fix: separate Anthropic output and context limits

Direct Anthropic connections reused the configured context window as max_tokens, which could impose an unintended output value or send a provider-invalid request. Anthropic connections now expose an independent per-response maximum output setting, defaulting to 32K for the protocol-required field, while OpenAI direct requests remain without an added output token cap and direct tool rounds remain unmetered.

Release note: Anthropic 直连模型现在可单独配置单次最大输出，不再复用上下文窗口；OpenAI 直连请求和工具调用轮次不增加额外配额。

src/main/runtime-settings-store.test.ts

@@ -283,6 +283,7 @@ describe('RuntimeSettingsStore', () => {
             authentication: 'none',
             supportsImageInput: false,
             contextWindowTokens: 256_000,
+            maximumOutputTokens: 48_000,
             imageGenerationQuality: 'auto',
             apiKey: { action: 'keep' }
           }
@@ -302,7 +303,8 @@ describe('RuntimeSettingsStore', () => {
       modelProfiles: [
         {
           id: profileId,
-          contextWindowTokens: 256_000
+          contextWindowTokens: 256_000,
+          maximumOutputTokens: 48_000
         }
       ],
       contextCompression: {
@@ -316,7 +318,8 @@ describe('RuntimeSettingsStore', () => {
       modelProfiles: [
         {
           id: profileId,
-          contextWindowTokens: 256_000
+          contextWindowTokens: 256_000,
+          maximumOutputTokens: 48_000
         }
       ],
       contextCompression: {