feat(llm): support incremental Responses WebSocket transport

apps/admin_console/services/model_settings_service.py

@@ -22,6 +22,7 @@ class ModelSettingsUpdate(BaseModel):
     api_key: SecretStr | None = None  # Omitted/blank keeps the existing key.
     timeout_seconds: float = Field(default=300, gt=0, le=3600)
     max_retries: int = Field(default=5, ge=0, le=10)
+    transport: Literal["http", "websocket"] | None = None
     retry_interval_seconds: float = Field(default=10, ge=0, le=300)
     rate_limit_retry_seconds: float | None = Field(default=None, ge=0, le=3600)
     tool_fallback_model: str | None = Field(default=None, min_length=1, max_length=200)
@@ -72,6 +73,7 @@ def get_model_settings() -> dict:
         "api_key_configured": bool(settings.OPENAI_API_KEY),
         "timeout_seconds": settings.OPENAI_TIMEOUT_SECONDS,
         "max_retries": settings.OPENAI_MAX_RETRIES,
+        "transport": settings.OPENAI_TRANSPORT,
         "retry_interval_seconds": settings.OPENAI_RETRY_INTERVAL_SECONDS,
         "rate_limit_retry_seconds": settings.OPENAI_RATE_LIMIT_RETRY_SECONDS,
         "tool_fallback_model": settings.OPENAI_TOOL_FALLBACK_MODEL,
@@ -102,6 +104,7 @@ def save_model_settings(update: ModelSettingsUpdate) -> dict:
         "OPENAI_REASONING_EFFORT": update.reasoning_effort,
     }
     optional_settings = {
+        "transport": ("OPENAI_TRANSPORT", str),
         "rate_limit_retry_seconds": ("OPENAI_RATE_LIMIT_RETRY_SECONDS", float),
         "tool_fallback_model": ("OPENAI_TOOL_FALLBACK_MODEL", str),
         "tool_fallback_reasoning_effort": ("OPENAI_TOOL_FALLBACK_REASONING_EFFORT", str),
@@ -261,10 +264,19 @@ async def test_model_settings(update: ModelSettingsUpdate) -> dict:
         api_base=update.base_url,
         timeout_seconds=update.timeout_seconds,
         max_retries=0,
+        transport=update.transport or settings.OPENAI_TRANSPORT,
         reasoning_effort=None if update.reasoning_effort == "default" else update.reasoning_effort,
     )
     model = ModelFactory.create_model(endpoint)
-    result = await model.ainvoke([HumanMessage(content="Reply with OK only.")])
+    try:
+        result = await model.ainvoke([HumanMessage(content="Reply with OK only.")])
+    finally:
+        await model.http_async_client.aclose()
+        model.http_client.close()
     if not result.content:
         raise ValueError("Responses 接口返回空内容，请检查模型配置")
-    return {"success": True, "message": "Responses 连接测试成功", "model": update.model}
+    return {
+        "success": True,
+        "message": f"Responses {endpoint.transport.upper()} 连接测试成功",
+        "model": update.model,
+    }

apps/showcase_ui/src/app/components/model-settings/model-settings.component.spec.ts

@@ -30,6 +30,31 @@ describe('持久化模型与功能设置', () => {
     http.expectNone('/api/system/model-settings');
   }));
 
+  it('加载、测试和保存 WebSocket 选择，旧配置默认 HTTP', fakeAsync(() => {
+    const fixture = TestBed.createComponent(ModelSettingsComponent);
+    fixture.detectChanges();
+    http.expectOne('/api/system/model-settings').flush(config);
+    tick();
+    fixture.detectChanges();
+    const component = fixture.componentInstance;
+    expect(component.transport).toBe('http');
+    const selector: HTMLSelectElement = fixture.nativeElement.querySelector('#model-transport');
+    selector.value = 'websocket';
+    selector.dispatchEvent(new Event('change'));
+    tick();
+    fixture.detectChanges();
+    component.test();
+    const check = http.expectOne('/api/system/model-settings/test');
+    expect(check.request.body.transport).toBe('websocket');
+    check.flush({message: 'Responses WEBSOCKET 连接测试成功'});
+    component.save();
+    const save = http.expectOne('/api/system/model-settings');
+    expect(save.request.body.transport).toBe('websocket');
+    expect(save.request.body.api_key).toBeUndefined();
+    save.flush({...config, transport: 'websocket'});
+    expect(component.transport).toBe('websocket');
+  }));
+
   it('加载配置后保留密钥，保存新模型且不发送空密钥', () => {
     const fixture = TestBed.createComponent(ModelSettingsComponent);
     fixture.detectChanges();

