runtime_provider_resolution.py

@@ -534,8 +534,8 @@ def test_minimax_explicit_api_mode_respected(monkeypatch):
     assert resolved["api_mode"] == "chat_completions"
 
 
-def test_alibaba_default_anthropic_endpoint_uses_anthropic_messages(monkeypatch):
+def test_alibaba_default_coding_intl_endpoint_uses_chat_completions(monkeypatch):
-    """Alibaba with default /apps/anthropic URL should use anthropic_messages mode."""
+    """Alibaba default coding-intl /v1 URL should use chat_completions mode."""
     monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "alibaba")
     monkeypatch.setattr(rp, "_get_model_config", lambda: {})
     monkeypatch.setenv("DASHSCOPE_API_KEY", "test-dashscope-key")
@@ -544,22 +544,22 @@ def test_alibaba_default_anthropic_endpoint_uses_anthropic_messages(monkeypatch)
     resolved = rp.resolve_runtime_provider(requested="alibaba")
 
     assert resolved["provider"] == "alibaba"
-    assert resolved["api_mode"] == "anthropic_messages"
+    assert resolved["api_mode"] == "chat_completions"
-    assert resolved["base_url"] == "https://dashscope-intl.aliyuncs.com/apps/anthropic"
+    assert resolved["base_url"] == "https://coding-intl.dashscope.aliyuncs.com/v1"
 
 
-def test_alibaba_openai_compatible_v1_endpoint_stays_chat_completions(monkeypatch):
+def test_alibaba_anthropic_endpoint_override_uses_anthropic_messages(monkeypatch):
-    """Alibaba with /v1 coding endpoint should use chat_completions mode."""
+    """Alibaba with /apps/anthropic URL override should auto-detect anthropic_messages mode."""
     monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "alibaba")
     monkeypatch.setattr(rp, "_get_model_config", lambda: {})
     monkeypatch.setenv("DASHSCOPE_API_KEY", "test-dashscope-key")
-    monkeypatch.setenv("DASHSCOPE_BASE_URL", "https://coding-intl.dashscope.aliyuncs.com/v1")
+    monkeypatch.setenv("DASHSCOPE_BASE_URL", "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic")
 
     resolved = rp.resolve_runtime_provider(requested="alibaba")
 
     assert resolved["provider"] == "alibaba"
-    assert resolved["api_mode"] == "chat_completions"
+    assert resolved["api_mode"] == "anthropic_messages"
-    assert resolved["base_url"] == "https://coding-intl.dashscope.aliyuncs.com/v1"
+    assert resolved["base_url"] == "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic"
 
 
 def test_named_custom_provider_anthropic_api_mode(monkeypatch):