Add Z.AI provider support for GLM-5 (#938)

FEATURE_PARITY.md

@@ -245,7 +245,7 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
 | Ollama (local) | ✅ | ✅ | - | via `rig::providers::ollama` (full support) |
 | Perplexity | ✅ | ❌ | P3 | Freshness parameter for web_search |
 | MiniMax | ✅ | ❌ | P3 | Regional endpoint selection |
-| GLM-5 | ✅ | ❌ | P3 | |
+| GLM-5 | ✅ | ✅ | P3 | Via Z.AI provider (`zai`) using OpenAI-compatible chat completions |
 | node-llama-cpp | ✅ | ➖ | - | N/A for Rust |
 | llama.cpp (native) | ❌ | 🔮 | P3 | Rust bindings |
 

providers.json

@@ -238,6 +238,26 @@
       "can_list_models": false
     }
   },
+  {
+    "id": "zai",
+    "aliases": [
+      "bigmodel"
+    ],
+    "protocol": "open_ai_completions",
+    "default_base_url": "https://api.z.ai/api/paas/v4",
+    "api_key_env": "ZAI_API_KEY",
+    "api_key_required": true,
+    "model_env": "ZAI_MODEL",
+    "default_model": "glm-5",
+    "description": "Z.AI GLM inference API",
+    "setup": {
+      "kind": "api_key",
+      "secret_name": "llm_zai_api_key",
+      "key_url": "https://z.ai/manage-apikey/apikey-list",
+      "display_name": "Z.AI",
+      "can_list_models": false
+    }
+  },
   {
     "id": "cerebras",
     "aliases": [],

src/config/llm.rs

@@ -637,6 +637,31 @@ mod tests {
         );
     }
 
+    #[test]
+    fn registry_provider_alias_resolves_zai() {
+        let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
+        // SAFETY: Under ENV_MUTEX.
+        unsafe {
+            std::env::remove_var("LLM_BACKEND");
+            std::env::remove_var("ZAI_API_KEY");
+            std::env::remove_var("ZAI_MODEL");
+        }
+
+        let settings = Settings {
+            llm_backend: Some("bigmodel".to_string()),
+            selected_model: Some("glm-5".to_string()),
+            ..Default::default()
+        };
+
+        let cfg = LlmConfig::resolve(&settings).expect("resolve should succeed");
+        assert_eq!(cfg.backend, "zai");
+        let provider = cfg.provider.expect("provider config should be present");
+        assert_eq!(provider.provider_id, "zai");
+        assert_eq!(provider.model, "glm-5");
+        assert_eq!(provider.base_url, "https://api.z.ai/api/paas/v4");
+        assert_eq!(provider.protocol, ProviderProtocol::OpenAiCompletions);
+    }
+
     #[test]
     fn nearai_backend_has_no_registry_provider() {
         let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");