apps/showcase_ui/src/app/components/model-settings/model-settings.component.ts

@@ -8,6 +8,7 @@ import { ModelSelectorComponent } from '../model-selector/model-selector.compone
 import { MODEL_PRESETS } from '../../core/model-presets';
 
 interface ModelSettings {
+  transport?: 'http' | 'websocket';
   base_url: string;
   model: string;
   api_key_configured: boolean;
@@ -36,6 +37,12 @@ interface ModelSettings {
       <input id="model-base-url" name="baseUrl" type="url" [(ngModel)]="baseUrl" required
         placeholder="https://api-n-cd.playones.com/v1" [disabled]="busy() || loading()" />
       <small>填写接口根地址，通常包含 /v1，无需添加 /responses。</small>
+      <label for="model-transport">传输协议</label>
+      <select id="model-transport" name="transport" [(ngModel)]="transport" [disabled]="busy() || loading()">
+        <option value="http">HTTP（兼容模式）</option>
+        <option value="websocket">WebSocket（增量传输）</option>
+      </select>
+      <small>WebSocket 可减少重复历史与截图的上传，需要接口支持。保存后对新任务生效。</small>
       <app-model-selector label="模型名称" [(value)]="model" [presets]="modelPresets" [disabled]="!!busy() || loading()" />
       <small>选择预设模型，或选择“自定义模型”填写名称。</small>
       <app-setting-slider label="思考强度" [(value)]="reasoning" [values]="reasoningValues" [labels]="reasoningLabels" [disabled]="!!busy() || loading()" hint="更高的强度适合复杂推理；需接口支持，也可选择模型默认。" />
@@ -102,6 +109,7 @@ interface ModelSettings {
   `]
 })
 export class ModelSettingsComponent implements OnInit {
+  transport: 'http' | 'websocket' = 'http';
   readonly reasoningValues = REASONING_VALUES;
   readonly reasoningLabels = REASONING_LABELS;
   private http = inject(HttpClient);
@@ -128,7 +136,7 @@ export class ModelSettingsComponent implements OnInit {
       && Number.isInteger(this.toolFallbackNoProgress) && this.toolFallbackNoProgress >= 1 && this.toolFallbackNoProgress <= 10;
   }
   private payload() {
-    return { base_url: this.baseUrl.trim(), model: this.model.trim(), api_key: this.apiKey.trim() || undefined,
+    return { base_url: this.baseUrl.trim(), transport: this.transport, model: this.model.trim(), api_key: this.apiKey.trim() || undefined,
       timeout_seconds: this.timeout, max_retries: this.retries, retry_interval_seconds: this.retryInterval, reasoning_effort: this.reasoning,
       rate_limit_retry_seconds: this.rateLimitRetry, tool_fallback_model: this.toolFallbackModel.trim(),
       tool_fallback_reasoning_effort: this.toolFallbackReasoning, tool_fallback_max_retries: this.toolFallbackRetries,
@@ -136,6 +144,7 @@ export class ModelSettingsComponent implements OnInit {
   }
   private apply(config: ModelSettings): void {
     this.baseUrl = config.base_url; this.model = config.model; this.timeout = config.timeout_seconds;
+    this.transport = config.transport ?? 'http';
     this.modelPresets = config.model_presets;
     this.retries = config.max_retries; this.retryInterval = config.retry_interval_seconds ?? 10; this.reasoning = config.reasoning_effort ?? 'high'; this.keyConfigured.set(config.api_key_configured); this.envPath.set(config.env_path);
     this.rateLimitRetry = config.rate_limit_retry_seconds ?? 60;