feat: add Moonshot AI (Kimi) provider and update xAI Grok models (#1953)

- Add comprehensive Moonshot AI provider with 11 models including:
  * Legacy moonshot-v1 series (8k, 32k, 128k context)
  * Latest Kimi K2 models (K2 Preview, Turbo, Thinking)
  * Vision-enabled models for multimodal capabilities
  * Auto-selecting model variants

- Update xAI provider with latest Grok models:
  * Add Grok 4 (256K context) and Grok 4 (07-09) variant
  * Add Grok 3 Mini Beta and Mini Fast Beta variants
  * Update context limits to match actual model capabilities
  * Remove outdated grok-beta and grok-2-1212 models

- Add MOONSHOT_API_KEY to environment configuration
- Register Moonshot provider in service status monitoring
- Full OpenAI-compatible API integration via api.moonshot.ai
- Fix TypeScript errors in GitHub provider

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Claude <noreply@anthropic.com>

app/lib/modules/llm/providers/anthropic.ts

@@ -33,6 +33,15 @@ export default class AnthropicProvider extends BaseProvider {
       maxTokenAllowed: 200000,
       maxCompletionTokens: 128000,
     },
+
+    // Claude Opus 4: 200k context, 32k output limit (latest flagship model)
+    {
+      name: 'claude-opus-4-20250514',
+      label: 'Claude 4 Opus',
+      provider: 'Anthropic',
+      maxTokenAllowed: 200000,
+      maxCompletionTokens: 32000,
+    },
   ];
 
   async getDynamicModels(
@@ -81,12 +90,23 @@ export default class AnthropicProvider extends BaseProvider {
         contextWindow = 200000; // Claude 3 Sonnet has 200k context
       }
 
+      // Determine completion token limits based on specific model
+      let maxCompletionTokens = 128000; // default for older Claude 3 models
+
+      if (m.id?.includes('claude-opus-4')) {
+        maxCompletionTokens = 32000; // Claude 4 Opus: 32K output limit
+      } else if (m.id?.includes('claude-sonnet-4')) {
+        maxCompletionTokens = 64000; // Claude 4 Sonnet: 64K output limit
+      } else if (m.id?.includes('claude-4')) {
+        maxCompletionTokens = 32000; // Other Claude 4 models: conservative 32K limit
+      }
+
       return {
         name: m.id,
         label: `${m.display_name} (${Math.floor(contextWindow / 1000)}k context)`,
         provider: this.name,
         maxTokenAllowed: contextWindow,
-        maxCompletionTokens: 128000, // Claude models support up to 128k completion tokens
+        maxCompletionTokens,
       };
     });
   }