chore(provider): add GLM-5 and GLM-4.7 flash models (#2388)

Author: amitksingh1490

crates/forge_repo/src/provider/provider.json

@@ -646,6 +646,16 @@
     "response_type": "OpenAI",
     "url": "https://api.z.ai/api/paas/v4/chat/completions",
     "models": [
+      {
+        "id": "glm-5",
+        "name": "GLM-5",
+        "description": "Latest flagship model series, foundational models specifically designed for agent applications with 200K context window and 128K maximum output",
+        "context_length": 200000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text"]
+      },
       {
         "id": "glm-4.7",
         "name": "GLM-4.7",
@@ -656,6 +666,26 @@
         "supports_reasoning": true,
         "input_modalities": ["text"]
       },
+      {
+        "id": "glm-4.7-flash",
+        "name": "GLM-4.7 Flash",
+        "description": "Latest 4.7 model series, foundational models specifically designed for agent applications with 200K context window and 128K maximum output",
+        "context_length": 200000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text"]
+      },
+      {
+        "id": "glm-4.7-flashx",
+        "name": "GLM-4.7 Flash X",
+        "description": "Latest 4.7 model series, foundational models specifically designed for agent applications with 200K context window and 128K maximum output",
+        "context_length": 200000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text"]
+      },
       {
         "id": "glm-4.6",
         "name": "GLM-4.6",
@@ -736,6 +766,16 @@
     "response_type": "OpenAI",
     "url": "https://api.z.ai/api/coding/paas/v4/chat/completions",
     "models": [
+      {
+        "id": "glm-5",
+        "name": "GLM-5",
+        "description": "Latest flagship model series, foundational models specifically designed for agent applications with 200K context window and 128K maximum output",
+        "context_length": 200000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text"]
+      },
       {
         "id": "glm-4.7",
         "name": "GLM-4.7",
@@ -746,6 +786,26 @@
         "supports_reasoning": true,
         "input_modalities": ["text"]
       },
+      {
+        "id": "glm-4.7-flash",
+        "name": "GLM-4.7 Flash",
+        "description": "Latest 4.7 model series, foundational models specifically designed for agent applications with 200K context window and 128K maximum output",
+        "context_length": 200000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text"]
+      },
+      {
+        "id": "glm-4.7-flashx",
+        "name": "GLM-4.7 Flash X",
+        "description": "Latest 4.7 model series, foundational models specifically designed for agent applications with 200K context window and 128K maximum output",
+        "context_length": 200000,
+        "tools_supported": true,
+        "supports_parallel_tool_calls": true,
+        "supports_reasoning": true,
+        "input_modalities": ["text"]
+      },
       {
         "id": "glm-4.6",
         "name": "GLM-4.6",