fix: resolve PR review issues for Proxy API Server

- Fix tool result content bug: return `values` array instead of empty array
- Fix empty message bug: skip pushing user/assistant messages when content is empty
- Expand provider support: remove type restrictions to support all AI SDK providers
- Add missing alias for @cherrystudio/ai-sdk-provider in main process config

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

Co-Authored-By: Claude <noreply@anthropic.com>

electron.vite.config.ts

@@ -27,7 +27,8 @@ export default defineConfig({
         '@mcp-trace/trace-core': resolve('packages/mcp-trace/trace-core'),
         '@mcp-trace/trace-node': resolve('packages/mcp-trace/trace-node'),
         '@cherrystudio/ai-core/provider': resolve('packages/aiCore/src/core/providers'),
-        '@cherrystudio/ai-core': resolve('packages/aiCore/src')
+        '@cherrystudio/ai-core': resolve('packages/aiCore/src'),
+        '@cherrystudio/ai-sdk-provider': resolve('packages/ai-sdk-provider/src')
       }
     },
     build: {

src/main/apiServer/services/unified-messages.ts

@@ -186,7 +186,7 @@ IANA media type.
     }
     return {
       type: 'content',
-      value: []
+      value: values
     }
   }
 }
@@ -313,17 +313,24 @@ function convertAnthropicToAiMessages(params: MessageCreateParams): ModelMessage
       }
 
       // Build the message based on role
+      // Only push user/assistant message if there's actual content (avoid empty messages)
       if (msg.role === 'user') {
-        messages.push({
+        const userContent = [...textParts, ...imageParts]
-          role: 'user',
+        if (userContent.length > 0) {
-          content: [...textParts, ...imageParts]
+          messages.push({
-        })
+            role: 'user',
+            content: userContent
+          })
+        }
       } else {
         // Assistant messages contain tool calls, not tool results
-        messages.push({
+        const assistantContent = [...reasoningParts, ...textParts, ...toolCallParts]
-          role: 'assistant',
+        if (assistantContent.length > 0) {
-          content: [...reasoningParts, ...textParts, ...toolCallParts]
+          messages.push({
-        })
+            role: 'assistant',
+            content: assistantContent
+          })
+        }
       }
     }
   }

src/main/apiServer/utils/index.ts

@@ -28,10 +28,9 @@ export async function getAvailableProviders(): Promise<Provider[]> {
       return []
     }
 
-    // Support OpenAI and Anthropic type providers for API server
+    // Support all provider types that AI SDK can handle
-    const supportedProviders = providers.filter(
+    // The unified-messages service uses AI SDK which supports many providers
-      (p: Provider) => p.enabled && (p.type === 'openai' || p.type === 'anthropic')
+    const supportedProviders = providers.filter((p: Provider) => p.enabled)
-    )
 
     // Cache the filtered results
     CacheService.set(PROVIDERS_CACHE_KEY, supportedProviders, PROVIDERS_CACHE_TTL)
@@ -160,7 +159,7 @@ export async function validateModelId(model: string): Promise<{
         valid: false,
         error: {
           type: 'provider_not_found',
-          message: `Provider '${providerId}' not found, not enabled, or not supported. Only OpenAI providers are currently supported.`,
+          message: `Provider '${providerId}' not found or not enabled.`,
           code: 'provider_not_found'
         }
       }
@@ -262,14 +261,8 @@ export function validateProvider(provider: Provider): boolean {
       return false
     }
 
-    // Support OpenAI and Anthropic type providers
+    // AI SDK supports many provider types, no longer need to filter by type
-    if (provider.type !== 'openai' && provider.type !== 'anthropic') {
+    // The unified-messages service handles all supported types
-      logger.debug('Provider type not supported', {
-        providerId: provider.id,
-        providerType: provider.type
-      })
-      return false
-    }
 
     return true
   } catch (error: any) {